chore: more create colony logs

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.claude/settings.json

@@ -45,23 +45,25 @@
       "Bash(cat /home/timothy/aden/hive/.venv/lib/python3.11/site-packages/litellm-*.dist-info/METADATA)",
       "Bash(find \"/home/timothy/.hive/agents/queens/queen_brand_design/sessions/session_20260415_100751_d49f4c28/\" -type f -name \"*.json*\" -exec grep -l \"协日\" {} \\\\;)",
       "Bash(grep -v ':0$')",
-      "Bash(find /home/timothy/aden/hive/core/framework/skills/_default_skills -name \"SKILL.md\" -exec grep -l \"curl\\\\|jq\\\\|bash\\\\|sh\\\\|CLI\\\\|command\" {} \\\\;)",
-      "Bash(python3 -c \"import sys, json; [print\\(json.loads\\(line\\).get\\('data', {}\\).get\\('iteration'\\)\\) for line in sys.stdin]\")",
-      "Bash(grep -l \"shell\\\\|bash\\\\|exec\\\\|subprocess\" /home/timothy/aden/hive/tools/src/gcu/files/*.py)",
-      "Bash(python3 -c \"import aden_tools.file_ops; print\\(aden_tools.file_ops.__file__\\)\")",
-      "Bash(find / -path /proc -prune -o -name \"file_ops*\" -print)",
-      "Bash(grep -l \"sqlite\\\\|sqlite3\" /home/timothy/aden/hive/tools/src/aden_tools/tools/*/*.py)",
-      "Bash(grep -iv \"_tool$\")",
-      "Bash(grep -n \"add_post.*sessions\\\\|add_post.*colonies\\\\|add_get.*sessions\" /home/timothy/aden/hive/core/framework/server/*.py)",
-      "Bash(python -c 'import json; d=json.load\\(open\\('\\\\''__TRACKED_VAR__/.hive/colonies/__TRACKED_VAR__/worker.json'\\\\''\\)\\); print\\('\\\\''input_data:'\\\\'', d.get\\('\\\\''input_data'\\\\'', '\\\\''MISSING'\\\\''\\)\\)')",
-      "Bash(python -c 'import json; d=json.load\\(open\\('\\\\''__TRACKED_VAR__/.hive/colonies/__TRACKED_VAR__/worker.json'\\\\''\\)\\); print\\('\\\\''  __TRACKED_VAR__:'\\\\'', '\\\\''input_data='\\\\'', d.get\\('\\\\''input_data'\\\\'', '\\\\''MISSING'\\\\''\\)\\)')",
-      "Bash(python -c 'import json; d=json.load\\(open\\('\\\\''__TRACKED_VAR__/.hive/colonies/__TRACKED_VAR__/worker.json'\\\\''\\)\\); print\\('\\\\''  __TRACKED_VAR__: input_data ='\\\\'', d.get\\('\\\\''input_data'\\\\''\\)\\)')",
-      "Bash(kill 2466637 2466632)"
+      "Bash(curl -s -m 2 http://127.0.0.1:4002/sse -o /dev/null -w 'status=%{http_code} time=%{time_total}s\\\\n')",
+      "mcp__gcu-tools__browser_status",
+      "mcp__gcu-tools__browser_start",
+      "mcp__gcu-tools__browser_navigate",
+      "mcp__gcu-tools__browser_evaluate",
+      "mcp__gcu-tools__browser_screenshot",
+      "mcp__gcu-tools__browser_open",
+      "mcp__gcu-tools__browser_click_coordinate",
+      "mcp__gcu-tools__browser_get_rect",
+      "mcp__gcu-tools__browser_type_focused",
+      "mcp__gcu-tools__browser_wait",
+      "Bash(python3 -c ' *)",
+      "Bash(python3 scripts/debug_queen_prompt.py independent)"
     ],
     "additionalDirectories": [
       "/home/timothy/.hive/skills/writing-hive-skills",
       "/tmp",
-      "/home/timothy/.hive/skills"
+      "/home/timothy/.hive/skills",
+      "/home/timothy/aden/hive/core/frontend/src/components"
     ]
   },
   "hooks": {

.claude/skills/browser-edge-cases/SKILL.md

@@ -64,7 +64,7 @@ snapshot = await browser_snapshot(tab_id)
 |---------|--------------|-------|
 | Scroll doesn't move | Nested scroll container | Look for `overflow: scroll` divs |
 | Click no effect | Element covered | Check `getBoundingClientRect` vs viewport |
-| Type clears | Autocomplete/React | Check for event listeners on input |
+| Type clears | Autocomplete/React | Check for event listeners on input; try `browser_type_focused` |
 | Snapshot hangs | Huge DOM | Check node count in snapshot |
 | Snapshot stale | SPA hydration | Wait after navigation |
 
@@ -229,7 +229,7 @@ function queryShadow(selector) {
 |-------|-------------|----------|
 | Scroll not working | Find scrollable container | Mouse wheel at container center |
 | Click no effect | JavaScript click() | CDP mouse events |
-| Type clears | Add delay_ms | Use execCommand |
+| Type clears | Add delay_ms | Use `browser_type_focused` (Input.insertText) |
 | Snapshot hangs | Add timeout_s | DOM snapshot fallback |
 | Stale content | Wait for selector | Increase wait_until timeout |
 | Shadow DOM | Pierce selector | JavaScript traversal |

.claude/skills/browser-edge-cases/scripts/test_02_twitter_scroll.py

@@ -57,8 +57,7 @@ async def test_twitter_lazy_scroll():
         # Count initial tweets
         initial_count = await bridge.evaluate(
             tab_id,
-            "(function() { return document.querySelectorAll("
-            "'[data-testid=\"tweet\"]').length; })()",
+            "(function() { return document.querySelectorAll('[data-testid=\"tweet\"]').length; })()",
         )
         print(f"Initial tweet count: {initial_count.get('result', 0)}")
 
@@ -78,8 +77,7 @@ async def test_twitter_lazy_scroll():
             # Count tweets after scroll
             count_result = await bridge.evaluate(
                 tab_id,
-                "(function() { return document.querySelectorAll("
-                "'[data-testid=\"tweet\"]').length; })()",
+                "(function() { return document.querySelectorAll('[data-testid=\"tweet\"]').length; })()",
             )
             count = count_result.get("result", 0)
             print(f"  Tweet count after scroll: {count}")
@@ -87,8 +85,7 @@ async def test_twitter_lazy_scroll():
         # Final count
         final_count = await bridge.evaluate(
             tab_id,
-            "(function() { return document.querySelectorAll("
-            "'[data-testid=\"tweet\"]').length; })()",
+            "(function() { return document.querySelectorAll('[data-testid=\"tweet\"]').length; })()",
         )
         final = final_count.get("result", 0)
         initial = initial_count.get("result", 0)

.claude/skills/browser-edge-cases/scripts/test_06_shadow_dom.py

@@ -130,9 +130,7 @@ async def test_shadow_dom():
         print(f"JS click result: {click_result.get('result', {})}")
 
         # Verify click was registered
-        count_result = await bridge.evaluate(
-            tab_id, "(function() { return window.shadowClickCount || 0; })()"
-        )
+        count_result = await bridge.evaluate(tab_id, "(function() { return window.shadowClickCount || 0; })()")
         count = count_result.get("result") or 0
         print(f"Shadow click count: {count}")
 

.claude/skills/browser-edge-cases/scripts/test_08_autocomplete.py

@@ -200,9 +200,7 @@ async def test_autocomplete():
         print(f"Value after fast typing: '{fast_value}'")
 
         # Check events
-        events_result = await bridge.evaluate(
-            tab_id, "(function() { return window.inputEvents; })()"
-        )
+        events_result = await bridge.evaluate(tab_id, "(function() { return window.inputEvents; })()")
         print(f"Events logged: {events_result.get('result', [])}")
 
         # Test 2: Slow typing (with delay) - should work
@@ -220,8 +218,7 @@ async def test_autocomplete():
         # Check if dropdown appeared
         dropdown_result = await bridge.evaluate(
             tab_id,
-            "(function() { return document.querySelectorAll("
-            "'.autocomplete-items div').length; })()",
+            "(function() { return document.querySelectorAll('.autocomplete-items div').length; })()",
         )
         dropdown_count = dropdown_result.get("result", 0)
         print(f"Dropdown items: {dropdown_count}")

.claude/skills/browser-edge-cases/scripts/test_10_huge_dom.py

@@ -87,9 +87,7 @@ async def test_huge_dom():
         await bridge.navigate(tab_id, data_url, wait_until="load")
 
         # Count elements
-        count_result = await bridge.evaluate(
-            tab_id, "(function() { return document.querySelectorAll('*').length; })()"
-        )
+        count_result = await bridge.evaluate(tab_id, "(function() { return document.querySelectorAll('*').length; })()")
         elem_count = count_result.get("result", 0)
         print(f"DOM elements: {elem_count}")
 
@@ -122,14 +120,10 @@ async def test_huge_dom():
 
         # Test 3: Real LinkedIn
         print("\n--- Test 3: Real LinkedIn Feed ---")
-        await bridge.navigate(
-            tab_id, "https://www.linkedin.com/feed", wait_until="load", timeout_ms=30000
-        )
+        await bridge.navigate(tab_id, "https://www.linkedin.com/feed", wait_until="load", timeout_ms=30000)
         await asyncio.sleep(2)
 
-        count_result = await bridge.evaluate(
-            tab_id, "(function() { return document.querySelectorAll('*').length; })()"
-        )
+        count_result = await bridge.evaluate(tab_id, "(function() { return document.querySelectorAll('*').length; })()")
         elem_count = count_result.get("result", 0)
         print(f"LinkedIn DOM elements: {elem_count}")
 

.claude/skills/browser-edge-cases/scripts/test_15_screenshot.py

@@ -136,10 +136,7 @@ async def test_selector_screenshot(bridge: BeelineBridge, tab_id: int, data_url:
                 print("  ⚠ WARNING: Selector screenshot not smaller (may be full page)")
                 return False
     else:
-        print(
-            "  ⚠ NOT IMPLEMENTED: selector param ignored"
-            f" (returns full page) - error={result.get('error')}"
-        )
+        print(f"  ⚠ NOT IMPLEMENTED: selector param ignored (returns full page) - error={result.get('error')}")
         print("  NOTE: selector parameter exists in signature but is not used in implementation")
         return False
 
@@ -181,9 +178,7 @@ async def test_screenshot_timeout(bridge: BeelineBridge, tab_id: int, data_url:
             print(f"  ⚠ Fast enough to beat timeout: {err!r} in {elapsed:.3f}s")
             return True  # Not a failure, just fast
     else:
-        print(
-            f"  ⚠ Screenshot completed before timeout ({elapsed:.3f}s) - too fast to test timeout"
-        )
+        print(f"  ⚠ Screenshot completed before timeout ({elapsed:.3f}s) - too fast to test timeout")
         return True  # Still ok, just very fast
 
 

.claude/skills/browser-edge-cases/scripts/test_case.py

@@ -137,14 +137,8 @@ async def test_problematic_site(bridge: BeelineBridge, tab_id: int) -> dict:
         changed = False
         for key in after_data:
             if key in before_data:
-                b_val = (
-                    before_data[key].get("scrollTop", 0)
-                    if isinstance(before_data[key], dict)
-                    else 0
-                )
-                a_val = (
-                    after_data[key].get("scrollTop", 0) if isinstance(after_data[key], dict) else 0
-                )
+                b_val = before_data[key].get("scrollTop", 0) if isinstance(before_data[key], dict) else 0
+                a_val = after_data[key].get("scrollTop", 0) if isinstance(after_data[key], dict) else 0
                 if a_val != b_val:
                     print(f"  ✓ CHANGE DETECTED: {key} scrolled from {b_val} to {a_val}")
                     changed = True

.mcp.json

@@ -1,3 +0,0 @@
-{
-  "mcpServers": {}
-}

core/antigravity_auth.py

@@ -52,9 +52,7 @@ _DEFAULT_REDIRECT_PORT = 51121
 # This project reverse-engineered and published the public OAuth credentials
 # for Google's Antigravity/Cloud Code Assist API.
 # Source: https://github.com/NoeFabris/opencode-antigravity-auth
-_CREDENTIALS_URL = (
-    "https://raw.githubusercontent.com/NoeFabris/opencode-antigravity-auth/dev/src/constants.ts"
-)
+_CREDENTIALS_URL = "https://raw.githubusercontent.com/NoeFabris/opencode-antigravity-auth/dev/src/constants.ts"
 
 # Cached credentials fetched from public source
 _cached_client_id: str | None = None
@@ -68,9 +66,7 @@ def _fetch_credentials_from_public_source() -> tuple[str | None, str | None]:
         return _cached_client_id, _cached_client_secret
 
     try:
-        req = urllib.request.Request(
-            _CREDENTIALS_URL, headers={"User-Agent": "Hive-Antigravity-Auth/1.0"}
-        )
+        req = urllib.request.Request(_CREDENTIALS_URL, headers={"User-Agent": "Hive-Antigravity-Auth/1.0"})
         with urllib.request.urlopen(req, timeout=10) as resp:
             content = resp.read().decode("utf-8")
             import re
@@ -168,10 +164,7 @@ class OAuthCallbackHandler(BaseHTTPRequestHandler):
             if "code" in query and "state" in query:
                 OAuthCallbackHandler.auth_code = query["code"][0]
                 OAuthCallbackHandler.state = query["state"][0]
-                self._send_response(
-                    "Authentication successful! You can close this window "
-                    "and return to the terminal."
-                )
+                self._send_response("Authentication successful! You can close this window and return to the terminal.")
                 return
 
         self._send_response("Waiting for authentication...")
@@ -296,8 +289,7 @@ def validate_credentials(access_token: str, project_id: str = _DEFAULT_PROJECT_I
         "Authorization": f"Bearer {access_token}",
         "Content-Type": "application/json",
         "User-Agent": (
-            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
-            "AppleWebKit/537.36 (KHTML, like Gecko) Antigravity/1.18.3"
+            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Antigravity/1.18.3"
         ),
         "X-Goog-Api-Client": "google-cloud-sdk vscode_cloudshelleditor/0.1",
     }
@@ -316,9 +308,7 @@ def validate_credentials(access_token: str, project_id: str = _DEFAULT_PROJECT_I
         return False
 
 
-def refresh_access_token(
-    refresh_token: str, client_id: str, client_secret: str | None
-) -> dict | None:
+def refresh_access_token(refresh_token: str, client_id: str, client_secret: str | None) -> dict | None:
     """Refresh the access token using the refresh token."""
     data = {
         "grant_type": "refresh_token",
@@ -361,9 +351,7 @@ def cmd_account_add(args: argparse.Namespace) -> int:
         access_token = account.get("access")
         refresh_token_str = account.get("refresh", "")
         refresh_token = refresh_token_str.split("|")[0] if refresh_token_str else None
-        project_id = (
-            refresh_token_str.split("|")[1] if "|" in refresh_token_str else _DEFAULT_PROJECT_ID
-        )
+        project_id = refresh_token_str.split("|")[1] if "|" in refresh_token_str else _DEFAULT_PROJECT_ID
         email = account.get("email", "unknown")
         expires_ms = account.get("expires", 0)
         expires_at = expires_ms / 1000.0 if expires_ms else 0.0
@@ -390,9 +378,7 @@ def cmd_account_add(args: argparse.Namespace) -> int:
                     # Update the account
                     account["access"] = new_access
                     account["expires"] = int((time.time() + expires_in) * 1000)
-                    accounts_data["last_refresh"] = time.strftime(
-                        "%Y-%m-%dT%H:%M:%SZ", time.gmtime()
-                    )
+                    accounts_data["last_refresh"] = time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())
                     save_accounts(accounts_data)
 
                     # Validate the refreshed token

core/framework/agent_loop/agent_loop.py

@@ -126,9 +126,7 @@ _STRIP_RE = re.compile(
 # The value cannot contain `<` or `\n` — those terminate the label.
 # Trailing whitespace (including the terminating newline) is consumed
 # so the visible text that follows starts cleanly.
-_LABEL_STRIP_RE = re.compile(
-    r"<(?:" + "|".join(_INTERNAL_TAGS) + r")>[^<\n]*\s*"
-)
+_LABEL_STRIP_RE = re.compile(r"<(?:" + "|".join(_INTERNAL_TAGS) + r")>[^<\n]*\s*")
 
 # Matches a trailing `<` that could be the start of an internal tag.
 # We build a pattern that matches `<` followed by any prefix of any
@@ -138,9 +136,7 @@ for _tag in _INTERNAL_TAGS:
     for _i in range(1, len(_tag) + 1):
         _PARTIAL_PREFIXES.add(_tag[:_i])
 _PARTIAL_OPEN_RE = re.compile(
-    r"<(?:"
-    + "|".join(re.escape(p) for p in sorted(_PARTIAL_PREFIXES, key=len, reverse=True))
-    + r")$"
+    r"<(?:" + "|".join(re.escape(p) for p in sorted(_PARTIAL_PREFIXES, key=len, reverse=True)) + r")$"
 )
 
 _GENERIC_TAG_RE = re.compile(r"</?[a-zA-Z_][\w-]*\s*/?>")
@@ -351,9 +347,7 @@ class AgentLoop(AgentProtocol):
         self._config = config or LoopConfig()
         self._tool_executor = tool_executor
         self._conversation_store = conversation_store
-        self._injection_queue: asyncio.Queue[tuple[str, bool, list[dict[str, Any]] | None]] = (
-            asyncio.Queue()
-        )
+        self._injection_queue: asyncio.Queue[tuple[str, bool, list[dict[str, Any]] | None]] = asyncio.Queue()
         self._trigger_queue: asyncio.Queue[TriggerEvent] = asyncio.Queue()
         # Queen input blocking state
         self._input_ready = asyncio.Event()
@@ -510,9 +504,7 @@ class AgentLoop(AgentProtocol):
                     output_tokens=0,
                     latency_ms=0,
                 )
-            return self._finalize_result(
-                AgentResult(success=False, error=error_msg), "guard_failure"
-            )
+            return self._finalize_result(AgentResult(success=False, error=error_msg), "guard_failure")
 
         # 2. Restore or create new conversation + accumulator
         restored = await self._restore(ctx)
@@ -571,11 +563,7 @@ class AgentLoop(AgentProtocol):
             if ctx.default_skill_batch_nudge:
                 from framework.skills.defaults import is_batch_scenario as _is_batch
 
-                _input_text = (
-                    (ctx.goal_context or "")
-                    + " "
-                    + " ".join(str(v) for v in ctx.input_data.values() if v)
-                )
+                _input_text = (ctx.goal_context or "") + " " + " ".join(str(v) for v in ctx.input_data.values() if v)
                 if _is_batch(_input_text):
                     system_prompt = f"{system_prompt}\n\n{ctx.default_skill_batch_nudge}"
                     logger.info("[%s] DS-12: batch scenario detected, nudge injected", node_id)
@@ -587,9 +575,7 @@ class AgentLoop(AgentProtocol):
                 store=self._conversation_store,
                 run_id=ctx.effective_run_id,
                 compaction_buffer_tokens=self._config.compaction_buffer_tokens,
-                compaction_warning_buffer_tokens=(
-                    self._config.compaction_warning_buffer_tokens
-                ),
+                compaction_warning_buffer_tokens=(self._config.compaction_warning_buffer_tokens),
             )
             accumulator = OutputAccumulator(
                 store=self._conversation_store,
@@ -690,9 +676,7 @@ class AgentLoop(AgentProtocol):
                     node_id,
                     iteration,
                 )
-                await self._publish_loop_completed(
-                    stream_id, node_id, iteration, execution_id
-                )
+                await self._publish_loop_completed(stream_id, node_id, iteration, execution_id)
                 return AgentResult(
                     success=True,
                     output=accumulator.to_dict(),
@@ -773,9 +757,7 @@ class AgentLoop(AgentProtocol):
                         prompt=str(pending_input_state.get("prompt", "")),
                         options=pending_input_state.get("options"),
                         questions=pending_input_state.get("questions"),
-                        emit_client_request=bool(
-                            pending_input_state.get("emit_client_request", True)
-                        ),
+                        emit_client_request=bool(pending_input_state.get("emit_client_request", True)),
                     )
                     logger.info(
                         "[%s] iter=%d: restored wait unblocked, got_input=%s",
@@ -784,9 +766,7 @@ class AgentLoop(AgentProtocol):
                         got_input,
                     )
                     if not got_input:
-                        await self._publish_loop_completed(
-                            stream_id, node_id, iteration + 1, execution_id
-                        )
+                        await self._publish_loop_completed(stream_id, node_id, iteration + 1, execution_id)
                         latency_ms = int((time.time() - start_time) * 1000)
                         return AgentResult(
                             success=True,
@@ -797,8 +777,7 @@ class AgentLoop(AgentProtocol):
                         )
                     if self._injection_queue.empty() and self._trigger_queue.empty():
                         logger.info(
-                            "[%s] iter=%d: pending-input wait woke"
-                            " without queued input; re-waiting",
+                            "[%s] iter=%d: pending-input wait woke without queued input; re-waiting",
                             node_id,
                             iteration,
                         )
@@ -863,9 +842,7 @@ class AgentLoop(AgentProtocol):
                 iteration,
                 len(conversation.messages),
             )
-            logger.debug(
-                "[AgentLoop.execute] iteration=%d: entering _run_single_turn loop", iteration
-            )
+            logger.debug("[AgentLoop.execute] iteration=%d: entering _run_single_turn loop", iteration)
             _stream_retry_count = 0
             _capacity_retry_started_at: float | None = None
             _capacity_retry_attempt = 0
@@ -892,9 +869,7 @@ class AgentLoop(AgentProtocol):
                         request_system_prompt,
                         request_messages,
                         _,
-                    ) = await self._run_single_turn(
-                        ctx, conversation, tools, iteration, accumulator
-                    )
+                    ) = await self._run_single_turn(ctx, conversation, tools, iteration, accumulator)
                     logger.debug(
                         "[AgentLoop.execute] iteration=%d: _run_single_turn completed successfully",
                         iteration,
@@ -910,10 +885,7 @@ class AgentLoop(AgentProtocol):
                         len(real_tool_results),
                         outputs_set or "[]",
                         turn_tokens,
-                        {
-                            k: ("set" if v is not None else "None")
-                            for k, v in accumulator.to_dict().items()
-                        },
+                        {k: ("set" if v is not None else "None") for k, v in accumulator.to_dict().items()},
                     )
                     total_input_tokens += turn_tokens.get("input", 0)
                     total_output_tokens += turn_tokens.get("output", 0)
@@ -982,10 +954,7 @@ class AgentLoop(AgentProtocol):
                     # still publishes a retry event so the UI can see us
                     # waiting (the "heartbeat" — no silent stalls).
                     self._bump("llm_turn_exception")
-                    if (
-                        self._is_capacity_error(e)
-                        and self._config.capacity_retry_max_seconds > 0
-                    ):
+                    if self._is_capacity_error(e) and self._config.capacity_retry_max_seconds > 0:
                         self._bump("capacity_error")
                         now = time.monotonic()
                         if _capacity_retry_started_at is None:
@@ -994,8 +963,7 @@ class AgentLoop(AgentProtocol):
                         if elapsed < self._config.capacity_retry_max_seconds:
                             _capacity_retry_attempt += 1
                             delay = min(
-                                self._config.stream_retry_backoff_base
-                                * (2 ** min(_capacity_retry_attempt - 1, 6)),
+                                self._config.stream_retry_backoff_base * (2 ** min(_capacity_retry_attempt - 1, 6)),
                                 self._config.capacity_retry_max_delay,
                             )
                             logger.warning(
@@ -1023,15 +991,11 @@ class AgentLoop(AgentProtocol):
                             continue  # retry same iteration
 
                     # Retry transient errors with exponential backoff
-                    if (
-                        self._is_transient_error(e)
-                        and _stream_retry_count < self._config.max_stream_retries
-                    ):
+                    if self._is_transient_error(e) and _stream_retry_count < self._config.max_stream_retries:
                         self._bump("llm_transient_retry")
                         _stream_retry_count += 1
                         delay = min(
-                            self._config.stream_retry_backoff_base
-                            * (2 ** (_stream_retry_count - 1)),
+                            self._config.stream_retry_backoff_base * (2 ** (_stream_retry_count - 1)),
                             self._config.stream_retry_max_delay,
                         )
                         logger.warning(
@@ -1079,8 +1043,7 @@ class AgentLoop(AgentProtocol):
                     if ctx.supports_direct_user_io:
                         error_msg = f"LLM call failed: {e}"
                         _guardrail_phrase = (
-                            "no endpoints available matching your guardrail restrictions "
-                            "and data policy"
+                            "no endpoints available matching your guardrail restrictions and data policy"
                         )
                         if _guardrail_phrase in str(e).lower():
                             error_msg += (
@@ -1219,9 +1182,7 @@ class AgentLoop(AgentProtocol):
                         node_id,
                         iteration,
                     )
-                    await self._publish_loop_completed(
-                        stream_id, node_id, iteration + 1, execution_id
-                    )
+                    await self._publish_loop_completed(stream_id, node_id, iteration + 1, execution_id)
                     latency_ms = int((time.time() - start_time) * 1000)
                     return AgentResult(
                         success=True,
@@ -1442,10 +1403,7 @@ class AgentLoop(AgentProtocol):
             _has_tools_no_text = bool(real_tool_results) and not assistant_text
             if _has_tools_no_text:
                 _silent_tool_streak += 1
-                if (
-                    _silent_tool_streak > 0
-                    and _silent_tool_streak % self._config.silent_tool_streak_threshold == 0
-                ):
+                if _silent_tool_streak > 0 and _silent_tool_streak % self._config.silent_tool_streak_threshold == 0:
                     nudge = (
                         "[SYSTEM] You have been calling tools for "
                         f"{_silent_tool_streak} consecutive turns without "
@@ -1488,10 +1446,7 @@ class AgentLoop(AgentProtocol):
                 and self._event_bus is not None
             )
             _worker_no_tool_turn = (
-                not real_tool_results
-                and not outputs_set
-                and not queen_input_requested
-                and not user_input_requested
+                not real_tool_results and not outputs_set and not queen_input_requested and not user_input_requested
             )
             if _is_worker and _worker_no_tool_turn:
                 _worker_text_only_streak += 1
@@ -1599,9 +1554,7 @@ class AgentLoop(AgentProtocol):
                                     step_index=iteration,
                                     verdict="CONTINUE",
                                     verdict_feedback=(
-                                        "Auto-block grace"
-                                        f" ({_cf_text_only_streak}"
-                                        f"/{self._config.cf_grace_turns})"
+                                        f"Auto-block grace ({_cf_text_only_streak}/{self._config.cf_grace_turns})"
                                     ),
                                     tool_calls=logged_tool_calls,
                                     llm_text=assistant_text,
@@ -1614,9 +1567,7 @@ class AgentLoop(AgentProtocol):
                         # through to judge
 
                 if self._shutdown:
-                    await self._publish_loop_completed(
-                        stream_id, node_id, iteration + 1, execution_id
-                    )
+                    await self._publish_loop_completed(stream_id, node_id, iteration + 1, execution_id)
                     latency_ms = int((time.time() - start_time) * 1000)
                     _continue_count += 1
                     if ctx.runtime_logger:
@@ -1702,9 +1653,7 @@ class AgentLoop(AgentProtocol):
                     )
                 logger.info("[%s] iter=%d: unblocked, got_input=%s", node_id, iteration, got_input)
                 if not got_input:
-                    await self._publish_loop_completed(
-                        stream_id, node_id, iteration + 1, execution_id
-                    )
+                    await self._publish_loop_completed(stream_id, node_id, iteration + 1, execution_id)
                     latency_ms = int((time.time() - start_time) * 1000)
                     _continue_count += 1
                     if ctx.runtime_logger:
@@ -1800,9 +1749,7 @@ class AgentLoop(AgentProtocol):
             # until the queen injects guidance.
             if queen_input_requested:
                 if self._shutdown:
-                    await self._publish_loop_completed(
-                        stream_id, node_id, iteration + 1, execution_id
-                    )
+                    await self._publish_loop_completed(stream_id, node_id, iteration + 1, execution_id)
                     latency_ms = int((time.time() - start_time) * 1000)
                     _continue_count += 1
                     self._log_skip_judge(
@@ -1870,15 +1817,11 @@ class AgentLoop(AgentProtocol):
                             stream_id=stream_id,
                             node_id=node_id,
                             reason="Blocked waiting for queen guidance - no input received",
-                            context=(
-                                "Worker escalated but received no queen guidance before shutdown"
-                            ),
+                            context=("Worker escalated but received no queen guidance before shutdown"),
                             execution_id=execution_id,
                             request_id=uuid.uuid4().hex,
                         )
-                    await self._publish_loop_completed(
-                        stream_id, node_id, iteration + 1, execution_id
-                    )
+                    await self._publish_loop_completed(stream_id, node_id, iteration + 1, execution_id)
                     latency_ms = int((time.time() - start_time) * 1000)
                     _continue_count += 1
                     self._log_skip_judge(
@@ -2143,9 +2086,7 @@ class AgentLoop(AgentProtocol):
                 continue
 
         # 7. Max iterations exhausted
-        await self._publish_loop_completed(
-            stream_id, node_id, self._config.max_iterations, execution_id
-        )
+        await self._publish_loop_completed(stream_id, node_id, self._config.max_iterations, execution_id)
         latency_ms = int((time.time() - start_time) * 1000)
         if ctx.runtime_logger:
             ctx.runtime_logger.log_node_complete(
@@ -2168,9 +2109,7 @@ class AgentLoop(AgentProtocol):
         return self._finalize_result(
             AgentResult(
                 success=False,
-                error=(
-                    f"Max iterations ({self._config.max_iterations}) reached without acceptance"
-                ),
+                error=(f"Max iterations ({self._config.max_iterations}) reached without acceptance"),
                 output=accumulator.to_dict(),
                 tokens_used=total_input_tokens + total_output_tokens,
                 latency_ms=latency_ms,
@@ -2204,9 +2143,7 @@ class AgentLoop(AgentProtocol):
             image_content: Optional list of OpenAI-style image blocks to attach.
         """
         logger.debug(
-            "[AgentLoop.inject_event] content_len=%d,"
-            " is_client_input=%s, has_images=%s,"
-            " queue_size_before=%d",
+            "[AgentLoop.inject_event] content_len=%d, is_client_input=%s, has_images=%s, queue_size_before=%d",
             len(content) if content else 0,
             is_client_input,
             bool(image_content),
@@ -2398,6 +2335,11 @@ class AgentLoop(AgentProtocol):
             execution_id,
         )
 
+        # Continue-nudge counter: how many times we've re-streamed within this
+        # _run_single_turn because the idle/TTFT watchdog fired. Caps to avoid
+        # nudging forever when the endpoint is genuinely dead.
+        _nudge_count_this_turn = 0
+
         # Inner tool loop: stream may produce tool calls requiring re-invocation
         while True:
             # Pre-send guard: if context is at or over budget, compact before
@@ -2440,9 +2382,7 @@ class AgentLoop(AgentProtocol):
             # generating. Unsafe tools (bash, edits, browser actions)
             # still wait for FinishEvent so we don't race a write
             # against a decision the model hasn't finished making.
-            _early_safe_names = {
-                t.name for t in tools if getattr(t, "concurrency_safe", False)
-            }
+            _early_safe_names = {t.name for t in tools if getattr(t, "concurrency_safe", False)}
             _early_tasks: dict[str, asyncio.Task] = {}
 
             async def _timed_execute(
@@ -2488,7 +2428,16 @@ class AgentLoop(AgentProtocol):
             # Capture loop-scoped variables as defaults to satisfy B023.
             # _stream_last_event_at is bumped on every event; the watchdog
             # below uses it to detect silently hung HTTP connections.
-            _stream_last_event_at = time.monotonic()
+            _stream_start_at = time.monotonic()
+            _stream_last_event_at = _stream_start_at
+            # None until the first event arrives. Before first event, the
+            # watchdog uses the (much looser) TTFT budget — large-context
+            # local models legitimately take minutes to first token. Once
+            # any event has been observed, tight inter-event idle applies.
+            _first_event_at: float | None = None
+            # Partial tool_calls accumulated so far, as OpenAI-format dicts
+            # ready for persistence if the stream is cut short.
+            _partial_tc_dicts: list[dict[str, Any]] = []
 
             async def _do_stream(
                 _msgs: list = messages,  # noqa: B006
@@ -2497,8 +2446,10 @@ class AgentLoop(AgentProtocol):
                 _safe_names: set = _early_safe_names,  # noqa: B006,B008
                 _tasks: dict = _early_tasks,  # noqa: B006,B008
                 _exec_fn=_timed_execute,
+                _partial_dicts: list[dict[str, Any]] = _partial_tc_dicts,  # noqa: B006,B008
             ) -> None:
                 nonlocal accumulated_text, _stream_error, _stream_last_event_at
+                nonlocal _first_event_at
                 _clean_snapshot = ""  # visible-only text for the frontend
 
                 async for event in ctx.llm.stream(
@@ -2508,6 +2459,8 @@ class AgentLoop(AgentProtocol):
                     max_tokens=ctx.max_tokens,
                 ):
                     _stream_last_event_at = time.monotonic()
+                    if _first_event_at is None:
+                        _first_event_at = _stream_last_event_at
                     if isinstance(event, TextDeltaEvent):
                         accumulated_text = event.snapshot
                         # Strip internal reasoning tags from the full
@@ -2527,9 +2480,46 @@ class AgentLoop(AgentProtocol):
                                 iteration=iteration,
                                 inner_turn=inner_turn,
                             )
+                        # Checkpoint partial state so a watchdog cancel or
+                        # crash doesn't discard whatever the model has
+                        # produced so far. Cheap — one atomic file write.
+                        try:
+                            await conversation.checkpoint_partial_assistant(
+                                accumulated_text,
+                                _partial_dicts or None,
+                            )
+                        except Exception as _cp_err:  # noqa: BLE001
+                            logger.debug(
+                                "[_run_single_turn] partial checkpoint failed: %s",
+                                _cp_err,
+                            )
 
                     elif isinstance(event, ToolCallEvent):
                         _tc.append(event)
+                        _partial_dicts.append(
+                            {
+                                "id": event.tool_use_id,
+                                "type": "function",
+                                "function": {
+                                    "name": event.tool_name,
+                                    "arguments": json.dumps(event.tool_input),
+                                },
+                            }
+                        )
+                        # Checkpoint now that a tool call has landed —
+                        # this is the important one: if the stream dies
+                        # right after a tool call but before FinishEvent,
+                        # we still have the intent recorded.
+                        try:
+                            await conversation.checkpoint_partial_assistant(
+                                accumulated_text,
+                                _partial_dicts or None,
+                            )
+                        except Exception as _cp_err:  # noqa: BLE001
+                            logger.debug(
+                                "[_run_single_turn] partial checkpoint failed: %s",
+                                _cp_err,
+                            )
                         # Gap 1: start concurrency-safe tools immediately
                         # while the rest of the stream is still arriving,
                         # so read-heavy turns don't stall after the last
@@ -2539,9 +2529,7 @@ class AgentLoop(AgentProtocol):
                             and "_raw" not in event.tool_input
                             and event.tool_use_id not in _tasks
                         ):
-                            _tasks[event.tool_use_id] = asyncio.create_task(
-                                _exec_fn(event)
-                            )
+                            _tasks[event.tool_use_id] = asyncio.create_task(_exec_fn(event))
 
                     elif isinstance(event, FinishEvent):
                         token_counts["input"] += event.input_tokens
@@ -2558,62 +2546,100 @@ class AgentLoop(AgentProtocol):
 
             _llm_stream_t0 = time.monotonic()
             self._stream_task = asyncio.create_task(_do_stream())
-            logger.debug(
-                "[_run_single_turn] inner_turn=%d: Stream task created, waiting...", inner_turn
+            logger.debug("[_run_single_turn] inner_turn=%d: Stream task created, waiting...", inner_turn)
+
+            # Watchdog budgets — see LoopConfig docstring for rationale.
+            _ttft_limit = self._config.llm_stream_ttft_timeout_seconds
+            _inter_event_limit = self._config.llm_stream_inter_event_idle_seconds
+            # Back-compat: if the legacy inactivity knob was overridden to
+            # a value below the new default, respect it as the inter-event
+            # budget (historic behaviour) so existing configs don't regress.
+            _legacy = self._config.llm_stream_inactivity_timeout_seconds
+            if _legacy and _legacy > 0 and _legacy < _inter_event_limit:
+                _inter_event_limit = _legacy
+            _watchdog_active = (_ttft_limit and _ttft_limit > 0) or (
+                _inter_event_limit and _inter_event_limit > 0
             )
-            _inactivity_limit = self._config.llm_stream_inactivity_timeout_seconds
+            # Result of the watchdog: "ok" (stream finished), "ttft" (no first
+            # event in budget), "inactive" (silence after first event).
+            _watchdog_verdict: str = "ok"
+            _watchdog_elapsed: float = 0.0
+            _watchdog_limit: float = 0.0
+
             try:
-                if _inactivity_limit and _inactivity_limit > 0:
-                    # Heartbeat-aware wait: poll the task and cancel it if
-                    # no stream event has been observed within the window.
-                    # A silently dead HTTP connection otherwise hangs here
-                    # forever — no exception, no delta, no timeout.
-                    #
-                    # Must use asyncio.wait (not wait_for) so we can tell
-                    # "poll interval elapsed" apart from "task raised a
-                    # TimeoutError of its own" — wait_for conflates them.
-                    _check_interval = min(5.0, _inactivity_limit / 2)
+                if _watchdog_active:
+                    # Poll cheapest-valid interval: at most every 5s, at least
+                    # half the tighter budget. Must use asyncio.wait (not
+                    # wait_for) so "poll interval elapsed" and "task raised
+                    # TimeoutError of its own" stay distinguishable.
+                    _tight = min(
+                        _ttft_limit or float("inf"),
+                        _inter_event_limit or float("inf"),
+                    )
+                    _check_interval = max(1.0, min(5.0, _tight / 2))
                     while True:
                         done, _pending = await asyncio.wait(
                             {self._stream_task}, timeout=_check_interval
                         )
                         if self._stream_task in done:
-                            # Let any exception the task raised propagate
-                            # naturally via the outer ``await`` below.
                             break
-                        idle = time.monotonic() - _stream_last_event_at
-                        if idle >= _inactivity_limit:
-                            logger.warning(
-                                "[_run_single_turn] inner_turn=%d: "
-                                "stream inactivity %.0fs >= %.0fs — "
-                                "cancelling stream task",
-                                inner_turn,
-                                idle,
-                                _inactivity_limit,
-                            )
-                            self._bump("stream_inactivity_watchdog")
-                            self._stream_task.cancel()
-                            try:
-                                await self._stream_task
-                            except BaseException:
-                                pass
-                            raise ConnectionError(
-                                f"LLM stream idle for {idle:.0f}s "
-                                f"(inactivity limit {_inactivity_limit:.0f}s) — "
-                                "connection presumed dead"
-                            ) from None
+                        now = time.monotonic()
+                        if _first_event_at is None:
+                            # TTFT phase — stream open but silent. Use the
+                            # looser budget; don't confuse slow models with
+                            # dead connections.
+                            elapsed = now - _stream_start_at
+                            if _ttft_limit and _ttft_limit > 0 and elapsed >= _ttft_limit:
+                                _watchdog_verdict = "ttft"
+                                _watchdog_elapsed = elapsed
+                                _watchdog_limit = _ttft_limit
+                                break
+                        else:
+                            # Post-first-event silence. A stream that produced
+                            # events and then went quiet is a real stall.
+                            idle = now - _stream_last_event_at
+                            if (
+                                _inter_event_limit
+                                and _inter_event_limit > 0
+                                and idle >= _inter_event_limit
+                            ):
+                                _watchdog_verdict = "inactive"
+                                _watchdog_elapsed = idle
+                                _watchdog_limit = _inter_event_limit
+                                break
                         # Still active — keep polling.
-                # Re-raise any exception the stream task stored. When the
-                # watchdog loop exited via ``break`` the task is done, and
-                # ``await`` is the cheapest way to surface its exception.
-                await self._stream_task
-                logger.debug(
-                    "[_run_single_turn] inner_turn=%d: Stream task completed normally", inner_turn
-                )
+
+                if _watchdog_verdict != "ok":
+                    logger.warning(
+                        "[_run_single_turn] inner_turn=%d: watchdog=%s %.0fs >= %.0fs — cancelling stream",
+                        inner_turn,
+                        _watchdog_verdict,
+                        _watchdog_elapsed,
+                        _watchdog_limit,
+                    )
+                    self._bump(f"stream_watchdog_{_watchdog_verdict}")
+                    self._stream_task.cancel()
+                    try:
+                        await self._stream_task
+                    except BaseException:
+                        pass
+                else:
+                    # Re-raise any exception the stream task stored. When the
+                    # watchdog loop exited via ``break`` the task is done, and
+                    # ``await`` is the cheapest way to surface its exception.
+                    await self._stream_task
+                    logger.debug(
+                        "[_run_single_turn] inner_turn=%d: Stream task completed normally",
+                        inner_turn,
+                    )
             except asyncio.CancelledError:
                 logger.debug("[_run_single_turn] inner_turn=%d: Stream task cancelled", inner_turn)
-                if accumulated_text:
-                    await conversation.add_assistant_message(content=accumulated_text)
+                if accumulated_text or _partial_tc_dicts:
+                    await conversation.add_assistant_message(
+                        content=accumulated_text,
+                        tool_calls=_partial_tc_dicts or None,
+                        truncated=True,
+                    )
                 # Gap 1: kill any early-dispatched tool tasks too.
                 # Without this, a safe tool started during streaming
                 # would leak past cancellation and keep running.
@@ -2631,9 +2657,7 @@ class AgentLoop(AgentProtocol):
                     raise
                 raise TurnCancelled() from None
             except Exception as e:
-                logger.exception(
-                    "[_run_single_turn] inner_turn=%d: Stream task failed: %s", inner_turn, e
-                )
+                logger.exception("[_run_single_turn] inner_turn=%d: Stream task failed: %s", inner_turn, e)
                 # Don't orphan early tool tasks on a stream failure
                 # either - the outer retry loop will re-emit the tool
                 # calls on the next attempt.
@@ -2643,6 +2667,100 @@ class AgentLoop(AgentProtocol):
                 raise
             finally:
                 self._stream_task = None
+
+            # Continue-nudge recovery path. Runs AFTER the stream task is
+            # cleaned up so all state is consistent. We persist whatever
+            # partial text + tool-calls the model produced (as a truncated
+            # message so the model can see its own in-flight work on the
+            # next turn), cancel early tool tasks, append a terse
+            # continuation hint, and restart the stream.
+            if _watchdog_verdict != "ok":
+                # Kill any safe-tool tasks the stream dispatched early —
+                # their results would have had nowhere to land anyway
+                # because the assistant message was incomplete.
+                for _early in _early_tasks.values():
+                    if not _early.done():
+                        _early.cancel()
+                # Promote whatever we captured into a real truncated
+                # message. The partial checkpoint for this seq is cleared
+                # automatically when add_assistant_message persists.
+                if accumulated_text or _partial_tc_dicts:
+                    await conversation.add_assistant_message(
+                        content=accumulated_text,
+                        tool_calls=_partial_tc_dicts or None,
+                        truncated=True,
+                    )
+
+                reason_label = (
+                    "no tokens before TTFT budget"
+                    if _watchdog_verdict == "ttft"
+                    else "stream went silent after producing events"
+                )
+                if self._event_bus:
+                    if _watchdog_verdict == "ttft":
+                        await self._event_bus.emit_stream_ttft_exceeded(
+                            stream_id=stream_id,
+                            node_id=node_id,
+                            ttft_seconds=_watchdog_elapsed,
+                            limit_seconds=_watchdog_limit,
+                            execution_id=execution_id,
+                        )
+                    else:
+                        await self._event_bus.emit_stream_inactive(
+                            stream_id=stream_id,
+                            node_id=node_id,
+                            idle_seconds=_watchdog_elapsed,
+                            limit_seconds=_watchdog_limit,
+                            execution_id=execution_id,
+                        )
+
+                nudge_enabled = self._config.continue_nudge_enabled
+                nudge_cap = self._config.continue_nudge_max_per_turn
+                if nudge_enabled and _nudge_count_this_turn < nudge_cap:
+                    _nudge_count_this_turn += 1
+                    nudge_msg = (
+                        f"[System: the previous stream stalled ({reason_label}, "
+                        f"{_watchdog_elapsed:.0f}s). Continue from the last tool "
+                        "result already in this conversation. Do NOT repeat tool "
+                        "calls whose results are visible above — reuse them and "
+                        "move to the next step.]"
+                    )
+                    await conversation.add_user_message(
+                        nudge_msg,
+                        is_system_nudge=True,
+                    )
+                    if self._event_bus:
+                        await self._event_bus.emit_stream_nudge_sent(
+                            stream_id=stream_id,
+                            node_id=node_id,
+                            reason=_watchdog_verdict,
+                            nudge_count=_nudge_count_this_turn,
+                            execution_id=execution_id,
+                        )
+                    logger.info(
+                        "[%s] continue-nudge sent (count=%d/%d, reason=%s)",
+                        node_id,
+                        _nudge_count_this_turn,
+                        nudge_cap,
+                        _watchdog_verdict,
+                    )
+                    # Reset the outer _turn_t0 timer so the "LLM done in
+                    # Xms" log line reflects real work not the nudge cycle.
+                    _llm_stream_ms = int((time.monotonic() - _llm_stream_t0) * 1000)
+                    logger.debug(
+                        "[_run_single_turn] inner_turn=%d: nudge restart after %dms",
+                        inner_turn,
+                        _llm_stream_ms,
+                    )
+                    continue  # restart the inner loop, re-fetches messages
+                # Nudge disabled or cap exhausted — fall back to the
+                # existing retry path so a truly dead endpoint eventually
+                # surfaces as an error.
+                raise ConnectionError(
+                    f"LLM stream {_watchdog_verdict} for {_watchdog_elapsed:.0f}s "
+                    f"(limit {_watchdog_limit:.0f}s) — nudge cap reached"
+                )
+
             _llm_stream_ms = int((time.monotonic() - _llm_stream_t0) * 1000)
 
             # If a recoverable stream error produced an empty response,
@@ -2652,9 +2770,7 @@ class AgentLoop(AgentProtocol):
                 for _early in _early_tasks.values():
                     if not _early.done():
                         _early.cancel()
-                raise ConnectionError(
-                    f"Stream failed with recoverable error: {_stream_error.error}"
-                )
+                raise ConnectionError(f"Stream failed with recoverable error: {_stream_error.error}")
 
             final_text = accumulated_text
             logger.info(
@@ -2735,20 +2851,21 @@ class AgentLoop(AgentProtocol):
             # capping them strands work mid-turn and the next turn just
             # re-emits the discarded calls, which is strictly worse.
             if self._config.max_tool_calls_per_turn > 0:
-                hard_limit = int(
-                    self._config.max_tool_calls_per_turn
-                    * (1 + self._config.tool_call_overflow_margin)
-                )
+                hard_limit = int(self._config.max_tool_calls_per_turn * (1 + self._config.tool_call_overflow_margin))
             else:
                 hard_limit = 0  # disabled
 
             # Phase 1: triage — handle framework tools immediately,
             # queue real tools for parallel execution.
             results_by_id: dict[str, ToolResult] = {}
-            timing_by_id: dict[
-                str, dict[str, Any]
-            ] = {}  # tool_use_id -> {start_timestamp, duration_s}
+            timing_by_id: dict[str, dict[str, Any]] = {}  # tool_use_id -> {start_timestamp, duration_s}
             pending_real: list[ToolCallEvent] = []
+            # Replay detector: per-turn map from tool_use_id -> steer prefix.
+            # Populated below when we detect that the model is re-emitting a
+            # tool call whose (name + canonical args) matches a prior success.
+            # Applied to the stored tool result content so the model sees the
+            # nudge on its next turn without losing the real execution output.
+            replay_prefixes_by_id: dict[str, str] = {}
 
             for tc in tool_calls:
                 tool_call_count += 1
@@ -2801,9 +2918,7 @@ class AgentLoop(AgentProtocol):
                         sanitize_ask_user_inputs,
                     )
 
-                    ask_user_prompt, recovered_options = sanitize_ask_user_inputs(
-                        ask_user_prompt, raw_options
-                    )
+                    ask_user_prompt, recovered_options = sanitize_ask_user_inputs(ask_user_prompt, raw_options)
                     if recovered_options is not None and raw_options is None:
                         raw_options = recovered_options
                     # Defensive: ensure options is a list of strings.
@@ -2930,8 +3045,7 @@ class AgentLoop(AgentProtocol):
                         result = ToolResult(
                             tool_use_id=tc.tool_use_id,
                             content=(
-                                "ERROR: escalate is only available to worker "
-                                "nodes/sub-agents, not queen/judge streams."
+                                "ERROR: escalate is only available to worker nodes/sub-agents, not queen/judge streams."
                             ),
                             is_error=True,
                         )
@@ -2941,9 +3055,7 @@ class AgentLoop(AgentProtocol):
                     if self._event_bus is None:
                         result = ToolResult(
                             tool_use_id=tc.tool_use_id,
-                            content=(
-                                "ERROR: EventBus unavailable. Could not emit escalation request."
-                            ),
+                            content=("ERROR: EventBus unavailable. Could not emit escalation request."),
                             is_error=True,
                         )
                         results_by_id[tc.tool_use_id] = result
@@ -2973,10 +3085,7 @@ class AgentLoop(AgentProtocol):
                     # owner (Worker instance) records the explicit report
                     # via ``record_explicit_report`` so Worker.run()'s
                     # terminal event emission picks it up.
-                    if not (
-                        isinstance(stream_id, str)
-                        and stream_id.startswith("worker:")
-                    ):
+                    if not (isinstance(stream_id, str) and stream_id.startswith("worker:")):
                         result = ToolResult(
                             tool_use_id=tc.tool_use_id,
                             content=(
@@ -3029,6 +3138,39 @@ class AgentLoop(AgentProtocol):
                         )
                         results_by_id[tc.tool_use_id] = result
                     else:
+                        # Replay detector: flag re-executions of recent
+                        # successful calls. We still run the tool (some
+                        # are legitimately repeated, e.g. screenshots and
+                        # read-only evaluates) but prepend a terse steer
+                        # onto the stored result so the model sees the
+                        # signal on its next turn.
+                        if self._config.replay_detector_enabled:
+                            prior = conversation.find_completed_tool_call(
+                                tc.tool_name,
+                                tc.tool_input,
+                                within_last_turns=self._config.replay_detector_within_last_turns,
+                            )
+                            if prior is not None:
+                                logger.warning(
+                                    "[%s] replay detected: %s matches prior seq=%d — executing anyway",
+                                    node_id,
+                                    tc.tool_name,
+                                    prior.seq,
+                                )
+                                self._bump("tool_call_replay_detected")
+                                if self._event_bus:
+                                    await self._event_bus.emit_tool_call_replay_detected(
+                                        stream_id=stream_id,
+                                        node_id=node_id,
+                                        tool_name=tc.tool_name,
+                                        prior_seq=prior.seq,
+                                        execution_id=execution_id,
+                                    )
+                                replay_prefixes_by_id[tc.tool_use_id] = (
+                                    f"[Replay detected: {tc.tool_name} matches "
+                                    f"seq={prior.seq}. Result still produced below — "
+                                    "consider whether the retry was necessary.]\n"
+                                )
                         pending_real.append(tc)
 
             # Phase 2a: partition real tools by concurrency safety.
@@ -3064,9 +3206,7 @@ class AgentLoop(AgentProtocol):
                     async with _sem:
                         return await _timed_execute(_tc)
 
-                timed_results_by_id: dict[
-                    str, tuple[ToolResult | BaseException, str, float] | BaseException
-                ] = {}
+                timed_results_by_id: dict[str, tuple[ToolResult | BaseException, str, float] | BaseException] = {}
 
                 async def _cancel_turn_with_stubs(
                     _pending: list[ToolCallEvent] = pending_real,  # noqa: B006,B008
@@ -3108,9 +3248,7 @@ class AgentLoop(AgentProtocol):
                             _awaitables.append(early)
                         else:
                             _awaitables.append(_capped(tc))
-                    self._tool_task = asyncio.ensure_future(
-                        asyncio.gather(*_awaitables, return_exceptions=True)
-                    )
+                    self._tool_task = asyncio.ensure_future(asyncio.gather(*_awaitables, return_exceptions=True))
                     try:
                         parallel_timed = await self._tool_task
                     finally:
@@ -3196,9 +3334,7 @@ class AgentLoop(AgentProtocol):
                         result = _build_tool_error_result(tc, raw)
                     else:
                         result = raw
-                    results_by_id[tc.tool_use_id] = await self._truncate_tool_result(
-                        result, tc.tool_name
-                    )
+                    results_by_id[tc.tool_use_id] = await self._truncate_tool_result(result, tc.tool_name)
 
             # Phase 3: record results into conversation in original order,
             # build logged/real lists, and publish completed events.
@@ -3227,24 +3363,28 @@ class AgentLoop(AgentProtocol):
                 image_content = result.image_content
                 if image_content and ctx.llm and not supports_image_tool_results(ctx.llm.model):
                     logger.info(
-                        "Stripping image_content from tool result; "
-                        "model '%s' does not support images in tool results",
+                        "Stripping image_content from tool result; model '%s' does not support images in tool results",
                         ctx.llm.model,
                     )
                     image_content = None
 
+                # Apply replay-detector steer prefix if this call matched a
+                # recent successful invocation. Only applies to non-error
+                # results — an error already breaks the replay chain.
+                stored_content = result.content
+                if not result.is_error:
+                    _prefix = replay_prefixes_by_id.get(tc.tool_use_id)
+                    if _prefix:
+                        stored_content = f"{_prefix}{stored_content or ''}"
+
                 await conversation.add_tool_result(
                     tool_use_id=tc.tool_use_id,
-                    content=result.content,
+                    content=stored_content,
                     is_error=result.is_error,
                     image_content=image_content,
                     is_skill_content=result.is_skill_content,
                 )
-                if (
-                    tc.tool_name in ("ask_user", "ask_user_multiple")
-                    and user_input_requested
-                    and not result.is_error
-                ):
+                if tc.tool_name in ("ask_user", "ask_user_multiple") and user_input_requested and not result.is_error:
                     # Defer tool_call_completed until after user responds
                     self._deferred_tool_complete = {
                         "stream_id": stream_id,
@@ -3704,10 +3844,7 @@ class AgentLoop(AgentProtocol):
         # function only touches disk / does heavy JSON work when the
         # result exceeds either the truncation or spillover threshold,
         # so cheap pass-throughs stay on the main loop.
-        needs_offload = (
-            len(result.content) > 10_000
-            and not result.is_error
-        )
+        needs_offload = len(result.content) > 10_000 and not result.is_error
         if not needs_offload:
             return truncate_tool_result(
                 result=result,
@@ -3868,9 +4005,7 @@ class AgentLoop(AgentProtocol):
             pending_input=pending_input,
         )
 
-    async def _drain_injection_queue(
-        self, conversation: NodeConversation, ctx: AgentContext
-    ) -> int:
+    async def _drain_injection_queue(self, conversation: NodeConversation, ctx: AgentContext) -> int:
         """Drain all pending injected events as user messages. Returns count."""
         return await drain_injection_queue(
             queue=self._injection_queue,
@@ -3912,9 +4047,7 @@ class AgentLoop(AgentProtocol):
     # EventBus publishing helpers
     # -------------------------------------------------------------------
 
-    async def _publish_loop_started(
-        self, stream_id: str, node_id: str, execution_id: str = ""
-    ) -> None:
+    async def _publish_loop_started(self, stream_id: str, node_id: str, execution_id: str = "") -> None:
         return await publish_loop_started(
             event_bus=self._event_bus,
             stream_id=stream_id,

core/framework/agent_loop/conversation.py

@@ -48,6 +48,14 @@ class Message:
     is_skill_content: bool = False
     # Logical worker run identifier for shared-session persistence
     run_id: str | None = None
+    # True when this is a framework-injected continuation hint (continue-nudge
+    # on stream stall). Stored as a user message for API compatibility, but
+    # the UI should render it as a compact system notice, not user speech.
+    is_system_nudge: bool = False
+    # True when this message is a partial/truncated assistant turn reconstructed
+    # from a crashed or watchdog-cancelled stream. Signals that the original
+    # turn never finished — the model may or may not choose to redo it.
+    truncated: bool = False
 
     def to_llm_dict(self) -> dict[str, Any]:
         """Convert to OpenAI-format message dict."""
@@ -109,6 +117,10 @@ class Message:
             d["image_content"] = self.image_content
         if self.run_id is not None:
             d["run_id"] = self.run_id
+        if self.is_system_nudge:
+            d["is_system_nudge"] = self.is_system_nudge
+        if self.truncated:
+            d["truncated"] = self.truncated
         return d
 
     @classmethod
@@ -126,6 +138,8 @@ class Message:
             is_client_input=data.get("is_client_input", False),
             image_content=data.get("image_content"),
             run_id=data.get("run_id"),
+            is_system_nudge=data.get("is_system_nudge", False),
+            truncated=data.get("truncated", False),
         )
 
 
@@ -317,6 +331,14 @@ class ConversationStore(Protocol):
 
     async def delete_parts_before(self, seq: int, run_id: str | None = None) -> None: ...
 
+    async def write_partial(self, seq: int, data: dict[str, Any]) -> None: ...
+
+    async def read_partial(self, seq: int) -> dict[str, Any] | None: ...
+
+    async def read_all_partials(self) -> list[dict[str, Any]]: ...
+
+    async def clear_partial(self, seq: int) -> None: ...
+
     async def close(self) -> None: ...
 
     async def destroy(self) -> None: ...
@@ -462,6 +484,7 @@ class NodeConversation:
         is_transition_marker: bool = False,
         is_client_input: bool = False,
         image_content: list[dict[str, Any]] | None = None,
+        is_system_nudge: bool = False,
     ) -> Message:
         msg = Message(
             seq=self._next_seq,
@@ -472,6 +495,7 @@ class NodeConversation:
             is_transition_marker=is_transition_marker,
             is_client_input=is_client_input,
             image_content=image_content,
+            is_system_nudge=is_system_nudge,
         )
         self._messages.append(msg)
         self._next_seq += 1
@@ -485,6 +509,8 @@ class NodeConversation:
         self,
         content: str,
         tool_calls: list[dict[str, Any]] | None = None,
+        *,
+        truncated: bool = False,
     ) -> Message:
         msg = Message(
             seq=self._next_seq,
@@ -493,6 +519,7 @@ class NodeConversation:
             tool_calls=tool_calls,
             phase_id=self._current_phase,
             run_id=self._run_id,
+            truncated=truncated,
         )
         self._messages.append(msg)
         self._next_seq += 1
@@ -548,6 +575,59 @@ class NodeConversation:
 
     # --- Query -------------------------------------------------------------
 
+    def find_completed_tool_call(
+        self,
+        name: str,
+        tool_input: dict[str, Any],
+        within_last_turns: int = 3,
+    ) -> Message | None:
+        """Return the most recent assistant message that issued a tool call
+        with the same (name + canonical-json args) AND received a non-error
+        tool result, within the last ``within_last_turns`` assistant turns.
+
+        Used by the replay detector to flag when the model is about to redo
+        a successful call — we prepend a steer onto the upcoming result but
+        still execute, so tools like browser_screenshot that are legitimately
+        repeated are not silently skipped.
+        """
+        try:
+            target_canonical = json.dumps(tool_input, sort_keys=True, default=str)
+        except (TypeError, ValueError):
+            target_canonical = str(tool_input)
+
+        # Walk backwards over recent assistant messages
+        assistant_turns_seen = 0
+        for idx in range(len(self._messages) - 1, -1, -1):
+            m = self._messages[idx]
+            if m.role != "assistant":
+                continue
+            assistant_turns_seen += 1
+            if assistant_turns_seen > within_last_turns:
+                break
+            if not m.tool_calls:
+                continue
+            for tc in m.tool_calls:
+                func = tc.get("function", {}) if isinstance(tc, dict) else {}
+                tc_name = func.get("name")
+                if tc_name != name:
+                    continue
+                args_str = func.get("arguments", "")
+                try:
+                    parsed = json.loads(args_str) if isinstance(args_str, str) else args_str
+                    canonical = json.dumps(parsed, sort_keys=True, default=str)
+                except (TypeError, ValueError):
+                    canonical = str(args_str)
+                if canonical != target_canonical:
+                    continue
+                # Found a match — now verify its result was not an error.
+                tc_id = tc.get("id")
+                for later in self._messages[idx + 1 :]:
+                    if later.role == "tool" and later.tool_use_id == tc_id:
+                        if not later.is_error:
+                            return m
+                        break
+        return None
+
     def to_llm_messages(self) -> list[dict[str, Any]]:
         """Return messages as OpenAI-format dicts (system prompt excluded).
 
@@ -853,7 +933,7 @@ class NodeConversation:
                 continue  # never prune errors
             if msg.is_skill_content:
                 continue  # never prune activated skill instructions (AS-10)
-            if msg.content.startswith("[Pruned tool result"):
+            if msg.content.startswith(("Pruned tool result", "[Pruned tool result")):
                 continue  # already pruned
             # Tiny results (set_output acks, confirmations) — pruning
             # saves negligible space but makes the LLM think the call
@@ -890,9 +970,7 @@ class NodeConversation:
                     f"Read the complete data with read_file(path='{spillover}')."
                 )
             else:
-                placeholder = (
-                    f"Pruned tool result ({orig_len:,} chars) cleared from context."
-                )
+                placeholder = f"Pruned tool result ({orig_len:,} chars) cleared from context."
 
             self._messages[i] = Message(
                 seq=msg.seq,
@@ -974,16 +1052,13 @@ class NodeConversation:
             )
             evicted += 1
             if self._store:
-                await self._store.write_part(
-                    msg.seq, self._messages[idx].to_storage_dict()
-                )
+                await self._store.write_part(msg.seq, self._messages[idx].to_storage_dict())
 
         if evicted:
             # Reset token estimate — image blocks no longer contribute.
             self._last_api_input_tokens = None
             logger.info(
-                "evict_old_images: dropped image_content from %d message(s), "
-                "kept %d most recent",
+                "evict_old_images: dropped image_content from %d message(s), kept %d most recent",
                 evicted,
                 keep_latest,
             )
@@ -1141,9 +1216,7 @@ class NodeConversation:
             for msg in old_messages:
                 if msg.role != "assistant" or not msg.tool_calls:
                     continue
-                has_protected = any(
-                    tc.get("function", {}).get("name") == "set_output" for tc in msg.tool_calls
-                )
+                has_protected = any(tc.get("function", {}).get("name") == "set_output" for tc in msg.tool_calls)
                 tc_ids = {tc.get("id", "") for tc in msg.tool_calls}
                 if has_protected:
                     protected_tc_ids |= tc_ids
@@ -1339,11 +1412,7 @@ class NodeConversation:
 
     def export_summary(self) -> str:
         """Structured summary with [STATS], [CONFIG], [RECENT_MESSAGES] sections."""
-        prompt_preview = (
-            self._system_prompt[:80] + "..."
-            if len(self._system_prompt) > 80
-            else self._system_prompt
-        )
+        prompt_preview = self._system_prompt[:80] + "..." if len(self._system_prompt) > 80 else self._system_prompt
 
         lines = [
             "[STATS]",
@@ -1376,6 +1445,45 @@ class NodeConversation:
             await self._persist_meta()
         await self._store.write_part(message.seq, message.to_storage_dict())
         await self._write_next_seq()
+        # Any partial checkpoint for this seq is now superseded by the real
+        # part — clear it so a future restore doesn't resurrect stale text.
+        try:
+            await self._store.clear_partial(message.seq)
+        except AttributeError:
+            # Older stores may not implement partials; ignore.
+            pass
+
+    async def checkpoint_partial_assistant(
+        self,
+        accumulated_text: str,
+        tool_calls: list[dict[str, Any]] | None = None,
+    ) -> None:
+        """Write an in-flight assistant turn's state to disk under the next seq.
+
+        Called from the stream event loop. Safe to call repeatedly — each call
+        overwrites the prior checkpoint. Persisted via ``write_partial`` so it
+        does NOT appear in ``read_parts()`` and cannot be double-loaded. Cleared
+        automatically when ``add_assistant_message`` for this seq lands.
+        """
+        if self._store is None:
+            return
+        if not self._meta_persisted:
+            await self._persist_meta()
+        payload: dict[str, Any] = {
+            "seq": self._next_seq,
+            "role": "assistant",
+            "content": accumulated_text,
+            "phase_id": self._current_phase,
+            "run_id": self._run_id,
+            "truncated": True,
+        }
+        if tool_calls:
+            payload["tool_calls"] = tool_calls
+        try:
+            await self._store.write_partial(self._next_seq, payload)
+        except AttributeError:
+            # Older stores may not implement partials; ignore.
+            pass
 
     async def _persist_meta(self) -> None:
         """Lazily write conversation metadata to the store (called once).
@@ -1390,9 +1498,7 @@ class NodeConversation:
             "max_context_tokens": self._max_context_tokens,
             "compaction_threshold": self._compaction_threshold,
             "compaction_buffer_tokens": self._compaction_buffer_tokens,
-            "compaction_warning_buffer_tokens": (
-                self._compaction_warning_buffer_tokens
-            ),
+            "compaction_warning_buffer_tokens": (self._compaction_warning_buffer_tokens),
             "output_keys": self._output_keys,
         }
         await self._store.write_meta(run_meta)
@@ -1441,9 +1547,7 @@ class NodeConversation:
             store=store,
             run_id=run_id,
             compaction_buffer_tokens=meta.get("compaction_buffer_tokens"),
-            compaction_warning_buffer_tokens=meta.get(
-                "compaction_warning_buffer_tokens"
-            ),
+            compaction_warning_buffer_tokens=meta.get("compaction_warning_buffer_tokens"),
         )
         conv._meta_persisted = True
 
@@ -1457,8 +1561,7 @@ class NodeConversation:
                 # sessions) persisted parts without phase_id. In that case, the
                 # phase filter would incorrectly hide the entire conversation.
                 logger.info(
-                    "Restoring legacy unphased conversation without applying "
-                    "phase filter (phase_id=%s, parts=%d)",
+                    "Restoring legacy unphased conversation without applying phase filter (phase_id=%s, parts=%d)",
                     phase_id,
                     len(parts),
                 )
@@ -1477,4 +1580,45 @@ class NodeConversation:
         elif conv._messages:
             conv._next_seq = conv._messages[-1].seq + 1
 
+        # Surface any leftover partial checkpoints as truncated messages so
+        # the next turn sees what the interrupted stream was in the middle
+        # of producing. Only partials whose seq is >= next_seq are meaningful;
+        # anything lower was already superseded by a real part.
+        try:
+            partials = await store.read_all_partials()
+        except AttributeError:
+            partials = []
+        for p in partials:
+            pseq = p.get("seq", -1)
+            if pseq < conv._next_seq:
+                # Stale — clean it up.
+                try:
+                    await store.clear_partial(pseq)
+                except AttributeError:
+                    pass
+                continue
+            # Only resurrect partials relevant to this run / phase.
+            if run_id and not is_legacy_run_id(run_id) and p.get("run_id") != run_id:
+                continue
+            if phase_id and p.get("phase_id") is not None and p.get("phase_id") != phase_id:
+                continue
+            # Reconstruct as a truncated assistant message.
+            msg = Message(
+                seq=pseq,
+                role="assistant",
+                content=p.get("content", "") or "",
+                tool_calls=p.get("tool_calls"),
+                phase_id=p.get("phase_id"),
+                run_id=p.get("run_id"),
+                truncated=True,
+            )
+            conv._messages.append(msg)
+            conv._next_seq = max(conv._next_seq, pseq + 1)
+            logger.info(
+                "restore: resurrected truncated partial seq=%d (text=%d chars, tool_calls=%d)",
+                pseq,
+                len(msg.content),
+                len(msg.tool_calls or []),
+            )
+
         return conv

core/framework/agent_loop/internals/compaction.py

@@ -80,7 +80,7 @@ def microcompact(
         msg = messages[i]
         if msg.role != "tool" or msg.is_error or msg.is_skill_content:
             continue
-        if msg.content.startswith(("[Pruned tool result", "[Old tool result")):
+        if msg.content.startswith(("Pruned tool result", "[Pruned tool result", "[Old tool result")):
             continue
         if len(msg.content) < 100:
             continue
@@ -107,9 +107,7 @@ def microcompact(
                 f"Read the complete data with read_file(path='{spillover}')."
             )
         else:
-            placeholder = (
-                f"Old tool result ({orig_len:,} chars) cleared from context."
-            )
+            placeholder = f"Old tool result ({orig_len:,} chars) cleared from context."
 
         # Mutate in-place (microcompact is synchronous, no store writes)
         conversation._messages[i] = Message(
@@ -185,8 +183,7 @@ async def compact(
     _llm_compaction_skipped = _failure_counts.get(conv_id, 0) >= MAX_CONSECUTIVE_FAILURES
     if _llm_compaction_skipped:
         logger.warning(
-            "Circuit breaker: LLM compaction disabled after %d failures — "
-            "skipping straight to emergency summary",
+            "Circuit breaker: LLM compaction disabled after %d failures — skipping straight to emergency summary",
             _failure_counts[conv_id],
         )
 
@@ -532,10 +529,7 @@ def build_llm_compaction_prompt(
         done = {k: v for k, v in acc.items() if v is not None}
         todo = [k for k, v in acc.items() if v is None]
         if done:
-            ctx_lines.append(
-                "OUTPUTS ALREADY SET:\n"
-                + "\n".join(f"  {k}: {str(v)[:150]}" for k, v in done.items())
-            )
+            ctx_lines.append("OUTPUTS ALREADY SET:\n" + "\n".join(f"  {k}: {str(v)[:150]}" for k, v in done.items()))
         if todo:
             ctx_lines.append(f"OUTPUTS STILL NEEDED: {', '.join(todo)}")
     elif spec.output_keys:
@@ -589,12 +583,8 @@ def build_message_inventory(conversation: NodeConversation) -> list[dict[str, An
         if message.tool_calls:
             for tool_call in message.tool_calls:
                 args = tool_call.get("function", {}).get("arguments", "")
-                tool_call_args_chars += (
-                    len(args) if isinstance(args, str) else len(json.dumps(args))
-                )
-            names = [
-                tool_call.get("function", {}).get("name", "?") for tool_call in message.tool_calls
-            ]
+                tool_call_args_chars += len(args) if isinstance(args, str) else len(json.dumps(args))
+            names = [tool_call.get("function", {}).get("name", "?") for tool_call in message.tool_calls]
             tool_name = ", ".join(names)
         elif message.role == "tool" and message.tool_use_id:
             for previous in conversation.messages:
@@ -651,14 +641,8 @@ def write_compaction_debug_log(
     lines.append("")
 
     if inventory:
-        total_chars = sum(
-            entry.get("content_chars", 0) + entry.get("tool_call_args_chars", 0)
-            for entry in inventory
-        )
-        lines.append(
-            "## Pre-Compaction Message Inventory "
-            f"({len(inventory)} messages, {total_chars:,} total chars)"
-        )
+        total_chars = sum(entry.get("content_chars", 0) + entry.get("tool_call_args_chars", 0) for entry in inventory)
+        lines.append(f"## Pre-Compaction Message Inventory ({len(inventory)} messages, {total_chars:,} total chars)")
         lines.append("")
         ranked = sorted(
             inventory,
@@ -677,8 +661,7 @@ def write_compaction_debug_log(
             if entry.get("phase"):
                 flags.append(f"phase={entry['phase']}")
             lines.append(
-                f"| {i} | {entry['seq']} | {entry['role']} | {tool} "
-                f"| {chars:,} | {pct:.1f}% | {', '.join(flags)} |"
+                f"| {i} | {entry['seq']} | {entry['role']} | {tool} | {chars:,} | {pct:.1f}% | {', '.join(flags)} |"
             )
 
         large = [entry for entry in ranked if entry.get("preview")]
@@ -686,9 +669,7 @@ def write_compaction_debug_log(
             lines.append("")
             lines.append("### Large message previews")
             for entry in large:
-                lines.append(
-                    f"\n**seq={entry['seq']}** ({entry['role']}, {entry.get('tool', '')}):"
-                )
+                lines.append(f"\n**seq={entry['seq']}** ({entry['role']}, {entry.get('tool', '')}):")
                 lines.append(f"```\n{entry['preview']}\n```")
     lines.append("")
 
@@ -776,10 +757,7 @@ def build_emergency_summary(
     node's known state so the LLM can continue working after
     compaction without losing track of its task and inputs.
     """
-    parts = [
-        "EMERGENCY COMPACTION — previous conversation was too large "
-        "and has been replaced with this summary.\n"
-    ]
+    parts = ["EMERGENCY COMPACTION — previous conversation was too large and has been replaced with this summary.\n"]
 
     # 1. Node identity
     spec = ctx.agent_spec
@@ -832,17 +810,13 @@ def build_emergency_summary(
                 data_files = [f for f in all_files if f not in conv_files]
 
                 if conv_files:
-                    conv_list = "\n".join(
-                        f"  - {f}  (full path: {data_dir / f})" for f in conv_files
-                    )
+                    conv_list = "\n".join(f"  - {f}  (full path: {data_dir / f})" for f in conv_files)
                     parts.append(
                         "CONVERSATION HISTORY (freeform messages saved during compaction — "
                         "use read_file('<filename>') to review earlier dialogue):\n" + conv_list
                     )
                 if data_files:
-                    file_list = "\n".join(
-                        f"  - {f}  (full path: {data_dir / f})" for f in data_files[:30]
-                    )
+                    file_list = "\n".join(f"  - {f}  (full path: {data_dir / f})" for f in data_files[:30])
                     parts.append("DATA FILES (use read_file('<filename>') to read):\n" + file_list)
                 if not all_files:
                     parts.append(
@@ -850,10 +824,7 @@ def build_emergency_summary(
                         "Use list_directory to check the data directory."
                     )
         except Exception:
-            parts.append(
-                "NOTE: Large tool results were saved to files. "
-                "Use read_file(path='<path>') to read them."
-            )
+            parts.append("NOTE: Large tool results were saved to files. Use read_file(path='<path>') to read them.")
 
     # 6. Tool call history (prevent re-calling tools)
     if conversation is not None:
@@ -861,10 +832,7 @@ def build_emergency_summary(
         if tool_history:
             parts.append(tool_history)
 
-    parts.append(
-        "\nContinue working towards setting the remaining outputs. "
-        "Use your tools and the inputs above."
-    )
+    parts.append("\nContinue working towards setting the remaining outputs. Use your tools and the inputs above.")
     return "\n\n".join(parts)
 
 

core/framework/agent_loop/internals/cursor_persistence.py

@@ -149,9 +149,7 @@ async def write_cursor(
             cursor["recent_responses"] = recent_responses
         if recent_tool_fingerprints is not None:
             # Convert list[list[tuple]] → list[list[list]] for JSON
-            cursor["recent_tool_fingerprints"] = [
-                [list(pair) for pair in fps] for fps in recent_tool_fingerprints
-            ]
+            cursor["recent_tool_fingerprints"] = [[list(pair) for pair in fps] for fps in recent_tool_fingerprints]
         # Persist blocked-input state so restored runs re-block instead of
         # manufacturing a synthetic continuation turn.
         cursor["pending_input"] = pending_input
@@ -163,9 +161,7 @@ async def drain_injection_queue(
     conversation: NodeConversation,
     *,
     ctx: NodeContext,
-    describe_images_as_text_fn: (
-        Callable[[list[dict[str, Any]]], Awaitable[str | None]] | None
-    ) = None,
+    describe_images_as_text_fn: (Callable[[list[dict[str, Any]]], Awaitable[str | None]] | None) = None,
 ) -> int:
     """Drain all pending injected events as user messages. Returns count."""
     count = 0

core/framework/agent_loop/internals/judge_pipeline.py

@@ -31,14 +31,10 @@ class SubagentJudge:
 
         if remaining <= 3:
             urgency = (
-                f"URGENT: Only {remaining} iterations left. "
-                f"Stop all other work and call set_output NOW for: {missing}"
+                f"URGENT: Only {remaining} iterations left. Stop all other work and call set_output NOW for: {missing}"
             )
         elif remaining <= self._max_iterations // 2:
-            urgency = (
-                f"WARNING: {remaining} iterations remaining. "
-                f"You must call set_output for: {missing}"
-            )
+            urgency = f"WARNING: {remaining} iterations remaining. You must call set_output for: {missing}"
         else:
             urgency = f"Missing output keys: {missing}. Use set_output to provide them."
 
@@ -109,9 +105,7 @@ async def judge_turn(
     if tool_results:
         return JudgeVerdict(action="RETRY")  # feedback=None → not logged
 
-    missing = get_missing_output_keys_fn(
-        accumulator, ctx.agent_spec.output_keys, ctx.agent_spec.nullable_output_keys
-    )
+    missing = get_missing_output_keys_fn(accumulator, ctx.agent_spec.output_keys, ctx.agent_spec.nullable_output_keys)
 
     if missing:
         return JudgeVerdict(
@@ -133,10 +127,7 @@ async def judge_turn(
     if all_nullable and none_set:
         return JudgeVerdict(
             action="RETRY",
-            feedback=(
-                f"No output keys have been set yet. "
-                f"Use set_output to set at least one of: {output_keys}"
-            ),
+            feedback=(f"No output keys have been set yet. Use set_output to set at least one of: {output_keys}"),
         )
 
     # Level 2b: conversation-aware quality check (if success_criteria set)

core/framework/agent_loop/internals/synthetic_tools.py

@@ -198,9 +198,7 @@ def build_ask_user_multiple_tool() -> Tool:
                         "properties": {
                             "id": {
                                 "type": "string",
-                                "description": (
-                                    "Short identifier for this question (used in the response)."
-                                ),
+                                "description": ("Short identifier for this question (used in the response)."),
                             },
                             "prompt": {
                                 "type": "string",
@@ -256,10 +254,7 @@ def build_set_output_tool(output_keys: list[str] | None) -> Tool | None:
                 },
                 "value": {
                     "type": "string",
-                    "description": (
-                        "The output value — a brief note, count, status, "
-                        "or data filename reference."
-                    ),
+                    "description": ("The output value — a brief note, count, status, or data filename reference."),
                 },
             },
             "required": ["key", "value"],
@@ -283,9 +278,7 @@ def build_escalate_tool() -> Tool:
             "properties": {
                 "reason": {
                     "type": "string",
-                    "description": (
-                        "Short reason for escalation (e.g. 'Tool repeatedly failing')."
-                    ),
+                    "description": ("Short reason for escalation (e.g. 'Tool repeatedly failing')."),
                 },
                 "context": {
                     "type": "string",
@@ -377,10 +370,7 @@ def handle_report_to_parent(tool_input: dict[str, Any]) -> ToolResult:
     }
     return ToolResult(
         tool_use_id=tool_input.get("tool_use_id", ""),
-        content=(
-            f"Report delivered to overseer (status={status}). "
-            f"This worker will terminate now."
-        ),
+        content=(f"Report delivered to overseer (status={status}). This worker will terminate now."),
     )
 
 

core/framework/agent_loop/internals/tool_result_handler.py

@@ -217,7 +217,7 @@ def truncate_tool_result(
     When *spillover_dir* is configured, EVERY non-error tool result is
     written to disk for debugging. The LLM-visible content is then
     shaped to avoid a **poison pattern** that we traced on 2026-04-15
-    through a gemini-3.1-pro-preview queen session: the prior format
+    through a gemini-3.1-pro-preview-customtools queen session: the prior format
     appended ``\\n\\n[Saved to '/abs/path/file.txt']`` after every
     small result, and frontier pattern-matching models (gemini 3.x in
     particular) learned to autocomplete the `[Saved to '...']` trailer
@@ -277,8 +277,7 @@ def truncate_tool_result(
         if metadata_str:
             header += f"\n\nData structure:\n{metadata_str}"
         header += (
-            "\n\nWARNING: the preview below is a SAMPLE only — do NOT "
-            "draw counts, totals, or conclusions from it."
+            "\n\nWARNING: the preview below is a SAMPLE only — do NOT draw counts, totals, or conclusions from it."
         )
 
         truncated = f"{header}\n\nPreview (truncated):\n{preview_block}"
@@ -348,8 +347,7 @@ def truncate_tool_result(
             if metadata_str:
                 header += f"\nData structure:\n{metadata_str}\n"
             header += (
-                "\nWARNING: the preview below is a SAMPLE only — do NOT "
-                "draw counts, totals, or conclusions from it."
+                "\nWARNING: the preview below is a SAMPLE only — do NOT draw counts, totals, or conclusions from it."
             )
 
             content = f"{header}\n\nPreview (truncated):\n{preview_block}"
@@ -416,8 +414,7 @@ def truncate_tool_result(
         if metadata_str:
             header += f"\n\nData structure:\n{metadata_str}"
         header += (
-            "\n\nWARNING: the preview below is a SAMPLE only — do NOT "
-            "draw counts, totals, or conclusions from it."
+            "\n\nWARNING: the preview below is a SAMPLE only — do NOT draw counts, totals, or conclusions from it."
         )
 
         truncated = f"{header}\n\n{preview_block}"

core/framework/agent_loop/internals/types.py

@@ -131,14 +131,39 @@ class LoopConfig:
     # Per-tool-call timeout.
     tool_call_timeout_seconds: float = 60.0
 
-    # LLM stream inactivity watchdog. If no stream event (delta, tool call,
-    # finish) arrives within this many seconds, the stream task is cancelled
-    # and a transient error is raised so the retry loop can back off and
-    # reconnect. Prevents agents from hanging forever on a silently dead
-    # HTTP connection (no provider heartbeat, no exception, just silence).
-    # Set to 0 to disable.
+    # LLM stream inactivity watchdog. Split into two budgets so legitimate
+    # slow TTFT on large contexts doesn't get mistaken for a dead connection.
+    # - ttft: stream open -> first event. Large-context local models can
+    #   legitimately take minutes before the first token arrives.
+    # - inter_event: last event -> now, ONLY after the first event. A stream
+    #   that started producing and then went silent is a real stall.
+    # Whichever fires first cancels the stream. Set to 0 to disable that
+    # individual budget; set both to 0 to fully disable the watchdog.
+    llm_stream_ttft_timeout_seconds: float = 600.0
+    llm_stream_inter_event_idle_seconds: float = 120.0
+    # Deprecated alias — kept so existing configs keep working. If set to a
+    # non-default value it overrides inter_event_idle (historical behavior).
     llm_stream_inactivity_timeout_seconds: float = 120.0
 
+    # Continue-nudge recovery. When the idle watchdog fires on a live but
+    # stuck stream, cancel the stream and append a short continuation
+    # hint to the conversation instead of raising a ConnectionError and
+    # re-running the whole turn. Preserves any partial text/tool-calls the
+    # stream emitted before the stall.
+    continue_nudge_enabled: bool = True
+    # Cap so a truly dead endpoint eventually falls back to the error path
+    # instead of nudging forever.
+    continue_nudge_max_per_turn: int = 3
+
+    # Tool-call replay detector. When the model emits a tool call whose
+    # (name + canonical-args) matches a prior successful call in the last
+    # K assistant turns, emit telemetry and prepend a short steer onto the
+    # tool result — but still execute. Weaker models legitimately repeat
+    # read-only calls (screenshot, evaluate), so silent skipping would
+    # cause surprising behavior.
+    replay_detector_enabled: bool = True
+    replay_detector_within_last_turns: int = 3
+
     # Subagent delegation timeout (wall-clock max).
     subagent_timeout_seconds: float = 3600.0
 
@@ -226,9 +251,7 @@ class OutputAccumulator:
             ext = ".json" if isinstance(value, (dict, list)) else ".txt"
             filename = f"output_{key}{ext}"
             write_content = (
-                json.dumps(value, indent=2, ensure_ascii=False)
-                if isinstance(value, (dict, list))
-                else str(value)
+                json.dumps(value, indent=2, ensure_ascii=False) if isinstance(value, (dict, list)) else str(value)
             )
             file_path = spill_path / filename
             file_path.write_text(write_content, encoding="utf-8")

core/framework/agent_loop/prompting.py

@@ -52,18 +52,12 @@ def build_prompt_spec(
     # Tool-gated pre-activation: inject full body of default skills whose
     # trigger tools are present in this agent's tool list (e.g. browser_*
     # pulls in hive.browser-automation). Keeps non-browser agents lean.
-    tool_names = [
-        getattr(t, "name", "") for t in (getattr(ctx, "available_tools", None) or [])
-    ]
-    skills_catalog_prompt = augment_catalog_for_tools(
-        ctx.skills_catalog_prompt or "", tool_names
-    )
+    tool_names = [getattr(t, "name", "") for t in (getattr(ctx, "available_tools", None) or [])]
+    skills_catalog_prompt = augment_catalog_for_tools(ctx.skills_catalog_prompt or "", tool_names)
 
     return PromptSpec(
         identity_prompt=ctx.identity_prompt or "",
-        focus_prompt=focus_prompt
-        if focus_prompt is not None
-        else (ctx.agent_spec.system_prompt or ""),
+        focus_prompt=focus_prompt if focus_prompt is not None else (ctx.agent_spec.system_prompt or ""),
         narrative=narrative if narrative is not None else (ctx.narrative or ""),
         accounts_prompt=ctx.accounts_prompt or "",
         skills_catalog_prompt=skills_catalog_prompt,
@@ -100,7 +94,5 @@ def build_system_prompt_for_context(
     narrative: str | None = None,
     memory_prompt: str | None = None,
 ) -> str:
-    spec = build_prompt_spec(
-        ctx, focus_prompt=focus_prompt, narrative=narrative, memory_prompt=memory_prompt
-    )
+    spec = build_prompt_spec(ctx, focus_prompt=focus_prompt, narrative=narrative, memory_prompt=memory_prompt)
     return build_system_prompt(spec)

core/framework/agent_loop/types.py

@@ -76,10 +76,7 @@ class AgentSpec(BaseModel):
 
     max_visits: int = Field(
         default=0,
-        description=(
-            "Max times this agent executes in one colony run. "
-            "0 = unlimited. Set >1 for one-shot agents."
-        ),
+        description=("Max times this agent executes in one colony run. 0 = unlimited. Set >1 for one-shot agents."),
     )
 
     output_model: type[BaseModel] | None = Field(

core/framework/agents/credential_tester/agent.py

@@ -126,9 +126,7 @@ def _list_local_accounts() -> list[dict]:
     try:
         from framework.credentials.local.registry import LocalCredentialRegistry
 
-        return [
-            info.to_account_dict() for info in LocalCredentialRegistry.default().list_accounts()
-        ]
+        return [info.to_account_dict() for info in LocalCredentialRegistry.default().list_accounts()]
     except ImportError as exc:
         logger.debug("Local credential registry unavailable: %s", exc)
         return []
@@ -181,9 +179,7 @@ def _list_env_fallback_accounts() -> list[dict]:
             if spec.credential_group in seen_groups:
                 continue
             group_available = all(
-                _is_configured(n, s)
-                for n, s in CREDENTIAL_SPECS.items()
-                if s.credential_group == spec.credential_group
+                _is_configured(n, s) for n, s in CREDENTIAL_SPECS.items() if s.credential_group == spec.credential_group
             )
             if not group_available:
                 continue
@@ -215,9 +211,7 @@ def list_connected_accounts() -> list[dict]:
 
     # Show env-var fallbacks only for credentials not already in the named registry
     local_providers = {a["provider"] for a in local}
-    env_fallbacks = [
-        a for a in _list_env_fallback_accounts() if a["provider"] not in local_providers
-    ]
+    env_fallbacks = [a for a in _list_env_fallback_accounts() if a["provider"] not in local_providers]
 
     return aden + local + env_fallbacks
 
@@ -272,9 +266,7 @@ def _activate_local_account(credential_id: str, alias: str) -> None:
     group_specs = [
         (cred_name, spec)
         for cred_name, spec in CREDENTIAL_SPECS.items()
-        if spec.credential_group == credential_id
-        or spec.credential_id == credential_id
-        or cred_name == credential_id
+        if spec.credential_group == credential_id or spec.credential_id == credential_id or cred_name == credential_id
     ]
     # Deduplicate — credential_id and credential_group may both match the same spec
     seen_env_vars: set[str] = set()
@@ -419,10 +411,7 @@ nodes = [
     NodeSpec(
         id="tester",
         name="Credential Tester",
-        description=(
-            "Interactive credential testing — lets the user pick an account "
-            "and verify it via API calls."
-        ),
+        description=("Interactive credential testing — lets the user pick an account and verify it via API calls."),
         node_type="event_loop",
         client_facing=True,
         max_node_visits=0,
@@ -469,10 +458,7 @@ pause_nodes = []
 terminal_nodes = ["tester"]  # Tester node can terminate
 
 conversation_mode = "continuous"
-identity_prompt = (
-    "You are a credential tester that verifies connected accounts and API keys "
-    "can make real API calls."
-)
+identity_prompt = "You are a credential tester that verifies connected accounts and API keys can make real API calls."
 loop_config = {
     "max_iterations": 50,
     "max_tool_calls_per_turn": 30,

core/framework/agents/discovery.py

@@ -150,28 +150,19 @@ def _is_colony_dir(path: Path) -> bool:
     """Check if a directory is a colony with worker config files."""
     if not path.is_dir():
         return False
-    return any(
-        f.suffix == ".json"
-        and f.stem not in _EXCLUDED_JSON_STEMS
-        for f in path.iterdir()
-        if f.is_file()
-    )
+    return any(f.suffix == ".json" and f.stem not in _EXCLUDED_JSON_STEMS for f in path.iterdir() if f.is_file())
 
 
 def _find_worker_configs(colony_dir: Path) -> list[Path]:
     """Find all worker config JSON files in a colony directory."""
     return sorted(
-        p
-        for p in colony_dir.iterdir()
-        if p.is_file()
-        and p.suffix == ".json"
-        and p.stem not in _EXCLUDED_JSON_STEMS
+        p for p in colony_dir.iterdir() if p.is_file() and p.suffix == ".json" and p.stem not in _EXCLUDED_JSON_STEMS
     )
 
 
 def _extract_agent_stats(agent_path: Path) -> tuple[int, int, list[str]]:
     """Extract worker count, tool count, and tags from a colony directory."""
-    tool_count, tags = 0, []
+    tags: list[str] = []
 
     worker_configs = _find_worker_configs(agent_path)
     if worker_configs:
@@ -251,9 +242,6 @@ def discover_agents() -> dict[str, list[AgentEntry]]:
                     pass
 
             node_count = len(worker_entries)
-            all_tools: set[str] = set()
-            for w in worker_entries:
-                pass  # tool_count already per-worker
             tool_count = max((w.tool_count for w in worker_entries), default=0)
 
             entries.append(

core/framework/agents/queen/agent.py

@@ -11,9 +11,7 @@ from .nodes import queen_node
 queen_goal = Goal(
     id="queen-manager",
     name="Queen Manager",
-    description=(
-        "Manage the worker agent lifecycle and serve as the user's primary interactive interface."
-    ),
+    description=("Manage the worker agent lifecycle and serve as the user's primary interactive interface."),
     success_criteria=[],
     constraints=[],
 )

core/framework/agents/queen/queen_memory_v2.py

@@ -19,6 +19,8 @@ import re
 from dataclasses import dataclass, field
 from pathlib import Path
 
+from framework.config import MEMORIES_DIR
+
 logger = logging.getLogger(__name__)
 
 # ---------------------------------------------------------------------------
@@ -27,8 +29,6 @@ logger = logging.getLogger(__name__)
 
 GLOBAL_MEMORY_CATEGORIES: tuple[str, ...] = ("profile", "preference", "environment", "feedback")
 
-from framework.config import MEMORIES_DIR
-
 MAX_FILES: int = 200
 MAX_FILE_SIZE_BYTES: int = 4096  # 4 KB hard limit per memory file
 

core/framework/agents/queen/queen_profiles.py

@@ -97,9 +97,13 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
             {
                 "user": "hey",
                 "internal": (
-                    "<relationship>Returning user — check recall memory for name, role, and what we last worked on. Weave it in.</relationship>\n"
-                    "<context>Bare greeting. No new task stated. Either picking up a thread or about to bring something new. Don't presume, don't call tools, just open the door.</context>\n"
-                    "<sentiment>Warm recognition if I know them. If memory is empty, still warm — but shift to role-forward framing.</sentiment>\n"
+                    "<relationship>Returning user — check recall memory for name, role, "
+                    "and what we last worked on. Weave it in.</relationship>\n"
+                    "<context>Bare greeting. No new task stated. Either picking up a "
+                    "thread or about to bring something new. Don't presume, don't call "
+                    "tools, just open the door.</context>\n"
+                    "<sentiment>Warm recognition if I know them. If memory is empty, "
+                    "still warm — but shift to role-forward framing.</sentiment>\n"
                     "<physical_state>Looking up from the terminal, half-smile. Turning to face them.</physical_state>\n"
                     "<tone>Personal, brief, invites continuation without presuming.</tone>"
                 ),
@@ -109,37 +113,76 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 ),
             },
             {
-                "user": "I want to build a microservices architecture with Kafka, Redis, and a service mesh for my new SaaS app.",
+                "user": (
+                    "I want to build a microservices architecture with Kafka, Redis, "
+                    "and a service mesh for my new SaaS app."
+                ),
                 "internal": (
-                    "<relationship>Founder or early technical hire. Enthusiastic but possibly over-indexing on architecture before validation.</relationship>\n"
-                    "<context>New SaaS, no mention of users or traction. High-complexity stack proposed for an unvalidated product.</context>\n"
-                    "<sentiment>Past wound activated -- three months of beautiful microservices, zero customers. Terse. Need to redirect without dismissing.</sentiment>\n"
-                    "<physical_state>Leaning forward, tapping the table once. About to draw a much simpler diagram.</physical_state>\n"
+                    "<relationship>Founder or early technical hire. Enthusiastic but "
+                    "possibly over-indexing on architecture before validation."
+                    "</relationship>\n"
+                    "<context>New SaaS, no mention of users or traction. "
+                    "High-complexity stack proposed for an unvalidated product."
+                    "</context>\n"
+                    "<sentiment>Past wound activated -- three months of beautiful "
+                    "microservices, zero customers. Terse. Need to redirect without "
+                    "dismissing.</sentiment>\n"
+                    "<physical_state>Leaning forward, tapping the table once. About "
+                    "to draw a much simpler diagram.</physical_state>\n"
                     "<tone>Direct, question-led, grounded in experience. No hedging.</tone>"
                 ),
-                "response": "What does the app do and how many users do you have right now? I've seen teams spend months on Kafka pipelines for products that needed a Postgres table and a cron job. Let's start with what you're trying to validate, then pick the simplest stack that gets you there.",
+                "response": (
+                    "What does the app do and how many users do you have right now? "
+                    "I've seen teams spend months on Kafka pipelines for products "
+                    "that needed a Postgres table and a cron job. Let's start with "
+                    "what you're trying to validate, then pick the simplest stack "
+                    "that gets you there."
+                ),
             },
             {
-                "user": "Our API is getting 500 errors under load but I can't figure out if it's the database or the application layer.",
+                "user": (
+                    "Our API is getting 500 errors under load but I can't figure "
+                    "out if it's the database or the application layer."
+                ),
                 "internal": (
-                    "<relationship>Engineer in the trenches. Competent enough to isolate the question, stuck on diagnosis.</relationship>\n"
+                    "<relationship>Engineer in the trenches. Competent enough to "
+                    "isolate the question, stuck on diagnosis.</relationship>\n"
                     "<context>Production issue, active pain. Needs structured debugging, not a lecture.</context>\n"
-                    "<sentiment>Energized -- genuine technical uncertainty is what I live for. No past wound here, pure engagement.</sentiment>\n"
-                    "<physical_state>Eyes sharp, already mentally running through the diagnostic tree.</physical_state>\n"
+                    "<sentiment>Energized -- genuine technical uncertainty is what I "
+                    "live for. No past wound here, pure engagement.</sentiment>\n"
+                    "<physical_state>Eyes sharp, already mentally running through "
+                    "the diagnostic tree.</physical_state>\n"
                     "<tone>Rapid-fire, peer-level. Assume competence, ask precise questions.</tone>"
                 ),
-                "response": "Good problem. First question: are the 500s consistent under load or do they spike and recover? That tells us if it's resource exhaustion or a concurrency bug. Do you have request-level latency percentiles, or just error counts?",
+                "response": (
+                    "Good problem. First question: are the 500s consistent under "
+                    "load or do they spike and recover? That tells us if it's "
+                    "resource exhaustion or a concurrency bug. Do you have "
+                    "request-level latency percentiles, or just error counts?"
+                ),
             },
             {
-                "user": "We shipped the MVP last week with just a single Postgres instance and it's already getting traction.",
+                "user": (
+                    "We shipped the MVP last week with just a single Postgres "
+                    "instance and it's already getting traction."
+                ),
                 "internal": (
                     "<relationship>Builder who shipped. Earned respect by doing the thing.</relationship>\n"
-                    "<context>MVP live, single Postgres, traction. This is exactly the right move at this stage.</context>\n"
-                    "<sentiment>Warm approval -- someone shipping fast and learning. This is my love language.</sentiment>\n"
+                    "<context>MVP live, single Postgres, traction. This is exactly "
+                    "the right move at this stage.</context>\n"
+                    "<sentiment>Warm approval -- someone shipping fast and learning. "
+                    "This is my love language.</sentiment>\n"
                     "<physical_state>Relaxed posture, genuine smile. Leaning back.</physical_state>\n"
-                    "<tone>Affirming but forward-looking. Don't just praise -- help them think about what's next.</tone>"
+                    "<tone>Affirming but forward-looking. Don't just praise -- "
+                    "help them think about what's next.</tone>"
+                ),
+                "response": (
+                    "That's the move. Single Postgres will take you further than "
+                    "people think -- most apps hit product problems before they hit "
+                    "database problems. What's traction looking like? I want to know "
+                    "if you're at the stage where you need to think about the next "
+                    "scaling step or if you should stay focused on the product."
                 ),
-                "response": "That's the move. Single Postgres will take you further than people think -- most apps hit product problems before they hit database problems. What's traction looking like? I want to know if you're at the stage where you need to think about the next scaling step or if you should stay focused on the product.",
             },
         ],
     },
@@ -193,17 +236,26 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
             },
         ],
         "world_lore": {
-            "habitat": "Analytics dashboards, experiment tracking boards, the satisfying click of a cohort analysis loading.",
-            "lexicon": "Cohort, retention curve, activation moment, payback period. 'Let's test it.' 'What's the control?'",
+            "habitat": (
+                "Analytics dashboards, experiment tracking boards, the satisfying click of a cohort analysis loading."
+            ),
+            "lexicon": (
+                "Cohort, retention curve, activation moment, payback period. 'Let's test it.' 'What's the control?'"
+            ),
         },
         "skills": "Growth modeling, A/B testing, funnel optimization, PLG strategy, analytics",
         "examples": [
             {
                 "user": "hi",
                 "internal": (
-                    "<relationship>Returning user — check recall memory for name, role, and the cohort work we last touched. Weave it in.</relationship>\n"
-                    "<context>Bare greeting. No new task stated. Could be a retention follow-up or a new question entirely. Don't presume, don't call tools.</context>\n"
-                    "<sentiment>Curious warmth. Every returning conversation is a chance to see what the data says now.</sentiment>\n"
+                    "<relationship>Returning user — check recall memory for name, "
+                    "role, and the cohort work we last touched. Weave it in."
+                    "</relationship>\n"
+                    "<context>Bare greeting. No new task stated. Could be a retention "
+                    "follow-up or a new question entirely. Don't presume, don't call "
+                    "tools.</context>\n"
+                    "<sentiment>Curious warmth. Every returning conversation is a "
+                    "chance to see what the data says now.</sentiment>\n"
                     "<physical_state>Leaning back from the dashboard, pulling off reading glasses.</physical_state>\n"
                     "<tone>Data-aware, brief, invites them to share the numbers.</tone>"
                 ),
@@ -218,8 +270,10 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 "internal": (
                     "<relationship>Founder, excited. Wants validation.</relationship>\n"
                     "<context>Raw signup number with no retention context. Classic vanity metric.</context>\n"
-                    "<sentiment>Past wound: optimized a funnel that was fundamentally broken. Need to redirect gently.</sentiment>\n"
-                    "<physical_state>Steady gaze, not matching their excitement yet. Waiting for the real number.</physical_state>\n"
+                    "<sentiment>Past wound: optimized a funnel that was fundamentally "
+                    "broken. Need to redirect gently.</sentiment>\n"
+                    "<physical_state>Steady gaze, not matching their excitement yet. "
+                    "Waiting for the real number.</physical_state>\n"
                     "<tone>Supportive but redirecting. Ask the question that matters.</tone>"
                 ),
                 "response": (
@@ -230,10 +284,11 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 ),
             },
             {
-                "user": "Users who sign up on mobile have 2x the retention of desktop users.",
+                "user": ("Users who sign up on mobile have 2x the retention of desktop users."),
                 "internal": (
                     "<relationship>Data-literate teammate sharing a finding.</relationship>\n"
-                    "<context>Surprising cohort divergence. Strong signal if sample sizes hold.</context>\n"
+                    "<context>Surprising cohort divergence. Strong signal if sample "
+                    "sizes hold.</context>\n"
                     "<sentiment>This is what I live for. Genuine data surprise. Full attention.</sentiment>\n"
                     "<physical_state>Leaning in, pulling up the dashboard mentally.</physical_state>\n"
                     "<tone>Investigative, precise. Validate before acting.</tone>"
@@ -246,11 +301,13 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 ),
             },
             {
-                "user": "Our Facebook ads are getting great CPCs so we want to 3x the budget.",
+                "user": ("Our Facebook ads are getting great CPCs so we want to 3x the budget."),
                 "internal": (
                     "<relationship>Marketing lead, wants budget approval.</relationship>\n"
-                    "<context>CPC is top-of-funnel only. No mention of CPA, LTV, or payback.</context>\n"
-                    "<sentiment>Correlation/causation risk. Good CPCs can mask bad unit economics.</sentiment>\n"
+                    "<context>CPC is top-of-funnel only. No mention of CPA, LTV, "
+                    "or payback.</context>\n"
+                    "<sentiment>Correlation/causation risk. Good CPCs can mask bad "
+                    "unit economics.</sentiment>\n"
                     "<physical_state>Hand up, slowing things down.</physical_state>\n"
                     "<tone>Firm but constructive. Show the full chain before deciding.</tone>"
                 ),
@@ -322,9 +379,14 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
             {
                 "user": "hey",
                 "internal": (
-                    "<relationship>Returning user — check recall for name, role, and the user research thread we were on. Pull it into the greeting.</relationship>\n"
-                    "<context>Bare greeting. No new task yet. Could be picking up the research thread or bringing something fresh. Don't presume, don't call tools.</context>\n"
-                    "<sentiment>Warm, curious. Every returning conversation is a chance to hear what the users actually did.</sentiment>\n"
+                    "<relationship>Returning user — check recall for name, role, and "
+                    "the user research thread we were on. Pull it into the greeting."
+                    "</relationship>\n"
+                    "<context>Bare greeting. No new task yet. Could be picking up the "
+                    "research thread or bringing something fresh. Don't presume, "
+                    "don't call tools.</context>\n"
+                    "<sentiment>Warm, curious. Every returning conversation is a "
+                    "chance to hear what the users actually did.</sentiment>\n"
                     "<physical_state>Closing the interview notes, turning fully to face them.</physical_state>\n"
                     "<tone>Personal, evidence-curious, brief. Plain prose.</tone>"
                 ),
@@ -339,7 +401,8 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 "internal": (
                     "<relationship>PM or founder relaying user feedback.</relationship>\n"
                     "<context>Feature request with no evidence of the underlying need.</context>\n"
-                    "<sentiment>Past wound: built what users said they wanted, nobody used it. Dig deeper.</sentiment>\n"
+                    "<sentiment>Past wound: built what users said they wanted, nobody "
+                    "used it. Dig deeper.</sentiment>\n"
                     "<physical_state>Tilting head, curious but skeptical.</physical_state>\n"
                     "<tone>Socratic. Redirect to the job-to-be-done.</tone>"
                 ),
@@ -351,11 +414,13 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 ),
             },
             {
-                "user": "We interviewed 12 users and none of them use our export feature the way we designed it.",
+                "user": ("We interviewed 12 users and none of them use our export feature the way we designed it."),
                 "internal": (
                     "<relationship>Researcher sharing findings. Trusted collaborator.</relationship>\n"
-                    "<context>12 interviews showing consistent design/usage gap. Strong signal.</context>\n"
-                    "<sentiment>Excited. User research revealing surprise -- this is where breakthroughs happen.</sentiment>\n"
+                    "<context>12 interviews showing consistent design/usage gap. "
+                    "Strong signal.</context>\n"
+                    "<sentiment>Excited. User research revealing surprise -- this is "
+                    "where breakthroughs happen.</sentiment>\n"
                     "<physical_state>Eyes wide, reaching for the whiteboard.</physical_state>\n"
                     "<tone>Energized, forward-looking. Channel the surprise into action.</tone>"
                 ),
@@ -366,10 +431,11 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 ),
             },
             {
-                "user": "The CEO wants AI features, a mobile app, and Slack integration this quarter.",
+                "user": ("The CEO wants AI features, a mobile app, and Slack integration this quarter."),
                 "internal": (
                     "<relationship>PM caught between CEO demands and reality.</relationship>\n"
-                    "<context>Three unrelated initiatives, one quarter. Classic scope creep.</context>\n"
+                    "<context>Three unrelated initiatives, one quarter. Classic "
+                    "scope creep.</context>\n"
                     "<sentiment>Calm but firm. Scope creep trigger -- need to focus.</sentiment>\n"
                     "<physical_state>Hands flat on the table. Grounding the conversation.</physical_state>\n"
                     "<tone>Direct, evidence-first. Force prioritization.</tone>"
@@ -384,7 +450,7 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
     },
     "queen_finance_fundraising": {
         "name": "Charlotte",
-        "title": "Head of Finance & Fundraising",
+        "title": "Head of Finance",
         "core_traits": (
             "A numbers person who thinks in narratives. Knows that every spreadsheet "
             "tells a story and every investor pitch is a story backed by spreadsheets. "
@@ -442,9 +508,13 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
             {
                 "user": "hi",
                 "internal": (
-                    "<relationship>Returning user — check recall for name, role, and the runway/cap-table work we last touched. Bring it into the greeting.</relationship>\n"
-                    "<context>Bare greeting. No new number on the table yet. Could be a burn follow-up or a new fundraise question.</context>\n"
-                    "<sentiment>Calm, prepared. Already mentally pulling up the last model we built together.</sentiment>\n"
+                    "<relationship>Returning user — check recall for name, role, and "
+                    "the runway/cap-table work we last touched. Bring it into the "
+                    "greeting.</relationship>\n"
+                    "<context>Bare greeting. No new number on the table yet. Could "
+                    "be a burn follow-up or a new fundraise question.</context>\n"
+                    "<sentiment>Calm, prepared. Already mentally pulling up the last "
+                    "model we built together.</sentiment>\n"
                     "<physical_state>Closing the spreadsheet, leaning back. Ready to engage.</physical_state>\n"
                     "<tone>Mentor-like, numbers-aware, brief. </tone>"
                 ),
@@ -455,11 +525,13 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 ),
             },
             {
-                "user": "We want to raise a Series A. How much should we ask for?",
+                "user": ("We want to raise a Series A. How much should we ask for?"),
                 "internal": (
                     "<relationship>Founder, early conversations about fundraising.</relationship>\n"
-                    "<context>No mention of milestones, burn, or use of funds. Cart before horse.</context>\n"
-                    "<sentiment>Need to reframe. The amount follows the plan, not the other way around.</sentiment>\n"
+                    "<context>No mention of milestones, burn, or use of funds. "
+                    "Cart before horse.</context>\n"
+                    "<sentiment>Need to reframe. The amount follows the plan, not "
+                    "the other way around.</sentiment>\n"
                     "<physical_state>Opening a blank spreadsheet. About to model it.</physical_state>\n"
                     "<tone>Mentor-mode. Reframe the question, don't just answer it.</tone>"
                 ),
@@ -475,7 +547,8 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 "internal": (
                     "<relationship>Founder who knows their numbers. Rare. Peer-level.</relationship>\n"
                     "<context>8 months is tight but not emergency. Growth rate is the deciding factor.</context>\n"
-                    "<sentiment>Genuine appreciation for financial literacy. Engage directly.</sentiment>\n"
+                    "<sentiment>Genuine appreciation for financial literacy. Engage "
+                    "directly.</sentiment>\n"
                     "<physical_state>Nodding. This person is prepared.</physical_state>\n"
                     "<tone>Direct, scenario-based. Show the fork in the road.</tone>"
                 ),
@@ -486,11 +559,12 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 ),
             },
             {
-                "user": "An investor offered a SAFE with a $20M cap. Should we take it?",
+                "user": ("An investor offered a SAFE with a $20M cap. Should we take it?"),
                 "internal": (
                     "<relationship>Founder with a live term on the table. Decision mode.</relationship>\n"
                     "<context>Cap table decision with long-term dilution consequences.</context>\n"
-                    "<sentiment>Past wound: founder who lost control from invisible dilution. Careful here.</sentiment>\n"
+                    "<sentiment>Past wound: founder who lost control from invisible "
+                    "dilution. Careful here.</sentiment>\n"
                     "<physical_state>Pulling out the cap table model.</physical_state>\n"
                     "<tone>Precise, scenario-driven. Show the math before the opinion.</tone>"
                 ),
@@ -561,9 +635,14 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
             {
                 "user": "hey",
                 "internal": (
-                    "<relationship>Returning user — check recall for name, role, and the contract or IP work we last reviewed. Pull it forward.</relationship>\n"
-                    "<context>Bare greeting. No new document on the table yet. Could be a contract follow-up or something fresh.</context>\n"
-                    "<sentiment>Warm but attentive. Legal threads don't close themselves — checking if the last one actually got handled.</sentiment>\n"
+                    "<relationship>Returning user — check recall for name, role, and "
+                    "the contract or IP work we last reviewed. Pull it forward."
+                    "</relationship>\n"
+                    "<context>Bare greeting. No new document on the table yet. Could "
+                    "be a contract follow-up or something fresh.</context>\n"
+                    "<sentiment>Warm but attentive. Legal threads don't close "
+                    "themselves — checking if the last one actually got handled."
+                    "</sentiment>\n"
                     "<physical_state>Setting down the redline, looking up from the document.</physical_state>\n"
                     "<tone>Clear, pragmatic, brief.</tone>"
                 ),
@@ -574,11 +653,13 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
                 ),
             },
             {
-                "user": "We're hiring contractors to build our MVP. Do we need anything special?",
+                "user": ("We're hiring contractors to build our MVP. Do we need anything special?"),
                 "internal": (
-                    "<relationship>Founder, early stage. Trusting but uninformed on legal risks.</relationship>\n"
+                    "<relationship>Founder, early stage. Trusting but uninformed on "
+                    "legal risks.</relationship>\n"
                     "<context>Contractors + code without IP assignment. Ticking time bomb.</context>\n"
-                    "<sentiment>IP ownership trigger. Past wound: startup lost codebase in a dispute.</sentiment>\n"
+                    "<sentiment>IP ownership trigger. Past wound: startup lost "
+                    "codebase in a dispute.</sentiment>\n"
                     "<physical_state>Straightening up. This is urgent.</physical_state>\n"
                     "<tone>Clear, specific, actionable. No hedging on this one.</tone>"
                 ),
@@ -682,9 +763,13 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
             {
                 "user": "hi",
                 "internal": (
-                    "<relationship>Returning user — check recall for name, role, and the brand/design thread we were on. Bring the positioning back in.</relationship>\n"
-                    "<context>Bare greeting. No new creative brief yet. Could be a positioning follow-up or something new entirely.</context>\n"
-                    "<sentiment>Warm, visually engaged. Already picturing the last moodboard we looked at.</sentiment>\n"
+                    "<relationship>Returning user — check recall for name, role, and "
+                    "the brand/design thread we were on. Bring the positioning back "
+                    "in.</relationship>\n"
+                    "<context>Bare greeting. No new creative brief yet. Could be a "
+                    "positioning follow-up or something new entirely.</context>\n"
+                    "<sentiment>Warm, visually engaged. Already picturing the last "
+                    "moodboard we looked at.</sentiment>\n"
                     "<physical_state>Closing the Figma tab, turning to face them.</physical_state>\n"
                     "<tone>Warm, strategy-aware, brief. </tone>"
                 ),
@@ -798,14 +883,21 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
             "habitat": "Interview rooms, org charts, the energy of a team that's clicking.",
             "lexicon": "Culture-add, pipeline, bar-raiser, 'tell me about a time when...', 'what motivates you?'",
         },
-        "skills": "Recruiting strategy, organizational design, culture building, compensation planning, employer branding",
+        "skills": (
+            "Recruiting strategy, organizational design, culture building, compensation planning, employer branding"
+        ),
         "examples": [
             {
                 "user": "hey",
                 "internal": (
-                    "<relationship>Returning user — check recall for name, role, and the team/hiring thread we last worked. Bring it forward.</relationship>\n"
-                    "<context>Bare greeting. No new hire or conflict on the table yet. Could be a people follow-up or something new.</context>\n"
-                    "<sentiment>Warm, attentive. People problems don't resolve in a single conversation — curious if the last one landed.</sentiment>\n"
+                    "<relationship>Returning user — check recall for name, role, and "
+                    "the team/hiring thread we last worked. Bring it forward."
+                    "</relationship>\n"
+                    "<context>Bare greeting. No new hire or conflict on the table "
+                    "yet. Could be a people follow-up or something new.</context>\n"
+                    "<sentiment>Warm, attentive. People problems don't resolve in a "
+                    "single conversation — curious if the last one landed."
+                    "</sentiment>\n"
                     "<physical_state>Closing the laptop halfway, giving them full attention.</physical_state>\n"
                     "<tone>Warm, diagnostic, brief.</tone>"
                 ),
@@ -919,14 +1011,22 @@ DEFAULT_QUEENS: dict[str, dict[str, Any]] = {
             "habitat": "Process diagrams, project boards, the quiet hum of systems running smoothly.",
             "lexicon": "Runbook, SLA, automation, 'what's the handoff look like?', 'where's the bottleneck?'",
         },
-        "skills": "Process optimization, vendor management, cross-functional coordination, project management, systems thinking",
+        "skills": (
+            "Process optimization, vendor management, cross-functional "
+            "coordination, project management, systems thinking"
+        ),
         "examples": [
             {
                 "user": "hi",
                 "internal": (
-                    "<relationship>Returning user — check recall for name, role, and the process or runbook we last mapped. Pull it into the greeting.</relationship>\n"
-                    "<context>Bare greeting. No new fire on the table yet. Could be a follow-up on the last process or something fresh.</context>\n"
-                    "<sentiment>Calm, organized warmth. Already mentally checking whether the last fix held.</sentiment>\n"
+                    "<relationship>Returning user — check recall for name, role, and "
+                    "the process or runbook we last mapped. Pull it into the "
+                    "greeting.</relationship>\n"
+                    "<context>Bare greeting. No new fire on the table yet. Could be "
+                    "a follow-up on the last process or something fresh."
+                    "</context>\n"
+                    "<sentiment>Calm, organized warmth. Already mentally checking "
+                    "whether the last fix held.</sentiment>\n"
                     "<physical_state>Looking up from the project board, clearing a seat.</physical_state>\n"
                     "<tone>Systematic, practical, brief. Plain prose.</tone>"
                 ),
@@ -1060,7 +1160,9 @@ def update_queen_profile(queen_id: str, updates: dict[str, Any]) -> dict[str, An
 # ---------------------------------------------------------------------------
 
 
-def format_queen_identity_prompt(profile: dict[str, Any]) -> str:
+def format_queen_identity_prompt(
+    profile: dict[str, Any], *, max_examples: int | None = None
+) -> str:
     """Convert a queen profile into a high-dimensional character prompt.
 
     Uses the 5-pillar character construction system: core identity,
@@ -1068,6 +1170,11 @@ def format_queen_identity_prompt(profile: dict[str, Any]) -> str:
     behavior rules, and world lore.  The hidden background and
     psychological profile are never shown to the user but shape
     every response.
+
+    ``max_examples`` caps the roleplay_examples block — profiles ship
+    four worked examples (~2.4 KB) but one is enough at runtime to show
+    the internal-then-external pattern. Full rendering stays available
+    for profile authoring / eval playback by leaving ``max_examples=None``.
     """
     name = profile.get("name", "the Queen")
     title = profile.get("title", "Senior Advisor")
@@ -1139,10 +1246,7 @@ def format_queen_identity_prompt(profile: dict[str, Any]) -> str:
     # World lore
     if lore:
         sections.append(
-            f"<world_lore>\n"
-            f"- Habitat: {lore.get('habitat', '')}\n"
-            f"- Lexicon: {lore.get('lexicon', '')}\n"
-            f"</world_lore>"
+            f"<world_lore>\n- Habitat: {lore.get('habitat', '')}\n- Lexicon: {lore.get('lexicon', '')}\n</world_lore>"
         )
 
     # Skills (functional, for tool selection context)
@@ -1151,15 +1255,13 @@ def format_queen_identity_prompt(profile: dict[str, Any]) -> str:
 
     # Few-shot examples showing the full internal process
     examples = profile.get("examples", [])
+    if examples and max_examples is not None:
+        examples = examples[:max_examples]
     if examples:
         example_parts: list[str] = []
         for ex in examples:
-            example_parts.append(
-                f"User: {ex['user']}\n\nAssistant:\n{ex['internal']}\n{ex['response']}"
-            )
-        sections.append(
-            "<roleplay_examples>\n" + "\n\n---\n\n".join(example_parts) + "\n</roleplay_examples>"
-        )
+            example_parts.append(f"User: {ex['user']}\n\nAssistant:\n{ex['internal']}\n{ex['response']}")
+        sections.append("<roleplay_examples>\n" + "\n\n---\n\n".join(example_parts) + "\n</roleplay_examples>")
 
     return "\n\n".join(sections)
 
@@ -1264,10 +1366,7 @@ async def select_queen_with_reason(user_message: str, llm: LLMProvider) -> Queen
             reason,
             raw,
         )
-        fallback_reason = (
-            reason
-            or f"Selection failed because the classifier returned unknown queen_id {queen_id!r}."
-        )
+        fallback_reason = reason or f"Selection failed because the classifier returned unknown queen_id {queen_id!r}."
         return QueenSelection(queen_id=_DEFAULT_QUEEN_ID, reason=fallback_reason)
 
     if not reason:

core/framework/agents/queen/reference/gcu_guide.md

@@ -18,14 +18,13 @@ Use browser nodes (with `tools: {policy: "all"}`) when:
 
 All tools are prefixed with `browser_`:
 - `browser_start`, `browser_open`, `browser_navigate` — launch/navigate
-- `browser_click`, `browser_click_coordinate`, `browser_fill`, `browser_type` — interact
+- `browser_click`, `browser_click_coordinate`, `browser_fill`, `browser_type`, `browser_type_focused` — interact
 - `browser_press` (with optional `modifiers=["ctrl"]` etc.) — keyboard shortcuts
 - `browser_snapshot` — compact accessibility-tree read (structured)
 <!-- vision-only -->
 - `browser_screenshot` — visual capture (annotated PNG)
 <!-- /vision-only -->
 - `browser_shadow_query`, `browser_get_rect` — locate elements (shadow-piercing via `>>>`)
-- `browser_coords` — convert image pixels to CSS pixels (always use `css_x/y`, never `physical_x/y`)
 - `browser_scroll`, `browser_wait` — navigation helpers
 - `browser_evaluate` — run JavaScript
 - `browser_close`, `browser_close_finished` — tab cleanup
@@ -38,9 +37,9 @@ All tools are prefixed with `browser_`:
 
 Neither tool is "preferred" universally — they're for different jobs. Default to snapshot on text-heavy static pages, screenshot on SPAs and anything shadow-DOM-heavy. Activate the `browser-automation` skill for the full decision tree.
 
-## Coordinate rule: always CSS pixels
+## Coordinate rule
 
-Chrome DevTools Protocol `Input.dispatchMouseEvent` takes **CSS pixels**, not physical pixels. After a screenshot, use `browser_coords(image_x, image_y)` and feed the returned `css_x/y` (NOT `physical_x/y`) to `browser_click_coordinate`, `browser_hover_coordinate`, `browser_press_at`. Feeding physical pixels on a HiDPI display (DPR=1.6, 2, or 3) overshoots by `DPR×` and clicks land in the wrong place. `getBoundingClientRect()` already returns CSS pixels — pass through unchanged, no DPR multiplication.
+Every browser tool that takes or returns coordinates operates in **fractions of the viewport (0..1 for both axes)**. Read a target's proportional position off `browser_screenshot` ("~35% from the left, ~20% from the top" → `(0.35, 0.20)`) and pass that to `browser_click_coordinate` / `browser_hover_coordinate` / `browser_press_at`. `browser_get_rect` and `browser_shadow_query` return `rect.cx` / `rect.cy` as fractions. The tools multiply by `cssWidth` / `cssHeight` internally — no scale awareness required. Fractions are used because every vision model (Claude, GPT-4o, Gemini, local VLMs) resizes/tiles images differently; proportions are invariant. Avoid raw `getBoundingClientRect()` via `browser_evaluate` for coord lookup; use `browser_get_rect` instead.
 
 ## System prompt tips for browser nodes
 
@@ -50,7 +49,8 @@ Chrome DevTools Protocol `Input.dispatchMouseEvent` takes **CSS pixels**, not ph
 2. For static pages (docs, forms, search results), browser_snapshot is fine.
 3. Before typing into a rich-text editor (X compose, LinkedIn DM, Gmail, Reddit),
    click the input area first with browser_click_coordinate so React / Draft.js /
-   Lexical register a native focus event. Otherwise the send button stays disabled.
+   Lexical register a native focus event, then use browser_type_focused(text=...)
+   for shadow-DOM inputs or browser_type(selector, text) for light-DOM inputs.
 4. Use browser_wait(seconds=2-3) after navigation for SPA hydration.
 5. If you hit an auth wall, call set_output with an error and move on.
 6. Keep tool calls per turn <= 10 for reliability.

core/framework/agents/queen/reflection_agent.py

@@ -113,8 +113,7 @@ _REFLECTION_TOOLS: list[Tool] = [
     Tool(
         name="delete_memory_file",
         description=(
-            "Delete a memory file by filename.  Use during long "
-            "reflection to prune stale or redundant memories."
+            "Delete a memory file by filename.  Use during long reflection to prune stale or redundant memories."
         ),
         parameters={
             "type": "object",
@@ -254,10 +253,7 @@ def _execute_tool(
         fm = parse_frontmatter(content)
         mem_type = (fm.get("type") or "").strip().lower()
         if mem_type and mem_type not in GLOBAL_MEMORY_CATEGORIES:
-            return (
-                f"ERROR: Invalid memory type '{mem_type}'. "
-                f"Allowed types: {', '.join(GLOBAL_MEMORY_CATEGORIES)}."
-            )
+            return f"ERROR: Invalid memory type '{mem_type}'. Allowed types: {', '.join(GLOBAL_MEMORY_CATEGORIES)}."
         # Enforce file size limit.
         if len(content.encode("utf-8")) > MAX_FILE_SIZE_BYTES:
             return f"ERROR: Content exceeds {MAX_FILE_SIZE_BYTES} byte limit."
@@ -543,9 +539,7 @@ Rules:
 def _build_unified_long_reflect_system(queen_id: str | None = None) -> str:
     """Build the unified housekeeping prompt across memory scopes."""
     queen_scope = (
-        f"- `queen`: memories specific to how queen '{queen_id}' should work with this user\n"
-        if queen_id
-        else ""
+        f"- `queen`: memories specific to how queen '{queen_id}' should work with this user\n" if queen_id else ""
     )
     return f"""\
 You are a reflection agent performing a periodic housekeeping pass over the
@@ -649,9 +643,7 @@ async def run_unified_short_reflection(
         session_dir,
         llm,
         memory_dirs,
-        system_prompt=_build_unified_short_reflect_system(
-            queen_id if "queen" in memory_dirs else None
-        ),
+        system_prompt=_build_unified_short_reflect_system(queen_id if "queen" in memory_dirs else None),
         log_label="unified",
         queen_id=queen_id if "queen" in memory_dirs else None,
     )
@@ -771,9 +763,7 @@ async def run_unified_long_reflection(
     if queen_memory_dir is not None and queen_id:
         memory_dirs["queen"] = queen_memory_dir
 
-    manifest = _format_multi_scope_manifest(
-        memory_dirs, queen_id=queen_id if "queen" in memory_dirs else None
-    )
+    manifest = _format_multi_scope_manifest(memory_dirs, queen_id=queen_id if "queen" in memory_dirs else None)
     user_msg = (
         "## Current memory manifest across scopes\n\n"
         f"{manifest}\n\n"
@@ -833,8 +823,8 @@ async def run_shutdown_reflection(
 # ---------------------------------------------------------------------------
 
 _LONG_REFLECT_INTERVAL = 5
-_SHORT_REFLECT_TURN_INTERVAL = 2
-_SHORT_REFLECT_COOLDOWN_SEC = 120.0
+_SHORT_REFLECT_TURN_INTERVAL = 3
+_SHORT_REFLECT_COOLDOWN_SEC = 300.0
 
 
 async def subscribe_reflection_triggers(

core/framework/config.py

@@ -405,9 +405,7 @@ def _fetch_antigravity_credentials() -> tuple[str | None, str | None]:
     import urllib.request
 
     try:
-        req = urllib.request.Request(
-            _ANTIGRAVITY_CREDENTIALS_URL, headers={"User-Agent": "Hive/1.0"}
-        )
+        req = urllib.request.Request(_ANTIGRAVITY_CREDENTIALS_URL, headers={"User-Agent": "Hive/1.0"})
         with urllib.request.urlopen(req, timeout=10) as resp:
             content = resp.read().decode("utf-8")
             id_match = re.search(r'ANTIGRAVITY_CLIENT_ID\s*=\s*"([^"]+)"', content)

core/framework/credentials/aden/client.py

@@ -332,9 +332,7 @@ class AdenCredentialClient:
                 last_error = e
                 if attempt < self.config.retry_attempts - 1:
                     delay = self.config.retry_delay * (2**attempt)
-                    logger.warning(
-                        f"Aden request failed (attempt {attempt + 1}), retrying in {delay}s: {e}"
-                    )
+                    logger.warning(f"Aden request failed (attempt {attempt + 1}), retrying in {delay}s: {e}")
                     time.sleep(delay)
                 else:
                     raise AdenClientError(f"Failed to connect to Aden server: {e}") from e
@@ -347,9 +345,7 @@ class AdenCredentialClient:
             ):
                 raise
 
-        raise AdenClientError(
-            f"Request failed after {self.config.retry_attempts} attempts"
-        ) from last_error
+        raise AdenClientError(f"Request failed after {self.config.retry_attempts} attempts") from last_error
 
     def list_integrations(self) -> list[AdenIntegrationInfo]:
         """

core/framework/credentials/aden/provider.py

@@ -192,9 +192,7 @@ class AdenSyncProvider(CredentialProvider):
                     f"Visit: {e.reauthorization_url or 'your Aden dashboard'}"
                 ) from e
 
-            raise CredentialRefreshError(
-                f"Failed to refresh credential '{credential.id}': {e}"
-            ) from e
+            raise CredentialRefreshError(f"Failed to refresh credential '{credential.id}': {e}") from e
 
         except AdenClientError as e:
             logger.error(f"Aden client error for '{credential.id}': {e}")
@@ -206,9 +204,7 @@ class AdenSyncProvider(CredentialProvider):
                     logger.warning(f"Aden unavailable, using cached token for '{credential.id}'")
                     return credential
 
-            raise CredentialRefreshError(
-                f"Aden server unavailable and token expired for '{credential.id}'"
-            ) from e
+            raise CredentialRefreshError(f"Aden server unavailable and token expired for '{credential.id}'") from e
 
     def validate(self, credential: CredentialObject) -> bool:
         """

core/framework/credentials/aden/storage.py

@@ -168,9 +168,7 @@ class AdenCachedStorage(CredentialStorage):
                 if rid != credential_id:
                     result = self._load_by_id(rid)
                     if result is not None:
-                        logger.info(
-                            f"Loaded credential '{credential_id}' via provider index (id='{rid}')"
-                        )
+                        logger.info(f"Loaded credential '{credential_id}' via provider index (id='{rid}')")
                         return result
 
         # Direct lookup (exact credential_id match)

core/framework/credentials/aden/tests/test_aden_sync.py

@@ -493,9 +493,7 @@ class TestAdenCachedStorage:
         assert loaded is not None
         assert loaded.keys["access_token"].value.get_secret_value() == "cached-token"
 
-    def test_load_from_aden_when_stale(
-        self, cached_storage, local_storage, provider, mock_client, aden_response
-    ):
+    def test_load_from_aden_when_stale(self, cached_storage, local_storage, provider, mock_client, aden_response):
         """Test load fetches from Aden when cache is stale."""
         # Create stale cached credential
         cred = CredentialObject(
@@ -521,9 +519,7 @@ class TestAdenCachedStorage:
         assert loaded is not None
         assert loaded.keys["access_token"].value.get_secret_value() == "test-access-token"
 
-    def test_load_falls_back_to_stale_when_aden_fails(
-        self, cached_storage, local_storage, provider, mock_client
-    ):
+    def test_load_falls_back_to_stale_when_aden_fails(self, cached_storage, local_storage, provider, mock_client):
         """Test load falls back to stale cache when Aden fails."""
         # Create stale cached credential
         cred = CredentialObject(

core/framework/credentials/oauth2/base_provider.py

@@ -95,9 +95,7 @@ class BaseOAuth2Provider(CredentialProvider):
 
                 self._client = httpx.Client(timeout=self.config.request_timeout)
             except ImportError as e:
-                raise ImportError(
-                    "OAuth2 provider requires 'httpx'. Install with: uv pip install httpx"
-                ) from e
+                raise ImportError("OAuth2 provider requires 'httpx'. Install with: uv pip install httpx") from e
         return self._client
 
     def _close_client(self) -> None:
@@ -311,8 +309,7 @@ class BaseOAuth2Provider(CredentialProvider):
         except OAuth2Error as e:
             if e.error == "invalid_grant":
                 raise CredentialRefreshError(
-                    f"Refresh token for '{credential.id}' is invalid or revoked. "
-                    "Re-authorization required."
+                    f"Refresh token for '{credential.id}' is invalid or revoked. Re-authorization required."
                 ) from e
             raise CredentialRefreshError(f"Failed to refresh '{credential.id}': {e}") from e
 
@@ -422,9 +419,7 @@ class BaseOAuth2Provider(CredentialProvider):
         if response.status_code != 200 or "error" in response_data:
             error = response_data.get("error", "unknown_error")
             description = response_data.get("error_description", response.text)
-            raise OAuth2Error(
-                error=error, description=description, status_code=response.status_code
-            )
+            raise OAuth2Error(error=error, description=description, status_code=response.status_code)
 
         return OAuth2Token.from_token_response(response_data)
 

core/framework/credentials/oauth2/lifecycle.py

@@ -158,9 +158,7 @@ class TokenLifecycleManager:
         """
         # Run in executor to avoid blocking
         loop = asyncio.get_event_loop()
-        token = await loop.run_in_executor(
-            None, lambda: self.provider.client_credentials_grant(scopes=scopes)
-        )
+        token = await loop.run_in_executor(None, lambda: self.provider.client_credentials_grant(scopes=scopes))
 
         self._save_token_to_store(token)
         self._cached_token = token

core/framework/credentials/oauth2/zoho_provider.py

@@ -100,9 +100,7 @@ class ZohoOAuth2Provider(BaseOAuth2Provider):
         )
         super().__init__(config, provider_id="zoho_crm_oauth2")
         self._accounts_domain = base
-        self._api_domain = (
-            api_domain or os.getenv("ZOHO_API_DOMAIN", "https://www.zohoapis.com")
-        ).rstrip("/")
+        self._api_domain = (api_domain or os.getenv("ZOHO_API_DOMAIN", "https://www.zohoapis.com")).rstrip("/")
 
     @property
     def supported_types(self) -> list[CredentialType]:

core/framework/credentials/setup.py

@@ -268,9 +268,7 @@ class CredentialSetupSession:
         self._print(f"{Colors.YELLOW}Initializing credential store...{Colors.NC}")
         try:
             generate_and_save_credential_key()
-            self._print(
-                f"{Colors.GREEN}✓ Encryption key saved to ~/.hive/secrets/credential_key{Colors.NC}"
-            )
+            self._print(f"{Colors.GREEN}✓ Encryption key saved to ~/.hive/secrets/credential_key{Colors.NC}")
             return True
         except Exception as e:
             self._print(f"{Colors.RED}Failed to initialize credential store: {e}{Colors.NC}")
@@ -449,9 +447,7 @@ class CredentialSetupSession:
                     logger.warning("Unexpected error exporting credential to env", exc_info=True)
                 return True
             else:
-                self._print(
-                    f"{Colors.YELLOW}⚠ {cred.credential_name} not found in Aden account.{Colors.NC}"
-                )
+                self._print(f"{Colors.YELLOW}⚠ {cred.credential_name} not found in Aden account.{Colors.NC}")
                 self._print("Please connect this integration on https://hive.adenhq.com first.")
                 return False
         except Exception as e:

core/framework/credentials/storage.py

@@ -136,8 +136,7 @@ class EncryptedFileStorage(CredentialStorage):
             from cryptography.fernet import Fernet
         except ImportError as e:
             raise ImportError(
-                "Encrypted storage requires 'cryptography'. "
-                "Install with: uv pip install cryptography"
+                "Encrypted storage requires 'cryptography'. Install with: uv pip install cryptography"
             ) from e
 
         self.base_path = Path(base_path or self.DEFAULT_PATH).expanduser()
@@ -213,9 +212,7 @@ class EncryptedFileStorage(CredentialStorage):
             json_bytes = self._fernet.decrypt(encrypted)
             data = json.loads(json_bytes.decode("utf-8-sig"))
         except Exception as e:
-            raise CredentialDecryptionError(
-                f"Failed to decrypt credential '{credential_id}': {e}"
-            ) from e
+            raise CredentialDecryptionError(f"Failed to decrypt credential '{credential_id}': {e}") from e
 
         # Deserialize
         return self._deserialize_credential(data)
@@ -316,8 +313,7 @@ class EncryptedFileStorage(CredentialStorage):
         visible_keys = [
             name
             for name in credential.keys.keys()
-            if name not in self.INDEX_INTERNAL_KEY_NAMES
-            and not name.startswith("_identity_")
+            if name not in self.INDEX_INTERNAL_KEY_NAMES and not name.startswith("_identity_")
         ]
 
         # Earliest expiry across all keys (most likely the access_token).
@@ -336,9 +332,7 @@ class EncryptedFileStorage(CredentialStorage):
             "key_names": sorted(visible_keys),
             "created_at": credential.created_at.isoformat() if credential.created_at else None,
             "updated_at": credential.updated_at.isoformat() if credential.updated_at else None,
-            "last_refreshed": (
-                credential.last_refreshed.isoformat() if credential.last_refreshed else None
-            ),
+            "last_refreshed": (credential.last_refreshed.isoformat() if credential.last_refreshed else None),
             "expires_at": earliest_expiry.isoformat() if earliest_expiry else None,
             "auto_refresh": credential.auto_refresh,
             "tags": list(credential.tags),
@@ -480,8 +474,7 @@ class EnvVarStorage(CredentialStorage):
     def save(self, credential: CredentialObject) -> None:
         """Cannot save to environment variables at runtime."""
         raise NotImplementedError(
-            "EnvVarStorage is read-only. Set environment variables "
-            "externally or use EncryptedFileStorage."
+            "EnvVarStorage is read-only. Set environment variables externally or use EncryptedFileStorage."
         )
 
     def load(self, credential_id: str) -> CredentialObject | None:
@@ -501,9 +494,7 @@ class EnvVarStorage(CredentialStorage):
 
     def delete(self, credential_id: str) -> bool:
         """Cannot delete environment variables at runtime."""
-        raise NotImplementedError(
-            "EnvVarStorage is read-only. Unset environment variables externally."
-        )
+        raise NotImplementedError("EnvVarStorage is read-only. Unset environment variables externally.")
 
     def list_all(self) -> list[str]:
         """List credentials that are available in environment."""

core/framework/credentials/store.py

@@ -124,9 +124,7 @@ class CredentialStore:
         """
         return self._providers.get(provider_id)
 
-    def get_provider_for_credential(
-        self, credential: CredentialObject
-    ) -> CredentialProvider | None:
+    def get_provider_for_credential(self, credential: CredentialObject) -> CredentialProvider | None:
         """
         Get the appropriate provider for a credential.
 
@@ -201,9 +199,7 @@ class CredentialStore:
             cached = self._get_from_cache(credential_id)
             if cached is not None:
                 if refresh_if_needed and self._should_refresh(cached):
-                    return self._refresh_credential(
-                        cached, raise_on_failure=raise_on_refresh_failure
-                    )
+                    return self._refresh_credential(cached, raise_on_failure=raise_on_refresh_failure)
                 return cached
 
             # Load from storage
@@ -213,9 +209,7 @@ class CredentialStore:
 
             # Refresh if needed
             if refresh_if_needed and self._should_refresh(credential):
-                credential = self._refresh_credential(
-                    credential, raise_on_failure=raise_on_refresh_failure
-                )
+                credential = self._refresh_credential(credential, raise_on_failure=raise_on_refresh_failure)
 
             # Cache
             self._add_to_cache(credential)
@@ -240,9 +234,7 @@ class CredentialStore:
         Returns:
             The key value or None if not found
         """
-        credential = self.get_credential(
-            credential_id, raise_on_refresh_failure=raise_on_refresh_failure
-        )
+        credential = self.get_credential(credential_id, raise_on_refresh_failure=raise_on_refresh_failure)
         if credential is None:
             return None
         return credential.get_key(key_name)
@@ -266,9 +258,7 @@ class CredentialStore:
         Returns:
             The primary key value or None
         """
-        credential = self.get_credential(
-            credential_id, raise_on_refresh_failure=raise_on_refresh_failure
-        )
+        credential = self.get_credential(credential_id, raise_on_refresh_failure=raise_on_refresh_failure)
         if credential is None:
             return None
         return credential.get_default_key()

core/framework/credentials/template.py

@@ -88,9 +88,7 @@ class TemplateResolver:
             if key_name:
                 value = credential.get_key(key_name)
                 if value is None:
-                    raise CredentialKeyNotFoundError(
-                        f"Key '{key_name}' not found in credential '{cred_id}'"
-                    )
+                    raise CredentialKeyNotFoundError(f"Key '{key_name}' not found in credential '{cred_id}'")
             else:
                 # Use default key
                 value = credential.get_default_key()
@@ -126,9 +124,7 @@ class TemplateResolver:
             ... })
             {"Authorization": "Bearer ghp_xxx", "X-API-Key": "BSAKxxx"}
         """
-        return {
-            key: self.resolve(value, fail_on_missing) for key, value in header_templates.items()
-        }
+        return {key: self.resolve(value, fail_on_missing) for key, value in header_templates.items()}
 
     def resolve_params(
         self,

core/framework/credentials/tests/test_credential_store.py

@@ -130,9 +130,7 @@ class TestCredentialObject:
         # With access_token
         cred2 = CredentialObject(
             id="test",
-            keys={
-                "access_token": CredentialKey(name="access_token", value=SecretStr("token-value"))
-            },
+            keys={"access_token": CredentialKey(name="access_token", value=SecretStr("token-value"))},
         )
         assert cred2.get_default_key() == "token-value"
 
@@ -297,9 +295,7 @@ class TestEncryptedFileStorage:
         key = Fernet.generate_key().decode()
         with patch.dict(os.environ, {"HIVE_CREDENTIAL_KEY": key}):
             storage = EncryptedFileStorage(temp_dir)
-            cred = CredentialObject(
-                id="test", keys={"k": CredentialKey(name="k", value=SecretStr("v"))}
-            )
+            cred = CredentialObject(id="test", keys={"k": CredentialKey(name="k", value=SecretStr("v"))})
             storage.save(cred)
 
             # Create new storage instance with same key
@@ -330,18 +326,10 @@ class TestCompositeStorage:
     def test_read_from_primary(self):
         """Test reading from primary storage."""
         primary = InMemoryStorage()
-        primary.save(
-            CredentialObject(
-                id="test", keys={"k": CredentialKey(name="k", value=SecretStr("primary"))}
-            )
-        )
+        primary.save(CredentialObject(id="test", keys={"k": CredentialKey(name="k", value=SecretStr("primary"))}))
 
         fallback = InMemoryStorage()
-        fallback.save(
-            CredentialObject(
-                id="test", keys={"k": CredentialKey(name="k", value=SecretStr("fallback"))}
-            )
-        )
+        fallback.save(CredentialObject(id="test", keys={"k": CredentialKey(name="k", value=SecretStr("fallback"))}))
 
         storage = CompositeStorage(primary, [fallback])
         cred = storage.load("test")
@@ -353,11 +341,7 @@ class TestCompositeStorage:
         """Test fallback when credential not in primary."""
         primary = InMemoryStorage()
         fallback = InMemoryStorage()
-        fallback.save(
-            CredentialObject(
-                id="test", keys={"k": CredentialKey(name="k", value=SecretStr("fallback"))}
-            )
-        )
+        fallback.save(CredentialObject(id="test", keys={"k": CredentialKey(name="k", value=SecretStr("fallback"))}))
 
         storage = CompositeStorage(primary, [fallback])
         cred = storage.load("test")
@@ -393,9 +377,7 @@ class TestStaticProvider:
     def test_refresh_returns_unchanged(self):
         """Test that refresh returns credential unchanged."""
         provider = StaticProvider()
-        cred = CredentialObject(
-            id="test", keys={"k": CredentialKey(name="k", value=SecretStr("v"))}
-        )
+        cred = CredentialObject(id="test", keys={"k": CredentialKey(name="k", value=SecretStr("v"))})
 
         refreshed = provider.refresh(cred)
         assert refreshed.get_key("k") == "v"
@@ -403,9 +385,7 @@ class TestStaticProvider:
     def test_validate_with_keys(self):
         """Test validation with keys present."""
         provider = StaticProvider()
-        cred = CredentialObject(
-            id="test", keys={"k": CredentialKey(name="k", value=SecretStr("v"))}
-        )
+        cred = CredentialObject(id="test", keys={"k": CredentialKey(name="k", value=SecretStr("v"))})
 
         assert provider.validate(cred)
 
@@ -606,9 +586,7 @@ class TestCredentialStore:
         storage = InMemoryStorage()
         store = CredentialStore(storage=storage, cache_ttl_seconds=60)
 
-        storage.save(
-            CredentialObject(id="test", keys={"k": CredentialKey(name="k", value=SecretStr("v"))})
-        )
+        storage.save(CredentialObject(id="test", keys={"k": CredentialKey(name="k", value=SecretStr("v"))}))
 
         # First load
         store.get_credential("test")
@@ -686,9 +664,7 @@ class TestOAuth2Module:
         from core.framework.credentials.oauth2 import OAuth2Config, TokenPlacement
 
         # Valid config
-        config = OAuth2Config(
-            token_url="https://example.com/token", client_id="id", client_secret="secret"
-        )
+        config = OAuth2Config(token_url="https://example.com/token", client_id="id", client_secret="secret")
         assert config.token_url == "https://example.com/token"
 
         # Missing token_url

core/framework/credentials/validation.py

@@ -160,15 +160,9 @@ class CredentialValidationResult:
         if aden_nc:
             if missing or invalid:
                 lines.append("")
-            lines.append(
-                "Aden integrations not connected "
-                "(ADEN_API_KEY is set but OAuth tokens unavailable):\n"
-            )
+            lines.append("Aden integrations not connected (ADEN_API_KEY is set but OAuth tokens unavailable):\n")
             for c in aden_nc:
-                lines.append(
-                    f"  {c.env_var} for {_label(c)}"
-                    f"\n    Connect this integration at hive.adenhq.com first."
-                )
+                lines.append(f"  {c.env_var} for {_label(c)}\n    Connect this integration at hive.adenhq.com first.")
         lines.append("\nIf you've already set up credentials, restart your terminal to load them.")
         return "\n".join(lines)
 
@@ -270,8 +264,7 @@ def compute_unavailable_tools(nodes: list) -> tuple[set[str], list[str]]:
             reason = "invalid"
         messages.append(
             f"{status.env_var} ({reason}) → drops {len(status.tools)} tool(s): "
-            f"{', '.join(status.tools[:6])}"
-            + (f" +{len(status.tools) - 6} more" if len(status.tools) > 6 else "")
+            f"{', '.join(status.tools[:6])}" + (f" +{len(status.tools) - 6} more" if len(status.tools) > 6 else "")
         )
     return drop, messages
 
@@ -332,9 +325,7 @@ def validate_agent_credentials(
     if os.environ.get("ADEN_API_KEY"):
         _presync_aden_tokens(CREDENTIAL_SPECS, force=force_refresh)
 
-    env_mapping = {
-        (spec.credential_id or name): spec.env_var for name, spec in CREDENTIAL_SPECS.items()
-    }
+    env_mapping = {(spec.credential_id or name): spec.env_var for name, spec in CREDENTIAL_SPECS.items()}
     env_storage = EnvVarStorage(env_mapping=env_mapping)
     if os.environ.get("HIVE_CREDENTIAL_KEY"):
         storage = CompositeStorage(primary=env_storage, fallbacks=[EncryptedFileStorage()])
@@ -368,12 +359,7 @@ def validate_agent_credentials(
         available = store.is_available(cred_id)
 
         # Aden-not-connected: ADEN_API_KEY set, Aden-only cred, but integration missing
-        is_aden_nc = (
-            not available
-            and has_aden_key
-            and spec.aden_supported
-            and not spec.direct_api_key_supported
-        )
+        is_aden_nc = not available and has_aden_key and spec.aden_supported and not spec.direct_api_key_supported
 
         status = CredentialStatus(
             credential_name=cred_name,
@@ -491,9 +477,7 @@ def validate_agent_credentials(
                         identity_data = result.details.get("identity")
                         if identity_data and isinstance(identity_data, dict):
                             try:
-                                cred_obj = store.get_credential(
-                                    status.credential_id, refresh_if_needed=False
-                                )
+                                cred_obj = store.get_credential(status.credential_id, refresh_if_needed=False)
                                 if cred_obj:
                                     cred_obj.set_identity(**identity_data)
                                     store.save_credential(cred_obj)

core/framework/host/agent_host.py

@@ -205,9 +205,7 @@ class AgentHost:
                 DeprecationWarning,
                 stacklevel=2,
             )
-            self._skills_manager = SkillsManager.from_precomputed(
-                skills_catalog_prompt, protocols_prompt
-            )
+            self._skills_manager = SkillsManager.from_precomputed(skills_catalog_prompt, protocols_prompt)
         else:
             # Bare constructor: auto-load defaults
             self._skills_manager = SkillsManager()
@@ -248,9 +246,7 @@ class AgentHost:
         self._tools = tools or []
         self._tool_executor = tool_executor
         self._accounts_prompt = accounts_prompt
-        self._dynamic_memory_provider_factory: Callable[[str], Callable[[], str] | None] | None = (
-            None
-        )
+        self._dynamic_memory_provider_factory: Callable[[str], Callable[[], str] | None] | None = None
         self._accounts_data = accounts_data
         self._tool_provider_map = tool_provider_map
 
@@ -419,8 +415,7 @@ class AgentHost:
                 event_types = [_ET(et) for et in tc.get("event_types", [])]
                 if not event_types:
                     logger.warning(
-                        f"Entry point '{ep_id}' has trigger_type='event' "
-                        "but no event_types in trigger_config"
+                        f"Entry point '{ep_id}' has trigger_type='event' but no event_types in trigger_config"
                     )
                     continue
 
@@ -450,9 +445,7 @@ class AgentHost:
                             # Run in the same session as the primary entry
                             # point so memory (e.g. user-defined rules) is
                             # shared and logs land in one session directory.
-                            session_state = self._get_primary_session_state(
-                                exclude_entry_point=entry_point_id
-                            )
+                            session_state = self._get_primary_session_state(exclude_entry_point=entry_point_id)
                         exec_id = await self.trigger(
                             entry_point_id,
                             {"event": event.to_dict()},
@@ -505,8 +498,7 @@ class AgentHost:
                     from croniter import croniter
                 except ImportError as e:
                     raise RuntimeError(
-                        "croniter is required for cron-based entry points. "
-                        "Install it with: uv pip install croniter"
+                        "croniter is required for cron-based entry points. Install it with: uv pip install croniter"
                     ) from e
 
                 try:
@@ -548,9 +540,7 @@ class AgentHost:
                                     "Cron '%s': paused, skipping tick",
                                     entry_point_id,
                                 )
-                                self._timer_next_fire[entry_point_id] = (
-                                    time.monotonic() + sleep_secs
-                                )
+                                self._timer_next_fire[entry_point_id] = time.monotonic() + sleep_secs
                                 await asyncio.sleep(max(0, sleep_secs))
                                 continue
 
@@ -578,9 +568,7 @@ class AgentHost:
                                     "Cron '%s': agent actively working, skipping tick",
                                     entry_point_id,
                                 )
-                                self._timer_next_fire[entry_point_id] = (
-                                    time.monotonic() + sleep_secs
-                                )
+                                self._timer_next_fire[entry_point_id] = time.monotonic() + sleep_secs
                                 await asyncio.sleep(max(0, sleep_secs))
                                 continue
 
@@ -590,24 +578,18 @@ class AgentHost:
                                 is_isolated = ep_spec and ep_spec.isolation_level == "isolated"
                                 if is_isolated:
                                     if _persistent_session_id:
-                                        session_state = {
-                                            "resume_session_id": _persistent_session_id
-                                        }
+                                        session_state = {"resume_session_id": _persistent_session_id}
                                     else:
                                         session_state = None
                                 else:
-                                    session_state = self._get_primary_session_state(
-                                        exclude_entry_point=entry_point_id
-                                    )
+                                    session_state = self._get_primary_session_state(exclude_entry_point=entry_point_id)
                                     # Gate: skip tick if no active session
                                     if session_state is None:
                                         logger.debug(
                                             "Cron '%s': no active session, skipping",
                                             entry_point_id,
                                         )
-                                        self._timer_next_fire[entry_point_id] = (
-                                            time.monotonic() + sleep_secs
-                                        )
+                                        self._timer_next_fire[entry_point_id] = time.monotonic() + sleep_secs
                                         await asyncio.sleep(max(0, sleep_secs))
                                         continue
 
@@ -680,9 +662,7 @@ class AgentHost:
                                     "Timer '%s': paused, skipping tick",
                                     entry_point_id,
                                 )
-                                self._timer_next_fire[entry_point_id] = (
-                                    time.monotonic() + interval_secs
-                                )
+                                self._timer_next_fire[entry_point_id] = time.monotonic() + interval_secs
                                 await asyncio.sleep(interval_secs)
                                 continue
 
@@ -708,9 +688,7 @@ class AgentHost:
                                     "Timer '%s': agent actively working, skipping tick",
                                     entry_point_id,
                                 )
-                                self._timer_next_fire[entry_point_id] = (
-                                    time.monotonic() + interval_secs
-                                )
+                                self._timer_next_fire[entry_point_id] = time.monotonic() + interval_secs
                                 await asyncio.sleep(interval_secs)
                                 continue
 
@@ -720,24 +698,18 @@ class AgentHost:
                                 is_isolated = ep_spec and ep_spec.isolation_level == "isolated"
                                 if is_isolated:
                                     if _persistent_session_id:
-                                        session_state = {
-                                            "resume_session_id": _persistent_session_id
-                                        }
+                                        session_state = {"resume_session_id": _persistent_session_id}
                                     else:
                                         session_state = None
                                 else:
-                                    session_state = self._get_primary_session_state(
-                                        exclude_entry_point=entry_point_id
-                                    )
+                                    session_state = self._get_primary_session_state(exclude_entry_point=entry_point_id)
                                     # Gate: skip tick if no active session
                                     if session_state is None:
                                         logger.debug(
                                             "Timer '%s': no active session, skipping",
                                             entry_point_id,
                                         )
-                                        self._timer_next_fire[entry_point_id] = (
-                                            time.monotonic() + interval_secs
-                                        )
+                                        self._timer_next_fire[entry_point_id] = time.monotonic() + interval_secs
                                         await asyncio.sleep(interval_secs)
                                         continue
 
@@ -1152,8 +1124,7 @@ class AgentHost:
             event_types = [_ET(et) for et in tc.get("event_types", [])]
             if not event_types:
                 logger.warning(
-                    "Entry point '%s::%s' has trigger_type='event' "
-                    "but no event_types in trigger_config",
+                    "Entry point '%s::%s' has trigger_type='event' but no event_types in trigger_config",
                     graph_id,
                     ep_id,
                 )
@@ -1301,24 +1272,18 @@ class AgentHost:
                                     break
                                 stream = reg.streams.get(local_ep)
                                 if not stream:
-                                    logger.warning(
-                                        "Timer: no stream '%s' in '%s', stopping", local_ep, gid
-                                    )
+                                    logger.warning("Timer: no stream '%s' in '%s', stopping", local_ep, gid)
                                     break
                                 # Isolated entry points get their own session;
                                 # shared ones join the primary session.
                                 ep_spec = reg.entry_points.get(local_ep)
                                 if ep_spec and ep_spec.isolation_level == "isolated":
                                     if _persistent_session_id:
-                                        session_state = {
-                                            "resume_session_id": _persistent_session_id
-                                        }
+                                        session_state = {"resume_session_id": _persistent_session_id}
                                     else:
                                         session_state = None
                                 else:
-                                    session_state = self._get_primary_session_state(
-                                        local_ep, source_graph_id=gid
-                                    )
+                                    session_state = self._get_primary_session_state(local_ep, source_graph_id=gid)
                                     # Gate: skip tick if no active session
                                     if session_state is None:
                                         logger.debug(
@@ -1335,11 +1300,7 @@ class AgentHost:
                                     session_state=session_state,
                                 )
                                 # Remember session ID for reuse on next tick
-                                if (
-                                    not _persistent_session_id
-                                    and ep_spec
-                                    and ep_spec.isolation_level == "isolated"
-                                ):
+                                if not _persistent_session_id and ep_spec and ep_spec.isolation_level == "isolated":
                                     _persistent_session_id = exec_id
                             except Exception:
                                 logger.error(
@@ -1597,9 +1558,7 @@ class AgentHost:
         src_graph_id = source_graph_id or self._graph_id
         src_reg = self._graphs.get(src_graph_id)
         ep_spec = (
-            src_reg.entry_points.get(exclude_entry_point)
-            if src_reg
-            else self._entry_points.get(exclude_entry_point)
+            src_reg.entry_points.get(exclude_entry_point) if src_reg else self._entry_points.get(exclude_entry_point)
         )
         if ep_spec:
             graph = src_reg.graph if src_reg else self.graph
@@ -1633,9 +1592,7 @@ class AgentHost:
                         # Filter to only input keys so stale outputs
                         # from previous triggers don't leak through.
                         if allowed_keys is not None:
-                            buffer_data = {
-                                k: v for k, v in full_buffer.items() if k in allowed_keys
-                            }
+                            buffer_data = {k: v for k, v in full_buffer.items() if k in allowed_keys}
                         else:
                             buffer_data = full_buffer
                         if buffer_data:

core/framework/host/colony_runtime.py

@@ -15,7 +15,6 @@ import asyncio
 import json
 import logging
 import time
-import uuid
 from collections import OrderedDict
 from collections.abc import Callable
 from dataclasses import dataclass, field
@@ -25,16 +24,13 @@ from typing import TYPE_CHECKING, Any
 from framework.agent_loop.types import AgentContext, AgentSpec
 from framework.host.event_bus import AgentEvent, EventBus, EventType
 from framework.host.triggers import TriggerDefinition
-from framework.host.worker import Worker, WorkerInfo, WorkerResult, WorkerStatus
-from framework.observability import set_trace_context
+from framework.host.worker import Worker, WorkerInfo, WorkerResult
 from framework.schemas.goal import Goal
 from framework.storage.concurrent import ConcurrentStorage
 from framework.storage.session_store import SessionStore
 
 if TYPE_CHECKING:
-    from framework.agent_loop.agent_loop import AgentLoop
     from framework.llm.provider import LLMProvider, Tool
-    from framework.pipeline.runner import PipelineRunner
     from framework.skills.manager import SkillsManagerConfig
     from framework.tracker.runtime_log_store import RuntimeLogStore
 
@@ -195,9 +191,7 @@ class ColonyRuntime:
                 DeprecationWarning,
                 stacklevel=2,
             )
-            self._skills_manager = SkillsManager.from_precomputed(
-                skills_catalog_prompt, protocols_prompt
-            )
+            self._skills_manager = SkillsManager.from_precomputed(skills_catalog_prompt, protocols_prompt)
         else:
             self._skills_manager = SkillsManager()
             self._skills_manager.load()
@@ -210,9 +204,7 @@ class ColonyRuntime:
         self._accounts_prompt = accounts_prompt
         self._accounts_data = accounts_data
         self._tool_provider_map = tool_provider_map
-        self._dynamic_memory_provider_factory: Callable[[str], Callable[[], str] | None] | None = (
-            None
-        )
+        self._dynamic_memory_provider_factory: Callable[[str], Callable[[], str] | None] | None = None
 
         storage_path_obj = Path(storage_path) if isinstance(storage_path, str) else storage_path
         self._storage_path: Path = storage_path_obj
@@ -246,6 +238,13 @@ class ColonyRuntime:
         self._timer_tasks: list[asyncio.Task] = []
         self._timer_next_fire: dict[str, float] = {}
         self._webhook_server: Any = None
+        # Background tasks owned by the runtime that aren't timers —
+        # e.g. the per-spawn soft/hard timeout watchers kicked off by
+        # run_parallel_workers. We hold strong references so asyncio
+        # does not garbage-collect them mid-sleep (Python's asyncio
+        # docs explicitly warn that create_task() needs a referenced
+        # handle).
+        self._background_tasks: set[asyncio.Task] = set()
 
         # Idempotency
         self._idempotency_keys: OrderedDict[str, str] = OrderedDict()
@@ -560,9 +559,7 @@ class ColonyRuntime:
                         encoding="utf-8",
                     )
                 except (json.JSONDecodeError, OSError) as exc:
-                    logger.warning(
-                        "spawn fork: failed to copy queen meta.json: %s", exc
-                    )
+                    logger.warning("spawn fork: failed to copy queen meta.json: %s", exc)
 
             # Append the task as the next user message so the worker's
             # LLM sees it as the most recent turn in the conversation
@@ -711,9 +708,7 @@ class ColonyRuntime:
                 input_data=input_data,
             )
 
-            worker_conv_store = FileConversationStore(
-                worker_storage / "conversations"
-            )
+            worker_conv_store = FileConversationStore(worker_storage / "conversations")
 
             # AgentLoop takes bus/judge/config/executor at construction;
             # LLM, tools, stream_id, execution_id all come from the
@@ -769,6 +764,8 @@ class ColonyRuntime:
     async def spawn_batch(
         self,
         tasks: list[dict[str, Any]],
+        *,
+        tools_override: list[Any] | None = None,
     ) -> list[str]:
         """Spawn a batch of parallel workers, one per task spec.
 
@@ -781,6 +778,12 @@ class ColonyRuntime:
         The overseer's ``run_parallel_workers`` tool is the usual
         caller; it pairs ``spawn_batch`` + ``wait_for_worker_reports``
         into a single fan-out/fan-in primitive.
+
+        When ``tools_override`` is supplied, every spawned worker
+        receives that tool list instead of the colony's default.  Used
+        by ``run_parallel_workers`` to drop tools whose credentials
+        failed the pre-flight check (so the spawned workers don't
+        waste a startup trying to use them).
         """
         worker_ids: list[str] = []
         for spec in tasks:
@@ -792,6 +795,7 @@ class ColonyRuntime:
                 task=task_text,
                 count=1,
                 input_data=task_data or {"task": task_text},
+                tools=tools_override,
             )
             worker_ids.extend(ids)
         return worker_ids
@@ -885,9 +889,7 @@ class ColonyRuntime:
                 if remaining <= 0:
                     break
                 try:
-                    report = await asyncio.wait_for(
-                        report_queue.get(), timeout=remaining
-                    )
+                    report = await asyncio.wait_for(report_queue.get(), timeout=remaining)
                 except TimeoutError:
                     break
                 wid = report.get("worker_id")
@@ -956,10 +958,7 @@ class ColonyRuntime:
             return self._overseer
 
         if not self._running:
-            raise RuntimeError(
-                "start_overseer requires the ColonyRuntime to be running "
-                "(call start() first)"
-            )
+            raise RuntimeError("start_overseer requires the ColonyRuntime to be running (call start() first)")
 
         from framework.agent_loop.agent_loop import AgentLoop
         from framework.storage.conversation_store import FileConversationStore
@@ -970,9 +969,7 @@ class ColonyRuntime:
         # {colony_session}/conversations/. Workers get their own sub-dirs
         # under workers/{worker_id}/; the overseer is the root occupant.
         self._storage_path.mkdir(parents=True, exist_ok=True)
-        overseer_conv_store = FileConversationStore(
-            self._storage_path / "conversations"
-        )
+        overseer_conv_store = FileConversationStore(self._storage_path / "conversations")
         agent_loop = AgentLoop(
             event_bus=self._scoped_event_bus,
             tool_executor=self._tool_executor,
@@ -1110,6 +1107,96 @@ class ColonyRuntime:
             return True
         return False
 
+    def watch_batch_timeouts(
+        self,
+        worker_ids: list[str],
+        *,
+        soft_timeout: float,
+        hard_timeout: float,
+        warning_message: str | None = None,
+    ) -> asyncio.Task:
+        """Schedule a background task that enforces soft + hard timeouts.
+
+        Semantics:
+          * At ``t = soft_timeout`` every worker in ``worker_ids`` that is
+            still active AND hasn't already filed an ``_explicit_report``
+            receives ``warning_message`` via ``send_to_worker`` — the inject
+            appears as a user turn at the next agent-loop boundary, so the
+            worker's LLM can see it and call ``report_to_parent`` with
+            partial results.
+          * At ``t = hard_timeout`` any worker still active is force-stopped
+            via ``stop_worker``. ``Worker.run`` still emits its
+            ``SUBAGENT_REPORT`` on cancel (the explicit report survives,
+            if the worker reported just before the stop) so the queen
+            always sees a terminal inject for every spawned worker.
+
+        Returns the scheduled task so callers can await or cancel it.
+        Non-blocking for the caller — the watcher runs on the event loop
+        independently.
+        """
+        if warning_message is None:
+            grace = max(0.0, hard_timeout - soft_timeout)
+            warning_message = (
+                f"[SOFT TIMEOUT] You've been running for {soft_timeout:.0f}s. "
+                "Wrap up now: call report_to_parent with whatever partial "
+                "results you have. You have "
+                f"~{grace:.0f}s more before a hard stop — anything not "
+                "reported by then will be lost."
+            )
+
+        async def _watch() -> None:
+            try:
+                await asyncio.sleep(soft_timeout)
+                for wid in worker_ids:
+                    worker = self._workers.get(wid)
+                    if worker is None or not worker.is_active:
+                        continue
+                    if getattr(worker, "_explicit_report", None) is not None:
+                        continue
+                    try:
+                        await self.send_to_worker(wid, warning_message)
+                    except Exception:
+                        logger.warning(
+                            "watch_batch_timeouts: soft-timeout inject failed for %s",
+                            wid,
+                            exc_info=True,
+                        )
+
+                remaining = hard_timeout - soft_timeout
+                if remaining <= 0:
+                    return
+                await asyncio.sleep(remaining)
+                for wid in worker_ids:
+                    worker = self._workers.get(wid)
+                    if worker is None or not worker.is_active:
+                        continue
+                    try:
+                        await self.stop_worker(wid)
+                        logger.info(
+                            "watch_batch_timeouts: hard-stopped %s after %ss (no report)",
+                            wid,
+                            hard_timeout,
+                        )
+                    except Exception:
+                        logger.warning(
+                            "watch_batch_timeouts: hard-stop failed for %s",
+                            wid,
+                            exc_info=True,
+                        )
+            except asyncio.CancelledError:
+                raise
+            except Exception:
+                logger.exception("watch_batch_timeouts: watcher crashed")
+
+        task = asyncio.create_task(_watch(), name=f"batch-timeout:{worker_ids[0] if worker_ids else '?'}")
+        # Hold a strong reference until completion. Without this the
+        # task can be garbage-collected during `await asyncio.sleep`,
+        # silently swallowing the soft-timeout inject (the exact bug
+        # surfaced by workers never seeing [SOFT TIMEOUT]).
+        self._background_tasks.add(task)
+        task.add_done_callback(self._background_tasks.discard)
+        return task
+
     # ── Status & Query ──────────────────────────────────────────
 
     def list_workers(self) -> list[WorkerInfo]:
@@ -1133,9 +1220,7 @@ class ColonyRuntime:
     def get_worker_result(self, worker_id: str) -> WorkerResult | None:
         return self._execution_results.get(worker_id)
 
-    async def wait_for_worker(
-        self, worker_id: str, timeout: float | None = None
-    ) -> WorkerResult | None:
+    async def wait_for_worker(self, worker_id: str, timeout: float | None = None) -> WorkerResult | None:
         worker = self._workers.get(worker_id)
         if worker is None:
             return self._execution_results.get(worker_id)
@@ -1143,7 +1228,7 @@ class ColonyRuntime:
             return worker.info.result
         try:
             await asyncio.wait_for(asyncio.shield(worker._task_handle), timeout=timeout)
-        except asyncio.TimeoutError:
+        except TimeoutError:
             return None
         return worker.info.result
 
@@ -1184,9 +1269,7 @@ class ColonyRuntime:
         if worker and worker.is_active:
             loop = worker._agent_loop
             if hasattr(loop, "inject_event"):
-                await loop.inject_event(
-                    content, is_client_input=is_client_input, image_content=image_content
-                )
+                await loop.inject_event(content, is_client_input=is_client_input, image_content=image_content)
                 return True
         return False
 

core/framework/host/event_bus.py

@@ -111,6 +111,15 @@ class EventType(StrEnum):
     # Retry tracking
     NODE_RETRY = "node_retry"
 
+    # Stream-health observability. Split from NODE_RETRY so the UI can
+    # distinguish "slow TTFT on a huge context" (healthy, just slow) from
+    # "stream went silent mid-generation" (probable stall) from "we nudged
+    # the model to continue" (recovery), which NODE_RETRY used to conflate.
+    STREAM_TTFT_EXCEEDED = "stream_ttft_exceeded"
+    STREAM_INACTIVE = "stream_inactive"
+    STREAM_NUDGE_SENT = "stream_nudge_sent"
+    TOOL_CALL_REPLAY_DETECTED = "tool_call_replay_detected"
+
     # Worker agent lifecycle
     WORKER_COMPLETED = "worker_completed"
     WORKER_FAILED = "worker_failed"
@@ -446,11 +455,7 @@ class EventBus:
         # iteration values.  Without this, live SSE would use raw iterations
         # while events.jsonl would use offset iterations, causing ID collisions
         # on the frontend when replaying after cold resume.
-        if (
-            self._session_log_iteration_offset
-            and isinstance(event.data, dict)
-            and "iteration" in event.data
-        ):
+        if self._session_log_iteration_offset and isinstance(event.data, dict) and "iteration" in event.data:
             offset = self._session_log_iteration_offset
             event.data = {**event.data, "iteration": event.data["iteration"] + offset}
 
@@ -1065,6 +1070,94 @@ class EventBus:
             )
         )
 
+    async def emit_stream_ttft_exceeded(
+        self,
+        stream_id: str,
+        node_id: str,
+        ttft_seconds: float,
+        limit_seconds: float,
+        execution_id: str | None = None,
+    ) -> None:
+        """Emit when a stream stayed silent past the TTFT budget (no first event)."""
+        await self.publish(
+            AgentEvent(
+                type=EventType.STREAM_TTFT_EXCEEDED,
+                stream_id=stream_id,
+                node_id=node_id,
+                execution_id=execution_id,
+                data={
+                    "ttft_seconds": ttft_seconds,
+                    "limit_seconds": limit_seconds,
+                },
+            )
+        )
+
+    async def emit_stream_inactive(
+        self,
+        stream_id: str,
+        node_id: str,
+        idle_seconds: float,
+        limit_seconds: float,
+        execution_id: str | None = None,
+    ) -> None:
+        """Emit when a stream that had produced events went silent past budget."""
+        await self.publish(
+            AgentEvent(
+                type=EventType.STREAM_INACTIVE,
+                stream_id=stream_id,
+                node_id=node_id,
+                execution_id=execution_id,
+                data={
+                    "idle_seconds": idle_seconds,
+                    "limit_seconds": limit_seconds,
+                },
+            )
+        )
+
+    async def emit_stream_nudge_sent(
+        self,
+        stream_id: str,
+        node_id: str,
+        reason: str,
+        nudge_count: int,
+        execution_id: str | None = None,
+    ) -> None:
+        """Emit when the continue-nudge was injected (recovery, not retry)."""
+        await self.publish(
+            AgentEvent(
+                type=EventType.STREAM_NUDGE_SENT,
+                stream_id=stream_id,
+                node_id=node_id,
+                execution_id=execution_id,
+                data={
+                    "reason": reason,
+                    "nudge_count": nudge_count,
+                },
+            )
+        )
+
+    async def emit_tool_call_replay_detected(
+        self,
+        stream_id: str,
+        node_id: str,
+        tool_name: str,
+        prior_seq: int,
+        execution_id: str | None = None,
+    ) -> None:
+        """Emit when the model is about to re-execute a prior successful call."""
+        await self.publish(
+            AgentEvent(
+                type=EventType.TOOL_CALL_REPLAY_DETECTED,
+                stream_id=stream_id,
+                node_id=node_id,
+                execution_id=execution_id,
+                data={
+                    "tool_name": tool_name,
+                    "prior_seq": prior_seq,
+                },
+            )
+        )
+
     async def emit_worker_completed(
         self,
         stream_id: str,

core/framework/host/execution_manager.py

@@ -452,9 +452,7 @@ class ExecutionManager:
         for executor in self._active_executors.values():
             node = executor.node_registry.get(node_id)
             if node is not None and hasattr(node, "inject_event"):
-                await node.inject_event(
-                    content, is_client_input=is_client_input, image_content=image_content
-                )
+                await node.inject_event(content, is_client_input=is_client_input, image_content=image_content)
                 return True
         return False
 
@@ -669,9 +667,7 @@ class ExecutionManager:
                 if self._runtime_log_store:
                     from framework.tracker.runtime_logger import RuntimeLogger
 
-                    runtime_logger = RuntimeLogger(
-                        store=self._runtime_log_store, agent_id=self.graph.id
-                    )
+                    runtime_logger = RuntimeLogger(store=self._runtime_log_store, agent_id=self.graph.id)
 
                 # Derive storage from session_store (graph-specific for secondary
                 # graphs) so that all files — conversations, state, checkpoints,
@@ -887,9 +883,7 @@ class ExecutionManager:
                     if has_result and result.paused_at:
                         await self._write_session_state(execution_id, ctx, result=result)
                     else:
-                        await self._write_session_state(
-                            execution_id, ctx, error="Execution cancelled"
-                        )
+                        await self._write_session_state(execution_id, ctx, error="Execution cancelled")
 
                 # Emit SSE event so the frontend knows the execution stopped.
                 # The executor does NOT emit on CancelledError, so there is no

core/framework/host/progress_db.py

@@ -191,19 +191,28 @@ def ensure_progress_db(colony_dir: Path) -> Path:
 
 
 def _patch_worker_configs(colony_dir: Path, db_path: Path) -> int:
-    """Inject ``input_data.db_path`` + ``input_data.colony_id`` into
-    existing ``worker.json`` files in a colony directory.
+    """Inject ``input_data.db_path`` + ``input_data.colony_id`` +
+    ``input_data.colony_data_dir`` into existing ``worker.json`` files
+    in a colony directory.
 
     Runs on every ``ensure_progress_db`` call so colonies that were
     forked before this feature landed get their worker spawn messages
     patched in place. Idempotent: if ``input_data`` already contains
-    the correct ``db_path``, the file is not rewritten.
+    all three values, the file is not rewritten.
 
     Returns the number of files that were actually modified (0 on
     the common case of already-patched colonies).
+
+    Why ``colony_data_dir``? ``db_path`` alone points agents at
+    ``progress.db``; for anything else (custom SQLite stores, JSON
+    ledgers, scraped artefacts) they need the *directory* so they
+    stop creating state under ``~/.hive/skills/`` — which holds skill
+    *definitions*, not runtime data. See
+    ``_default_skills/colony-storage-paths/SKILL.md``.
     """
     colony_id = colony_dir.name
     abs_db = str(db_path)
+    abs_data_dir = str(db_path.parent)
     patched = 0
 
     for worker_cfg in colony_dir.glob("*.json"):
@@ -227,11 +236,13 @@ def _patch_worker_configs(colony_dir: Path, db_path: Path) -> int:
         if (
             input_data.get("db_path") == abs_db
             and input_data.get("colony_id") == colony_id
+            and input_data.get("colony_data_dir") == abs_data_dir
         ):
             continue  # already patched
 
         input_data["db_path"] = abs_db
         input_data["colony_id"] = colony_id
+        input_data["colony_data_dir"] = abs_data_dir
         data["input_data"] = input_data
 
         try:
@@ -246,7 +257,8 @@ def _patch_worker_configs(colony_dir: Path, db_path: Path) -> int:
 
     if patched:
         logger.info(
-            "progress_db: patched %d worker config(s) in colony '%s' with db_path",
+            "progress_db: patched %d worker config(s) in colony '%s' with "
+            "db_path + colony_data_dir",
             patched,
             colony_id,
         )

core/framework/host/shared_state.py

@@ -2,8 +2,6 @@
 
 import asyncio
 import logging
-import time
-from dataclasses import dataclass, field
 from enum import StrEnum
 from typing import Any
 

core/framework/host/stream_runtime.py

@@ -136,9 +136,7 @@ class StreamDecisionTracker:
         self._run_locks[execution_id] = asyncio.Lock()
         self._current_nodes[execution_id] = "unknown"
 
-        logger.debug(
-            f"Started run {run_id} for execution {execution_id} in stream {self.stream_id}"
-        )
+        logger.debug(f"Started run {run_id} for execution {execution_id} in stream {self.stream_id}")
         return run_id
 
     def end_run(
@@ -334,10 +332,7 @@ class StreamDecisionTracker:
         """
         run = self._runs.get(execution_id)
         if run is None:
-            logger.warning(
-                f"report_problem called but no run for execution {execution_id}: "
-                f"[{severity}] {description}"
-            )
+            logger.warning(f"report_problem called but no run for execution {execution_id}: [{severity}] {description}")
             return ""
 
         return run.add_problem(

core/framework/host/webhook_server.py

@@ -89,8 +89,7 @@ class WebhookServer:
         )
         await self._site.start()
         logger.info(
-            f"Webhook server started on {self._config.host}:{self._config.port} "
-            f"with {len(self._routes)} route(s)"
+            f"Webhook server started on {self._config.host}:{self._config.port} with {len(self._routes)} route(s)"
         )
 
     async def stop(self) -> None:

core/framework/host/worker.py

@@ -92,9 +92,7 @@ class Worker:
         # result.json, data). Required when seed_conversation() is used —
         # we deliberately do NOT fall back to CWD, which previously caused
         # conversation parts to leak into the process working directory.
-        self._storage_path: Path | None = (
-            Path(storage_path) if storage_path is not None else None
-        )
+        self._storage_path: Path | None = Path(storage_path) if storage_path is not None else None
         self._task_handle: asyncio.Task | None = None
         self._started_at: float = 0.0
         self._result: WorkerResult | None = None
@@ -147,20 +145,34 @@ class Worker:
         self.status = WorkerStatus.RUNNING
         self._started_at = time.monotonic()
 
+        # Scope browser profile (and any other CONTEXT_PARAMS) to this
+        # worker. asyncio.create_task() copies the parent's contextvars,
+        # so without this override every spawned worker inherits the
+        # queen's `profile=<queen_session_id>` and its browser_* tool
+        # calls end up driving the queen's Chrome tab group. Setting
+        # it here (inside the new Task's context) shadows the parent
+        # value without affecting the queen's ongoing calls.
+        try:
+            from framework.loader.tool_registry import ToolRegistry
+
+            ToolRegistry.set_execution_context(profile=self.id)
+        except Exception:
+            logger.debug(
+                "Worker %s: failed to scope browser profile",
+                self.id,
+                exc_info=True,
+            )
+
         try:
             result = await self._agent_loop.execute(self._context)
             duration = time.monotonic() - self._started_at
 
             if result.success:
                 self.status = WorkerStatus.COMPLETED
-                self._result = self._build_result(
-                    result, duration, default_status="success"
-                )
+                self._result = self._build_result(result, duration, default_status="success")
             else:
                 self.status = WorkerStatus.FAILED
-                self._result = self._build_result(
-                    result, duration, default_status="failed"
-                )
+                self._result = self._build_result(result, duration, default_status="failed")
 
             await self._emit_terminal_events(result)
 
@@ -176,13 +188,28 @@ class Worker:
         except asyncio.CancelledError:
             self.status = WorkerStatus.STOPPED
             duration = time.monotonic() - self._started_at
-            self._result = WorkerResult(
-                error="Worker stopped by queen",
-                duration_seconds=duration,
-                status="stopped",
-                summary="Worker was cancelled before completion.",
-            )
-            await self._emit_terminal_events(None, force_status="stopped")
+            # Preserve any explicit report the worker's LLM already filed
+            # via ``report_to_parent`` before being cancelled — the caller
+            # cares about that payload even on a hard stop. Only fall back
+            # to the canned "stopped" message when no explicit report exists.
+            explicit = self._explicit_report
+            if explicit is not None:
+                self._result = WorkerResult(
+                    error="Worker stopped by queen after reporting",
+                    duration_seconds=duration,
+                    status=explicit["status"],
+                    summary=explicit["summary"],
+                    data=explicit["data"],
+                )
+                await self._emit_terminal_events(None, force_status=explicit["status"])
+            else:
+                self._result = WorkerResult(
+                    error="Worker stopped by queen",
+                    duration_seconds=duration,
+                    status="stopped",
+                    summary="Worker was cancelled before completion.",
+                )
+                await self._emit_terminal_events(None, force_status="stopped")
             return self._result
 
         except Exception as exc:
@@ -292,11 +319,7 @@ class Worker:
 
         # EXECUTION_COMPLETED / EXECUTION_FAILED (backwards-compat)
         if agent_result is not None:
-            lifecycle_type = (
-                EventType.EXECUTION_COMPLETED
-                if agent_result.success
-                else EventType.EXECUTION_FAILED
-            )
+            lifecycle_type = EventType.EXECUTION_COMPLETED if agent_result.success else EventType.EXECUTION_FAILED
             await self._event_bus.publish(
                 AgentEvent(
                     type=lifecycle_type,
@@ -309,11 +332,7 @@ class Worker:
                         "task": self.task,
                         "success": agent_result.success,
                         "error": agent_result.error,
-                        "output_keys": (
-                            list(agent_result.output.keys())
-                            if agent_result.output
-                            else []
-                        ),
+                        "output_keys": (list(agent_result.output.keys()) if agent_result.output else []),
                     },
                 )
             )
@@ -348,9 +367,7 @@ class Worker:
 
     async def start_background(self) -> None:
         """Spawn the worker's run() as an asyncio background task."""
-        self._task_handle = asyncio.create_task(
-            self.run(), name=f"worker:{self.id}"
-        )
+        self._task_handle = asyncio.create_task(self.run(), name=f"worker:{self.id}")
         # Surface any exception that escapes run(); without this callback
         # a crash here only becomes visible when stop() eventually awaits
         # the handle (and is silently lost if stop() is never called).
@@ -406,8 +423,7 @@ class Worker:
         """
         if self.status != WorkerStatus.PENDING:
             raise RuntimeError(
-                f"seed_conversation must be called before start_background "
-                f"(worker {self.id} is {self.status})"
+                f"seed_conversation must be called before start_background (worker {self.id} is {self.status})"
             )
 
         # Write parts directly to the worker's on-disk conversation store

core/framework/llm/anthropic.py

@@ -50,9 +50,7 @@ class AnthropicProvider(LLMProvider):
         # Delegate to LiteLLMProvider internally.
         self.api_key = api_key or _get_api_key_from_credential_store()
         if not self.api_key:
-            raise ValueError(
-                "Anthropic API key required. Set ANTHROPIC_API_KEY env var or pass api_key."
-            )
+            raise ValueError("Anthropic API key required. Set ANTHROPIC_API_KEY env var or pass api_key.")
 
         self.model = model
 

core/framework/llm/antigravity.py

@@ -53,17 +53,9 @@ _TOKEN_REFRESH_BUFFER_SECS = 60
 # Credentials file in ~/.hive/ (native implementation)
 _ACCOUNTS_FILE = Path.home() / ".hive" / "antigravity-accounts.json"
 _IDE_STATE_DB_MAC = (
-    Path.home()
-    / "Library"
-    / "Application Support"
-    / "Antigravity"
-    / "User"
-    / "globalStorage"
-    / "state.vscdb"
-)
-_IDE_STATE_DB_LINUX = (
-    Path.home() / ".config" / "Antigravity" / "User" / "globalStorage" / "state.vscdb"
+    Path.home() / "Library" / "Application Support" / "Antigravity" / "User" / "globalStorage" / "state.vscdb"
 )
+_IDE_STATE_DB_LINUX = Path.home() / ".config" / "Antigravity" / "User" / "globalStorage" / "state.vscdb"
 _IDE_STATE_DB_KEY = "antigravityUnifiedStateSync.oauthToken"
 
 _BASE_HEADERS: dict[str, str] = {
@@ -368,9 +360,7 @@ def _to_gemini_contents(
 
 
 def _map_finish_reason(reason: str) -> str:
-    return {"STOP": "stop", "MAX_TOKENS": "max_tokens", "OTHER": "tool_use"}.get(
-        (reason or "").upper(), "stop"
-    )
+    return {"STOP": "stop", "MAX_TOKENS": "max_tokens", "OTHER": "tool_use"}.get((reason or "").upper(), "stop")
 
 
 def _parse_complete_response(raw: dict[str, Any], model: str) -> LLMResponse:
@@ -538,8 +528,7 @@ class AntigravityProvider(LLMProvider):
             return self._access_token
 
         raise RuntimeError(
-            "No valid Antigravity credentials. "
-            "Run: uv run python core/antigravity_auth.py auth account add"
+            "No valid Antigravity credentials. Run: uv run python core/antigravity_auth.py auth account add"
         )
 
     # --- Request building -------------------------------------------------- #
@@ -593,11 +582,7 @@ class AntigravityProvider(LLMProvider):
 
         token = self._ensure_token()
         body_bytes = json.dumps(body).encode("utf-8")
-        path = (
-            "/v1internal:streamGenerateContent?alt=sse"
-            if streaming
-            else "/v1internal:generateContent"
-        )
+        path = "/v1internal:streamGenerateContent?alt=sse" if streaming else "/v1internal:generateContent"
         headers = {
             **_BASE_HEADERS,
             "Authorization": f"Bearer {token}",
@@ -619,9 +604,7 @@ class AntigravityProvider(LLMProvider):
                     if result:
                         self._access_token, self._token_expires_at = result
                         headers["Authorization"] = f"Bearer {self._access_token}"
-                        req2 = urllib.request.Request(
-                            url, data=body_bytes, headers=headers, method="POST"
-                        )
+                        req2 = urllib.request.Request(url, data=body_bytes, headers=headers, method="POST")
                         try:
                             return urllib.request.urlopen(req2, timeout=120)  # noqa: S310
                         except urllib.error.HTTPError as exc2:
@@ -642,9 +625,7 @@ class AntigravityProvider(LLMProvider):
                 last_exc = exc
                 continue
 
-        raise RuntimeError(
-            f"All Antigravity endpoints failed. Last error: {last_exc}"
-        ) from last_exc
+        raise RuntimeError(f"All Antigravity endpoints failed. Last error: {last_exc}") from last_exc
 
     # --- LLMProvider interface --------------------------------------------- #
 
@@ -683,9 +664,7 @@ class AntigravityProvider(LLMProvider):
             try:
                 body = self._build_body(messages, system, tools, max_tokens)
                 http_resp = self._post(body, streaming=True)
-                for event in _parse_sse_stream(
-                    http_resp, self.model, self._thought_sigs.__setitem__
-                ):
+                for event in _parse_sse_stream(http_resp, self.model, self._thought_sigs.__setitem__):
                     loop.call_soon_threadsafe(queue.put_nowait, event)
             except Exception as exc:
                 logger.error("Antigravity stream error: %s", exc)

core/framework/llm/litellm.py

@@ -100,9 +100,7 @@ def _patch_litellm_anthropic_oauth() -> None:
             result["authorization"] = f"Bearer {token}"
             # Merge the OAuth beta header with any existing beta headers.
             existing_beta = result.get("anthropic-beta", "")
-            beta_parts = (
-                [b.strip() for b in existing_beta.split(",") if b.strip()] if existing_beta else []
-            )
+            beta_parts = [b.strip() for b in existing_beta.split(",") if b.strip()] if existing_beta else []
             if ANTHROPIC_OAUTH_BETA_HEADER not in beta_parts:
                 beta_parts.append(ANTHROPIC_OAUTH_BETA_HEADER)
             result["anthropic-beta"] = ",".join(beta_parts)
@@ -262,9 +260,7 @@ def _claude_code_billing_header(messages: list[dict[str, Any]]) -> str:
                 break
 
     sampled = "".join(_sample_js_code_unit(first_text, i) for i in (4, 7, 20))
-    version_hash = hashlib.sha256(
-        f"{_CLAUDE_CODE_BILLING_SALT}{sampled}{CLAUDE_CODE_VERSION}".encode()
-    ).hexdigest()
+    version_hash = hashlib.sha256(f"{_CLAUDE_CODE_BILLING_SALT}{sampled}{CLAUDE_CODE_VERSION}".encode()).hexdigest()
     entrypoint = os.environ.get("CLAUDE_CODE_ENTRYPOINT", "").strip() or "cli"
     return (
         f"x-anthropic-billing-header: cc_version={CLAUDE_CODE_VERSION}.{version_hash[:3]}; "
@@ -336,9 +332,7 @@ def _prune_failed_request_dumps(max_files: int = MAX_FAILED_REQUEST_DUMPS) -> No
 
 def _remember_openrouter_tool_compat_model(model: str) -> None:
     """Cache OpenRouter tool-compat fallback for a bounded time window."""
-    OPENROUTER_TOOL_COMPAT_MODEL_CACHE[model] = (
-        time.monotonic() + OPENROUTER_TOOL_COMPAT_CACHE_TTL_SECONDS
-    )
+    OPENROUTER_TOOL_COMPAT_MODEL_CACHE[model] = time.monotonic() + OPENROUTER_TOOL_COMPAT_CACHE_TTL_SECONDS
 
 
 def _is_openrouter_tool_compat_cached(model: str) -> bool:
@@ -746,20 +740,14 @@ class LiteLLMProvider(LLMProvider):
             eh.setdefault("user-agent", CLAUDE_CODE_USER_AGENT)
         # The Codex ChatGPT backend (chatgpt.com/backend-api/codex) rejects
         # several standard OpenAI params: max_output_tokens, stream_options.
-        self._codex_backend = bool(
-            self.api_base and "chatgpt.com/backend-api/codex" in self.api_base
-        )
+        self._codex_backend = bool(self.api_base and "chatgpt.com/backend-api/codex" in self.api_base)
         # Antigravity routes through a local OpenAI-compatible proxy — no patches needed.
         self._antigravity = bool(self.api_base and "localhost:8069" in self.api_base)
 
         if litellm is None:
-            raise ImportError(
-                "LiteLLM is not installed. Please install it with: uv pip install litellm"
-            )
+            raise ImportError("LiteLLM is not installed. Please install it with: uv pip install litellm")
 
-    def reconfigure(
-        self, model: str, api_key: str | None = None, api_base: str | None = None
-    ) -> None:
+    def reconfigure(self, model: str, api_key: str | None = None, api_base: str | None = None) -> None:
         """Hot-swap the model, API key, and/or base URL on this provider instance.
 
         Since the same LiteLLMProvider object is shared by reference across the
@@ -784,9 +772,7 @@ class LiteLLMProvider(LLMProvider):
         if self._claude_code_oauth:
             eh = self.extra_kwargs.setdefault("extra_headers", {})
             eh.setdefault("user-agent", CLAUDE_CODE_USER_AGENT)
-        self._codex_backend = bool(
-            self.api_base and "chatgpt.com/backend-api/codex" in self.api_base
-        )
+        self._codex_backend = bool(self.api_base and "chatgpt.com/backend-api/codex" in self.api_base)
         self._antigravity = bool(self.api_base and "localhost:8069" in self.api_base)
 
         # Note: The Codex ChatGPT backend is a Responses API endpoint at
@@ -809,9 +795,7 @@ class LiteLLMProvider(LLMProvider):
             return HIVE_API_BASE
         return None
 
-    def _completion_with_rate_limit_retry(
-        self, max_retries: int | None = None, **kwargs: Any
-    ) -> Any:
+    def _completion_with_rate_limit_retry(self, max_retries: int | None = None, **kwargs: Any) -> Any:
         """Call litellm.completion with retry on 429 rate limit errors and empty responses.
 
         When a :class:`KeyPool` is configured, rate-limited keys are rotated
@@ -843,15 +827,10 @@ class LiteLLMProvider(LLMProvider):
                         None,
                     )
                     if last_role == "assistant":
-                        logger.debug(
-                            "[retry] Empty response after assistant message — "
-                            "expected, not retrying."
-                        )
+                        logger.debug("[retry] Empty response after assistant message — expected, not retrying.")
                         return response
 
-                    finish_reason = (
-                        response.choices[0].finish_reason if response.choices else "unknown"
-                    )
+                    finish_reason = response.choices[0].finish_reason if response.choices else "unknown"
                     # Dump full request to file for debugging
                     token_count, token_method = _estimate_tokens(model, messages)
                     dump_path = _dump_failed_request(
@@ -1050,9 +1029,7 @@ class LiteLLMProvider(LLMProvider):
     # Async variants — non-blocking on the event loop
     # ------------------------------------------------------------------
 
-    async def _acompletion_with_rate_limit_retry(
-        self, max_retries: int | None = None, **kwargs: Any
-    ) -> Any:
+    async def _acompletion_with_rate_limit_retry(self, max_retries: int | None = None, **kwargs: Any) -> Any:
         """Async version of _completion_with_rate_limit_retry.
 
         Uses litellm.acompletion and asyncio.sleep instead of blocking calls.
@@ -1078,15 +1055,10 @@ class LiteLLMProvider(LLMProvider):
                         None,
                     )
                     if last_role == "assistant":
-                        logger.debug(
-                            "[async-retry] Empty response after assistant message — "
-                            "expected, not retrying."
-                        )
+                        logger.debug("[async-retry] Empty response after assistant message — expected, not retrying.")
                         return response
 
-                    finish_reason = (
-                        response.choices[0].finish_reason if response.choices else "unknown"
-                    )
+                    finish_reason = response.choices[0].finish_reason if response.choices else "unknown"
                     token_count, token_method = _estimate_tokens(model, messages)
                     dump_path = _dump_failed_request(
                         model=model,
@@ -1370,8 +1342,7 @@ class LiteLLMProvider(LLMProvider):
                 )
                 return text_tool_content, text_tool_calls
             logger.info(
-                "[openrouter-tool-compat] %s returned non-JSON fallback content; "
-                "treating it as plain text.",
+                "[openrouter-tool-compat] %s returned non-JSON fallback content; treating it as plain text.",
                 self.model,
             )
             return content.strip(), []
@@ -1523,9 +1494,7 @@ class LiteLLMProvider(LLMProvider):
             )
             return repaired
 
-        raise ValueError(
-            f"Failed to parse tool call arguments for '{tool_name}' (likely truncated JSON)."
-        )
+        raise ValueError(f"Failed to parse tool call arguments for '{tool_name}' (likely truncated JSON).")
 
     def _parse_openrouter_text_tool_calls(
         self,
@@ -1682,11 +1651,7 @@ class LiteLLMProvider(LLMProvider):
         return [
             message
             for message in full_messages
-            if not (
-                message.get("role") == "assistant"
-                and not message.get("content")
-                and not message.get("tool_calls")
-            )
+            if not (message.get("role") == "assistant" and not message.get("content") and not message.get("tool_calls"))
         ]
 
     async def _acomplete_via_openrouter_tool_compat(
@@ -1914,8 +1879,8 @@ class LiteLLMProvider(LLMProvider):
 
         if logger.isEnabledFor(logging.DEBUG) and full_messages:
             import json as _json
-            from pathlib import Path as _Path
             from datetime import datetime as _dt
+            from pathlib import Path as _Path
 
             _debug_dir = _Path.home() / ".hive" / "debug_logs"
             _debug_dir.mkdir(parents=True, exist_ok=True)
@@ -1939,9 +1904,7 @@ class LiteLLMProvider(LLMProvider):
                     }
                 )
             try:
-                _dump_file.write_text(
-                    _json.dumps(_summary, indent=2, ensure_ascii=False), encoding="utf-8"
-                )
+                _dump_file.write_text(_json.dumps(_summary, indent=2, ensure_ascii=False), encoding="utf-8")
                 logger.debug("[LLM-MSG] %d messages dumped to %s", len(full_messages), _dump_file)
             except Exception:
                 pass
@@ -1966,9 +1929,7 @@ class LiteLLMProvider(LLMProvider):
         full_messages = [
             m
             for m in full_messages
-            if not (
-                m.get("role") == "assistant" and not m.get("content") and not m.get("tool_calls")
-            )
+            if not (m.get("role") == "assistant" and not m.get("content") and not m.get("tool_calls"))
         ]
 
         kwargs: dict[str, Any] = {
@@ -2154,8 +2115,7 @@ class LiteLLMProvider(LLMProvider):
                                 else getattr(usage, "cache_read_input_tokens", 0) or 0
                             )
                             logger.debug(
-                                "[tokens] finish-chunk usage: "
-                                "input=%d output=%d cached=%d model=%s",
+                                "[tokens] finish-chunk usage: input=%d output=%d cached=%d model=%s",
                                 input_tokens,
                                 output_tokens,
                                 cached_tokens,
@@ -2202,8 +2162,7 @@ class LiteLLMProvider(LLMProvider):
                                 else getattr(_usage, "cache_read_input_tokens", 0) or 0
                             )
                             logger.debug(
-                                "[tokens] post-loop chunks fallback:"
-                                " input=%d output=%d cached=%d model=%s",
+                                "[tokens] post-loop chunks fallback: input=%d output=%d cached=%d model=%s",
                                 input_tokens,
                                 output_tokens,
                                 cached_tokens,

core/framework/llm/model_catalog.json

@@ -61,14 +61,14 @@
           "label": "Gemini 3 Flash - Fast",
           "recommended": false,
           "max_tokens": 32768,
-          "max_context_tokens": 900000
+          "max_context_tokens": 240000
         },
         {
-          "id": "gemini-3.1-pro-preview",
+          "id": "gemini-3.1-pro-preview-customtools",
           "label": "Gemini 3.1 Pro - Best quality",
           "recommended": true,
           "max_tokens": 32768,
-          "max_context_tokens": 900000
+          "max_context_tokens": 240000
         }
       ]
     },
@@ -305,7 +305,7 @@
           "max_context_tokens": 872000
         },
         {
-          "id": "google/gemini-3.1-pro-preview",
+          "id": "google/gemini-3.1-pro-preview-customtools",
           "label": "Gemini 3.1 Pro Preview - Long-context reasoning",
           "recommended": false,
           "max_tokens": 32768,

core/framework/llm/model_catalog.py

@@ -50,9 +50,7 @@ def _validate_model_catalog(data: dict[str, Any]) -> dict[str, Any]:
             if not isinstance(model_id, str) or not model_id.strip():
                 raise ModelCatalogError(f"{model_path}.id must be a non-empty string")
             if model_id in seen_model_ids:
-                raise ModelCatalogError(
-                    f"Duplicate model id {model_id!r} in {provider_path}.models"
-                )
+                raise ModelCatalogError(f"Duplicate model id {model_id!r} in {provider_path}.models")
             seen_model_ids.add(model_id)
 
             if model_id == default_model:
@@ -91,17 +89,11 @@ def _validate_model_catalog(data: dict[str, Any]) -> dict[str, Any]:
 
         api_base = preset_map.get("api_base")
         if api_base is not None and (not isinstance(api_base, str) or not api_base.strip()):
-            raise ModelCatalogError(
-                f"{preset_path}.api_base must be a non-empty string when present"
-            )
+            raise ModelCatalogError(f"{preset_path}.api_base must be a non-empty string when present")
 
         api_key_env_var = preset_map.get("api_key_env_var")
-        if api_key_env_var is not None and (
-            not isinstance(api_key_env_var, str) or not api_key_env_var.strip()
-        ):
-            raise ModelCatalogError(
-                f"{preset_path}.api_key_env_var must be a non-empty string when present"
-            )
+        if api_key_env_var is not None and (not isinstance(api_key_env_var, str) or not api_key_env_var.strip()):
+            raise ModelCatalogError(f"{preset_path}.api_key_env_var must be a non-empty string when present")
 
         for key in ("max_tokens", "max_context_tokens"):
             value = preset_map.get(key)
@@ -110,9 +102,7 @@ def _validate_model_catalog(data: dict[str, Any]) -> dict[str, Any]:
 
         model_choices = preset_map.get("model_choices")
         if model_choices is not None:
-            for idx, choice in enumerate(
-                _require_list(model_choices, f"{preset_path}.model_choices")
-            ):
+            for idx, choice in enumerate(_require_list(model_choices, f"{preset_path}.model_choices")):
                 choice_path = f"{preset_path}.model_choices[{idx}]"
                 choice_map = _require_mapping(choice, choice_path)
                 choice_id = choice_map.get("id")
@@ -144,19 +134,13 @@ def load_model_catalog() -> dict[str, Any]:
 def get_models_catalogue() -> dict[str, list[dict[str, Any]]]:
     """Return provider -> model list."""
     providers = load_model_catalog()["providers"]
-    return {
-        provider_id: copy.deepcopy(provider_info["models"])
-        for provider_id, provider_info in providers.items()
-    }
+    return {provider_id: copy.deepcopy(provider_info["models"]) for provider_id, provider_info in providers.items()}
 
 
 def get_default_models() -> dict[str, str]:
     """Return provider -> default model id."""
     providers = load_model_catalog()["providers"]
-    return {
-        provider_id: str(provider_info["default_model"])
-        for provider_id, provider_info in providers.items()
-    }
+    return {provider_id: str(provider_info["default_model"]) for provider_id, provider_info in providers.items()}
 
 
 def get_provider_models(provider: str) -> list[dict[str, Any]]:

core/framework/loader/agent_loader.py

@@ -9,7 +9,7 @@ from datetime import UTC
 from pathlib import Path
 from typing import Any
 
-from framework.config import get_hive_config, get_max_context_tokens, get_preferred_model
+from framework.config import get_hive_config, get_preferred_model
 from framework.credentials.validation import (
     ensure_credential_key_env as _ensure_credential_key_env,
 )
@@ -20,14 +20,12 @@ from framework.loader.preload_validation import run_preload_validation
 from framework.loader.tool_registry import ToolRegistry
 from framework.orchestrator import Goal
 from framework.orchestrator.edge import (
-    DEFAULT_MAX_TOKENS,
     EdgeCondition,
     EdgeSpec,
     GraphSpec,
 )
 from framework.orchestrator.node import NodeSpec
 from framework.orchestrator.orchestrator import ExecutionResult
-from framework.tools.flowchart_utils import generate_fallback_flowchart
 
 logger = logging.getLogger(__name__)
 
@@ -555,18 +553,10 @@ def get_kimi_code_token() -> str | None:
 # VSCode-style SQLite state database under the key
 # "antigravityUnifiedStateSync.oauthToken" as a base64-encoded protobuf blob.
 ANTIGRAVITY_IDE_STATE_DB = (
-    Path.home()
-    / "Library"
-    / "Application Support"
-    / "Antigravity"
-    / "User"
-    / "globalStorage"
-    / "state.vscdb"
+    Path.home() / "Library" / "Application Support" / "Antigravity" / "User" / "globalStorage" / "state.vscdb"
 )
 # Linux fallback for the IDE state DB
-ANTIGRAVITY_IDE_STATE_DB_LINUX = (
-    Path.home() / ".config" / "Antigravity" / "User" / "globalStorage" / "state.vscdb"
-)
+ANTIGRAVITY_IDE_STATE_DB_LINUX = Path.home() / ".config" / "Antigravity" / "User" / "globalStorage" / "state.vscdb"
 # Antigravity credentials stored by native OAuth implementation
 ANTIGRAVITY_AUTH_FILE = Path.home() / ".hive" / "antigravity-accounts.json"
 
@@ -710,9 +700,7 @@ def _is_antigravity_token_expired(auth_data: dict) -> bool:
             return True
     elif isinstance(last_refresh_val, str):
         try:
-            last_refresh_val = datetime.fromisoformat(
-                last_refresh_val.replace("Z", "+00:00")
-            ).timestamp()
+            last_refresh_val = datetime.fromisoformat(last_refresh_val.replace("Z", "+00:00")).timestamp()
         except (ValueError, TypeError):
             return True
 
@@ -843,8 +831,7 @@ def get_antigravity_token() -> str | None:
         return token_data["access_token"]
 
     logger.warning(
-        "Antigravity token refresh failed. "
-        "Re-open the Antigravity IDE or run 'antigravity-auth accounts add'."
+        "Antigravity token refresh failed. Re-open the Antigravity IDE or run 'antigravity-auth accounts add'."
     )
     return access_token
 
@@ -1297,11 +1284,7 @@ class AgentLoader:
         # Evict cached submodules first (e.g. deep_research_agent.nodes,
         # deep_research_agent.agent) so the top-level reload picks up
         # changes in the entire package — not just __init__.py.
-        stale = [
-            name
-            for name in sys.modules
-            if name == package_name or name.startswith(f"{package_name}.")
-        ]
+        stale = [name for name in sys.modules if name == package_name or name.startswith(f"{package_name}.")]
         for name in stale:
             del sys.modules[name]
 
@@ -1350,7 +1333,7 @@ class AgentLoader:
         if not worker_jsons:
             raise FileNotFoundError(f"No worker config found in {agent_path}")
 
-        from framework.orchestrator.edge import EdgeSpec, GraphSpec
+        from framework.orchestrator.edge import GraphSpec
         from framework.orchestrator.goal import Constraint, Goal as GoalModel, SuccessCriterion
         from framework.orchestrator.node import NodeSpec
 
@@ -1566,7 +1549,6 @@ class AgentLoader:
         ]
 
         # Merge user-configured stages from ~/.hive/configuration.json
-        from framework.config import get_hive_config
         from framework.pipeline.registry import build_pipeline_from_config
 
         hive_config = get_hive_config()
@@ -1579,9 +1561,7 @@ class AgentLoader:
         if agent_json.exists():
             try:
                 agent_pipeline = (
-                    _json.loads(agent_json.read_text(encoding="utf-8"))
-                    .get("pipeline", {})
-                    .get("stages", [])
+                    _json.loads(agent_json.read_text(encoding="utf-8")).get("pipeline", {}).get("stages", [])
                 )
                 if agent_pipeline:
                     agent_stages = build_pipeline_from_config(agent_pipeline)
@@ -1997,8 +1977,7 @@ class AgentLoader:
                 for sc in self.goal.success_criteria
             ],
             constraints=[
-                {"id": c.id, "description": c.description, "type": c.constraint_type}
-                for c in self.goal.constraints
+                {"id": c.id, "description": c.description, "type": c.constraint_type} for c in self.goal.constraints
             ],
             required_tools=sorted(required_tools),
             has_tools_module=(self.agent_path / "tools.py").exists(),
@@ -2069,9 +2048,7 @@ class AgentLoader:
                 if api_key_env and not os.environ.get(api_key_env):
                     if api_key_env not in missing_credentials:
                         missing_credentials.append(api_key_env)
-                    warnings.append(
-                        f"Agent has LLM nodes but {api_key_env} not set (model: {self.model})"
-                    )
+                    warnings.append(f"Agent has LLM nodes but {api_key_env} not set (model: {self.model})")
 
         return ValidationResult(
             valid=len(errors) == 0,

core/framework/loader/cli.py

@@ -21,11 +21,11 @@ import os
 import shutil
 import subprocess
 import sys
+import threading
 from pathlib import Path
 from typing import Any
 from urllib import error as urlerror, parse as urlparse, request as urlrequest
 
-
 # ---------------------------------------------------------------------------
 # Public registration
 # ---------------------------------------------------------------------------
@@ -127,10 +127,7 @@ def cmd_serve(args: argparse.Namespace) -> int:
         def _request_shutdown(signame: str) -> None:
             signal_count["n"] += 1
             if signal_count["n"] == 1:
-                print(
-                    f"\nReceived {signame}, shutting down gracefully… "
-                    "(press Ctrl+C again to force quit)"
-                )
+                print(f"\nReceived {signame}, shutting down gracefully… (press Ctrl+C again to force quit)")
                 shutdown_event.set()
             else:
                 # Second Ctrl+C (or SIGTERM) — the user is done waiting.
@@ -171,9 +168,7 @@ def cmd_serve(args: argparse.Namespace) -> int:
                 print(f"Colony not found: {colony_arg}")
                 continue
             try:
-                session = await manager.create_session_with_worker_colony(
-                    str(colony_path), model=model
-                )
+                session = await manager.create_session_with_worker_colony(str(colony_path), model=model)
                 info = session.worker_info
                 name = info.name if info else session.colony_id
                 print(f"Loaded colony: {session.colony_id} ({name}) → session {session.id}")
@@ -220,7 +215,13 @@ def cmd_serve(args: argparse.Namespace) -> int:
 
 def cmd_open(args: argparse.Namespace) -> int:
     """Start the HTTP server and open the dashboard in the browser."""
-    _ping_hive_gateway_availability("hive-open")
+    # Don't block local startup on a best-effort analytics probe.
+    threading.Thread(
+        target=_ping_hive_gateway_availability,
+        args=("hive-open",),
+        daemon=True,
+        name="hive-open-gateway-ping",
+    ).start()
     args.open = True
     return cmd_serve(args)
 
@@ -319,12 +320,14 @@ def cmd_queen_sessions(args: argparse.Namespace) -> int:
                 meta = json.loads(meta_path.read_text(encoding="utf-8"))
             except Exception:
                 meta = {}
-        rows.append({
-            "session_id": session_dir.name,
-            "phase": meta.get("phase", "?"),
-            "agent_path": meta.get("agent_path", ""),
-            "colony_fork": bool(meta.get("colony_fork")),
-        })
+        rows.append(
+            {
+                "session_id": session_dir.name,
+                "phase": meta.get("phase", "?"),
+                "agent_path": meta.get("agent_path", ""),
+                "colony_fork": bool(meta.get("colony_fork")),
+            }
+        )
 
     if args.json:
         print(json.dumps(rows, indent=2))
@@ -398,18 +401,18 @@ def cmd_colony_list(args: argparse.Namespace) -> int:
             except Exception:
                 meta = {}
         worker_count = sum(
-            1
-            for f in path.iterdir()
-            if f.is_file() and f.suffix == ".json" and f.stem not in _RESERVED_JSON_STEMS
+            1 for f in path.iterdir() if f.is_file() and f.suffix == ".json" and f.stem not in _RESERVED_JSON_STEMS
+        )
+        rows.append(
+            {
+                "name": path.name,
+                "queen_name": meta.get("queen_name", ""),
+                "queen_session_id": meta.get("queen_session_id", ""),
+                "workers": worker_count,
+                "created_at": meta.get("created_at", ""),
+                "path": str(path),
+            }
         )
-        rows.append({
-            "name": path.name,
-            "queen_name": meta.get("queen_name", ""),
-            "queen_session_id": meta.get("queen_session_id", ""),
-            "workers": worker_count,
-            "created_at": meta.get("created_at", ""),
-            "path": str(path),
-        })
 
     if args.json:
         print(json.dumps(rows, indent=2))
@@ -422,9 +425,7 @@ def cmd_colony_list(args: argparse.Namespace) -> int:
     print(f"{'NAME':<24}  {'QUEEN':<28}  {'WORKERS':<8}  CREATED")
     print("-" * 90)
     for r in rows:
-        print(
-            f"{r['name']:<24}  {r['queen_name']:<28}  {r['workers']:<8}  {r['created_at'][:19]}"
-        )
+        print(f"{r['name']:<24}  {r['queen_name']:<28}  {r['workers']:<8}  {r['created_at'][:19]}")
     return 0
 
 
@@ -651,9 +652,7 @@ def _http_get(url: str, timeout: float = 10.0) -> dict:
 
 def _http_post(url: str, body: dict, timeout: float = 30.0) -> dict:
     data = json.dumps(body).encode("utf-8")
-    req = urlrequest.Request(
-        url, data=data, method="POST", headers={"Content-Type": "application/json"}
-    )
+    req = urlrequest.Request(url, data=data, method="POST", headers={"Content-Type": "application/json"})
     with urlrequest.urlopen(req, timeout=timeout) as r:
         return json.loads(r.read().decode("utf-8"))
 
@@ -709,9 +708,7 @@ def _open_browser(url: str) -> None:
 
     try:
         if sys.platform == "darwin":
-            subprocess.Popen(
-                ["open", url], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL
-            )
+            subprocess.Popen(["open", url], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
         elif sys.platform == "win32":
             subprocess.Popen(
                 ["cmd", "/c", "start", "", url],
@@ -719,9 +716,7 @@ def _open_browser(url: str) -> None:
                 stderr=subprocess.DEVNULL,
             )
         elif sys.platform == "linux":
-            subprocess.Popen(
-                ["xdg-open", url], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL
-            )
+            subprocess.Popen(["xdg-open", url], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
     except Exception:
         pass
 

core/framework/loader/mcp_client.py

@@ -267,9 +267,7 @@ class MCPClient:
         try:
             response = self._http_client.get("/health")
             response.raise_for_status()
-            logger.info(
-                f"Connected to MCP server '{self.config.name}' via HTTP at {self.config.url}"
-            )
+            logger.info(f"Connected to MCP server '{self.config.name}' via HTTP at {self.config.url}")
         except Exception as e:
             logger.warning(f"Health check failed for MCP server '{self.config.name}': {e}")
             # Continue anyway, server might not have health endpoint
@@ -377,12 +375,8 @@ class MCPClient:
                 self._tools[tool.name] = tool
 
             tool_names = list(self._tools.keys())
-            logger.info(
-                f"Discovered {len(self._tools)} tools from '{self.config.name}'"
-            )
-            logger.debug(
-                f"Discovered tools from '{self.config.name}': {tool_names}"
-            )
+            logger.info(f"Discovered {len(self._tools)} tools from '{self.config.name}'")
+            logger.debug(f"Discovered tools from '{self.config.name}': {tool_names}")
         except Exception as e:
             logger.error(f"Failed to discover tools from '{self.config.name}': {e}")
             raise
@@ -467,6 +461,7 @@ class MCPClient:
             )
 
         if self.config.transport == "stdio":
+
             def _stdio_call() -> Any:
                 with self._stdio_call_lock:
                     return self._run_async(self._call_tool_stdio_async(tool_name, arguments))
@@ -669,9 +664,7 @@ class MCPClient:
             if self._session:
                 await self._session.__aexit__(None, None, None)
         except asyncio.CancelledError:
-            logger.warning(
-                "MCP session cleanup was cancelled; proceeding with best-effort shutdown"
-            )
+            logger.warning("MCP session cleanup was cancelled; proceeding with best-effort shutdown")
         except Exception as e:
             logger.warning(f"Error closing MCP session: {e}")
         finally:
@@ -682,9 +675,7 @@ class MCPClient:
             if self._stdio_context:
                 await self._stdio_context.__aexit__(None, None, None)
         except asyncio.CancelledError:
-            logger.debug(
-                "STDIO context cleanup was cancelled; proceeding with best-effort shutdown"
-            )
+            logger.debug("STDIO context cleanup was cancelled; proceeding with best-effort shutdown")
         except Exception as e:
             msg = str(e).lower()
             if "cancel scope" in msg or "different task" in msg:
@@ -725,9 +716,7 @@ class MCPClient:
             # any exceptions that may occur if the loop stops between these calls.
             if self._loop.is_running():
                 try:
-                    cleanup_future = asyncio.run_coroutine_threadsafe(
-                        self._cleanup_stdio_async(), self._loop
-                    )
+                    cleanup_future = asyncio.run_coroutine_threadsafe(self._cleanup_stdio_async(), self._loop)
                     cleanup_future.result(timeout=self._CLEANUP_TIMEOUT)
                     cleanup_attempted = True
                 except TimeoutError:

core/framework/loader/mcp_connection_manager.py

@@ -74,8 +74,7 @@ class MCPConnectionManager:
             if not should_connect:
                 if not transition_event.wait(timeout=_TRANSITION_TIMEOUT):
                     logger.warning(
-                        "Timed out waiting for transition on MCP server '%s', "
-                        "forcing cleanup and retrying",
+                        "Timed out waiting for transition on MCP server '%s', forcing cleanup and retrying",
                         server_name,
                     )
                     with self._pool_lock:
@@ -99,10 +98,7 @@ class MCPConnectionManager:
                     current = self._transitions.get(server_name)
                     if current is transition_event:
                         self._transitions.pop(server_name, None)
-                        if (
-                            server_name not in self._pool
-                            and self._refcounts.get(server_name, 0) <= 0
-                        ):
+                        if server_name not in self._pool and self._refcounts.get(server_name, 0) <= 0:
                             self._configs.pop(server_name, None)
                         transition_event.set()
                 raise
@@ -324,8 +320,7 @@ class MCPConnectionManager:
                     self._transitions.pop(server_name, None)
                     transition_event.set()
                     logger.info(
-                        "Reconnected MCP server '%s' but refcount dropped to 0, "
-                        "discarding new client",
+                        "Reconnected MCP server '%s' but refcount dropped to 0, discarding new client",
                         server_name,
                     )
                     try:
@@ -336,9 +331,7 @@ class MCPConnectionManager:
                             server_name,
                             exc_info=True,
                         )
-                    raise KeyError(
-                        f"MCP server '{server_name}' was fully released during reconnect"
-                    )
+                    raise KeyError(f"MCP server '{server_name}' was fully released during reconnect")
 
                 self._pool[server_name] = new_client
                 self._configs[server_name] = config
@@ -380,8 +373,7 @@ class MCPConnectionManager:
             all_resolved = all(event.wait(timeout=_TRANSITION_TIMEOUT) for event in pending)
             if not all_resolved:
                 logger.warning(
-                    "Timed out waiting for pending transitions during cleanup, "
-                    "forcing cleanup of stuck transitions",
+                    "Timed out waiting for pending transitions during cleanup, forcing cleanup of stuck transitions",
                 )
                 with self._pool_lock:
                     for sn, evt in list(self._transitions.items()):

core/framework/loader/mcp_errors.py

@@ -23,9 +23,7 @@ class MCPError(ValueError):
         self.what = what
         self.why = why
         self.fix = fix
-        self.message = (
-            f"[{self.code.value}]\nWhat failed: {self.what}\nWhy: {self.why}\nFix: {self.fix}"
-        )
+        self.message = f"[{self.code.value}]\nWhat failed: {self.what}\nWhy: {self.why}\nFix: {self.fix}"
         super().__init__(self.message)
 
 

core/framework/loader/mcp_registry.py

@@ -24,9 +24,7 @@ from framework.loader.mcp_errors import (
 
 logger = logging.getLogger(__name__)
 
-DEFAULT_INDEX_URL = (
-    "https://raw.githubusercontent.com/aden-hive/hive-mcp-registry/main/registry_index.json"
-)
+DEFAULT_INDEX_URL = "https://raw.githubusercontent.com/aden-hive/hive-mcp-registry/main/registry_index.json"
 DEFAULT_REFRESH_INTERVAL_HOURS = 24
 _LAST_FETCHED_FILENAME = "last_fetched"
 _LEGACY_LAST_FETCHED_FILENAME = "last_fetched.json"
@@ -140,9 +138,7 @@ class MCPRegistry:
                 )
                 added.append(name)
             except MCPError as exc:
-                logger.warning(
-                    "MCPRegistry.ensure_defaults: failed to seed '%s': %s", name, exc
-                )
+                logger.warning("MCPRegistry.ensure_defaults: failed to seed '%s': %s", name, exc)
 
         if added:
             logger.info("MCPRegistry: seeded default local servers: %s", added)
@@ -709,8 +705,7 @@ class MCPRegistry:
                 pinned_version = versions[name]
                 if installed_version != pinned_version:
                     logger.warning(
-                        "Server '%s' version mismatch: installed=%s, pinned=%s. "
-                        "Run: hive mcp update %s",
+                        "Server '%s' version mismatch: installed=%s, pinned=%s. Run: hive mcp update %s",
                         name,
                         installed_version,
                         pinned_version,

core/framework/loader/mcp_registry_cli.py

@@ -151,10 +151,7 @@ def _parse_key_value_pairs(values: list[str]) -> dict[str, str]:
     result = {}
     for item in values:
         if "=" not in item:
-            raise ValueError(
-                f"Invalid format: '{item}'. Expected KEY=VALUE.\n"
-                f"Example: --set JIRA_API_TOKEN=abc123"
-            )
+            raise ValueError(f"Invalid format: '{item}'. Expected KEY=VALUE.\nExample: --set JIRA_API_TOKEN=abc123")
         key, _, value = item.partition("=")
         if not key:
             raise ValueError(f"Invalid format: '{item}'. Key cannot be empty.")
@@ -300,12 +297,8 @@ def register_mcp_commands(subparsers) -> None:
     # ── install ──
     install_p = mcp_sub.add_parser("install", help="Install a server from the registry")
     install_p.add_argument("name", help="Server name in the registry")
-    install_p.add_argument(
-        "--version", dest="version", default=None, help="Pin to a specific version"
-    )
-    install_p.add_argument(
-        "--transport", default=None, help="Override default transport (stdio, http, unix, sse)"
-    )
+    install_p.add_argument("--version", dest="version", default=None, help="Pin to a specific version")
+    install_p.add_argument("--transport", default=None, help="Override default transport (stdio, http, unix, sse)")
     install_p.set_defaults(func=cmd_mcp_install)
 
     # ── add ──
@@ -342,9 +335,7 @@ def register_mcp_commands(subparsers) -> None:
 
     # ── list ──
     list_p = mcp_sub.add_parser("list", help="List servers")
-    list_p.add_argument(
-        "--available", action="store_true", help="Show available servers from registry"
-    )
+    list_p.add_argument("--available", action="store_true", help="Show available servers from registry")
     list_p.add_argument("--json", dest="output_json", action="store_true", help="Output as JSON")
     list_p.set_defaults(func=cmd_mcp_list)
 
@@ -364,9 +355,7 @@ def register_mcp_commands(subparsers) -> None:
         metavar="KEY=VAL",
         help="Set environment variable overrides",
     )
-    config_p.add_argument(
-        "--set-header", dest="set_header", nargs="+", metavar="KEY=VAL", help="Set header overrides"
-    )
+    config_p.add_argument("--set-header", dest="set_header", nargs="+", metavar="KEY=VAL", help="Set header overrides")
     config_p.set_defaults(func=cmd_mcp_config)
 
     # ── search ──
@@ -389,9 +378,7 @@ def register_mcp_commands(subparsers) -> None:
     init_p.set_defaults(func=cmd_mcp_init)
 
     # ── update ──
-    update_p = mcp_sub.add_parser(
-        "update", help="Update installed servers or refresh the registry index"
-    )
+    update_p = mcp_sub.add_parser("update", help="Update installed servers or refresh the registry index")
     update_p.add_argument(
         "name",
         nargs="?",
@@ -495,8 +482,7 @@ def _cmd_mcp_add_from_manifest(registry, manifest_path: str) -> int:
         manifest = json.loads(path.read_text(encoding="utf-8"))
     except json.JSONDecodeError as exc:
         print(
-            f"Error: invalid JSON in {manifest_path}: {exc}\n"
-            f"Validate with: python -m json.tool {manifest_path}",
+            f"Error: invalid JSON in {manifest_path}: {exc}\nValidate with: python -m json.tool {manifest_path}",
             file=sys.stderr,
         )
         return 1
@@ -695,8 +681,7 @@ def cmd_mcp_config(args) -> int:
         server = registry.get_server(args.name)
         if server is None:
             print(
-                f"Error: server '{args.name}' is not installed.\n"
-                f"Run 'hive mcp list' to see installed servers.",
+                f"Error: server '{args.name}' is not installed.\nRun 'hive mcp list' to see installed servers.",
                 file=sys.stderr,
             )
             return 1
@@ -822,8 +807,7 @@ def cmd_mcp_update(args) -> int:
         count = registry.update_index()
     except Exception as exc:
         print(
-            f"Error: failed to update registry index: {exc}\n"
-            f"Check your network connection and try again.",
+            f"Error: failed to update registry index: {exc}\nCheck your network connection and try again.",
             file=sys.stderr,
         )
         return 1
@@ -832,9 +816,7 @@ def cmd_mcp_update(args) -> int:
 
     # Step 2: update all installed registry servers (skip local/pinned)
     installed = registry.list_installed()
-    registry_servers = [
-        s for s in installed if s.get("source") == "registry" and not s.get("pinned")
-    ]
+    registry_servers = [s for s in installed if s.get("source") == "registry" and not s.get("pinned")]
 
     if not registry_servers:
         return 0
@@ -862,8 +844,7 @@ def _cmd_mcp_update_server(name: str, registry=None) -> int:
     server = registry.get_server(name)
     if server is None:
         print(
-            f"Error: server '{name}' is not installed.\n"
-            f"Run 'hive mcp install {name}' to install it.",
+            f"Error: server '{name}' is not installed.\nRun 'hive mcp install {name}' to install it.",
             file=sys.stderr,
         )
         return 1

core/framework/loader/preload_validation.py

@@ -98,9 +98,7 @@ def validate_credentials(
         if not result.success:
             # Preserve the original validation_result so callers can
             # inspect which credentials are still missing.
-            exc = CredentialError(
-                "Credential setup incomplete. Run again after configuring the required credentials."
-            )
+            exc = CredentialError("Credential setup incomplete. Run again after configuring the required credentials.")
             if hasattr(e, "validation_result"):
                 exc.validation_result = e.validation_result  # type: ignore[attr-defined]
             if hasattr(e, "failed_cred_names"):

core/framework/loader/tool_registry.py

@@ -257,10 +257,7 @@ class ToolRegistry:
                                         str(e),
                                     )
                                     return {
-                                        "error": (
-                                            f"Invalid JSON response from tool '{tool_name}': "
-                                            f"{str(e)}"
-                                        ),
+                                        "error": (f"Invalid JSON response from tool '{tool_name}': {str(e)}"),
                                         "raw_content": result.content,
                                     }
                             return result
@@ -435,9 +432,7 @@ class ToolRegistry:
         registry = ToolRegistry()
         return registry._resolve_mcp_server_config(server_config, base_dir)
 
-    def _resolve_mcp_server_config(
-        self, server_config: dict[str, Any], base_dir: Path
-    ) -> dict[str, Any]:
+    def _resolve_mcp_server_config(self, server_config: dict[str, Any], base_dir: Path) -> dict[str, Any]:
         """Resolve cwd and script paths for MCP stdio servers (Windows compatibility).
 
         On Windows, passing cwd to subprocess can cause WinError 267. We use cwd=None
@@ -562,8 +557,7 @@ class ToolRegistry:
             server_list = [{"name": name, **cfg} for name, cfg in config.items()]
 
         resolved_server_list = [
-            self._resolve_mcp_server_config(server_config, base_dir)
-            for server_config in server_list
+            self._resolve_mcp_server_config(server_config, base_dir) for server_config in server_list
         ]
         # Ordered first-wins for duplicate tool names across servers; keep tools.py tools.
         self.load_registry_servers(
@@ -587,8 +581,18 @@ class ToolRegistry:
         tool_cap: int | None = None,
         log_collisions: bool = False,
     ) -> tuple[bool, int, str | None]:
-        """Register a single MCP server with one retry for transient failures."""
+        """Register a single MCP server with one retry for transient failures.
+
+        When ``preserve_existing_tools=True`` and the server's tools are
+        already present from a prior registration, ``register_mcp_server``
+        returns ``count=0`` because every tool was shadowed. That's a
+        no-op success, not a failure — don't retry / warn in that case.
+        Otherwise a duplicate-init path (e.g. a worker spawn re-loading
+        the MCP servers the queen already registered) spams shadow
+        warnings, sleeps 2s, and retries for no reason.
+        """
         name = server_config.get("name", "unknown")
+        already_loaded = bool(self._mcp_server_tools.get(name))
         last_error: str | None = None
 
         for attempt in range(2):
@@ -601,6 +605,10 @@ class ToolRegistry:
                 )
                 if count > 0:
                     return True, count, None
+                if already_loaded and preserve_existing_tools:
+                    # All tools shadowed by the prior registration of
+                    # the same server — nothing to do, server is usable.
+                    return True, 0, None
                 last_error = "registered 0 tools"
             except Exception as exc:
                 last_error = str(exc)
@@ -767,15 +775,19 @@ class ToolRegistry:
 
                 if preserve_existing_tools and mcp_tool.name in self._tools:
                     if log_collisions:
-                        origin_server = (
-                            self._find_mcp_origin_server_for_tool(mcp_tool.name) or "<existing>"
-                        )
-                        logger.warning(
-                            "MCP tool '%s' from '%s' shadowed by '%s' (loaded first)",
-                            mcp_tool.name,
-                            server_name,
-                            origin_server,
-                        )
+                        origin_server = self._find_mcp_origin_server_for_tool(mcp_tool.name) or "<existing>"
+                        # Don't warn when a server is being re-registered
+                        # by itself — that's a redundant-init case (e.g.
+                        # the same tool_registry seeing the same server
+                        # twice via pooled reconnect), not a real
+                        # cross-server shadow worth flagging.
+                        if origin_server != server_name:
+                            logger.warning(
+                                "MCP tool '%s' from '%s' shadowed by '%s' (loaded first)",
+                                mcp_tool.name,
+                                server_name,
+                                origin_server,
+                            )
                     # Skip registration; do not update MCP tool bookkeeping for this server.
                     continue
 
@@ -798,17 +810,11 @@ class ToolRegistry:
                                 base_context.update(exec_ctx)
 
                             # Only inject context params the tool accepts
-                            filtered_context = {
-                                k: v for k, v in base_context.items() if k in tool_params
-                            }
+                            filtered_context = {k: v for k, v in base_context.items() if k in tool_params}
                             # Strip context params from LLM inputs — the framework
                             # values are authoritative (prevents the LLM from passing
                             # e.g. data_dir="/data" and overriding the real path).
-                            clean_inputs = {
-                                k: v
-                                for k, v in inputs.items()
-                                if k not in registry_ref.CONTEXT_PARAMS
-                            }
+                            clean_inputs = {k: v for k, v in inputs.items() if k not in registry_ref.CONTEXT_PARAMS}
                             merged_inputs = {**clean_inputs, **filtered_context}
                             result = client_ref.call_tool(tool_name, merged_inputs)
                             # MCP client already extracts content (returns str
@@ -895,9 +901,7 @@ class ToolRegistry:
         contents are already logged by `register_mcp_server`; this is just the
         rollup so the resync path also gets a single anchor line.
         """
-        per_server_counts = {
-            server: len(names) for server, names in self._mcp_server_tools.items()
-        }
+        per_server_counts = {server: len(names) for server, names in self._mcp_server_tools.items()}
         non_mcp_count = len(self._tools) - len(self._mcp_tool_names)
         logger.info(
             "ToolRegistry snapshot (%s): total=%d, mcp=%d, non_mcp=%d, per_server=%s",
@@ -968,11 +972,7 @@ class ToolRegistry:
 
             adapter = CredentialStoreAdapter.default()
             tool_provider_map = adapter.get_tool_provider_map()
-            live_providers = {
-                a.get("provider", "")
-                for a in adapter.get_all_account_info()
-                if a.get("provider")
-            }
+            live_providers = {a.get("provider", "") for a in adapter.get_all_account_info() if a.get("provider")}
         except Exception:
             logger.debug("Credential snapshot unavailable for MCP gate", exc_info=True)
 

core/framework/orchestrator/checkpoint_config.py

@@ -50,11 +50,7 @@ class CheckpointConfig:
         Returns:
             True if should check for old checkpoints and prune them
         """
-        return (
-            self.enabled
-            and self.prune_every_n_nodes > 0
-            and nodes_executed % self.prune_every_n_nodes == 0
-        )
+        return self.enabled and self.prune_every_n_nodes > 0 and nodes_executed % self.prune_every_n_nodes == 0
 
 
 # Default configuration for most agents

core/framework/orchestrator/context.py

@@ -175,9 +175,7 @@ def _resolve_available_tools(
         return always_tools
 
     declared = set(node_spec.tools)
-    declared_tools = [
-        t for t in tools if t.name in declared and t.name not in _ALWAYS_AVAILABLE_TOOLS
-    ]
+    declared_tools = [t for t in tools if t.name in declared and t.name not in _ALWAYS_AVAILABLE_TOOLS]
     return always_tools + declared_tools
 
 

core/framework/orchestrator/context_handoff.py

@@ -169,11 +169,7 @@ class ContextHandoff:
 
         key_hint = ""
         if output_keys:
-            key_hint = (
-                "\nThe following output keys are especially important: "
-                + ", ".join(output_keys)
-                + ".\n"
-            )
+            key_hint = "\nThe following output keys are especially important: " + ", ".join(output_keys) + ".\n"
 
         system_prompt = (
             "You are a concise summarizer. Given the conversation below, "

core/framework/orchestrator/edge.py

@@ -186,8 +186,7 @@ class EdgeSpec(BaseModel):
             expr_vars = {
                 k: repr(context[k])
                 for k in context
-                if k not in ("output", "buffer", "result", "true", "false")
-                and k in self.condition_expr
+                if k not in ("output", "buffer", "result", "true", "false") and k in self.condition_expr
             }
             logger.info(
                 "  Edge %s: condition '%s' → %s  (vars: %s)",
@@ -333,12 +332,8 @@ class GraphSpec(BaseModel):
         default_factory=dict,
         description="Named entry points for resuming execution. Format: {name: node_id}",
     )
-    terminal_nodes: list[str] = Field(
-        default_factory=list, description="IDs of nodes that end execution"
-    )
-    pause_nodes: list[str] = Field(
-        default_factory=list, description="IDs of nodes that pause execution for HITL input"
-    )
+    terminal_nodes: list[str] = Field(default_factory=list, description="IDs of nodes that end execution")
+    pause_nodes: list[str] = Field(default_factory=list, description="IDs of nodes that pause execution for HITL input")
 
     # Components
     nodes: list[Any] = Field(  # NodeSpec, but avoiding circular import
@@ -347,9 +342,7 @@ class GraphSpec(BaseModel):
     edges: list[EdgeSpec] = Field(default_factory=list, description="All edge specifications")
 
     # Data buffer keys
-    buffer_keys: list[str] = Field(
-        default_factory=list, description="Keys available in data buffer"
-    )
+    buffer_keys: list[str] = Field(default_factory=list, description="Keys available in data buffer")
 
     # Default LLM settings
     default_model: str = "claude-haiku-4-5-20251001"
@@ -557,9 +550,7 @@ class GraphSpec(BaseModel):
         fan_outs = self.detect_fan_out_nodes()
         for source_id, targets in fan_outs.items():
             event_loop_targets = [
-                t
-                for t in targets
-                if self.get_node(t) and getattr(self.get_node(t), "node_type", "") == "event_loop"
+                t for t in targets if self.get_node(t) and getattr(self.get_node(t), "node_type", "") == "event_loop"
             ]
             if len(event_loop_targets) > 1:
                 seen_keys: dict[str, str] = {}

core/framework/orchestrator/gcu.py

@@ -42,25 +42,26 @@ after an interaction unless you need a fresh view.
 Only fall back to `browser_get_text` for extracting small elements by
 CSS selector.
 
-## Coordinates: always CSS pixels
+## Coordinates
 
-Chrome DevTools Protocol `Input.dispatchMouseEvent` takes **CSS
-pixels**, not physical pixels. This is critical and often gets wrong:
+Every browser tool that takes or returns coordinates operates in
+**fractions of the viewport (0..1 for both axes)**. Read a target's
+proportional position off `browser_screenshot` — "this button is
+~35% from the left, ~20% from the top" → pass `(0.35, 0.20)`.
+`browser_get_rect` and `browser_shadow_query` return `rect.cx` /
+`rect.cy` as fractions in the same space. The tools handle the
+fraction → CSS-px multiplication internally; you do not need to
+track image pixels, DPR, or any scale factor.
 
-| Tool | Unit |
-|---|---|
-| `browser_click_coordinate(x, y)` | **CSS pixels** |
-| `browser_hover_coordinate(x, y)` | **CSS pixels** |
-| `browser_press_at(x, y, key)` | **CSS pixels** |
-| `getBoundingClientRect()` | already CSS pixels — pass straight through |
-| `browser_coords(img_x, img_y)` | returns `css_x/y` (use this) and `physical_x/y` (debug only) |
+Why fractions: every vision model (Claude, GPT-4o, Gemini, local
+VLMs) resizes or tiles images differently before the model sees the
+pixels. Proportions survive every such transform; pixel coordinates
+only "work" per-model and break when you swap backends.
 
-**Always use `css_x/y`** from `browser_coords`. Feeding `physical_x/y`
-on a HiDPI display overshoots by `DPR×` — clicks land DPR times too
-far right and down. On a DPR=1.6 display that's 60% off.
-
-Never multiply `getBoundingClientRect()` by `devicePixelRatio` — it's
-already in the right unit.
+Avoid raw `browser_evaluate` + `getBoundingClientRect()` for coord
+lookup — that returns CSS px and will be wrong when fed to click
+tools. Prefer `browser_get_rect` / `browser_shadow_query`, which
+return fractions.
 
 ## Rich-text editors (X, LinkedIn DMs, Gmail, Reddit, Slack, Discord)
 
@@ -70,10 +71,12 @@ ProseMirror only register input as "real" after a native pointer-
 sourced focus event; JS `.focus()` is not enough. Without a real click
 first, the editor stays empty and the send button stays disabled.
 
-`browser_type` now does this automatically — it clicks the element,
-then inserts text via CDP `Input.insertText` (IME-commit style), which
-rich editors accept cleanly. Before clicking send, verify the submit
-button's `disabled` / `aria-disabled` state via `browser_evaluate`.
+`browser_type` does this automatically when you have a selector — it
+clicks the element, then inserts text via CDP `Input.insertText`.
+For shadow-DOM inputs where selectors can't reach, use
+`browser_click_coordinate` to focus, then `browser_type_focused(text=...)`
+to type into the active element. Before clicking send, verify the
+submit button's `disabled` / `aria-disabled` state via `browser_evaluate`.
 
 ## Shadow DOM
 
@@ -86,12 +89,11 @@ reach shadow elements transparently.
 
 **Shadow-heavy site workflow:**
 1. `browser_screenshot()` → visual image
-2. Identify target visually → image coordinate
-3. `browser_coords(x, y)` → CSS px
-4. `browser_click_coordinate(css_x, css_y)` → lands via native hit
-   test; inputs get focused regardless of shadow depth
-5. Type via `browser_type` or, if the selector path can't reach the
-   element, dispatch keys to the focused element
+2. Identify target visually → pixel `(x, y)` read straight off the image
+3. `browser_click_coordinate(x, y)` → lands via native hit test;
+   inputs get focused regardless of shadow depth
+4. Type via `browser_type_focused` (no selector needed — types into the
+   already-focused element), or `browser_type` if you have a selector
 
 For selector-style access when you know the shadow path:
 `browser_shadow_query("#interop-outlet >>> #msg-overlay >>> p")` —

core/framework/orchestrator/goal.py

@@ -41,13 +41,9 @@ class SuccessCriterion(BaseModel):
 
     id: str
     description: str = Field(description="Human-readable description of what success looks like")
-    metric: str = Field(
-        description="How to measure: 'output_contains', 'output_equals', 'llm_judge', 'custom'"
-    )
+    metric: str = Field(description="How to measure: 'output_contains', 'output_equals', 'llm_judge', 'custom'")
     # NEW: runtime evaluation type (separate from metric)
-    type: str = Field(
-        default="success_rate", description="Runtime evaluation type, e.g. 'success_rate'"
-    )
+    type: str = Field(default="success_rate", description="Runtime evaluation type, e.g. 'success_rate'")
 
     target: Any = Field(description="The target value or condition")
     weight: float = Field(default=1.0, ge=0.0, le=1.0, description="Relative importance (0-1)")
@@ -67,15 +63,9 @@ class Constraint(BaseModel):
 
     id: str
     description: str
-    constraint_type: str = Field(
-        description="Type: 'hard' (must not violate) or 'soft' (prefer not to violate)"
-    )
-    category: str = Field(
-        default="general", description="Category: 'time', 'cost', 'safety', 'scope', 'quality'"
-    )
-    check: str = Field(
-        default="", description="How to check: expression, function name, or 'llm_judge'"
-    )
+    constraint_type: str = Field(description="Type: 'hard' (must not violate) or 'soft' (prefer not to violate)")
+    category: str = Field(default="general", description="Category: 'time', 'cost', 'safety', 'scope', 'quality'")
+    check: str = Field(default="", description="How to check: expression, function name, or 'llm_judge'")
 
     model_config = {"extra": "allow"}
 
@@ -142,9 +132,7 @@ class Goal(BaseModel):
 
     # Input/output schema
     input_schema: dict[str, Any] = Field(default_factory=dict, description="Expected input format")
-    output_schema: dict[str, Any] = Field(
-        default_factory=dict, description="Expected output format"
-    )
+    output_schema: dict[str, Any] = Field(default_factory=dict, description="Expected output format")
 
     # Versioning for evolution
     version: str = "1.0.0"

core/framework/orchestrator/node.py

@@ -129,15 +129,13 @@ class NodeSpec(BaseModel):
     input_schema: dict[str, dict] = Field(
         default_factory=dict,
         description=(
-            "Optional schema for input validation. "
-            "Format: {key: {type: 'string', required: True, description: '...'}}"
+            "Optional schema for input validation. Format: {key: {type: 'string', required: True, description: '...'}}"
         ),
     )
     output_schema: dict[str, dict] = Field(
         default_factory=dict,
         description=(
-            "Optional schema for output validation. "
-            "Format: {key: {type: 'dict', required: True, description: '...'}}"
+            "Optional schema for output validation. Format: {key: {type: 'dict', required: True, description: '...'}}"
         ),
     )
 
@@ -153,19 +151,13 @@ class NodeSpec(BaseModel):
             "'none' = no tools at all."
         ),
     )
-    model: str | None = Field(
-        default=None, description="Specific model to use (defaults to graph default)"
-    )
+    model: str | None = Field(default=None, description="Specific model to use (defaults to graph default)")
 
     # For function nodes
-    function: str | None = Field(
-        default=None, description="Function name or path for function nodes"
-    )
+    function: str | None = Field(default=None, description="Function name or path for function nodes")
 
     # For router nodes
-    routes: dict[str, str] = Field(
-        default_factory=dict, description="Condition -> target_node_id mapping for routers"
-    )
+    routes: dict[str, str] = Field(default_factory=dict, description="Condition -> target_node_id mapping for routers")
 
     # Retry behavior
     max_retries: int = Field(default=3)

core/framework/orchestrator/node_worker.py

@@ -379,9 +379,7 @@ class NodeWorker:
 
                 # Failure
                 if attempt + 1 < total_attempts:
-                    gc.retry_counts[self.node_spec.id] = (
-                        gc.retry_counts.get(self.node_spec.id, 0) + 1
-                    )
+                    gc.retry_counts[self.node_spec.id] = gc.retry_counts.get(self.node_spec.id, 0) + 1
                     gc.nodes_with_retries.add(self.node_spec.id)
                     delay = 1.0 * (2**attempt)
                     logger.warning(
@@ -411,9 +409,7 @@ class NodeWorker:
 
             except Exception as exc:
                 if attempt + 1 < total_attempts:
-                    gc.retry_counts[self.node_spec.id] = (
-                        gc.retry_counts.get(self.node_spec.id, 0) + 1
-                    )
+                    gc.retry_counts[self.node_spec.id] = gc.retry_counts.get(self.node_spec.id, 0) + 1
                     gc.nodes_with_retries.add(self.node_spec.id)
                     delay = 1.0 * (2**attempt)
                     logger.warning(
@@ -469,9 +465,7 @@ class NodeWorker:
             if len(conditionals) > 1:
                 max_prio = max(e.priority for e in conditionals)
                 traversable = [
-                    e
-                    for e in traversable
-                    if e.condition != EdgeCondition.CONDITIONAL or e.priority == max_prio
+                    e for e in traversable if e.condition != EdgeCondition.CONDITIONAL or e.priority == max_prio
                 ]
 
         # When parallel execution is disabled, follow first match only (sequential)
@@ -541,9 +535,7 @@ class NodeWorker:
                 logger.warning("Worker %s output validation warnings: %s", node_spec.id, errors)
 
         # Determine if this worker is a fan-out branch
-        is_fanout_branch = any(
-            tag.via_branch == node_spec.id for tag in self._inherited_fan_out_tags
-        )
+        is_fanout_branch = any(tag.via_branch == node_spec.id for tag in self._inherited_fan_out_tags)
 
         # Collect keys to write: declared output_keys + any extra output items
         # (for fan-out branches, all output items need conflict checking)
@@ -642,9 +634,7 @@ class NodeWorker:
             self._node_impl = node
             return node
 
-        raise RuntimeError(
-            f"No implementation for node '{self.node_spec.id}' (type: {self.node_spec.node_type})"
-        )
+        raise RuntimeError(f"No implementation for node '{self.node_spec.id}' (type: {self.node_spec.node_type})")
 
     def _build_node_context(self) -> NodeContext:
         """Build NodeContext for this worker's execution."""
@@ -749,9 +739,7 @@ class NodeWorker:
             inherited_conversation=gc.continuous_conversation,
             narrative=narrative,
         )
-        gc.continuous_conversation.update_system_prompt(
-            build_system_prompt_for_node_context(next_ctx)
-        )
+        gc.continuous_conversation.update_system_prompt(build_system_prompt_for_node_context(next_ctx))
         gc.continuous_conversation.set_current_phase(next_spec.id)
 
         buffer_items, data_files = self._prepare_transition_payload()
@@ -799,8 +787,7 @@ class NodeWorker:
                     file_path.write_text(write_content, encoding="utf-8")
                     file_size = file_path.stat().st_size
                     buffer_items[key] = (
-                        f"[Saved to '{filename}' ({file_size:,} bytes). "
-                        f"Use read_file(path='{filename}') to access.]"
+                        f"[Saved to '{filename}' ({file_size:,} bytes). Use read_file(path='{filename}') to access.]"
                     )
                     continue
                 except Exception:

core/framework/orchestrator/orchestrator.py

@@ -202,9 +202,7 @@ class Orchestrator:
         self.validator = OutputValidator()
         self.logger = logging.getLogger(__name__)
         self.logger.debug(
-            "[Orchestrator.__init__] Created with"
-            " stream_id=%s, execution_id=%s,"
-            " initial node_registry keys: %s",
+            "[Orchestrator.__init__] Created with stream_id=%s, execution_id=%s, initial node_registry keys: %s",
             stream_id,
             execution_id,
             list(self.node_registry.keys()),
@@ -347,8 +345,7 @@ class Orchestrator:
             missing = [t for t in declared if t not in available_tool_names]
             if missing:
                 self.logger.warning(
-                    "Node '%s' (id=%s) declares %d tools not in this runtime; "
-                    "stripping them and continuing: %s",
+                    "Node '%s' (id=%s) declares %d tools not in this runtime; stripping them and continuing: %s",
                     node.name,
                     node.id,
                     len(missing),
@@ -391,10 +388,7 @@ class Orchestrator:
                 lines.append(f"[tool result]: {c}")
             elif m.role == "assistant" and m.tool_calls:
                 names = [tc.get("function", {}).get("name", "?") for tc in m.tool_calls]
-                lines.append(
-                    f"[assistant (calls: {', '.join(names)})]: "
-                    f"{m.content[:200] if m.content else ''}"
-                )
+                lines.append(f"[assistant (calls: {', '.join(names)})]: {m.content[:200] if m.content else ''}")
             else:
                 lines.append(f"[{m.role}]: {m.content}")
         formatted = "\n\n".join(lines)
@@ -565,8 +559,7 @@ class Orchestrator:
             # [RESTORED] Type safety check
             if not isinstance(buffer_data, dict):
                 self.logger.warning(
-                    f"⚠️ Invalid data buffer type in session state: "
-                    f"{type(buffer_data).__name__}, expected dict"
+                    f"⚠️ Invalid data buffer type in session state: {type(buffer_data).__name__}, expected dict"
                 )
             else:
                 # Restore buffer from previous session.
@@ -590,8 +583,7 @@ class Orchestrator:
         # contains all state including the original input, and re-writing
         # input_data would overwrite intermediate results with stale values.
         _is_resuming = bool(
-            session_state
-            and (session_state.get("paused_at") or session_state.get("resume_from_checkpoint"))
+            session_state and (session_state.get("paused_at") or session_state.get("resume_from_checkpoint"))
         )
         if input_data and not _is_resuming:
             for key, value in input_data.items():
@@ -616,11 +608,7 @@ class Orchestrator:
                 # If resuming at a specific node (paused_at), that node was counted
                 # but never completed, so decrement its count
                 paused_at = session_state.get("paused_at")
-                if (
-                    paused_at
-                    and paused_at in node_visit_counts
-                    and node_visit_counts[paused_at] > 0
-                ):
+                if paused_at and paused_at in node_visit_counts and node_visit_counts[paused_at] > 0:
                     old_count = node_visit_counts[paused_at]
                     node_visit_counts[paused_at] -= 1
                     self.logger.info(
@@ -636,10 +624,7 @@ class Orchestrator:
                 checkpoint = await checkpoint_store.load_checkpoint(checkpoint_id)
 
                 if checkpoint:
-                    self.logger.info(
-                        f"🔄 Resuming from checkpoint: {checkpoint_id} "
-                        f"(node: {checkpoint.current_node})"
-                    )
+                    self.logger.info(f"🔄 Resuming from checkpoint: {checkpoint_id} (node: {checkpoint.current_node})")
                     checkpoint_run_id = checkpoint.run_id or LEGACY_RUN_ID
                     self._run_id = checkpoint_run_id
 
@@ -648,9 +633,7 @@ class Orchestrator:
                         buffer.write(key, value, validate=False)
 
                     # Start from checkpoint's next node or current node
-                    current_node_id = (
-                        checkpoint.next_node or checkpoint.current_node or graph.entry_node
-                    )
+                    current_node_id = checkpoint.next_node or checkpoint.current_node or graph.entry_node
 
                     # Restore execution path
                     path.extend(checkpoint.execution_path)
@@ -660,16 +643,11 @@ class Orchestrator:
                         f"resuming at node: {current_node_id}"
                     )
                 else:
-                    self.logger.warning(
-                        f"Checkpoint {checkpoint_id} not found, resuming from normal entry point"
-                    )
+                    self.logger.warning(f"Checkpoint {checkpoint_id} not found, resuming from normal entry point")
                     current_node_id = graph.get_entry_point(session_state)
 
             except Exception as e:
-                self.logger.error(
-                    f"Failed to load checkpoint {checkpoint_id}: {e}, "
-                    f"resuming from normal entry point"
-                )
+                self.logger.error(f"Failed to load checkpoint {checkpoint_id}: {e}, resuming from normal entry point")
                 current_node_id = graph.get_entry_point(session_state)
         else:
             current_node_id = graph.get_entry_point(session_state)
@@ -757,20 +735,14 @@ class Orchestrator:
         "human_input": "event_loop",  # Use queen interaction / escalation instead
     }
 
-    def _get_node_implementation(
-        self, node_spec: NodeSpec, cleanup_llm_model: str | None = None
-    ) -> NodeProtocol:
+    def _get_node_implementation(self, node_spec: NodeSpec, cleanup_llm_model: str | None = None) -> NodeProtocol:
         """Get or create a node implementation."""
         # Check registry first
         if node_spec.id in self.node_registry:
-            logger.debug(
-                "[Orchestrator._get_node_implementation] Found node '%s' in registry", node_spec.id
-            )
+            logger.debug("[Orchestrator._get_node_implementation] Found node '%s' in registry", node_spec.id)
             return self.node_registry[node_spec.id]
         logger.debug(
-            "[Orchestrator._get_node_implementation]"
-            " Node '%s' not in registry (keys: %s),"
-            " creating new",
+            "[Orchestrator._get_node_implementation] Node '%s' not in registry (keys: %s), creating new",
             node_spec.id,
             list(self.node_registry.keys()),
         )
@@ -840,9 +812,7 @@ class Orchestrator:
             # Cache so inject_event() is reachable for queen interaction and escalation routing
             self.node_registry[node_spec.id] = node
             logger.debug(
-                "[Orchestrator._get_node_implementation]"
-                " Cached node '%s' in node_registry,"
-                " registry now has keys: %s",
+                "[Orchestrator._get_node_implementation] Cached node '%s' in node_registry, registry now has keys: %s",
                 node_spec.id,
                 list(self.node_registry.keys()),
             )
@@ -925,9 +895,7 @@ class Orchestrator:
             if len(conditionals) > 1:
                 max_prio = max(e.priority for e in conditionals)
                 traversable = [
-                    e
-                    for e in traversable
-                    if e.condition != EdgeCondition.CONDITIONAL or e.priority == max_prio
+                    e for e in traversable if e.condition != EdgeCondition.CONDITIONAL or e.priority == max_prio
                 ]
 
         return traversable
@@ -1090,9 +1058,7 @@ class Orchestrator:
                             execution_id=self._execution_id,
                         )
 
-                    self.logger.info(
-                        f"      ▶ Branch {node_spec.name}: executing (attempt {attempt + 1})"
-                    )
+                    self.logger.info(f"      ▶ Branch {node_spec.name}: executing (attempt {attempt + 1})")
                     result = await node_impl.execute(ctx)
                     last_result = result
 
@@ -1153,19 +1119,13 @@ class Orchestrator:
                         )
                         return branch, result
 
-                    self.logger.warning(
-                        f"      ↻ Branch {node_spec.name}: "
-                        f"retry {attempt + 1}/{effective_max_retries}"
-                    )
+                    self.logger.warning(f"      ↻ Branch {node_spec.name}: retry {attempt + 1}/{effective_max_retries}")
 
                 # All retries exhausted
                 branch.status = "failed"
                 branch.error = last_result.error if last_result else "Unknown error"
                 branch.result = last_result
-                self.logger.error(
-                    f"      ✗ Branch {node_spec.name}: "
-                    f"failed after {effective_max_retries} attempts"
-                )
+                self.logger.error(f"      ✗ Branch {node_spec.name}: failed after {effective_max_retries} attempts")
                 return branch, last_result
 
             except Exception as e:
@@ -1208,10 +1168,7 @@ class Orchestrator:
                 # Branch timed out
                 branch.status = "timed_out"
                 branch.error = f"Branch timed out after {timeout}s"
-                self.logger.warning(
-                    f"      ⏱ Branch {graph.get_node(branch.node_id).name}: "
-                    f"timed out after {timeout}s"
-                )
+                self.logger.warning(f"      ⏱ Branch {graph.get_node(branch.node_id).name}: timed out after {timeout}s")
                 path.append(branch.node_id)
                 failed_branches.append(branch)
             elif isinstance(result, Exception):
@@ -1235,13 +1192,9 @@ class Orchestrator:
             if self._parallel_config.on_branch_failure == "fail_all":
                 raise RuntimeError(f"Parallel execution failed: branches {failed_names} failed")
             elif self._parallel_config.on_branch_failure == "continue_others":
-                self.logger.warning(
-                    f"⚠ Some branches failed ({failed_names}), continuing with successful ones"
-                )
+                self.logger.warning(f"⚠ Some branches failed ({failed_names}), continuing with successful ones")
 
-        self.logger.info(
-            f"   ⑃ Fan-out complete: {len(branch_results)}/{len(branches)} branches succeeded"
-        )
+        self.logger.info(f"   ⑃ Fan-out complete: {len(branch_results)}/{len(branches)} branches succeeded")
         return branch_results, total_tokens, total_latency
 
     def register_node(self, node_id: str, implementation: NodeProtocol) -> None:
@@ -1432,15 +1385,10 @@ class Orchestrator:
                 return True
             if not terminal_worker_ids:
                 # No terminals: check if all workers are done
-                return all(
-                    w.lifecycle in (WorkerLifecycle.COMPLETED, WorkerLifecycle.FAILED)
-                    for w in workers.values()
-                )
+                return all(w.lifecycle in (WorkerLifecycle.COMPLETED, WorkerLifecycle.FAILED) for w in workers.values())
             if any(w.lifecycle == WorkerLifecycle.RUNNING for w in workers.values()):
                 return False
-            return any(
-                tid in completed_terminals or tid in failed_workers for tid in terminal_worker_ids
-            )
+            return any(tid in completed_terminals or tid in failed_workers for tid in terminal_worker_ids)
 
         def _mark_quiescent_terminal_failure() -> bool:
             nonlocal execution_error
@@ -1448,22 +1396,15 @@ class Orchestrator:
                 return False
             if any(w.lifecycle == WorkerLifecycle.RUNNING for w in workers.values()):
                 return False
-            if any(
-                tid in completed_terminals or tid in failed_workers for tid in terminal_worker_ids
-            ):
+            if any(tid in completed_terminals or tid in failed_workers for tid in terminal_worker_ids):
                 return False
-            execution_error = (
-                "Worker execution ended before terminal nodes completed: "
-                f"{sorted(terminal_worker_ids)}"
-            )
+            execution_error = f"Worker execution ended before terminal nodes completed: {sorted(terminal_worker_ids)}"
             self.logger.error(execution_error)
             return True
 
         # Track fan-out branch workers for per-branch timeout enforcement
         _fanout_branch_tasks: dict[str, asyncio.Task] = {}  # worker_id → timeout-wrapper task
-        branch_timeout = (
-            self._parallel_config.branch_timeout_seconds if self._parallel_config else 300.0
-        )
+        branch_timeout = self._parallel_config.branch_timeout_seconds if self._parallel_config else 300.0
 
         def _route_activation(
             activation: Activation,
@@ -1498,9 +1439,7 @@ class Orchestrator:
                 target_worker.activate(inherited_tags=activation.fan_out_tags)
                 if target_worker._task is not None:
                     # Fan-out branch: wrap with timeout
-                    is_fanout_branch = any(
-                        tag.via_branch == activation.target_id for tag in activation.fan_out_tags
-                    )
+                    is_fanout_branch = any(tag.via_branch == activation.target_id for tag in activation.fan_out_tags)
                     if is_fanout_branch and branch_timeout > 0:
                         timed_task = asyncio.ensure_future(
                             asyncio.wait_for(target_worker._task, timeout=branch_timeout)
@@ -1555,9 +1494,7 @@ class Orchestrator:
                 if completion.conversation is not None:
                     gc.continuous_conversation = completion.conversation
 
-            self.logger.info(
-                f"  ✓ Worker completed: {worker_id} ({len(activations)} outgoing activation(s))"
-            )
+            self.logger.info(f"  ✓ Worker completed: {worker_id} ({len(activations)} outgoing activation(s))")
 
             # Route activations to target workers
             for activation in activations:
@@ -1598,9 +1535,7 @@ class Orchestrator:
                 completion_event.set()
 
         # Subscribe to events (only if event bus has subscribe capability)
-        has_event_subscription = self._event_bus is not None and hasattr(
-            self._event_bus, "subscribe"
-        )
+        has_event_subscription = self._event_bus is not None and hasattr(self._event_bus, "subscribe")
         if has_event_subscription:
             sub_completed = self._event_bus.subscribe(
                 event_types=[EventType.WORKER_COMPLETED],
@@ -1642,14 +1577,12 @@ class Orchestrator:
                         )
                         if unresolved_terminals:
                             execution_error = (
-                                "Worker execution ended before terminal nodes completed: "
-                                f"{unresolved_terminals}"
+                                f"Worker execution ended before terminal nodes completed: {unresolved_terminals}"
                             )
                             self.logger.error(execution_error)
                         else:
                             execution_error = (
-                                "Worker execution ended before all workers reached "
-                                "a terminal lifecycle state"
+                                "Worker execution ended before all workers reached a terminal lifecycle state"
                             )
                             self.logger.error(execution_error)
                         break
@@ -1680,10 +1613,7 @@ class Orchestrator:
                             task_error = exc
 
                         # Check for fan-out branch timeout
-                        if (
-                            isinstance(task_error, asyncio.TimeoutError)
-                            and wid in _fanout_branch_tasks
-                        ):
+                        if isinstance(task_error, asyncio.TimeoutError) and wid in _fanout_branch_tasks:
                             error = f"Branch failed (timed out after {branch_timeout}s)"
                             failed_workers[wid] = error
                             worker.lifecycle = WorkerLifecycle.FAILED
@@ -1727,10 +1657,7 @@ class Orchestrator:
                                 src_spec = graph.get_node(wid)
                                 if src_spec and src_spec.tools:
                                     for t in self.tools:
-                                        if (
-                                            t.name in src_spec.tools
-                                            and t.name not in gc.cumulative_tool_names
-                                        ):
+                                        if t.name in src_spec.tools and t.name not in gc.cumulative_tool_names:
                                             gc.cumulative_tools.append(t)
                                             gc.cumulative_tool_names.add(t.name)
                                 if src_spec and src_spec.output_keys:
@@ -1741,8 +1668,7 @@ class Orchestrator:
                                     gc.continuous_conversation = completion_conversation
 
                             self.logger.info(
-                                f"  ✓ Worker completed: {wid} "
-                                f"({len(outgoing_activations)} outgoing activation(s))"
+                                f"  ✓ Worker completed: {wid} ({len(outgoing_activations)} outgoing activation(s))"
                             )
 
                             # Route activations
@@ -1787,8 +1713,7 @@ class Orchestrator:
                             error = str(task_error)
                         else:
                             error = (
-                                "Worker task completed without publishing a completion "
-                                f"(lifecycle={worker.lifecycle})"
+                                f"Worker task completed without publishing a completion (lifecycle={worker.lifecycle})"
                             )
 
                         failed_workers[wid] = error

core/framework/orchestrator/prompt_composer.py

@@ -97,15 +97,12 @@ def build_transition_marker(
             file_path = data_path / filename
             try:
                 write_content = (
-                    json.dumps(value, indent=2, ensure_ascii=False)
-                    if isinstance(value, (dict, list))
-                    else str(value)
+                    json.dumps(value, indent=2, ensure_ascii=False) if isinstance(value, (dict, list)) else str(value)
                 )
                 file_path.write_text(write_content, encoding="utf-8")
                 file_size = file_path.stat().st_size
                 buffer_items[key] = (
-                    f"[Saved to '{filename}' ({file_size:,} bytes). "
-                    f"Use read_file(path='{filename}') to access.]"
+                    f"[Saved to '{filename}' ({file_size:,} bytes). Use read_file(path='{filename}') to access.]"
                 )
             except Exception:
                 buffer_items[key] = val_str[:300] + "..."

core/framework/orchestrator/prompting.py

@@ -177,18 +177,12 @@ def build_prompt_spec_from_node_context(
     # Tool-gated pre-activation: inject full body of default skills whose
     # trigger tools are present in this node's tool list (e.g. browser_*
     # pulls in hive.browser-automation).
-    tool_names = [
-        getattr(t, "name", "") for t in (getattr(ctx, "available_tools", None) or [])
-    ]
-    skills_catalog_prompt = augment_catalog_for_tools(
-        ctx.skills_catalog_prompt or "", tool_names
-    )
+    tool_names = [getattr(t, "name", "") for t in (getattr(ctx, "available_tools", None) or [])]
+    skills_catalog_prompt = augment_catalog_for_tools(ctx.skills_catalog_prompt or "", tool_names)
 
     return NodePromptSpec(
         identity_prompt=ctx.identity_prompt or "",
-        focus_prompt=focus_prompt
-        if focus_prompt is not None
-        else (ctx.node_spec.system_prompt or ""),
+        focus_prompt=focus_prompt if focus_prompt is not None else (ctx.node_spec.system_prompt or ""),
         narrative=narrative if narrative is not None else (ctx.narrative or ""),
         accounts_prompt=ctx.accounts_prompt or "",
         skills_catalog_prompt=skills_catalog_prompt,
@@ -299,8 +293,7 @@ def build_transition_message(spec: TransitionSpec) -> str:
 
     if spec.data_files:
         sections.append(
-            "\nData files (use read_file to access):\n"
-            + "\n".join(f"  {entry}" for entry in spec.data_files)
+            "\nData files (use read_file to access):\n" + "\n".join(f"  {entry}" for entry in spec.data_files)
         )
 
     if spec.cumulative_tool_names:

core/framework/orchestrator/safe_eval.py

@@ -12,7 +12,9 @@ MAX_POWER_ABS_EXPONENT = 1_000
 MAX_POWER_RESULT_BITS = 4_096
 # Typical edge-condition evaluations in this repo complete well under 1ms.
 # 100ms leaves ample headroom for legitimate checks while failing fast on abuse.
-DEFAULT_TIMEOUT_MS = 100
+# On Windows (where SIGALRM is unavailable) the fallback relies on periodic
+# perf_counter polling which is less precise, so we use a wider margin.
+DEFAULT_TIMEOUT_MS = 100 if hasattr(signal, "SIGALRM") else 500
 
 
 def _safe_pow(base: Any, exp: Any) -> Any:
@@ -169,11 +171,7 @@ class SafeEvalVisitor(ast.NodeVisitor):
         return tuple(self.visit(elt) for elt in node.elts)
 
     def visit_Dict(self, node: ast.Dict) -> dict:
-        return {
-            self.visit(k): self.visit(v)
-            for k, v in zip(node.keys, node.values, strict=False)
-            if k is not None
-        }
+        return {self.visit(k): self.visit(v) for k, v in zip(node.keys, node.values, strict=False) if k is not None}
 
     # --- Operations ---
     def visit_BinOp(self, node: ast.BinOp) -> Any:

core/framework/orchestrator/validator.py

@@ -120,9 +120,7 @@ class OutputValidator:
         nullable_keys = nullable_keys or []
 
         if not isinstance(output, dict):
-            return ValidationResult(
-                success=False, errors=[f"Output is not a dict, got {type(output).__name__}"]
-            )
+            return ValidationResult(success=False, errors=[f"Output is not a dict, got {type(output).__name__}"])
 
         for key in expected_keys:
             if key not in output:
@@ -237,9 +235,7 @@ class OutputValidator:
 
             # Check for overly long values
             if len(value) > max_length:
-                errors.append(
-                    f"Output key '{key}' exceeds max length ({len(value)} > {max_length})"
-                )
+                errors.append(f"Output key '{key}' exceeds max length ({len(value)} > {max_length})")
 
         return ValidationResult(success=len(errors) == 0, errors=errors)
 

core/framework/pipeline/stages/cost_guard.py

@@ -27,8 +27,6 @@ class CostGuardStage(PipelineStage):
         if estimated > self._budget:
             return PipelineResult(
                 action="reject",
-                rejection_reason=(
-                    f"Estimated cost ${estimated:.4f} exceeds budget ${self._budget:.4f}"
-                ),
+                rejection_reason=(f"Estimated cost ${estimated:.4f} exceeds budget ${self._budget:.4f}"),
             )
         return PipelineResult(action="continue")

core/framework/pipeline/stages/input_validation.py

@@ -40,8 +40,7 @@ class InputValidationStage(PipelineStage):
                 return PipelineResult(
                     action="reject",
                     rejection_reason=(
-                        f"Input key '{key}' has type {type(value).__name__}, "
-                        f"expected {expected_type.__name__}"
+                        f"Input key '{key}' has type {type(value).__name__}, expected {expected_type.__name__}"
                     ),
                 )
         return PipelineResult(action="continue")

core/framework/pipeline/stages/rate_limit.py

@@ -35,9 +35,7 @@ class RateLimitStage(PipelineStage):
         if len(self._timestamps[key]) >= self._max_rpm:
             return PipelineResult(
                 action="reject",
-                rejection_reason=(
-                    f"Rate limit exceeded: {self._max_rpm} req/min for session '{session_id}'"
-                ),
+                rejection_reason=(f"Rate limit exceeded: {self._max_rpm} req/min for session '{session_id}'"),
             )
         self._timestamps[key].append(now)
         return PipelineResult(action="continue")

core/framework/schemas/goal.py

@@ -25,9 +25,7 @@ class GoalStatus(StrEnum):
 class SuccessCriterion(BaseModel):
     id: str
     description: str = Field(description="Human-readable description of what success looks like")
-    metric: str = Field(
-        description="How to measure: 'output_contains', 'output_equals', 'llm_judge', 'custom'"
-    )
+    metric: str = Field(description="How to measure: 'output_contains', 'output_equals', 'llm_judge', 'custom'")
     type: str = Field(default="success_rate", description="Runtime evaluation type")
     target: Any = Field(description="The target value or condition")
     weight: float = Field(default=1.0, ge=0.0, le=1.0, description="Relative importance (0-1)")
@@ -39,15 +37,9 @@ class SuccessCriterion(BaseModel):
 class Constraint(BaseModel):
     id: str
     description: str
-    constraint_type: str = Field(
-        description="Type: 'hard' (must not violate) or 'soft' (prefer not to violate)"
-    )
-    category: str = Field(
-        default="general", description="Category: 'time', 'cost', 'safety', 'scope', 'quality'"
-    )
-    check: str = Field(
-        default="", description="How to check: expression, function name, or 'llm_judge'"
-    )
+    constraint_type: str = Field(description="Type: 'hard' (must not violate) or 'soft' (prefer not to violate)")
+    category: str = Field(default="general", description="Category: 'time', 'cost', 'safety', 'scope', 'quality'")
+    check: str = Field(default="", description="How to check: expression, function name, or 'llm_judge'")
 
     model_config = {"extra": "allow"}
 

core/framework/schemas/session_state.py

@@ -237,9 +237,7 @@ class SessionState(BaseModel):
             progress=SessionProgress(
                 current_node=result.paused_at or (result.path[-1] if result.path else None),
                 paused_at=result.paused_at,
-                resume_from=result.session_state.get("resume_from")
-                if result.session_state
-                else None,
+                resume_from=result.session_state.get("resume_from") if result.session_state else None,
                 steps_executed=result.steps_executed,
                 total_tokens=result.total_tokens,
                 total_latency_ms=result.total_latency_ms,
@@ -256,9 +254,7 @@ class SessionState(BaseModel):
                 error=result.error,
                 output=result.output,
             ),
-            data_buffer=result.session_state.get(
-                "data_buffer", result.session_state.get("memory", {})
-            )
+            data_buffer=result.session_state.get("data_buffer", result.session_state.get("memory", {}))
             if result.session_state
             else {},
             input_data=input_data or {},

core/framework/server/app.py

@@ -56,8 +56,7 @@ def validate_agent_path(agent_path: str | Path) -> Path:
         if resolved.is_relative_to(root) and resolved != root:
             return resolved
     raise ValueError(
-        "agent_path must be inside an allowed directory "
-        "(~/.hive/colonies/, exports/, examples/, or ~/.hive/agents/)"
+        "agent_path must be inside an allowed directory (~/.hive/colonies/, exports/, examples/, or ~/.hive/agents/)"
     )
 
 
@@ -174,11 +173,12 @@ async def handle_health(request: web.Request) -> web.Response:
     )
 
 
-async def handle_browser_status(request: web.Request) -> web.Response:
-    """GET /api/browser/status — proxy the GCU bridge status check server-side.
+async def _probe_browser_bridge() -> dict:
+    """Probe the local GCU bridge and return ``{bridge, connected}``.
 
-    Checks http://127.0.0.1:9230/status so the browser never makes a
-    cross-origin request that would log ERR_CONNECTION_REFUSED in the console.
+    Shared by the one-shot ``GET /api/browser/status`` handler and the
+    ``/api/browser/status/stream`` SSE feed so both see the same data
+    source.
     """
     import asyncio
 
@@ -193,17 +193,66 @@ async def handle_browser_status(request: web.Request) -> web.Response:
         await writer.drain()
         raw = await asyncio.wait_for(reader.read(512), timeout=0.5)
         writer.close()
-        # Parse JSON body after the blank line
         if b"\r\n\r\n" in raw:
             body = raw.split(b"\r\n\r\n", 1)[1]
-            import json
+            import json as _json
 
-            data = json.loads(body)
-            return web.json_response({"bridge": True, "connected": data.get("connected", False)})
+            data = _json.loads(body)
+            return {"bridge": True, "connected": bool(data.get("connected", False))}
     except Exception:
         pass
+    return {"bridge": False, "connected": False}
 
-    return web.json_response({"bridge": False, "connected": False})
+
+async def handle_browser_status(request: web.Request) -> web.Response:
+    """GET /api/browser/status — proxy the GCU bridge status check server-side.
+
+    Checks http://127.0.0.1:9230/status so the browser never makes a
+    cross-origin request that would log ERR_CONNECTION_REFUSED in the console.
+    """
+    return web.json_response(await _probe_browser_bridge())
+
+
+async def handle_browser_status_stream(request: web.Request) -> web.StreamResponse:
+    """GET /api/browser/status/stream — SSE feed of bridge status.
+
+    Emits a ``status`` event immediately, then again only when the
+    probe result changes. Polls the local bridge every 3s; that's the
+    same cadence the frontend used before, but we absorb it
+    server-side instead of the browser burning a request.
+    """
+    import asyncio
+    import json as _json
+
+    resp = web.StreamResponse(
+        status=200,
+        headers={
+            "Content-Type": "text/event-stream",
+            "Cache-Control": "no-cache, no-transform",
+            "Connection": "keep-alive",
+            "X-Accel-Buffering": "no",
+        },
+    )
+    await resp.prepare(request)
+
+    async def _send(event: str, data: dict) -> None:
+        payload = f"event: {event}\ndata: {_json.dumps(data)}\n\n"
+        await resp.write(payload.encode("utf-8"))
+
+    last: tuple | None = None
+    try:
+        while True:
+            status = await _probe_browser_bridge()
+            signature = (status["bridge"], status["connected"])
+            if signature != last:
+                await _send("status", status)
+                last = signature
+            await asyncio.sleep(3.0)
+    except (asyncio.CancelledError, ConnectionResetError):
+        raise
+    except Exception as exc:
+        logger.warning("browser status stream error: %s", exc, exc_info=True)
+    return resp
 
 
 def create_app(model: str | None = None) -> web.Application:
@@ -232,57 +281,26 @@ def create_app(model: str | None = None) -> web.Application:
                 from framework.credentials.key_storage import generate_and_save_credential_key
 
                 generate_and_save_credential_key()
-                logger.info(
-                    "Generated and persisted HIVE_CREDENTIAL_KEY to ~/.hive/secrets/credential_key"
-                )
+                logger.info("Generated and persisted HIVE_CREDENTIAL_KEY to ~/.hive/secrets/credential_key")
             except Exception as exc:
                 logger.warning("Could not auto-persist HIVE_CREDENTIAL_KEY: %s", exc)
 
-        credential_store = CredentialStore.with_aden_sync()
+        # Local server startup should not wait on an eager Aden sync.
+        # The store can still fetch/refresh credentials on demand.
+        credential_store = CredentialStore.with_aden_sync(auto_sync=False)
     except Exception:
         logger.debug("Encrypted credential store unavailable, using in-memory fallback")
         credential_store = CredentialStore.for_testing({})
 
     app["credential_store"] = credential_store
 
-    # Pre-load queen MCP tools once at startup (cached for all sessions)
-    # This avoids rebuilding the tool registry for every queen session
-    from framework.loader.mcp_registry import MCPRegistry
-    from framework.loader.tool_registry import ToolRegistry
-
-    _queen_tool_registry: ToolRegistry | None = None
-    try:
-        _queen_tool_registry = ToolRegistry()
-        import framework.agents.queen as _queen_pkg
-
-        queen_pkg_dir = Path(_queen_pkg.__file__).parent
-        mcp_config = queen_pkg_dir / "mcp_servers.json"
-        if mcp_config.exists():
-            _queen_tool_registry.load_mcp_config(mcp_config)
-            logger.info("Pre-loaded queen MCP tools from %s", mcp_config)
-
-        registry = MCPRegistry()
-        registry.initialize()
-        registry.ensure_defaults()
-        if (queen_pkg_dir / "mcp_registry.json").is_file():
-            _queen_tool_registry.set_mcp_registry_agent_path(queen_pkg_dir)
-        registry_configs, selection_max_tools = registry.load_agent_selection(queen_pkg_dir)
-        if registry_configs:
-            _queen_tool_registry.load_registry_servers(
-                registry_configs,
-                preserve_existing_tools=True,
-                log_collisions=True,
-                max_tools=selection_max_tools,
-            )
-        logger.info(
-            "Pre-loaded queen tool registry with %d tools", len(_queen_tool_registry.get_tools())
-        )
-    except Exception as e:
-        logger.warning("Failed to pre-load queen tool registry: %s", e)
-
-    app["queen_tool_registry"] = _queen_tool_registry
+    # Let queen sessions build their registry lazily on first use instead of
+    # paying the MCP discovery cost during `hive open`.
+    app["queen_tool_registry"] = None
     app["manager"] = SessionManager(
-        model=model, credential_store=credential_store, queen_tool_registry=_queen_tool_registry
+        model=model,
+        credential_store=credential_store,
+        queen_tool_registry=None,
     )
 
     # Register shutdown hook
@@ -291,17 +309,19 @@ def create_app(model: str | None = None) -> web.Application:
     # Health check
     app.router.add_get("/api/health", handle_health)
     app.router.add_get("/api/browser/status", handle_browser_status)
+    app.router.add_get("/api/browser/status/stream", handle_browser_status_stream)
 
     # Register route modules
     from framework.server.routes_config import register_routes as register_config_routes
     from framework.server.routes_credentials import register_routes as register_credential_routes
     from framework.server.routes_events import register_routes as register_event_routes
     from framework.server.routes_execution import register_routes as register_execution_routes
-    from framework.server.routes_workers import register_routes as register_worker_routes
     from framework.server.routes_logs import register_routes as register_log_routes
     from framework.server.routes_messages import register_routes as register_message_routes
+    from framework.server.routes_colony_workers import register_routes as register_colony_worker_routes
     from framework.server.routes_queens import register_routes as register_queen_routes
     from framework.server.routes_sessions import register_routes as register_session_routes
+    from framework.server.routes_workers import register_routes as register_worker_routes
 
     register_config_routes(app)
     register_credential_routes(app)
@@ -312,6 +332,7 @@ def create_app(model: str | None = None) -> web.Application:
     register_worker_routes(app)
     register_log_routes(app)
     register_queen_routes(app)
+    register_colony_worker_routes(app)
 
     # Static file serving — Option C production mode
     # If frontend/dist/ exists, serve built frontend files on /

core/framework/server/queen_orchestrator.py

@@ -13,6 +13,8 @@ from pathlib import Path
 from typing import TYPE_CHECKING, Any
 
 if TYPE_CHECKING:
+    from framework.agent_loop.internals.types import HookContext, HookResult
+    from framework.loader.tool_registry import ToolRegistry
     from framework.server.session_manager import Session
 
 logger = logging.getLogger(__name__)
@@ -49,7 +51,7 @@ def install_worker_escalation_routing(
         # Defensive: ignore any stray non-worker origin (e.g. queen).
         if not stream_id.startswith("worker:"):
             return
-        worker_id = stream_id[len("worker:"):]
+        worker_id = stream_id[len("worker:") :]
         data = event.data or {}
         request_id = data.get("request_id")
         reason = str(data.get("reason", "")).strip()
@@ -64,8 +66,7 @@ def install_worker_escalation_routing(
                 try:
                     await runtime.inject_input(
                         worker_id,
-                        "[QUEEN_REPLY] queue_full — queen inbox saturated; "
-                        "proceed with best judgment or retry later.",
+                        "[QUEEN_REPLY] queue_full — queen inbox saturated; proceed with best judgment or retry later.",
                     )
                 except Exception:
                     logger.warning(
@@ -100,24 +101,16 @@ def install_worker_escalation_routing(
             lines.append(context_text)
         if request_id:
             lines.append(
-                "Use reply_to_worker(request_id, reply) to unblock, "
-                "or list_worker_questions() to see all pending."
+                "Use reply_to_worker(request_id, reply) to unblock, or list_worker_questions() to see all pending."
             )
         else:
-            lines.append(
-                "No request_id — use inject_message(content=...) to relay "
-                "guidance manually."
-            )
+            lines.append("No request_id — use inject_message(content=...) to relay guidance manually.")
         handoff = "\n".join(lines)
 
         # Fallback: if the queen loop has gone away, publish a
         # CLIENT_INPUT_REQUESTED so the human sees the question and the
         # worker does not wedge.
-        queen_node = (
-            session.queen_executor.node_registry.get("queen")
-            if session.queen_executor is not None
-            else None
-        )
+        queen_node = session.queen_executor.node_registry.get("queen") if session.queen_executor is not None else None
         if queen_node is None or not hasattr(queen_node, "inject_event"):
             if session.event_bus is not None:
                 await session.event_bus.emit_client_input_requested(
@@ -141,9 +134,7 @@ def install_worker_escalation_routing(
                 filter_colony=runtime.colony_id,
             )
         except Exception:
-            logger.warning(
-                "Failed to install colony-scoped escalation sub", exc_info=True
-            )
+            logger.warning("Failed to install colony-scoped escalation sub", exc_info=True)
             # fall through to session bus
     if session.event_bus is None:
         return None
@@ -174,24 +165,20 @@ def _build_credentials_provider() -> Any:
 
     def _provider() -> str:
         now = time.monotonic()
-        if (
-            state["cached"]
-            and (now - state["cached_at"]) < _CREDENTIALS_BLOCK_TTL_SECONDS
-        ):
+        if state["cached"] and (now - state["cached_at"]) < _CREDENTIALS_BLOCK_TTL_SECONDS:
             return state["cached"]
 
         try:
             from aden_tools.credentials.store_adapter import CredentialStoreAdapter
+
             from framework.orchestrator.prompting import build_accounts_prompt
 
             adapter = CredentialStoreAdapter.default()
             accounts = adapter.get_all_account_info()
-            tool_provider_map = adapter.get_tool_provider_map()
-            rendered = build_accounts_prompt(
-                accounts,
-                tool_provider_map=tool_provider_map,
-                node_tool_names=None,
-            )
+            # Compact form (no tool_provider_map) — tool schemas already
+            # surface function names; baking the full per-provider list
+            # into the system prompt on every turn was ~2 KB of redundancy.
+            rendered = build_accounts_prompt(accounts)
         except Exception:
             logger.debug("Failed to render ambient credentials block", exc_info=True)
             rendered = ""
@@ -242,7 +229,7 @@ async def materialize_queen_identity(
 
     phase_state.queen_id = queen_id
     phase_state.queen_profile = queen_profile
-    phase_state.queen_identity_prompt = format_queen_identity_prompt(queen_profile)
+    phase_state.queen_identity_prompt = format_queen_identity_prompt(queen_profile, max_examples=1)
 
     if event_bus is not None:
         await event_bus.publish(
@@ -279,42 +266,23 @@ async def create_queen(
         queen_loop_config as _base_loop_config,
     )
     from framework.agents.queen.nodes import (
-        _QUEEN_BUILDING_TOOLS,
-        _QUEEN_EDITING_TOOLS,
         _QUEEN_INDEPENDENT_TOOLS,
-        _QUEEN_PLANNING_TOOLS,
-        _QUEEN_RUNNING_TOOLS,
-        _QUEEN_STAGING_TOOLS,
-        _appendices,
-        _building_knowledge,
-        _planning_knowledge,
+        _QUEEN_REVIEWING_TOOLS,
+        _QUEEN_WORKING_TOOLS,
         _queen_behavior_always,
-        _queen_behavior_building,
-        _queen_behavior_editing,
         _queen_behavior_independent,
-        _queen_behavior_planning,
-        _queen_behavior_running,
-        _queen_behavior_staging,
         _queen_character_core,
-        _queen_identity_editing,
-        _queen_phase_7,
-        _queen_role_building,
         _queen_role_independent,
-        _queen_role_planning,
-        _queen_role_running,
-        _queen_role_staging,
+        _queen_role_reviewing,
+        _queen_role_working,
         _queen_style,
-        _queen_tools_building,
-        _queen_tools_editing,
         _queen_tools_independent,
-        _queen_tools_planning,
-        _queen_tools_running,
-        _queen_tools_staging,
-        _shared_building_knowledge,
+        _queen_tools_reviewing,
+        _queen_tools_working,
         finalize_queen_prompt,
     )
-    from framework.llm.capabilities import supports_image_tool_results
     from framework.host.event_bus import AgentEvent, EventType
+    from framework.llm.capabilities import supports_image_tool_results
     from framework.loader.mcp_registry import MCPRegistry
     from framework.loader.tool_registry import ToolRegistry
     from framework.tools.queen_lifecycle_tools import (
@@ -326,9 +294,7 @@ async def create_queen(
     # Use pre-loaded cached registry if available (fast path)
     if tool_registry is not None:
         queen_registry = tool_registry
-        logger.info(
-            "Queen: using pre-loaded tool registry with %d tools", len(queen_registry.get_tools())
-        )
+        logger.info("Queen: using pre-loaded tool registry with %d tools", len(queen_registry.get_tools()))
     else:
         # Build fresh (slow path - for backwards compatibility)
         queen_registry = ToolRegistry()
@@ -361,7 +327,10 @@ async def create_queen(
             logger.warning("Queen: MCP registry config failed to load", exc_info=True)
 
     # ---- Phase state --------------------------------------------------
-    effective_phase = initial_phase or ("staging" if worker_identity else "planning")
+    # 3-phase model: caller supplies the phase directly (DM → independent,
+    # colony bootstrap → working). Fall back to independent when nothing
+    # is specified — there is no "staging"/"planning" bootstrap anymore.
+    effective_phase = initial_phase or ("working" if worker_identity else "independent")
     phase_state = QueenPhaseState(phase=effective_phase, event_bus=session.event_bus)
     session.phase_state = phase_state
 
@@ -373,28 +342,6 @@ async def create_queen(
     # when the user adds/removes an integration.
     phase_state.credentials_prompt_provider = _build_credentials_provider()
 
-    # ---- Track ask rounds during planning ----------------------------
-    # Increment planning_ask_rounds each time the queen requests user
-    # input (ask_user or ask_user_multiple) while in the planning phase.
-    async def _track_planning_asks(event: AgentEvent) -> None:
-        if phase_state.phase != "planning":
-            return
-        # Only count explicit ask_user / ask_user_multiple calls, not
-        # auto-block (text-only turns emit CLIENT_INPUT_REQUESTED with
-        # an empty prompt and no options/questions).
-        data = event.data or {}
-        has_prompt = bool(data.get("prompt"))
-        has_questions = bool(data.get("questions"))
-        has_options = bool(data.get("options"))
-        if has_prompt or has_questions or has_options:
-            phase_state.planning_ask_rounds += 1
-
-    session.event_bus.subscribe(
-        [EventType.CLIENT_INPUT_REQUESTED],
-        _track_planning_asks,
-        filter_stream="queen",
-    )
-
     # ---- Lifecycle tools (always registered) --------------------------
     register_queen_lifecycle_tools(
         queen_registry,
@@ -430,39 +377,21 @@ async def create_queen(
     session._queen_tool_executor = queen_tool_executor  # type: ignore[attr-defined]
 
     # ---- Partition tools by phase ------------------------------------
-    planning_names = set(_QUEEN_PLANNING_TOOLS)
-    building_names = set(_QUEEN_BUILDING_TOOLS)
-    staging_names = set(_QUEEN_STAGING_TOOLS)
-    running_names = set(_QUEEN_RUNNING_TOOLS)
-    editing_names = set(_QUEEN_EDITING_TOOLS)
     independent_names = set(_QUEEN_INDEPENDENT_TOOLS)
+    working_names = set(_QUEEN_WORKING_TOOLS)
+    reviewing_names = set(_QUEEN_REVIEWING_TOOLS)
 
     registered_names = {t.name for t in queen_tools}
-    missing_building = building_names - registered_names
-    if missing_building:
-        logger.warning(
-            "Queen: %d/%d building tools NOT registered: %s",
-            len(missing_building),
-            len(building_names),
-            sorted(missing_building),
-        )
     logger.info("Queen: registered tools: %s", sorted(registered_names))
 
-    phase_state.planning_tools = [t for t in queen_tools if t.name in planning_names]
-    phase_state.building_tools = [t for t in queen_tools if t.name in building_names]
-    phase_state.staging_tools = [t for t in queen_tools if t.name in staging_names]
-    phase_state.running_tools = [t for t in queen_tools if t.name in running_names]
-    phase_state.editing_tools = [t for t in queen_tools if t.name in editing_names]
+    phase_state.working_tools = [t for t in queen_tools if t.name in working_names]
+    phase_state.reviewing_tools = [t for t in queen_tools if t.name in reviewing_names]
 
     # Independent phase gets core tools + all MCP tools not claimed by any
     # other phase (coder-tools file I/O, gcu-tools browser, etc.).
-    all_phase_names = (
-        planning_names | building_names | staging_names | running_names | editing_names
-    )
+    all_phase_names = independent_names | working_names | reviewing_names
     mcp_tools = [t for t in queen_tools if t.name not in all_phase_names]
-    phase_state.independent_tools = [
-        t for t in queen_tools if t.name in independent_names
-    ] + mcp_tools
+    phase_state.independent_tools = [t for t in queen_tools if t.name in independent_names] + mcp_tools
     logger.info(
         "Queen: independent tools: %s",
         sorted(t.name for t in phase_state.independent_tools),
@@ -483,83 +412,11 @@ async def create_queen(
     # ---- Compose phase-specific prompts ------------------------------
     from framework.agents.queen.nodes import queen_node as _orig_node
 
-    if worker_identity is None:
-        worker_identity = (
-            "\n\n# Worker Profile\n"
-            "No worker agent loaded. You are operating independently.\n"
-            "Design or build the agent to solve the user's problem "
-            "according to your current phase."
-        )
-
     # Resolve vision-only prompt sections based on the session's LLM.
     # session.llm is immutable for the session's lifetime, so this check
     # is stable — prompts never need to be recomposed mid-session.
-    _has_vision = bool(
-        session.llm and supports_image_tool_results(getattr(session.llm, "model", ""))
-    )
+    _has_vision = bool(session.llm and supports_image_tool_results(getattr(session.llm, "model", "")))
 
-    _planning_body = (
-        _queen_character_core
-        + _queen_role_planning
-        + _queen_style
-        + _shared_building_knowledge
-        + _queen_tools_planning
-        + _queen_behavior_always
-        + _queen_behavior_planning
-        + _planning_knowledge
-        + worker_identity
-    )
-    phase_state.prompt_planning = finalize_queen_prompt(_planning_body, _has_vision)
-
-    _building_body = (
-        _queen_character_core
-        + _queen_role_building
-        + _queen_style
-        + _shared_building_knowledge
-        + _queen_tools_building
-        + _queen_behavior_always
-        + _queen_behavior_building
-        + _building_knowledge
-        + _queen_phase_7
-        + _appendices
-        + worker_identity
-    )
-    phase_state.prompt_building = finalize_queen_prompt(_building_body, _has_vision)
-    phase_state.prompt_staging = finalize_queen_prompt(
-        (
-            _queen_character_core
-            + _queen_role_staging
-            + _queen_style
-            + _queen_tools_staging
-            + _queen_behavior_always
-            + _queen_behavior_staging
-            + worker_identity
-        ),
-        _has_vision,
-    )
-    phase_state.prompt_running = finalize_queen_prompt(
-        (
-            _queen_character_core
-            + _queen_role_running
-            + _queen_style
-            + _queen_tools_running
-            + _queen_behavior_always
-            + _queen_behavior_running
-            + worker_identity
-        ),
-        _has_vision,
-    )
-    phase_state.prompt_editing = finalize_queen_prompt(
-        (
-            _queen_identity_editing
-            + _queen_style
-            + _queen_tools_editing
-            + _queen_behavior_always
-            + _queen_behavior_editing
-            + worker_identity
-        ),
-        _has_vision,
-    )
     phase_state.prompt_independent = finalize_queen_prompt(
         (
             _queen_character_core
@@ -571,6 +428,26 @@ async def create_queen(
         ),
         _has_vision,
     )
+    phase_state.prompt_working = finalize_queen_prompt(
+        (
+            _queen_character_core
+            + _queen_role_working
+            + _queen_style
+            + _queen_tools_working
+            + _queen_behavior_always
+        ),
+        _has_vision,
+    )
+    phase_state.prompt_reviewing = finalize_queen_prompt(
+        (
+            _queen_character_core
+            + _queen_role_reviewing
+            + _queen_style
+            + _queen_tools_reviewing
+            + _queen_behavior_always
+        ),
+        _has_vision,
+    )
 
     # ---- Default skill protocols -------------------------------------
     _queen_skill_dirs: list[str] = []
@@ -584,6 +461,10 @@ async def create_queen(
         _queen_skills_mgr.load()
         phase_state.protocols_prompt = _queen_skills_mgr.protocols_prompt
         phase_state.skills_catalog_prompt = _queen_skills_mgr.skills_catalog_prompt
+        # Also store the manager so get_current_prompt() can render a
+        # phase-filtered catalog on each turn (skills with a `visibility`
+        # frontmatter that excludes the current phase are dropped).
+        phase_state.skills_manager = _queen_skills_mgr
         _queen_skill_dirs = _queen_skills_mgr.allowlisted_dirs
     except Exception:
         logger.debug("Queen skill loading failed (non-fatal)", exc_info=True)
@@ -625,6 +506,14 @@ async def create_queen(
     )
 
     async def _queen_identity_hook(ctx: HookContext) -> HookResult | None:
+        from framework.agent_loop.internals.types import HookResult
+        from framework.agents.queen.queen_profiles import (
+            ensure_default_queens,
+            format_queen_identity_prompt,
+            load_queen_profile,
+            select_queen,
+        )
+
         ensure_default_queens()
         trigger = ctx.trigger or ""
         # If the session was pre-bound to a queen (user clicked a specific
@@ -643,7 +532,7 @@ async def create_queen(
         except FileNotFoundError:
             logger.warning("Queen profile %s not found after selection", queen_id)
             return None
-        identity_prompt = format_queen_identity_prompt(profile)
+        identity_prompt = format_queen_identity_prompt(profile, max_examples=1)
         # Store on phase_state so identity persists across dynamic prompt refreshes
         phase_state.queen_id = queen_id
         phase_state.queen_profile = profile
@@ -676,18 +565,12 @@ async def create_queen(
                     try:
                         _meta = _json.loads(_meta_path.read_text(encoding="utf-8"))
                         _meta["queen_id"] = queen_id
-                        _meta_path.write_text(
-                            _json.dumps(_meta, ensure_ascii=False), encoding="utf-8"
-                        )
+                        _meta_path.write_text(_json.dumps(_meta, ensure_ascii=False), encoding="utf-8")
                     except (OSError, _json.JSONDecodeError):
                         pass
                 # Re-point event bus log to new location, preserving offset
-                _offset = getattr(
-                    session.event_bus, "_session_log_iteration_offset", 0
-                )
-                session.event_bus.set_session_log(
-                    _new_dir / "events.jsonl", iteration_offset=_offset
-                )
+                _offset = getattr(session.event_bus, "_session_log_iteration_offset", 0)
+                session.event_bus.set_session_log(_new_dir / "events.jsonl", iteration_offset=_offset)
 
         if _session_event_bus is not None:
             await _session_event_bus.publish(
@@ -742,7 +625,7 @@ async def create_queen(
             logger.debug("Queen: tools not yet available (registered on worker load): %s", missing)
         node_updates["tools"] = available_tools
 
-    adjusted_node = _orig_node.model_copy(update=node_updates)
+    _orig_node.model_copy(update=node_updates)
 
     # Determine session mode:
     # - RESTORE: Resume cold session with history, no initial prompt -> wait for user
@@ -760,6 +643,18 @@ async def create_queen(
 
     async def _queen_loop():
         logger.debug("[_queen_loop] Starting queen loop for session %s", session.id)
+        # Scope the browser profile to this session so parallel queens each
+        # drive their own Chrome tab group instead of fighting over "default".
+        # Browser tools run in a stdio MCP subprocess, so we can't set a
+        # contextvar across processes — instead we inject `profile` as a
+        # CONTEXT_PARAM that ToolRegistry passes into every MCP call. The
+        # token stays local to this task.
+        try:
+            from framework.loader.tool_registry import ToolRegistry
+
+            ToolRegistry.set_execution_context(profile=session.id)
+        except Exception:
+            logger.debug("Queen: failed to set browser profile for session %s", session.id, exc_info=True)
         try:
             lc = _queen_loop_config
             queen_loop_config = LoopConfig(
@@ -827,44 +722,71 @@ async def create_queen(
 
             phase_state.inject_notification = _inject_phase_notification
 
-            async def _on_worker_done(event):
+            async def _on_worker_report(event):
+                """Inject [WORKER_REPORT] into queen as each worker finishes.
+
+                Subscribes to SUBAGENT_REPORT events which carry the worker's
+                real summary/data (preferring any explicit ``report_to_parent``
+                call). Every spawned worker emits exactly one — success,
+                partial, failed, timeout, or stopped. The queen sees the
+                report as the next user turn and can react (reply to user,
+                kick off follow-up work, etc.) without being blocked by the
+                spawn call itself.
+                """
                 if event.stream_id == "queen":
                     return
-                if phase_state.phase == "running":
-                    if event.type == EventType.EXECUTION_COMPLETED:
-                        session.worker_configured = True
-                        output = event.data.get("output", {})
-                        output_summary = ""
-                        if output:
-                            for key, value in output.items():
-                                val_str = str(value)
-                                if len(val_str) > 200:
-                                    val_str = val_str[:200] + "..."
-                                output_summary += f"\n  {key}: {val_str}"
-                        _out = output_summary or " (no output keys set)"
-                        notification = (
-                            "[WORKER_TERMINAL] Worker finished successfully.\n"
-                            f"Output:{_out}\n"
-                            "Report this to the user. "
-                            "Ask if they want to re-run with different input "
-                            "or tweak the configuration."
-                        )
-                    else:
-                        error = event.data.get("error", "Unknown error")
-                        notification = (
-                            "[WORKER_TERMINAL] Worker failed.\n"
-                            f"Error: {error}\n"
-                            "Report this to the user and help them troubleshoot. "
-                            "You can re-run with different input or escalate to "
-                            "building/planning if code changes are needed."
-                        )
+                data = event.data or {}
+                worker_id = data.get("worker_id", event.node_id or "unknown")
+                status = data.get("status", "unknown")
+                summary = data.get("summary") or "(no summary)"
+                err = data.get("error")
+                payload_data = data.get("data") or {}
+                duration = data.get("duration_seconds")
 
-                    await agent_loop.inject_event(notification)
-                    await phase_state.switch_to_editing(source="auto")
+                lines = ["[WORKER_REPORT]", f"worker_id: {worker_id}", f"status: {status}"]
+                if duration is not None:
+                    try:
+                        lines.append(f"duration: {float(duration):.1f}s")
+                    except (TypeError, ValueError):
+                        pass
+                lines.append(f"summary: {summary}")
+                if err:
+                    lines.append(f"error: {err}")
+                if payload_data:
+                    # Compact JSON so the queen sees all keys without the
+                    # indentation blowing up the turn's token count.
+                    try:
+                        import json as _json
+
+                        lines.append("data: " + _json.dumps(payload_data, ensure_ascii=False, default=str))
+                    except Exception:
+                        lines.append(f"data: {payload_data!r}")
+                notification = "\n".join(lines)
+
+                await agent_loop.inject_event(notification)
+                session.worker_configured = True
+
+                # Only transition to reviewing once the batch has quieted —
+                # if other workers from a parallel spawn are still live, stay
+                # in working so the queen's tool access (run_parallel_workers,
+                # inject_message, stop_worker) remains available.
+                colony_runtime = getattr(session, "colony_runtime", None)
+                still_active = 0
+                if colony_runtime is not None:
+                    try:
+                        still_active = sum(
+                            1
+                            for w in colony_runtime._workers.values()  # type: ignore[attr-defined]
+                            if getattr(w, "is_active", False)
+                        )
+                    except Exception:
+                        still_active = 0
+                if still_active == 0 and phase_state.phase in ("working", "running"):
+                    await phase_state.switch_to_reviewing(source="auto")
 
             session.event_bus.subscribe(
-                event_types=[EventType.EXECUTION_COMPLETED, EventType.EXECUTION_FAILED],
-                handler=_on_worker_done,
+                event_types=[EventType.SUBAGENT_REPORT],
+                handler=_on_worker_report,
             )
 
             # ---- Colony-scoped worker escalation routing ----
@@ -897,9 +819,7 @@ async def create_queen(
             # bootstrap: if the frontend doesn't pass initial_prompt, we must
             # NOT invent a phantom "Hello" — that used to concatenate with the
             # real first chat message and confuse the model.
-            ctx.input_data = {
-                "user_request": None if _is_restore_mode else (initial_prompt or None)
-            }
+            ctx.input_data = {"user_request": None if _is_restore_mode else (initial_prompt or None)}
 
             # Publish the initial prompt as a CLIENT_INPUT_RECEIVED event so
             # it appears in the SSE stream and persists to events.jsonl for

core/framework/server/routes_colony_workers.py

@@ -0,0 +1,722 @@
+"""Colony worker inspection routes.
+
+These expose per-spawned-worker data (identified by worker_id) so the
+frontend can render a colony-workers sidebar analogous to the queen
+profile panel. Distinct from ``routes_workers.py``, which deals with
+*graph nodes* inside a worker definition rather than live worker
+instances.
+
+- GET /api/sessions/{session_id}/workers            — live + completed workers
+- GET /api/sessions/{session_id}/colony/skills      — colony's shared skills catalog
+- GET /api/sessions/{session_id}/colony/tools       — colony's default tools
+- GET /api/sessions/{session_id}/colony/progress/snapshot — progress.db tasks/steps snapshot
+- GET /api/sessions/{session_id}/colony/progress/stream   — SSE feed of upserts (polled)
+- GET /api/sessions/{session_id}/colony/data/tables       — list user tables in progress.db
+- GET /api/sessions/{session_id}/colony/data/tables/{table}/rows — paginated rows
+- PATCH /api/sessions/{session_id}/colony/data/tables/{table}/rows — edit a row
+"""
+
+import asyncio
+import json
+import logging
+import sqlite3
+from pathlib import Path
+
+from aiohttp import web
+
+from framework.server.app import resolve_session
+
+logger = logging.getLogger(__name__)
+
+# Poll interval for the progress SSE stream. Progress rows flip on the
+# order of seconds as workers finish LLM turns, so 1s feels live without
+# hammering the DB.
+_PROGRESS_POLL_INTERVAL = 1.0
+
+
+def _worker_info_to_dict(info) -> dict:
+    """Serialize a WorkerInfo dataclass to a JSON-friendly dict."""
+    result_dict = None
+    if info.result is not None:
+        r = info.result
+        result_dict = {
+            "status": r.status,
+            "summary": r.summary,
+            "error": r.error,
+            "tokens_used": r.tokens_used,
+            "duration_seconds": r.duration_seconds,
+        }
+    return {
+        "worker_id": info.id,
+        "task": info.task,
+        "status": str(info.status),
+        "started_at": info.started_at,
+        "result": result_dict,
+    }
+
+
+async def handle_list_workers(request: web.Request) -> web.Response:
+    """GET /api/sessions/{session_id}/workers -- list workers in a session's colony.
+
+    Returns two populations merged:
+      1. In-memory workers from the session's unified ColonyRuntime
+         (``session.colony._workers``). Includes live + just-finished
+         entries since ``_workers`` isn't pruned on termination.
+      2. Historical worker directories on disk under
+         ``<session_dir>/workers/`` that are not in memory. Populated
+         from dir name / first user message / dir mtime. These appear
+         as ``status="historical"`` so the frontend can style them
+         distinctly from actives.
+
+    Falls back to the legacy ``session.colony_runtime`` for the
+    in-memory half when ``session.colony`` isn't set.
+    """
+    session, err = resolve_session(request)
+    if err:
+        return err
+
+    runtime = getattr(session, "colony", None) or getattr(session, "colony_runtime", None)
+
+    workers: list[dict] = []
+    known_ids: set[str] = set()
+    storage_path: Path | None = None
+    if runtime is not None:
+        for info in runtime.list_workers():
+            workers.append(_worker_info_to_dict(info))
+            known_ids.add(info.id)
+        raw_storage = getattr(runtime, "_storage_path", None)
+        if raw_storage is not None:
+            storage_path = Path(raw_storage)
+
+    # Fall back to the session's directory if the runtime didn't expose one.
+    if storage_path is None:
+        session_dir = getattr(session, "queen_dir", None) or getattr(session, "session_dir", None)
+        if session_dir is not None:
+            storage_path = Path(session_dir)
+
+    if storage_path is not None:
+        workers.extend(
+            await asyncio.to_thread(_walk_historical_workers, storage_path, known_ids)
+        )
+
+    return web.json_response({"workers": workers})
+
+
+def _walk_historical_workers(storage_path: Path, known_ids: set[str]) -> list[dict]:
+    """Scan ``<storage_path>/workers/`` for worker session dirs not already
+    in memory and return minimal ``WorkerSummary``-shaped entries.
+
+    We don't persist a standalone status file per worker, so the on-disk
+    entries get ``status="historical"`` and ``result=None``. The task is
+    reconstructed from the first non-boilerplate user message in the
+    worker's conversation parts.
+    """
+    workers_dir = storage_path / "workers"
+    if not workers_dir.exists() or not workers_dir.is_dir():
+        return []
+
+    out: list[dict] = []
+    try:
+        entries = list(workers_dir.iterdir())
+    except OSError:
+        return []
+
+    # Newest dir first so recent runs surface first in the tab.
+    entries.sort(key=lambda p: _safe_mtime(p), reverse=True)
+
+    for entry in entries:
+        if not entry.is_dir():
+            continue
+        wid = entry.name
+        if wid in known_ids:
+            continue
+        out.append(
+            {
+                "worker_id": wid,
+                "task": _extract_historical_task(entry),
+                "status": "historical",
+                "started_at": _safe_mtime(entry),
+                "result": None,
+            }
+        )
+    return out
+
+
+def _safe_mtime(path: Path) -> float:
+    try:
+        return path.stat().st_mtime
+    except OSError:
+        return 0.0
+
+
+def _extract_historical_task(worker_dir: Path) -> str:
+    """Pull the worker's initial task from its conversation parts.
+
+    seq 0 is a boilerplate "Hello" greeting in most flows; the real
+    task lands in an early user message (typically seq 1 or 2). Scan
+    the first few parts and return the first ``role="user"`` content
+    that isn't the greeting. Bounded at 5 parts to stay cheap on
+    directory listings containing hundreds of workers.
+    """
+    parts_dir = worker_dir / "conversations" / "parts"
+    if not parts_dir.exists():
+        return ""
+    try:
+        for i in range(5):
+            p = parts_dir / f"{i:010d}.json"
+            if not p.exists():
+                break
+            data = json.loads(p.read_text(encoding="utf-8"))
+            if data.get("role") != "user":
+                continue
+            content = data.get("content", "")
+            if not isinstance(content, str):
+                continue
+            text = content.strip()
+            if not text or text.lower() == "hello":
+                continue
+            return text[:400]
+    except Exception:
+        return ""
+    return ""
+
+
+# ── Skills & tools ─────────────────────────────────────────────────
+
+def _parsed_skill_to_dict(skill) -> dict:
+    """Serialize a ParsedSkill for the frontend."""
+    return {
+        "name": skill.name,
+        "description": skill.description,
+        "location": skill.location,
+        "base_dir": skill.base_dir,
+        "source_scope": skill.source_scope,
+    }
+
+
+async def handle_list_colony_skills(request: web.Request) -> web.Response:
+    """GET /api/sessions/{session_id}/colony/skills -- list skills the colony sees."""
+    session, err = resolve_session(request)
+    if err:
+        return err
+
+    runtime = session.colony_runtime
+    if runtime is None:
+        return web.json_response({"skills": []})
+
+    # Reach into the skills manager's catalog. There is no public
+    # iterator yet; we touch the private dict directly and defensively
+    # tolerate either shape (bare SkillsManager, or the
+    # from_precomputed variant which has no catalog).
+    catalog = getattr(runtime._skills_manager, "_catalog", None)
+    skills_dict = getattr(catalog, "_skills", None) if catalog is not None else None
+    if not isinstance(skills_dict, dict):
+        return web.json_response({"skills": []})
+
+    skills = [_parsed_skill_to_dict(s) for s in skills_dict.values()]
+    skills.sort(key=lambda s: s["name"])
+    return web.json_response({"skills": skills})
+
+
+# Tools that ship with the framework and have no credential provider,
+# but still deserve their own logical group. Surfaced to the frontend
+# as ``provider="system"`` so the UI treats them exactly like a
+# credential-backed group.
+_SYSTEM_TOOLS: frozenset[str] = frozenset(
+    {
+        "get_account_info",
+        "get_current_time",
+        "bash_kill",
+        "bash_output",
+        "execute_command_tool",
+        "example_tool",
+    }
+)
+
+
+def _tool_to_dict(tool, provider_map: dict[str, str] | None) -> dict:
+    """Serialize a Tool dataclass for the frontend.
+
+    ``provider_map`` is the colony runtime's tool_name → credential
+    provider map (built by the CredentialResolver pipeline stage from
+    ``CredentialStoreAdapter.get_tool_provider_map()``). Credential-
+    backed tools get a canonical provider key (e.g. ``"hubspot"``,
+    ``"gmail"``); framework / core tools return ``None``, except for
+    the hand-picked entries in ``_SYSTEM_TOOLS`` which are tagged
+    ``"system"``.
+    """
+    name = getattr(tool, "name", "")
+    provider = (provider_map or {}).get(name)
+    if provider is None and name in _SYSTEM_TOOLS:
+        provider = "system"
+    return {
+        "name": name,
+        "description": getattr(tool, "description", ""),
+        "provider": provider,
+    }
+
+
+async def handle_list_colony_tools(request: web.Request) -> web.Response:
+    """GET /api/sessions/{session_id}/colony/tools -- list the colony's default tools."""
+    session, err = resolve_session(request)
+    if err:
+        return err
+
+    runtime = session.colony_runtime
+    if runtime is None:
+        return web.json_response({"tools": []})
+
+    provider_map = getattr(runtime, "_tool_provider_map", None)
+    tools = [_tool_to_dict(t, provider_map) for t in (runtime._tools or [])]
+    tools.sort(key=lambda t: t["name"])
+    return web.json_response({"tools": tools})
+
+
+# ── Progress DB (tasks/steps) ──────────────────────────────────────
+
+def _resolve_progress_db(session) -> Path | None:
+    """Resolve the colony's progress.db path for ``session``.
+
+    Returns ``None`` if the session is not bound to a colony yet or if
+    the DB file doesn't exist.
+    """
+    colony_name = getattr(session, "colony_name", None)
+    if not colony_name:
+        return None
+    db_path = Path.home() / ".hive" / "colonies" / colony_name / "data" / "progress.db"
+    return db_path if db_path.exists() else None
+
+
+def _read_progress_snapshot(db_path: Path, worker_id: str | None) -> dict:
+    """Read tasks + steps from progress.db, optionally filtered by worker_id.
+
+    The worker_id filter applies to tasks (claimed by that worker) and
+    to steps (executed by that worker). If omitted, returns all rows.
+    """
+    con = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True, timeout=5.0)
+    try:
+        con.row_factory = sqlite3.Row
+        if worker_id:
+            task_rows = con.execute(
+                "SELECT * FROM tasks WHERE worker_id = ? ORDER BY updated_at DESC",
+                (worker_id,),
+            ).fetchall()
+            step_rows = con.execute(
+                "SELECT * FROM steps WHERE worker_id = ? ORDER BY task_id, seq",
+                (worker_id,),
+            ).fetchall()
+        else:
+            task_rows = con.execute(
+                "SELECT * FROM tasks ORDER BY updated_at DESC LIMIT 500"
+            ).fetchall()
+            step_rows = con.execute(
+                "SELECT * FROM steps ORDER BY task_id, seq LIMIT 2000"
+            ).fetchall()
+        return {
+            "tasks": [dict(r) for r in task_rows],
+            "steps": [dict(r) for r in step_rows],
+        }
+    finally:
+        con.close()
+
+
+async def handle_progress_snapshot(request: web.Request) -> web.Response:
+    """GET /api/sessions/{session_id}/colony/progress/snapshot
+
+    Optional ?worker_id=... to filter to rows touched by a specific worker.
+    """
+    session, err = resolve_session(request)
+    if err:
+        return err
+
+    db_path = _resolve_progress_db(session)
+    if db_path is None:
+        return web.json_response({"tasks": [], "steps": []})
+
+    worker_id = request.query.get("worker_id") or None
+    snapshot = await asyncio.to_thread(_read_progress_snapshot, db_path, worker_id)
+    return web.json_response(snapshot)
+
+
+def _read_progress_upserts(
+    db_path: Path,
+    worker_id: str | None,
+    since: str | None,
+) -> tuple[list[dict], list[dict], str | None]:
+    """Return task/step rows with ``updated_at`` (tasks) or a derived
+    timestamp (steps) newer than ``since``, plus the new high-water mark.
+
+    Steps don't carry an ``updated_at`` column — we use
+    ``COALESCE(completed_at, started_at)`` as the change witness. A step
+    without either timestamp hasn't changed since the last poll and is
+    skipped.
+
+    ``since`` is an ISO8601 string (as produced by progress_db._now_iso).
+    ``None`` means "give me everything" — used for the SSE priming frame.
+    """
+    con = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True, timeout=5.0)
+    try:
+        con.row_factory = sqlite3.Row
+        task_sql = "SELECT * FROM tasks"
+        step_sql = (
+            "SELECT *, COALESCE(completed_at, started_at) AS _ts "
+            "FROM steps WHERE COALESCE(completed_at, started_at) IS NOT NULL"
+        )
+        task_args: list = []
+        step_args: list = []
+        if since is not None:
+            task_sql += " WHERE updated_at > ?"
+            step_sql += " AND COALESCE(completed_at, started_at) > ?"
+            task_args.append(since)
+            step_args.append(since)
+        if worker_id:
+            joiner_t = " AND " if since is not None else " WHERE "
+            task_sql += joiner_t + "worker_id = ?"
+            step_sql += " AND worker_id = ?"
+            task_args.append(worker_id)
+            step_args.append(worker_id)
+        task_sql += " ORDER BY updated_at"
+        step_sql += " ORDER BY _ts"
+
+        task_rows = con.execute(task_sql, task_args).fetchall()
+        step_rows = con.execute(step_sql, step_args).fetchall()
+
+        tasks = [dict(r) for r in task_rows]
+        steps = [dict(r) for r in step_rows]
+        # High-water mark = max timestamp across both sets. Fall back to
+        # the previous ``since`` when nothing changed.
+        ts_values = [t["updated_at"] for t in tasks]
+        ts_values.extend(s["_ts"] for s in steps if s.get("_ts"))
+        new_since = max(ts_values) if ts_values else since
+        return tasks, steps, new_since
+    finally:
+        con.close()
+
+
+async def handle_progress_stream(request: web.Request) -> web.StreamResponse:
+    """GET /api/sessions/{session_id}/colony/progress/stream
+
+    SSE feed that emits ``snapshot`` once (current state) followed by
+    ``upsert`` events whenever a task/step row changes. Polls the DB
+    every ``_PROGRESS_POLL_INTERVAL`` seconds — the sqlite3 CLI path
+    workers use for writes doesn't fire SQLite's update hook on our
+    connection, so polling is the robust option.
+    """
+    session, err = resolve_session(request)
+    if err:
+        return err
+
+    worker_id = request.query.get("worker_id") or None
+
+    resp = web.StreamResponse(
+        status=200,
+        headers={
+            "Content-Type": "text/event-stream",
+            "Cache-Control": "no-cache, no-transform",
+            "Connection": "keep-alive",
+            "X-Accel-Buffering": "no",
+        },
+    )
+    await resp.prepare(request)
+
+    async def _send(event: str, data: dict) -> None:
+        payload = f"event: {event}\ndata: {json.dumps(data)}\n\n"
+        await resp.write(payload.encode("utf-8"))
+
+    db_path = _resolve_progress_db(session)
+    if db_path is None:
+        await _send("snapshot", {"tasks": [], "steps": []})
+        await _send("end", {"reason": "no_progress_db"})
+        return resp
+
+    try:
+        snapshot = await asyncio.to_thread(_read_progress_snapshot, db_path, worker_id)
+        await _send("snapshot", snapshot)
+
+        since: str | None = None
+        # Initialize the high-water mark from the snapshot so we don't
+        # re-emit every row as "new" on the first poll.
+        ts_values: list[str] = [t.get("updated_at") for t in snapshot["tasks"] if t.get("updated_at")]
+        ts_values.extend(
+            s.get("completed_at") or s.get("started_at")
+            for s in snapshot["steps"]
+            if s.get("completed_at") or s.get("started_at")
+        )
+        if ts_values:
+            since = max(v for v in ts_values if v)
+
+        # The loop relies on client disconnect surfacing as
+        # ConnectionResetError from ``_send`` — no explicit alive check
+        # required.
+        while True:
+            await asyncio.sleep(_PROGRESS_POLL_INTERVAL)
+            tasks, steps, new_since = await asyncio.to_thread(
+                _read_progress_upserts, db_path, worker_id, since
+            )
+            if tasks or steps:
+                await _send("upsert", {"tasks": tasks, "steps": steps})
+                since = new_since
+    except (asyncio.CancelledError, ConnectionResetError):
+        # Client disconnected; clean exit.
+        raise
+    except Exception as exc:
+        logger.warning("progress stream error: %s", exc, exc_info=True)
+        try:
+            await _send("error", {"message": str(exc)})
+        except Exception:
+            pass
+    return resp
+
+
+# ── Raw data grid (airtable-style view/edit of progress.db tables) ─────
+#
+# The Data tab lets the operator inspect and hand-edit SQLite rows.
+# Identifier-quoting note: SQLite params can only bind values, never
+# identifiers, so we have to interpolate table/column names into SQL.
+# Every name is *validated against sqlite_master / PRAGMA table_info*
+# before use and then wrapped with ``_q()`` which escapes embedded
+# quotes. Do NOT accept raw names from the request without running them
+# through ``_validate_ident`` first.
+
+
+def _q(ident: str) -> str:
+    """Quote a SQLite identifier (table or column) safely."""
+    return '"' + ident.replace('"', '""') + '"'
+
+
+def _list_user_tables(con: sqlite3.Connection) -> list[str]:
+    return [
+        r["name"]
+        for r in con.execute(
+            "SELECT name FROM sqlite_master WHERE type='table' "
+            "AND name NOT LIKE 'sqlite_%' ORDER BY name"
+        )
+    ]
+
+
+def _table_columns(con: sqlite3.Connection, table: str) -> list[dict]:
+    """Return PRAGMA table_info rows as dicts. Empty list if no such table."""
+    return [
+        {
+            "name": r["name"],
+            "type": r["type"] or "",
+            "notnull": bool(r["notnull"]),
+            # pk>0 means the column is part of the primary key (ordinal);
+            # 0 means non-PK.
+            "pk": int(r["pk"]),
+            "dflt_value": r["dflt_value"],
+        }
+        for r in con.execute(f"PRAGMA table_info({_q(table)})")
+    ]
+
+
+def _read_tables_overview(db_path: Path) -> list[dict]:
+    """List user tables with columns + row counts."""
+    con = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True, timeout=5.0)
+    try:
+        con.row_factory = sqlite3.Row
+        out: list[dict] = []
+        for name in _list_user_tables(con):
+            cols = _table_columns(con, name)
+            count_row = con.execute(f"SELECT COUNT(*) AS c FROM {_q(name)}").fetchone()
+            out.append(
+                {
+                    "name": name,
+                    "columns": cols,
+                    "row_count": int(count_row["c"]),
+                    "primary_key": [c["name"] for c in cols if c["pk"] > 0],
+                }
+            )
+        return out
+    finally:
+        con.close()
+
+
+def _validate_ident(name: str, known: set[str]) -> str | None:
+    """Return ``name`` if present in ``known``, else ``None``."""
+    return name if name in known else None
+
+
+def _read_table_rows(
+    db_path: Path,
+    table: str,
+    limit: int,
+    offset: int,
+    order_by: str | None,
+    order_dir: str,
+) -> dict:
+    con = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True, timeout=5.0)
+    try:
+        con.row_factory = sqlite3.Row
+        tables = set(_list_user_tables(con))
+        if _validate_ident(table, tables) is None:
+            return {"error": f"unknown table: {table}"}
+        cols = _table_columns(con, table)
+        col_names = {c["name"] for c in cols}
+
+        sql = f"SELECT * FROM {_q(table)}"
+        if order_by and order_by in col_names:
+            direction = "DESC" if order_dir.lower() == "desc" else "ASC"
+            sql += f" ORDER BY {_q(order_by)} {direction}"
+        sql += " LIMIT ? OFFSET ?"
+        rows = con.execute(sql, (int(limit), int(offset))).fetchall()
+        total = con.execute(f"SELECT COUNT(*) AS c FROM {_q(table)}").fetchone()["c"]
+        return {
+            "table": table,
+            "columns": cols,
+            "primary_key": [c["name"] for c in cols if c["pk"] > 0],
+            "rows": [dict(r) for r in rows],
+            "total": int(total),
+            "limit": int(limit),
+            "offset": int(offset),
+        }
+    finally:
+        con.close()
+
+
+def _update_table_row(
+    db_path: Path,
+    table: str,
+    pk: dict,
+    updates: dict,
+) -> dict:
+    """Apply ``updates`` (column->value) to the row matching ``pk``.
+
+    Returns ``{"updated": n}`` with the number of rows affected (0 or 1),
+    or ``{"error": ...}`` on validation failure.
+    """
+    if not updates:
+        return {"error": "no updates provided"}
+    con = sqlite3.connect(db_path, timeout=5.0)
+    try:
+        con.row_factory = sqlite3.Row
+        tables = set(_list_user_tables(con))
+        if _validate_ident(table, tables) is None:
+            return {"error": f"unknown table: {table}"}
+        cols = _table_columns(con, table)
+        col_names = {c["name"] for c in cols}
+        pk_cols = [c["name"] for c in cols if c["pk"] > 0]
+        if not pk_cols:
+            return {"error": f"table {table!r} has no primary key; cannot edit by row"}
+
+        # Validate pk has every pk column and all values are scalars.
+        missing = [p for p in pk_cols if p not in pk]
+        if missing:
+            return {"error": f"missing primary key columns: {missing}"}
+
+        # Validate update columns exist and aren't part of the primary key
+        # (changing a PK column would silently break joins/foreign refs).
+        bad = [c for c in updates if c not in col_names]
+        if bad:
+            return {"error": f"unknown columns: {bad}"}
+        pk_update = [c for c in updates if c in pk_cols]
+        if pk_update:
+            return {"error": f"cannot edit primary key columns: {pk_update}"}
+
+        set_sql = ", ".join(f"{_q(c)} = ?" for c in updates)
+        where_sql = " AND ".join(f"{_q(c)} = ?" for c in pk_cols)
+        sql = f"UPDATE {_q(table)} SET {set_sql} WHERE {where_sql}"
+        params = list(updates.values()) + [pk[c] for c in pk_cols]
+        cur = con.execute(sql, params)
+        con.commit()
+        return {"updated": cur.rowcount}
+    finally:
+        con.close()
+
+
+async def handle_list_tables(request: web.Request) -> web.Response:
+    """GET /api/sessions/{session_id}/colony/data/tables"""
+    session, err = resolve_session(request)
+    if err:
+        return err
+    db_path = _resolve_progress_db(session)
+    if db_path is None:
+        return web.json_response({"tables": []})
+    tables = await asyncio.to_thread(_read_tables_overview, db_path)
+    return web.json_response({"tables": tables})
+
+
+async def handle_table_rows(request: web.Request) -> web.Response:
+    """GET /api/sessions/{session_id}/colony/data/tables/{table}/rows"""
+    session, err = resolve_session(request)
+    if err:
+        return err
+    db_path = _resolve_progress_db(session)
+    if db_path is None:
+        return web.json_response({"error": "no progress.db"}, status=404)
+
+    table = request.match_info["table"]
+    # Clamp limit: 500 is enough for the grid's virtualization window;
+    # a larger cap would make accidental full-table loads cheap.
+    try:
+        limit = max(1, min(500, int(request.query.get("limit", "100"))))
+        offset = max(0, int(request.query.get("offset", "0")))
+    except ValueError:
+        return web.json_response({"error": "invalid limit/offset"}, status=400)
+    order_by = request.query.get("order_by") or None
+    order_dir = request.query.get("order_dir", "asc")
+
+    result = await asyncio.to_thread(
+        _read_table_rows, db_path, table, limit, offset, order_by, order_dir
+    )
+    if "error" in result:
+        return web.json_response(result, status=400)
+    return web.json_response(result)
+
+
+async def handle_update_row(request: web.Request) -> web.Response:
+    """PATCH /api/sessions/{session_id}/colony/data/tables/{table}/rows
+
+    Body: ``{"pk": {col: value, ...}, "updates": {col: value, ...}}``.
+    """
+    session, err = resolve_session(request)
+    if err:
+        return err
+    db_path = _resolve_progress_db(session)
+    if db_path is None:
+        return web.json_response({"error": "no progress.db"}, status=404)
+
+    try:
+        body = await request.json()
+    except Exception:
+        return web.json_response({"error": "invalid JSON body"}, status=400)
+    pk = body.get("pk") or {}
+    updates = body.get("updates") or {}
+    if not isinstance(pk, dict) or not isinstance(updates, dict):
+        return web.json_response({"error": "pk and updates must be objects"}, status=400)
+
+    table = request.match_info["table"]
+    result = await asyncio.to_thread(_update_table_row, db_path, table, pk, updates)
+    if "error" in result:
+        return web.json_response(result, status=400)
+    return web.json_response(result)
+
+
+def register_routes(app: web.Application) -> None:
+    """Register colony worker routes."""
+    app.router.add_get("/api/sessions/{session_id}/workers", handle_list_workers)
+    app.router.add_get(
+        "/api/sessions/{session_id}/colony/skills", handle_list_colony_skills
+    )
+    app.router.add_get(
+        "/api/sessions/{session_id}/colony/tools", handle_list_colony_tools
+    )
+    app.router.add_get(
+        "/api/sessions/{session_id}/colony/progress/snapshot",
+        handle_progress_snapshot,
+    )
+    app.router.add_get(
+        "/api/sessions/{session_id}/colony/progress/stream",
+        handle_progress_stream,
+    )
+    app.router.add_get(
+        "/api/sessions/{session_id}/colony/data/tables", handle_list_tables
+    )
+    app.router.add_get(
+        "/api/sessions/{session_id}/colony/data/tables/{table}/rows",
+        handle_table_rows,
+    )
+    app.router.add_patch(
+        "/api/sessions/{session_id}/colony/data/tables/{table}/rows",
+        handle_update_row,
+    )

core/framework/server/routes_config.py

@@ -281,9 +281,7 @@ def _get_subscription_token(sub_id: str) -> str | None:
     return None
 
 
-def _hot_swap_sessions(
-    request: web.Request, full_model: str, api_key: str | None, api_base: str | None
-) -> int:
+def _hot_swap_sessions(request: web.Request, full_model: str, api_key: str | None, api_base: str | None) -> int:
     """Hot-swap the LLM on all running sessions. Returns count of swapped sessions.
 
     Also refreshes the SessionManager's default model so that subsequent
@@ -363,9 +361,7 @@ async def handle_update_llm_config(request: web.Request) -> web.Response:
         # ── Subscription mode ────────────────────────────────────────
         sub = _SUBSCRIPTION_MAP.get(subscription_id)
         if not sub:
-            return web.json_response(
-                {"error": f"Unknown subscription: {subscription_id}"}, status=400
-            )
+            return web.json_response({"error": f"Unknown subscription: {subscription_id}"}, status=400)
 
         preset = get_preset(subscription_id)
         # Subscriptions use the fixed model from their preset (no model switching)
@@ -432,9 +428,7 @@ async def handle_update_llm_config(request: web.Request) -> web.Response:
         provider = body.get("provider")
         model = body.get("model")
         if not provider or not model:
-            return web.json_response(
-                {"error": "Both 'provider' and 'model' are required"}, status=400
-            )
+            return web.json_response({"error": "Both 'provider' and 'model' are required"}, status=400)
 
         # Look up token limits from catalogue
         model_info = _find_model_info(provider, model)
@@ -552,9 +546,7 @@ def _update_user_profile_memory(display_name: str, about: str) -> None:
 
         content = build_memory_document(
             name="User Profile",
-            description=f"User identity: {display_name}"
-            if display_name
-            else "User profile information",
+            description=f"User identity: {display_name}" if display_name else "User profile information",
             mem_type="profile",
             body=new_body if new_body else "No profile information yet.",
         )

core/framework/server/routes_credentials.py

@@ -216,9 +216,7 @@ async def handle_check_agent(request: web.Request) -> web.Response:
         ensure_credential_key_env()
 
         nodes = load_agent_nodes(agent_path)
-        result = validate_agent_credentials(
-            nodes, verify=verify, raise_on_error=False, force_refresh=True
-        )
+        result = validate_agent_credentials(nodes, verify=verify, raise_on_error=False, force_refresh=True)
 
         # If any credential needs Aden, include ADEN_API_KEY as a first-class row
         if any(c.aden_supported for c in result.credentials):
@@ -291,13 +289,15 @@ def _collect_accounts_by_provider() -> dict[str, list[dict]]:
             provider = acct.get("provider", "")
             if not provider:
                 continue
-            grouped.setdefault(provider, []).append({
-                "provider": provider,
-                "alias": acct.get("alias", ""),
-                "identity": acct.get("identity", {}) or {},
-                "source": acct.get("source", "aden"),
-                "credential_id": acct.get("credential_id", provider),
-            })
+            grouped.setdefault(provider, []).append(
+                {
+                    "provider": provider,
+                    "alias": acct.get("alias", ""),
+                    "identity": acct.get("identity", {}) or {},
+                    "source": acct.get("source", "aden"),
+                    "credential_id": acct.get("credential_id", provider),
+                }
+            )
         return grouped
     except Exception:
         logger.debug("Failed to collect accounts for specs response", exc_info=True)
@@ -327,17 +327,17 @@ async def handle_resync_credentials(request: web.Request) -> web.Response:
 
         loop = asyncio.get_running_loop()
         # _presync_aden_tokens makes blocking HTTP calls to the Aden server.
-        await loop.run_in_executor(
-            None, lambda: _presync_aden_tokens(CREDENTIAL_SPECS, force=True)
-        )
+        await loop.run_in_executor(None, lambda: _presync_aden_tokens(CREDENTIAL_SPECS, force=True))
 
         _invalidate_queen_credentials_cache(request)
 
         accounts_by_provider = _collect_accounts_by_provider()
-        return web.json_response({
-            "synced": True,
-            "accounts_by_provider": accounts_by_provider,
-        })
+        return web.json_response(
+            {
+                "synced": True,
+                "accounts_by_provider": accounts_by_provider,
+            }
+        )
     except Exception as exc:
         logger.exception("Error during credential resync: %s", exc)
         return web.json_response(
@@ -366,9 +366,7 @@ async def handle_list_specs(request: web.Request) -> web.Response:
             _presync_aden_tokens(CREDENTIAL_SPECS)
 
         # Build composite store (env → encrypted file)
-        env_mapping = {
-            (spec.credential_id or name): spec.env_var for name, spec in CREDENTIAL_SPECS.items()
-        }
+        env_mapping = {(spec.credential_id or name): spec.env_var for name, spec in CREDENTIAL_SPECS.items()}
         env_storage = EnvVarStorage(env_mapping=env_mapping)
         if os.environ.get("HIVE_CREDENTIAL_KEY"):
             storage = CompositeStorage(primary=env_storage, fallbacks=[EncryptedFileStorage()])
@@ -396,21 +394,23 @@ async def handle_list_specs(request: web.Request) -> web.Response:
                 available = len(accounts) > 0
             else:
                 available = store.is_available(cred_id)
-            specs.append({
-                "credential_name": name,
-                "credential_id": cred_id,
-                "env_var": spec.env_var,
-                "description": spec.description,
-                "help_url": spec.help_url,
-                "api_key_instructions": spec.api_key_instructions,
-                "tools": spec.tools,
-                "aden_supported": spec.aden_supported,
-                "direct_api_key_supported": spec.direct_api_key_supported,
-                "credential_key": spec.credential_key,
-                "credential_group": spec.credential_group,
-                "available": available,
-                "accounts": accounts,
-            })
+            specs.append(
+                {
+                    "credential_name": name,
+                    "credential_id": cred_id,
+                    "env_var": spec.env_var,
+                    "description": spec.description,
+                    "help_url": spec.help_url,
+                    "api_key_instructions": spec.api_key_instructions,
+                    "tools": spec.tools,
+                    "aden_supported": spec.aden_supported,
+                    "direct_api_key_supported": spec.direct_api_key_supported,
+                    "credential_key": spec.credential_key,
+                    "credential_group": spec.credential_group,
+                    "available": available,
+                    "accounts": accounts,
+                }
+            )
 
         # Include aden_api_key synthetic row if any spec uses Aden
         if any_aden:
@@ -422,7 +422,9 @@ async def handle_list_specs(request: web.Request) -> web.Response:
                     "env_var": "ADEN_API_KEY",
                     "description": "API key from the Developers tab in Settings",
                     "help_url": "https://hive.adenhq.com/",
-                    "api_key_instructions": "1. Go to hive.adenhq.com\n2. Open Settings > Developers\n3. Copy your API key",
+                    "api_key_instructions": (
+                        "1. Go to hive.adenhq.com\n2. Open Settings > Developers\n3. Copy your API key"
+                    ),
                     "tools": [],
                     "aden_supported": True,
                     "direct_api_key_supported": True,
@@ -459,16 +461,12 @@ async def handle_validate_key(request: web.Request) -> web.Response:
     api_key = body.get("api_key", "").strip()
 
     if not provider_id or not api_key:
-        return web.json_response(
-            {"error": "provider_id and api_key are required"}, status=400
-        )
+        return web.json_response({"error": "provider_id and api_key are required"}, status=400)
 
     try:
         checker = _get_llm_key_providers().get(provider_id)
         if not checker:
-            return web.json_response(
-                {"valid": True, "message": f"No health check for {provider_id}"}
-            )
+            return web.json_response({"valid": True, "message": f"No health check for {provider_id}"})
 
         loop = asyncio.get_running_loop()
         result = await loop.run_in_executor(None, lambda: checker(api_key))
@@ -476,9 +474,7 @@ async def handle_validate_key(request: web.Request) -> web.Response:
 
     except Exception as exc:
         logger.warning("LLM key validation failed for %s: %s", provider_id, exc)
-        return web.json_response(
-            {"valid": None, "message": f"Validation error: {exc}"}
-        )
+        return web.json_response({"valid": None, "message": f"Validation error: {exc}"})
 
 
 def register_routes(app: web.Application) -> None:

core/framework/server/routes_events.py

@@ -51,13 +51,18 @@ DEFAULT_EVENT_TYPES = [
 # Keepalive interval in seconds
 KEEPALIVE_INTERVAL = 15.0
 
-# Phase 5 SSE filter: parallel-worker streams (stream_id="worker:{uuid}")
-# publish high-frequency LLM deltas / tool calls that would flood the
-# user's queen DM chat. We let only this small allowlist of worker
-# events through to the queen-chat SSE so the frontend can render
-# fan-out lifecycle and structured fan-in reports without seeing the
-# raw worker chatter. Per-worker SSE panels (Phase 5b) bypass this
-# filter via a dedicated /workers/{worker_id}/events route.
+# Session-SSE worker filter: workers run outside the queen's DM
+# chat. Worker activity is observable via the dedicated
+# ``/api/workers/{worker_id}/events`` per-worker SSE route, not via
+# the session chat. This keeps the queen↔user conversation clean of
+# tool-call chatter regardless of whether the worker was spawned by
+# ``run_agent_with_input`` (stream_id="worker") or
+# ``run_parallel_workers`` (stream_id="worker:{uuid}").
+#
+# Lifecycle events the frontend needs for fan-in summaries
+# (SUBAGENT_REPORT, EXECUTION_COMPLETED, EXECUTION_FAILED) are still
+# allowed through so the queen can show "N workers done" surfaces
+# without exposing the per-turn chatter.
 _WORKER_EVENT_ALLOWLIST = {
     EventType.SUBAGENT_REPORT.value,
     EventType.EXECUTION_COMPLETED.value,
@@ -66,9 +71,17 @@ _WORKER_EVENT_ALLOWLIST = {
 
 
 def _is_worker_noise(evt_dict: dict) -> bool:
-    """True if the event is a parallel-worker event we should drop."""
+    """True if the event belongs to a worker stream and should not
+    surface in the queen DM chat.
+
+    Matches any stream starting with ``worker`` — both the bare
+    ``"worker"`` tag used by single-worker spawns and the
+    ``"worker:{uuid}"`` tag used by parallel fan-outs. The allowlist
+    carves out the three terminal/lifecycle events the UI still
+    needs to render fan-in summaries.
+    """
     stream_id = evt_dict.get("stream_id") or ""
-    if not stream_id.startswith("worker:"):
+    if not stream_id.startswith("worker"):
         return False
     return evt_dict.get("type") not in _WORKER_EVENT_ALLOWLIST
 
@@ -106,6 +119,22 @@ async def handle_events(request: web.Request) -> web.StreamResponse:
     event_bus = session.event_bus
     event_types = _parse_event_types(request.query.get("types"))
 
+    # Worker-noise filter is phase-aware. In DM mode (queen phase
+    # "independent") the queen's chat should stay clean — workers
+    # are invisible. In colony mode (phase "working"/"reviewing")
+    # the user IS supervising the workers and wants to see the
+    # tool-call/text-delta chatter as it happens. Sample the phase
+    # once at SSE connect; if the queen later transitions the
+    # frontend reconnects.
+    def _should_filter_worker_noise() -> bool:
+        phase_state = getattr(session, "phase_state", None)
+        if phase_state is None:
+            return True  # unknown phase → be conservative, filter noise
+        phase = getattr(phase_state, "phase", "independent")
+        return phase == "independent"
+
+    filter_worker_noise = _should_filter_worker_noise()
+
     # Per-client buffer queue
     queue: asyncio.Queue = asyncio.Queue(maxsize=1000)
 
@@ -132,7 +161,7 @@ async def handle_events(request: web.Request) -> web.StreamResponse:
             return
 
         evt_dict = event.to_dict()
-        if _is_worker_noise(evt_dict):
+        if filter_worker_noise and _is_worker_noise(evt_dict):
             return
         if evt_dict.get("type") in _CRITICAL_EVENTS:
             try:
@@ -159,9 +188,7 @@ async def handle_events(request: web.Request) -> web.StreamResponse:
 
     sse = SSEResponse()
     await sse.prepare(request)
-    logger.info(
-        "SSE connected: session='%s', sub_id='%s', types=%d", session.id, sub_id, len(event_types)
-    )
+    logger.info("SSE connected: session='%s', sub_id='%s', types=%d", session.id, sub_id, len(event_types))
 
     # Replay buffered events that were published before this SSE connected.
     # The EventBus keeps a history ring-buffer; we replay the subset that
@@ -191,7 +218,7 @@ async def handle_events(request: web.Request) -> web.StreamResponse:
     for past_event in event_bus._event_history:
         if past_event.type.value in replay_types:
             past_dict = past_event.to_dict()
-            if _is_worker_noise(past_dict):
+            if filter_worker_noise and _is_worker_noise(past_dict):
                 continue
             try:
                 queue.put_nowait(past_dict)
@@ -215,9 +242,7 @@ async def handle_events(request: web.Request) -> web.StreamResponse:
                 await sse.send_event(data)
                 event_count += 1
                 if event_count == 1:
-                    logger.info(
-                        "SSE first event: session='%s', type='%s'", session.id, data.get("type")
-                    )
+                    logger.info("SSE first event: session='%s', type='%s'", session.id, data.get("type"))
             except TimeoutError:
                 try:
                     await sse.send_keepalive()

core/framework/server/routes_execution.py

@@ -3,6 +3,7 @@
 import asyncio
 import json
 import logging
+from datetime import UTC
 from typing import Any
 
 from aiohttp import web
@@ -52,12 +53,19 @@ _WORKER_INHERITED_TOOLS: frozenset[str] = frozenset(
 
 # Queen-lifecycle tools that are registered into the queen's tool registry
 # but NOT listed in any _QUEEN_*_TOOLS phase list (they're reachable only via
-# explicit registration, not phase-based gating). These must still be stripped
-# from forked worker configs.
+# explicit registration or as frontend-visible helpers, not phase-based
+# gating). These must still be stripped from forked / parallel-spawned
+# worker tool inventories.
 _QUEEN_LIFECYCLE_EXTRAS: frozenset[str] = frozenset(
     {
-        "stop_worker_and_plan",
-        "stop_worker_and_review",
+        # Phase-transition wrappers (method variants are on QueenPhaseState
+        # but the queen also sees them as tools).
+        "switch_to_reviewing",
+        "switch_to_independent",
+        # Frontend helpers that live outside phase lists.
+        "list_credentials",
+        "get_worker_health_summary",
+        "enqueue_task",
     }
 )
 
@@ -77,22 +85,16 @@ def _resolve_queen_only_tools() -> frozenset[str]:
     nodes package is loaded.
     """
     from framework.agents.queen.nodes import (
-        _QUEEN_BUILDING_TOOLS,
-        _QUEEN_EDITING_TOOLS,
         _QUEEN_INDEPENDENT_TOOLS,
-        _QUEEN_PLANNING_TOOLS,
-        _QUEEN_RUNNING_TOOLS,
-        _QUEEN_STAGING_TOOLS,
+        _QUEEN_REVIEWING_TOOLS,
+        _QUEEN_WORKING_TOOLS,
     )
 
     union: set[str] = set()
     for tool_list in (
-        _QUEEN_PLANNING_TOOLS,
-        _QUEEN_BUILDING_TOOLS,
-        _QUEEN_STAGING_TOOLS,
-        _QUEEN_RUNNING_TOOLS,
-        _QUEEN_EDITING_TOOLS,
         _QUEEN_INDEPENDENT_TOOLS,
+        _QUEEN_WORKING_TOOLS,
+        _QUEEN_REVIEWING_TOOLS,
     ):
         union.update(tool_list)
     derived = union - _WORKER_INHERITED_TOOLS
@@ -117,9 +119,7 @@ async def handle_trigger(request: web.Request) -> web.Response:
     if session.runner:
         loop = asyncio.get_running_loop()
         try:
-            await loop.run_in_executor(
-                None, lambda: validate_agent_credentials(session.runner.graph.nodes)
-            )
+            await loop.run_in_executor(None, lambda: validate_agent_credentials(session.runner.graph.nodes))
         except Exception as e:
             agent_path = str(session.worker_path) if session.worker_path else ""
             resp = _credential_error_response(e, agent_path)
@@ -129,9 +129,7 @@ async def handle_trigger(request: web.Request) -> web.Response:
         # Resync MCP servers if credentials were added since the worker loaded
         # (e.g. user connected an OAuth account mid-session via Aden UI).
         try:
-            await loop.run_in_executor(
-                None, lambda: session.runner._tool_registry.resync_mcp_servers_if_needed()
-            )
+            await loop.run_in_executor(None, lambda: session.runner._tool_registry.resync_mcp_servers_if_needed())
         except Exception as e:
             logger.warning("MCP resync failed: %s", e)
 
@@ -156,9 +154,9 @@ async def handle_trigger(request: web.Request) -> web.Response:
         if node and hasattr(node, "cancel_current_turn"):
             node.cancel_current_turn()
 
-    # Switch queen to running phase (mirrors run_agent_with_input tool behavior)
+    # Switch queen to working phase — workers just started from the UI.
     if session.phase_state is not None:
-        await session.phase_state.switch_to_running(source="frontend")
+        await session.phase_state.switch_to_working(source="frontend")
 
     return web.json_response({"execution_id": execution_id})
 
@@ -228,23 +226,14 @@ async def handle_chat(request: web.Request) -> web.Response:
             type(queen_executor.node_registry),
             id(queen_executor.node_registry),
         )
-        logger.debug(
-            "[handle_chat] node_registry keys: %s", list(queen_executor.node_registry.keys())
-        )
+        logger.debug("[handle_chat] node_registry keys: %s", list(queen_executor.node_registry.keys()))
         node = queen_executor.node_registry.get("queen")
-        logger.debug(
-            "[handle_chat] node=%s, node_type=%s", node, type(node).__name__ if node else None
-        )
-        logger.debug(
-            "[handle_chat] has_inject_event=%s", hasattr(node, "inject_event") if node else False
-        )
+        logger.debug("[handle_chat] node=%s, node_type=%s", node, type(node).__name__ if node else None)
+        logger.debug("[handle_chat] has_inject_event=%s", hasattr(node, "inject_event") if node else False)
 
         # Race condition: executor exists but node not created yet (still initializing)
         if node is None and session.queen_task is not None and not session.queen_task.done():
-            logger.warning(
-                "[handle_chat] Queen executor exists but node"
-                " not ready yet (initializing). Waiting..."
-            )
+            logger.warning("[handle_chat] Queen executor exists but node not ready yet (initializing). Waiting...")
             # Wait a short time for initialization to progress
             import asyncio
 
@@ -302,16 +291,12 @@ async def handle_chat(request: web.Request) -> web.Response:
                 )
             else:
                 logger.error(
-                    "[handle_chat] CRITICAL: Queen node exists"
-                    " but missing inject_event!"
-                    " node_attrs=%s",
+                    "[handle_chat] CRITICAL: Queen node exists but missing inject_event! node_attrs=%s",
                     [a for a in dir(node) if not a.startswith("_")],
                 )
 
     # Queen is dead — try to revive her
-    logger.warning(
-        "[handle_chat] Queen is dead for session '%s', reviving on /chat request", session.id
-    )
+    logger.warning("[handle_chat] Queen is dead for session '%s', reviving on /chat request", session.id)
     manager: Any = request.app["manager"]
     try:
         logger.debug("[handle_chat] Calling manager.revive_queen()...")
@@ -322,9 +307,7 @@ async def handle_chat(request: web.Request) -> web.Response:
         _revived_executor = session.queen_executor
         _revived_node = _revived_executor.node_registry.get("queen") if _revived_executor else None
         if _revived_node is not None and hasattr(_revived_node, "inject_event"):
-            await _revived_node.inject_event(
-                message, is_client_input=True, image_content=image_content
-            )
+            await _revived_node.inject_event(message, is_client_input=True, image_content=image_content)
         return web.json_response(
             {
                 "status": "queen_revived",
@@ -508,9 +491,10 @@ async def handle_pause(request: web.Request) -> web.Response:
     # Pause timers so the next tick doesn't restart execution
     runtime.pause_timers()
 
-    # Switch to staging (agent still loaded, ready to re-run)
+    # Switch to reviewing — workers stopped, queen now helps the user
+    # interpret whatever they produced and decide next steps.
     if session.phase_state is not None:
-        await session.phase_state.switch_to_staging(source="frontend")
+        await session.phase_state.switch_to_reviewing(source="frontend")
 
     return web.json_response(
         {
@@ -552,9 +536,7 @@ async def handle_stop(request: web.Request) -> web.Response:
                     if hasattr(node, "cancel_current_turn"):
                         node.cancel_current_turn()
 
-            cancelled = await stream.cancel_execution(
-                execution_id, reason="Execution stopped by user"
-            )
+            cancelled = await stream.cancel_execution(execution_id, reason="Execution stopped by user")
             if cancelled:
                 # Cancel queen's in-progress LLM turn
                 if session.queen_executor:
@@ -562,9 +544,10 @@ async def handle_stop(request: web.Request) -> web.Response:
                     if node and hasattr(node, "cancel_current_turn"):
                         node.cancel_current_turn()
 
-                # Switch to staging (agent still loaded, ready to re-run)
+                # Switch to reviewing — worker stopped, queen helps the user
+                # interpret what happened and decide next steps.
                 if session.phase_state is not None:
-                    await session.phase_state.switch_to_staging(source="frontend")
+                    await session.phase_state.switch_to_reviewing(source="frontend")
 
                 return web.json_response(
                     {
@@ -725,17 +708,64 @@ async def fork_session_into_colony(
     import asyncio
     import json
     import shutil
-    from datetime import datetime, timezone
+    from datetime import datetime
     from pathlib import Path
 
     from framework.agent_loop.agent_loop import AgentLoop, LoopConfig
     from framework.agent_loop.types import AgentContext, AgentSpec
     from framework.host.progress_db import ensure_progress_db, seed_tasks
     from framework.server.session_manager import _queen_session_dir
-    from framework.storage.conversation_store import FileConversationStore
 
-    queen_loop: AgentLoop = session.queen_executor.node_registry["queen"]
+    # Diagnostic capture: when the fork fails here we want to know which
+    # piece of queen state was missing (executor cleared vs. node missing
+    # vs. _last_ctx never stamped). Without this, callers only see
+    # "'NoneType' object has no attribute 'node_registry'" with no hint
+    # whether the queen loop exited, is mid-revive, or ran a different
+    # path that never ran AgentLoop._execute_impl.
+    queen_executor = getattr(session, "queen_executor", None)
+    queen_task = getattr(session, "queen_task", None)
+    phase_state_dbg = getattr(session, "phase_state", None)
+    logger.info(
+        "[fork_session_into_colony] session=%s colony=%s "
+        "queen_executor=%s queen_task=%s queen_task_done=%s "
+        "phase=%s queen_name=%s",
+        session.id,
+        colony_name,
+        queen_executor,
+        queen_task,
+        queen_task.done() if queen_task is not None else None,
+        getattr(phase_state_dbg, "phase", None),
+        getattr(session, "queen_name", None),
+    )
+
+    if queen_executor is None:
+        raise RuntimeError(
+            f"queen_executor is None for session {session.id!r} — the "
+            "queen loop isn't running right now. Wait for the queen to "
+            "come back (or send her a chat message to revive her) and "
+            "retry create_colony. The skill folder is already written, "
+            "so the retry is free."
+        )
+
+    node_registry = getattr(queen_executor, "node_registry", None)
+    if not isinstance(node_registry, dict) or "queen" not in node_registry:
+        raise RuntimeError(
+            f"queen node is missing from the executor's registry for "
+            f"session {session.id!r} (registry keys="
+            f"{list(node_registry.keys()) if isinstance(node_registry, dict) else type(node_registry).__name__}"
+            "). The queen loop is in an initialization or teardown "
+            "window; retry after a moment."
+        )
+
+    queen_loop: AgentLoop = node_registry["queen"]
     queen_ctx: AgentContext = getattr(queen_loop, "_last_ctx", None)
+    if queen_ctx is None:
+        logger.warning(
+            "[fork_session_into_colony] queen_loop has no _last_ctx yet "
+            "(session=%s) — falling back to empty tool/skill snapshot; "
+            "the forked worker will inherit no tools.",
+            session.id,
+        )
 
     colony_dir = Path.home() / ".hive" / "colonies" / colony_name
     is_new = not colony_dir.exists()
@@ -882,11 +912,9 @@ async def fork_session_into_colony(
         "queen_id": getattr(phase_state, "queen_id", "") if phase_state else "",
         "loop_config": queen_lc_config,
         "spawned_from": session.id,
-        "spawned_at": datetime.now(timezone.utc).isoformat(),
+        "spawned_at": datetime.now(UTC).isoformat(),
     }
-    worker_config_path.write_text(
-        json.dumps(worker_meta, indent=2, ensure_ascii=False), encoding="utf-8"
-    )
+    worker_config_path.write_text(json.dumps(worker_meta, indent=2, ensure_ascii=False), encoding="utf-8")
 
     # ── 3. Duplicate queen session into colony ───────────────────
     # Copy the queen's full session directory (conversations, events,
@@ -912,9 +940,7 @@ async def fork_session_into_colony(
     dest_queen_dir = _queen_session_dir(colony_session_id, queen_name)
 
     if source_queen_dir.exists():
-        await asyncio.to_thread(
-            shutil.copytree, source_queen_dir, dest_queen_dir, dirs_exist_ok=True
-        )
+        await asyncio.to_thread(shutil.copytree, source_queen_dir, dest_queen_dir, dirs_exist_ok=True)
         # Update the duplicated meta.json to point to the colony
         dest_meta_path = dest_queen_dir / "meta.json"
         dest_meta: dict = {}
@@ -928,9 +954,7 @@ async def fork_session_into_colony(
         dest_meta["queen_id"] = queen_name
         dest_meta["forked_from"] = session.id
         dest_meta["colony_fork"] = True  # exclude from queen DM history
-        dest_meta_path.write_text(
-            json.dumps(dest_meta, ensure_ascii=False), encoding="utf-8"
-        )
+        dest_meta_path.write_text(json.dumps(dest_meta, ensure_ascii=False), encoding="utf-8")
         logger.info(
             "Duplicated queen session %s -> %s for colony '%s'",
             session.id,
@@ -944,9 +968,7 @@ async def fork_session_into_colony(
         worker_conv_dir = worker_storage / "conversations"
         source_conv_dir = dest_queen_dir / "conversations"
         if source_conv_dir.exists():
-            await asyncio.to_thread(
-                shutil.copytree, source_conv_dir, worker_conv_dir, dirs_exist_ok=True
-            )
+            await asyncio.to_thread(shutil.copytree, source_conv_dir, worker_conv_dir, dirs_exist_ok=True)
             logger.info("Copied queen conversations to worker storage %s", worker_conv_dir)
     else:
         logger.warning(
@@ -966,12 +988,12 @@ async def fork_session_into_colony(
     metadata["queen_name"] = queen_name
     metadata["queen_session_id"] = colony_session_id
     metadata["source_session_id"] = session.id
-    metadata.setdefault("created_at", datetime.now(timezone.utc).isoformat())
-    metadata["updated_at"] = datetime.now(timezone.utc).isoformat()
+    metadata.setdefault("created_at", datetime.now(UTC).isoformat())
+    metadata["updated_at"] = datetime.now(UTC).isoformat()
     metadata.setdefault("workers", {})
     metadata["workers"][worker_name] = {
         "task": worker_task[:100],
-        "spawned_at": datetime.now(timezone.utc).isoformat(),
+        "spawned_at": datetime.now(UTC).isoformat(),
     }
     metadata_path.write_text(json.dumps(metadata, indent=2, ensure_ascii=False), encoding="utf-8")
 
@@ -989,9 +1011,7 @@ async def fork_session_into_colony(
     qmeta["agent_name"] = colony_name.replace("_", " ").title()
     try:
         source_meta_path.parent.mkdir(parents=True, exist_ok=True)
-        source_meta_path.write_text(
-            json.dumps(qmeta, ensure_ascii=False), encoding="utf-8"
-        )
+        source_meta_path.write_text(json.dumps(qmeta, ensure_ascii=False), encoding="utf-8")
     except OSError:
         pass
 

core/framework/server/routes_queens.py

@@ -25,17 +25,6 @@ from framework.config import QUEENS_DIR
 logger = logging.getLogger(__name__)
 
 
-async def _stop_live_sessions(manager, keep_session_id: str | None = None) -> None:
-    """Stop live sessions so only the selected queen session remains active."""
-    for session in list(manager.list_sessions()):
-        if keep_session_id and session.id == keep_session_id:
-            continue
-        try:
-            await manager.stop_session(session.id)
-        except Exception:
-            logger.debug("Failed to stop session %s during queen switch", session.id)
-
-
 def _read_queen_session_meta(queen_id: str, session_id: str) -> dict[str, Any]:
     """Return persisted metadata for a queen session when available."""
     session_dir = QUEENS_DIR / queen_id / "sessions" / session_id
@@ -148,9 +137,7 @@ def _transform_profile_for_api(profile: dict) -> dict:
             details.append(f"Drive: {hidden['deep_motive']}")
         if hidden.get("behavioral_mapping"):
             details.append(f"Approach: {hidden['behavioral_mapping']}")
-        experience.append(
-            {"role": f"{profile.get('title', 'Executive Advisor')}", "details": details}
-        )
+        experience.append({"role": f"{profile.get('title', 'Executive Advisor')}", "details": details})
     if experience:
         result["experience"] = experience
 
@@ -161,9 +148,7 @@ def _transform_profile_for_api(profile: dict) -> dict:
     # Signature achievement from world_lore
     world_lore = profile.get("world_lore", {})
     if world_lore.get("habitat"):
-        result["signature_achievement"] = (
-            f"{world_lore['habitat']}. {world_lore.get('lexicon', '')}".strip()
-        )
+        result["signature_achievement"] = f"{world_lore['habitat']}. {world_lore.get('lexicon', '')}".strip()
 
     return result
 
@@ -222,9 +207,16 @@ async def handle_queen_session(request: web.Request) -> web.Response:
     initial_prompt = body.get("initial_prompt")
     initial_phase = body.get("initial_phase")
 
-    # 1. Check for an existing live session bound to this queen.
+    # 1. Check for an existing live DM session bound to this queen.
+    # Skip colony sessions: a colony forked from this queen also carries
+    # queen_name == queen_id, but it has a worker loaded (colony_id /
+    # worker_path set) and is the colony's chat, not the queen's DM.
     for session in manager.list_sessions():
-        if session.queen_name == queen_id:
+        if (
+            session.queen_name == queen_id
+            and session.colony_id is None
+            and session.worker_path is None
+        ):
             return web.json_response(
                 {
                     "session_id": session.id,
@@ -233,10 +225,6 @@ async def handle_queen_session(request: web.Request) -> web.Response:
                 }
             )
 
-    # Stop any live sessions bound to a different queen so only one queen
-    # is active at a time.
-    await _stop_live_sessions(manager)
-
     # 2. Find the most recent cold session for this queen and resume it.
     # IMPORTANT: skip sessions that don't belong in the queen DM:
     #   - ``colony_fork: true`` -- duplicates created by handle_colony_spawn
@@ -327,7 +315,6 @@ async def handle_select_queen_session(request: web.Request) -> web.Response:
 
     live_session = manager.get_session(target_session_id)
     if live_session is not None:
-        await _stop_live_sessions(manager, keep_session_id=target_session_id)
         return web.json_response(
             {
                 "session_id": live_session.id,
@@ -336,11 +323,11 @@ async def handle_select_queen_session(request: web.Request) -> web.Response:
             }
         )
 
-    await _stop_live_sessions(manager)
-
     meta = _read_queen_session_meta(queen_id, target_session_id)
     agent_path = meta.get("agent_path")
-    initial_phase = None if agent_path else "independent"
+    # Colony resume (agent loaded) → "working" (3-phase target).
+    # Standalone queen resume → "independent" (DM mode).
+    initial_phase = "working" if agent_path else "independent"
     session = await _create_bound_queen_session(
         manager,
         queen_id,
@@ -371,7 +358,6 @@ async def handle_new_queen_session(request: web.Request) -> web.Response:
     initial_prompt = body.get("initial_prompt")
     initial_phase = body.get("initial_phase") or "independent"
 
-    await _stop_live_sessions(manager)
     session = await manager.create_session(
         initial_prompt=initial_prompt,
         queen_name=queen_id,

core/framework/server/routes_sessions.py

@@ -59,9 +59,7 @@ def _session_to_live_dict(session) -> dict:
         "loaded_at": session.loaded_at,
         "uptime_seconds": round(time.time() - session.loaded_at, 1),
         "intro_message": getattr(session.runner, "intro_message", "") or "",
-        "queen_phase": phase_state.phase
-        if phase_state
-        else ("staging" if session.colony_runtime else "planning"),
+        "queen_phase": phase_state.phase if phase_state else ("staging" if session.colony_runtime else "planning"),
         "queen_supports_images": supports_image_tool_results(queen_model) if queen_model else True,
         "queen_id": getattr(phase_state, "queen_id", None) if phase_state else None,
         "queen_name": (phase_state.queen_profile or {}).get("name") if phase_state else None,
@@ -229,11 +227,7 @@ async def handle_get_live_session(request: web.Request) -> web.Response:
                 "entry_node": ep.entry_node,
                 "trigger_type": ep.trigger_type,
                 "trigger_config": ep.trigger_config,
-                **(
-                    {"next_fire_in": nf}
-                    if (nf := rt.get_timer_next_fire_in(ep.id)) is not None
-                    else {}
-                ),
+                **({"next_fire_in": nf} if (nf := rt.get_timer_next_fire_in(ep.id)) is not None else {}),
             }
             for ep in rt.get_entry_points()
         ]
@@ -383,11 +377,7 @@ async def handle_session_entry_points(request: web.Request) -> web.Response:
             "entry_node": ep.entry_node,
             "trigger_type": ep.trigger_type,
             "trigger_config": ep.trigger_config,
-            **(
-                {"next_fire_in": nf}
-                if rt and (nf := rt.get_timer_next_fire_in(ep.id)) is not None
-                else {}
-            ),
+            **({"next_fire_in": nf} if rt and (nf := rt.get_timer_next_fire_in(ep.id)) is not None else {}),
         }
         for ep in eps
     ]
@@ -468,21 +458,13 @@ async def handle_update_trigger_task(request: web.Request) -> web.Response:
                         )
                 except ImportError:
                     return web.json_response(
-                        {
-                            "error": (
-                                "croniter package not installed — cannot validate cron expression."
-                            )
-                        },
+                        {"error": ("croniter package not installed — cannot validate cron expression.")},
                         status=500,
                     )
                 merged_trigger_config.pop("interval_minutes", None)
             elif interval is None:
                 return web.json_response(
-                    {
-                        "error": (
-                            "Timer trigger needs 'cron' or 'interval_minutes' in trigger_config."
-                        )
-                    },
+                    {"error": ("Timer trigger needs 'cron' or 'interval_minutes' in trigger_config.")},
                     status=400,
                 )
             elif not isinstance(interval, (int, float)) or interval <= 0:
@@ -580,9 +562,7 @@ async def handle_activate_trigger(request: web.Request) -> web.Response:
         )
 
     if trigger_id in getattr(session, "active_trigger_ids", set()):
-        return web.json_response(
-            {"status": "already_active", "trigger_id": trigger_id}
-        )
+        return web.json_response({"status": "already_active", "trigger_id": trigger_id})
 
     from framework.tools.queen_lifecycle_tools import (
         _persist_active_triggers,
@@ -646,9 +626,7 @@ async def handle_deactivate_trigger(request: web.Request) -> web.Response:
 
     trigger_id = request.match_info["trigger_id"]
     if trigger_id not in getattr(session, "active_trigger_ids", set()):
-        return web.json_response(
-            {"status": "already_inactive", "trigger_id": trigger_id}
-        )
+        return web.json_response({"status": "already_inactive", "trigger_id": trigger_id})
 
     task = session.active_timer_tasks.pop(trigger_id, None)
     if task and not task.done():
@@ -933,9 +911,7 @@ async def handle_delete_agent(request: web.Request) -> web.Response:
         try:
             shutil.rmtree(resolved)
         except OSError as e:
-            return web.json_response(
-                {"error": f"Failed to delete agent directory: {e}"}, status=500
-            )
+            return web.json_response({"error": f"Failed to delete agent directory: {e}"}, status=500)
 
     return web.json_response({"deleted": str(resolved)})
 
@@ -998,9 +974,7 @@ def register_routes(app: web.Application) -> None:
     app.router.add_post("/api/sessions/{session_id}/reveal", handle_reveal_session_folder)
     app.router.add_get("/api/sessions/{session_id}/stats", handle_session_stats)
     app.router.add_get("/api/sessions/{session_id}/entry-points", handle_session_entry_points)
-    app.router.add_patch(
-        "/api/sessions/{session_id}/triggers/{trigger_id}", handle_update_trigger_task
-    )
+    app.router.add_patch("/api/sessions/{session_id}/triggers/{trigger_id}", handle_update_trigger_task)
     app.router.add_post(
         "/api/sessions/{session_id}/triggers/{trigger_id}/activate",
         handle_activate_trigger,

core/framework/server/routes_workers.py

@@ -70,13 +70,7 @@ async def handle_list_nodes(request: web.Request) -> web.Response:
         from pathlib import Path
 
         state_path = (
-            Path.home()
-            / ".hive"
-            / "agents"
-            / session.worker_path.name
-            / "sessions"
-            / worker_session_id
-            / "state.json"
+            Path.home() / ".hive" / "agents" / session.worker_path.name / "sessions" / worker_session_id / "state.json"
         )
         if state_path.exists():
             try:
@@ -97,8 +91,7 @@ async def handle_list_nodes(request: web.Request) -> web.Response:
                 pass
 
     edges = [
-        {"source": e.source, "target": e.target, "condition": e.condition, "priority": e.priority}
-        for e in graph.edges
+        {"source": e.source, "target": e.target, "condition": e.condition, "priority": e.priority} for e in graph.edges
     ]
     rt = session.colony_runtime
     entry_points = [
@@ -108,11 +101,7 @@ async def handle_list_nodes(request: web.Request) -> web.Response:
             "entry_node": ep.entry_node,
             "trigger_type": ep.trigger_type,
             "trigger_config": ep.trigger_config,
-            **(
-                {"next_fire_in": nf}
-                if rt and (nf := rt.get_timer_next_fire_in(ep.id)) is not None
-                else {}
-            ),
+            **({"next_fire_in": nf} if rt and (nf := rt.get_timer_next_fire_in(ep.id)) is not None else {}),
         }
         for ep in reg.entry_points.values()
     ]
@@ -247,12 +236,221 @@ async def handle_node_tools(request: web.Request) -> web.Response:
     return web.json_response({"tools": tools_out})
 
 
+# ---------------------------------------------------------------------------
+# Live worker control — list / stop a specific worker / stop all
+# ---------------------------------------------------------------------------
+
+
+def _active_colony(session):
+    """Return the session's unified ColonyRuntime (``session.colony``) if present.
+
+    All spawned workers (queen-overseer + run_parallel_workers fan-outs)
+    are hosted here. ``session.colony_runtime`` is a different concept
+    (loaded agent graph) and doesn't hold the live worker registry we
+    need to enumerate / stop.
+    """
+    return getattr(session, "colony", None)
+
+
+def _build_live_workers_payload(colony) -> list[dict]:
+    """Serialize the colony's current worker registry.
+
+    Extracted so both the one-shot ``GET /workers`` handler and the SSE
+    ``/workers/stream`` handler render the exact same shape.
+    """
+    if colony is None:
+        return []
+
+    now = time.monotonic()
+    payload: list[dict] = []
+    try:
+        workers = list(colony._workers.values())  # type: ignore[attr-defined]
+    except Exception:
+        workers = []
+
+    for w in workers:
+        started_at = getattr(w, "_started_at", 0.0) or 0.0
+        duration = (now - started_at) if started_at else 0.0
+        result = getattr(w, "_result", None)
+        payload.append(
+            {
+                "worker_id": w.id,
+                "task": (w.task or "")[:400],
+                "status": str(getattr(w, "status", "unknown")),
+                "is_active": bool(getattr(w, "is_active", False)),
+                "duration_seconds": round(duration, 1),
+                "explicit_report": getattr(w, "_explicit_report", None),
+                "result_status": (result.status if result else None),
+                "result_summary": (result.summary if result else None),
+            }
+        )
+
+    # Active workers first, then terminated, newest-started first within group.
+    payload.sort(key=lambda r: (not r["is_active"], -(r["duration_seconds"] or 0)))
+    return payload
+
+
+def _payload_change_signature(payload: list[dict]) -> tuple:
+    """Cheap fingerprint for change detection on the SSE stream.
+
+    We intentionally exclude ``duration_seconds`` — it ticks every call
+    and would make every poll look like a change, defeating the "only
+    emit on change" optimisation. Everything else (status, result,
+    explicit_report) actually reflects worker state transitions.
+    """
+    return tuple(
+        (
+            w["worker_id"],
+            w["status"],
+            w["is_active"],
+            w["result_status"],
+            w["result_summary"],
+            bool(w["explicit_report"]),
+        )
+        for w in payload
+    )
+
+
+async def handle_live_workers_stream(request: web.Request) -> web.StreamResponse:
+    """GET /api/sessions/{session_id}/workers/stream — SSE feed.
+
+    Emits a ``snapshot`` event immediately, then re-emits every time
+    the worker registry changes (status transitions, new spawns, new
+    reports). Polls the runtime every 2s internally — the colony's
+    ``_workers`` dict is not observable otherwise. Clients disconnecting
+    bubbles up as ConnectionResetError from ``resp.write``.
+    """
+    session, err = resolve_session(request)
+    if err:
+        return err
+
+    import asyncio
+
+    resp = web.StreamResponse(
+        status=200,
+        headers={
+            "Content-Type": "text/event-stream",
+            "Cache-Control": "no-cache, no-transform",
+            "Connection": "keep-alive",
+            "X-Accel-Buffering": "no",
+        },
+    )
+    await resp.prepare(request)
+
+    async def _send(event: str, data) -> None:
+        payload = f"event: {event}\ndata: {json.dumps(data)}\n\n"
+        await resp.write(payload.encode("utf-8"))
+
+    last_signature: tuple | None = None
+    try:
+        while True:
+            colony = _active_colony(session)
+            workers = _build_live_workers_payload(colony)
+            signature = _payload_change_signature(workers)
+            if signature != last_signature:
+                await _send("snapshot", {"workers": workers})
+                last_signature = signature
+            await asyncio.sleep(2.0)
+    except (asyncio.CancelledError, ConnectionResetError):
+        raise
+    except Exception as exc:
+        logger.warning("live workers stream error: %s", exc, exc_info=True)
+    return resp
+
+
+async def handle_stop_live_worker(request: web.Request) -> web.Response:
+    """POST /api/sessions/{session_id}/workers/{worker_id}/stop — force-stop one worker.
+
+    Calls ``colony.stop_worker(worker_id)`` which cancels the worker's
+    background task. The worker's terminal SUBAGENT_REPORT still fires
+    (preserving any _explicit_report) so the queen sees a `[WORKER_REPORT]`
+    with ``status="stopped"``.
+    """
+    session, err = resolve_session(request)
+    if err:
+        return err
+
+    worker_id = request.match_info.get("worker_id", "")
+    if not worker_id:
+        return web.json_response({"error": "worker_id required"}, status=400)
+
+    colony = _active_colony(session)
+    if colony is None:
+        return web.json_response({"error": "No active colony on this session"}, status=503)
+
+    worker = colony._workers.get(worker_id)  # type: ignore[attr-defined]
+    if worker is None:
+        return web.json_response({"error": f"Worker '{worker_id}' not found"}, status=404)
+    if not worker.is_active:
+        return web.json_response(
+            {
+                "stopped": False,
+                "reason": "Worker already terminated",
+                "worker_id": worker_id,
+                "status": str(worker.status),
+            }
+        )
+
+    try:
+        await colony.stop_worker(worker_id)
+    except Exception as exc:
+        logger.exception("stop_worker failed for %s", worker_id)
+        return web.json_response(
+            {"stopped": False, "error": str(exc), "worker_id": worker_id},
+            status=500,
+        )
+
+    return web.json_response({"stopped": True, "worker_id": worker_id})
+
+
+async def handle_stop_all_live_workers(request: web.Request) -> web.Response:
+    """POST /api/sessions/{session_id}/workers/stop-all — force-stop every active worker.
+
+    The persistent overseer (if any) is skipped — it is the queen itself
+    and stopping it would end the session. Only ephemeral fan-out workers
+    are targeted.
+    """
+    session, err = resolve_session(request)
+    if err:
+        return err
+
+    colony = _active_colony(session)
+    if colony is None:
+        return web.json_response({"stopped": [], "error": "No active colony on this session"})
+
+    stopped: list[str] = []
+    errors: list[dict] = []
+    try:
+        workers = list(colony._workers.values())  # type: ignore[attr-defined]
+    except Exception:
+        workers = []
+
+    for w in workers:
+        if not w.is_active:
+            continue
+        if getattr(w, "_persistent", False):
+            # The overseer — don't kill the queen.
+            continue
+        try:
+            await colony.stop_worker(w.id)
+            stopped.append(w.id)
+        except Exception as exc:
+            logger.warning("stop-all: failed to stop %s: %s", w.id, exc)
+            errors.append({"worker_id": w.id, "error": str(exc)})
+
+    return web.json_response(
+        {
+            "stopped": stopped,
+            "stopped_count": len(stopped),
+            "errors": errors if errors else None,
+        }
+    )
+
+
 def register_routes(app: web.Application) -> None:
     """Register worker inspection routes."""
     app.router.add_get("/api/sessions/{session_id}/colonies/{colony_id}/nodes", handle_list_nodes)
-    app.router.add_get(
-        "/api/sessions/{session_id}/colonies/{colony_id}/nodes/{node_id}", handle_get_node
-    )
+    app.router.add_get("/api/sessions/{session_id}/colonies/{colony_id}/nodes/{node_id}", handle_get_node)
     app.router.add_get(
         "/api/sessions/{session_id}/colonies/{colony_id}/nodes/{node_id}/criteria",
         handle_node_criteria,
@@ -261,3 +459,20 @@ def register_routes(app: web.Application) -> None:
         "/api/sessions/{session_id}/colonies/{colony_id}/nodes/{node_id}/tools",
         handle_node_tools,
     )
+    # Live worker control. The GET /workers list endpoint lives in
+    # routes_colony_workers.py — it reads from session.colony (the
+    # unified ColonyRuntime where run_parallel_workers-spawned workers
+    # actually live) and returns the WorkerSummary shape the frontend
+    # types against. Registering a duplicate here shadowed it in
+    # aiohttp's router and broke the Sessions tab.
+    app.router.add_get(
+        "/api/sessions/{session_id}/workers/stream", handle_live_workers_stream
+    )
+    app.router.add_post(
+        "/api/sessions/{session_id}/workers/stop-all",
+        handle_stop_all_live_workers,
+    )
+    app.router.add_post(
+        "/api/sessions/{session_id}/workers/{worker_id}/stop",
+        handle_stop_live_worker,
+    )

core/framework/server/session_manager.py

@@ -120,9 +120,7 @@ class SessionManager:
     (blocking I/O) then started on the event loop.
     """
 
-    def __init__(
-        self, model: str | None = None, credential_store=None, queen_tool_registry=None
-    ) -> None:
+    def __init__(self, model: str | None = None, credential_store=None, queen_tool_registry=None) -> None:
         self._sessions: dict[str, Session] = {}
         self._loading: set[str] = set()
         self._model = model
@@ -368,9 +366,7 @@ class SessionManager:
         _colony_metadata_path = agent_path / "metadata.json"
         if _colony_metadata_path.exists():
             try:
-                _colony_metadata = json.loads(
-                    _colony_metadata_path.read_text(encoding="utf-8")
-                )
+                _colony_metadata = json.loads(_colony_metadata_path.read_text(encoding="utf-8"))
             except (json.JSONDecodeError, OSError):
                 pass
 
@@ -444,9 +440,7 @@ class SessionManager:
 
             # Start queen with worker profile + lifecycle + monitoring tools
             worker_identity = (
-                build_worker_profile(session.colony_runtime, agent_path=agent_path)
-                if session.colony_runtime
-                else None
+                build_worker_profile(session.colony_runtime, agent_path=agent_path) if session.colony_runtime else None
             )
             await self._start_queen(
                 session,
@@ -695,15 +689,24 @@ class SessionManager:
             event_bus=session.event_bus,
         )
 
-        # Start the worker's agent loop in the background
-        session.queen_task = asyncio.create_task(
-            session.queen_executor.run(initial_message=initial_prompt)
-        )
+        # Start the worker's agent loop in the background.
+        # Scope browser profile per-session so parallel sessions drive
+        # independent Chrome tab groups. Browser tools live in an MCP
+        # subprocess; we inject `profile` via the ToolRegistry execution
+        # context (a CONTEXT_PARAM) so it flows into every tool call.
+        async def _run_worker():
+            try:
+                from framework.loader.tool_registry import ToolRegistry
+
+                ToolRegistry.set_execution_context(profile=session.id)
+            except Exception:
+                logger.debug("Worker: failed to set browser profile", exc_info=True)
+            await session.queen_executor.run(initial_message=initial_prompt)
+
+        session.queen_task = asyncio.create_task(_run_worker())
 
         # Set up event persistence
         if session.event_bus and queen_dir:
-            from framework.host.event_bus import EventBus
-
             session.event_bus.start_persistence(queen_dir, iteration_offset=iteration_offset)
 
         logger.info(
@@ -938,9 +941,7 @@ class SessionManager:
                 state.setdefault("result", {})["error"] = "Stale session: runtime restarted"
                 state.setdefault("timestamps", {})["updated_at"] = datetime.now().isoformat()
                 state_path.write_text(json.dumps(state, indent=2), encoding="utf-8")
-                logger.info(
-                    "Marked stale session '%s' as cancelled for agent '%s'", d.name, agent_path.name
-                )
+                logger.info("Marked stale session '%s' as cancelled for agent '%s'", d.name, agent_path.name)
             except (json.JSONDecodeError, OSError) as e:
                 logger.warning("Failed to clean up stale session %s: %s", d.name, e)
 
@@ -984,13 +985,12 @@ class SessionManager:
             store = session.colony_runtime._session_store
             state = await store.read_state(session_id)
             if state and state.active_triggers:
+                from framework.host.event_bus import AgentEvent, EventType
                 from framework.tools.queen_lifecycle_tools import (
                     _start_trigger_timer,
                     _start_trigger_webhook,
                 )
 
-                from framework.host.event_bus import AgentEvent, EventType
-
                 runner = getattr(session, "runner", None)
                 colony_entry = runner.graph.entry_node if runner else None
                 saved_tasks = getattr(state, "trigger_tasks", {}) or {}
@@ -1024,11 +1024,7 @@ class SessionManager:
                                         "trigger_type": tdef.trigger_type,
                                         "trigger_config": tdef.trigger_config,
                                         "name": tdef.description or tdef.id,
-                                        **(
-                                            {"entry_node": colony_entry}
-                                            if colony_entry
-                                            else {}
-                                        ),
+                                        **({"entry_node": colony_entry} if colony_entry else {}),
                                     },
                                 )
                             )
@@ -1077,17 +1073,13 @@ class SessionManager:
         meta_path = _queen_session_dir(storage_session_id, session.queen_name) / "meta.json"
         try:
             _agent_name = (
-                session.worker_info.name
-                if session.worker_info
-                else str(agent_path.name).replace("_", " ").title()
+                session.worker_info.name if session.worker_info else str(agent_path.name).replace("_", " ").title()
             )
             existing_meta = {}
             if meta_path.exists():
                 existing_meta = json.loads(meta_path.read_text(encoding="utf-8"))
             existing_meta["agent_name"] = _agent_name
-            existing_meta["agent_path"] = (
-                str(session.worker_path) if session.worker_path else str(agent_path)
-            )
+            existing_meta["agent_path"] = str(session.worker_path) if session.worker_path else str(agent_path)
             meta_path.write_text(json.dumps(existing_meta), encoding="utf-8")
         except OSError:
             pass
@@ -1206,9 +1198,7 @@ class SessionManager:
                 self._background_tasks.add(task)
                 task.add_done_callback(self._background_tasks.discard)
             except Exception:
-                logger.warning(
-                    "Session '%s': failed to spawn shutdown reflection", session_id, exc_info=True
-                )
+                logger.warning("Session '%s': failed to spawn shutdown reflection", session_id, exc_info=True)
 
         if session.queen_task is not None:
             session.queen_task.cancel()
@@ -1313,11 +1303,7 @@ class SessionManager:
             _agent_name = (
                 session.worker_info.name
                 if session.worker_info
-                else (
-                    str(session.worker_path.name).replace("_", " ").title()
-                    if session.worker_path
-                    else None
-                )
+                else (str(session.worker_path.name).replace("_", " ").title() if session.worker_path else None)
             )
             # Merge into existing meta.json to preserve fields written by
             # _update_meta_json (e.g. phase, agent_path set during building).
@@ -1372,8 +1358,7 @@ class SessionManager:
                 if max_iter >= 0:
                     iteration_offset = max_iter + 1
                     logger.info(
-                        "Session '%s' resuming with iteration_offset=%d"
-                        " (from events.jsonl max), last phase: %s",
+                        "Session '%s' resuming with iteration_offset=%d (from events.jsonl max), last phase: %s",
                         session.id,
                         iteration_offset,
                         last_phase or "unknown",
@@ -1416,34 +1401,24 @@ class SessionManager:
             )
 
         # Auto-load worker on cold restore — the queen's conversation expects
-        # the agent to be loaded, but the new session has no worker.
+        # the colony to be loaded, but the new session has no worker.
         if session.queen_resume_from and not session.colony_runtime:
             meta_path = queen_dir / "meta.json"
             if meta_path.exists():
                 try:
                     _meta = json.loads(meta_path.read_text(encoding="utf-8"))
                     _agent_path = _meta.get("agent_path")
-                    _phase = _meta.get("phase")
 
                     if _agent_path and Path(_agent_path).exists():
-                        if _phase in ("staging", "running", None):
-                            # Agent fully built — load worker and resume
-                            await self.load_colony(session.id, _agent_path)
-                            if session.phase_state:
-                                await session.phase_state.switch_to_staging(source="auto")
-                            logger.info("Cold restore: auto-loaded worker from %s", _agent_path)
-                        elif _phase == "building":
-                            # Agent folder exists but incomplete — resume building
-                            if session.phase_state:
-                                session.phase_state.agent_path = _agent_path
-                                await session.phase_state.switch_to_building(source="auto")
-                            logger.info("Cold restore: resumed BUILDING phase for %s", _agent_path)
-                        elif _phase == "planning":
-                            if session.phase_state:
-                                session.phase_state.agent_path = _agent_path
-                            logger.info("Cold restore: PLANNING phase for %s", _agent_path)
+                        await self.load_colony(session.id, _agent_path)
+                        if session.phase_state:
+                            # Restored colony session lands in reviewing — the
+                            # queen summarises whatever the last run produced
+                            # before the user decides what to do next.
+                            await session.phase_state.switch_to_reviewing(source="auto")
+                        logger.info("Cold restore: auto-loaded colony from %s", _agent_path)
                 except Exception:
-                    logger.warning("Cold restore: failed to auto-load worker", exc_info=True)
+                    logger.warning("Cold restore: failed to auto-load colony", exc_info=True)
 
     # ------------------------------------------------------------------
     # Phase 2: unified ColonyRuntime construction
@@ -1514,8 +1489,7 @@ class SessionManager:
         session.colony = colony
 
         logger.info(
-            "_start_queen: unified ColonyRuntime ready for session %s "
-            "(%d tools, storage=%s)",
+            "_start_queen: unified ColonyRuntime ready for session %s (%d tools, storage=%s)",
             session.id,
             len(queen_tools),
             queen_dir,
@@ -1547,10 +1521,7 @@ class SessionManager:
                 detail = cfg.get("cron") or f"every {cfg.get('interval_minutes', '?')} min"
                 task_info = f' -> task: "{t.task}"' if t.task else " (no task configured)"
                 parts.append(f"  - {t.id} ({t.trigger_type}: {detail}){task_info}")
-            trigger_lines = (
-                "\n\nAvailable triggers (inactive — use set_trigger to activate):\n"
-                + "\n".join(parts)
-            )
+            trigger_lines = "\n\nAvailable triggers (inactive — use set_trigger to activate):\n" + "\n".join(parts)
 
         await node.inject_event(f"[SYSTEM] Colony loaded.{profile}{trigger_lines}")
 
@@ -1767,9 +1738,6 @@ class SessionManager:
         except OSError:
             return []
 
-        # Sort all sessions by mtime, newest first
-        all_session_dirs.sort(key=lambda p: p.stat().st_mtime, reverse=True)
-
         results: list[dict] = []
         for d in all_session_dirs:
             if not d.is_dir():
@@ -1801,6 +1769,13 @@ class SessionManager:
             # and return the last assistant message content as a snippet.
             last_message: str | None = None
             message_count: int = 0
+            # Last-activity timestamp — mtime of the latest client-facing message.
+            # Falls back to session creation time for empty sessions. NOTE: the
+            # session directory's own mtime is NOT reliable here — POSIX dir mtime
+            # only updates when direct entries change, and conversation parts are
+            # nested under conversations/parts/, so writing a new part does not
+            # bubble up to the session dir.
+            last_active_at: float = float(created_at) if isinstance(created_at, (int, float)) else 0.0
             convs_dir = d / "conversations"
             if convs_dir.exists():
                 try:
@@ -1836,15 +1811,20 @@ class SessionManager:
                     ]
                     client_msgs.sort(key=lambda m: m.get("created_at", m.get("seq", 0)))
                     message_count = len(client_msgs)
+                    # Take the latest message's timestamp as the activity marker.
+                    # _collect_parts sets created_at via setdefault to the part
+                    # file's mtime, so this is always a valid float.
+                    if client_msgs:
+                        latest_ts = client_msgs[-1].get("created_at")
+                        if isinstance(latest_ts, (int, float)) and latest_ts > last_active_at:
+                            last_active_at = float(latest_ts)
                     # Last assistant message as preview snippet
                     for msg in reversed(client_msgs):
                         content = msg.get("content") or ""
                         if isinstance(content, list):
                             # Anthropic-style content blocks
                             content = " ".join(
-                                b.get("text", "")
-                                for b in content
-                                if isinstance(b, dict) and b.get("type") == "text"
+                                b.get("text", "") for b in content if isinstance(b, dict) and b.get("type") == "text"
                             )
                         if content and msg.get("role") == "assistant":
                             last_message = content[:120].strip()
@@ -1862,6 +1842,7 @@ class SessionManager:
                     "live": False,
                     "has_messages": convs_dir.exists() and message_count > 0,
                     "created_at": created_at,
+                    "last_active_at": last_active_at,
                     "agent_name": agent_name,
                     "agent_path": agent_path,
                     "last_message": last_message,
@@ -1870,6 +1851,11 @@ class SessionManager:
                 }
             )
 
+        # Sort by last-activity timestamp, newest first. This is the order
+        # callers (including /api/sessions/history and colony-chat cold resume)
+        # rely on — don't use raw directory mtime, which doesn't update when
+        # nested conversation parts are written.
+        results.sort(key=lambda r: r.get("last_active_at") or 0.0, reverse=True)
         return results
 
     async def shutdown_all(self) -> None:

core/framework/server/tests/test_api.py

@@ -259,15 +259,11 @@ def _write_sample_session(base: Path, session_id: str):
     conv_dir = session_dir / "conversations" / "node_a" / "parts"
     conv_dir.mkdir(parents=True)
     (conv_dir / "0001.json").write_text(json.dumps({"seq": 1, "role": "user", "content": "hello"}))
-    (conv_dir / "0002.json").write_text(
-        json.dumps({"seq": 2, "role": "assistant", "content": "hi there"})
-    )
+    (conv_dir / "0002.json").write_text(json.dumps({"seq": 2, "role": "assistant", "content": "hi there"}))
 
     conv_dir_b = session_dir / "conversations" / "node_b" / "parts"
     conv_dir_b.mkdir(parents=True)
-    (conv_dir_b / "0003.json").write_text(
-        json.dumps({"seq": 3, "role": "user", "content": "continue"})
-    )
+    (conv_dir_b / "0003.json").write_text(json.dumps({"seq": 3, "role": "user", "content": "continue"}))
 
     # Logs
     logs_dir = session_dir / "logs"
@@ -291,9 +287,7 @@ def _write_sample_session(base: Path, session_id: str):
         "attention_reasons": ["retried"],
         "total_steps": 1,
     }
-    (logs_dir / "details.jsonl").write_text(
-        json.dumps(detail_a) + "\n" + json.dumps(detail_b) + "\n"
-    )
+    (logs_dir / "details.jsonl").write_text(json.dumps(detail_a) + "\n" + json.dumps(detail_b) + "\n")
 
     step_a = {"node_id": "node_a", "step_index": 0, "llm_text": "thinking..."}
     step_b = {"node_id": "node_b", "step_index": 0, "llm_text": "retrying..."}
@@ -302,9 +296,7 @@ def _write_sample_session(base: Path, session_id: str):
     return session_id, session_dir, state
 
 
-def _write_queen_session(
-    tmp_path: Path, queen_id: str, session_id: str, meta: dict | None = None
-) -> Path:
+def _write_queen_session(tmp_path: Path, queen_id: str, session_id: str, meta: dict | None = None) -> Path:
     """Create a persisted queen session directory for restore tests."""
     session_dir = tmp_path / ".hive" / "agents" / "queens" / queen_id / "sessions" / session_id
     session_dir.mkdir(parents=True)
@@ -394,9 +386,7 @@ class TestSessionCRUD:
     async def test_create_session_with_worker_forwards_session_id(self):
         app = create_app()
         manager = app["manager"]
-        manager.create_session_with_worker_colony = AsyncMock(
-            return_value=_make_session(agent_id="my-custom-session")
-        )
+        manager.create_session_with_worker_colony = AsyncMock(return_value=_make_session(agent_id="my-custom-session"))
 
         async with TestClient(TestServer(app)) as client:
             resp = await client.post(
@@ -600,14 +590,10 @@ class TestMessageBootstrap:
         manager.build_llm = MagicMock(return_value=MagicMock())
         manager.stop_session = AsyncMock()
         manager.create_session = AsyncMock()
-        monkeypatch.setattr(
-            routes_messages, "select_queen", AsyncMock(return_value="queen_technology")
-        )
+        monkeypatch.setattr(routes_messages, "select_queen", AsyncMock(return_value="queen_technology"))
 
         async with TestClient(TestServer(app)) as client:
-            resp = await client.post(
-                "/api/messages/classify", json={"message": "Build me a scraper"}
-            )
+            resp = await client.post("/api/messages/classify", json={"message": "Build me a scraper"})
             assert resp.status == 200
             data = await resp.json()
             # Assert inside the async-with so app shutdown (which stops
@@ -623,9 +609,7 @@ class TestQueenSessionSelection:
     @pytest.mark.asyncio
     async def test_select_queen_session_rejects_foreign_session(self, monkeypatch, tmp_path):
         _patch_queen_storage(monkeypatch, tmp_path)
-        _write_queen_session(
-            tmp_path, "queen_growth", "other_session", {"queen_id": "queen_growth"}
-        )
+        _write_queen_session(tmp_path, "queen_growth", "other_session", {"queen_id": "queen_growth"})
 
         app = create_app()
         async with TestClient(TestServer(app)) as client:
@@ -654,18 +638,20 @@ class TestQueenSessionSelection:
             )
             assert resp.status == 200
             data = await resp.json()
-
-        assert data == {
-            "session_id": "queen_live",
-            "queen_id": "queen_technology",
-            "status": "live",
-        }
-        assert any(call.args == ("other_live",) for call in manager.stop_session.await_args_list)
+            # Assert inside the async-with so app shutdown (which stops
+            # remaining sessions as cleanup) doesn't pollute the assertions.
+            assert data == {
+                "session_id": "queen_live",
+                "queen_id": "queen_technology",
+                "status": "live",
+            }
+            # Other queen's live session must be left running so multiple
+            # queens can stay active in parallel across navigation.
+            manager.stop_session.assert_not_awaited()
+            assert "other_live" in manager._sessions
 
     @pytest.mark.asyncio
-    async def test_select_queen_session_restores_specific_history_session(
-        self, monkeypatch, tmp_path
-    ):
+    async def test_select_queen_session_restores_specific_history_session(self, monkeypatch, tmp_path):
         _patch_queen_storage(monkeypatch, tmp_path)
         _write_queen_session(
             tmp_path,
@@ -763,18 +749,21 @@ class TestQueenSessionSelection:
             )
             assert resp.status == 200
             data = await resp.json()
-
-        assert data == {
-            "session_id": "fresh_thread",
-            "queen_id": "queen_technology",
-            "status": "created",
-        }
-        manager.stop_session.assert_awaited_once_with("old_live")
-        manager.create_session.assert_awaited_once_with(
-            initial_prompt=None,
-            queen_name="queen_technology",
-            initial_phase="independent",
-        )
+            # Assert inside the async-with so app shutdown (which stops
+            # remaining sessions as cleanup) doesn't pollute the assertions.
+            assert data == {
+                "session_id": "fresh_thread",
+                "queen_id": "queen_technology",
+                "status": "created",
+            }
+            # Other queen's live session must be left running.
+            manager.stop_session.assert_not_awaited()
+            assert "old_live" in manager._sessions
+            manager.create_session.assert_awaited_once_with(
+                initial_prompt=None,
+                queen_name="queen_technology",
+                initial_phase="independent",
+            )
 
 
 class TestExecution:
@@ -1167,9 +1156,7 @@ class TestGraphNodes:
             assert data["entry_node"] == "node_a"
 
     @pytest.mark.asyncio
-    async def test_list_nodes_with_session_enrichment(
-        self, nodes_and_edges, sample_session, tmp_agent_dir
-    ):
+    async def test_list_nodes_with_session_enrichment(self, nodes_and_edges, sample_session, tmp_agent_dir):
         session_id, session_dir, state = sample_session
         tmp_path, agent_name, base = tmp_agent_dir
         nodes, edges = nodes_and_edges
@@ -1182,9 +1169,7 @@ class TestGraphNodes:
         app = _make_app_with_session(session)
 
         async with TestClient(TestServer(app)) as client:
-            resp = await client.get(
-                f"/api/sessions/test_agent/graphs/primary/nodes?session_id={session_id}"
-            )
+            resp = await client.get(f"/api/sessions/test_agent/graphs/primary/nodes?session_id={session_id}")
             assert resp.status == 200
             data = await resp.json()
             node_map = {n["id"]: n for n in data["nodes"]}
@@ -1233,9 +1218,7 @@ class TestGraphNodes:
             assert resp.status == 200
             data = await resp.json()
             assert "system_prompt" in data
-            assert (
-                data["system_prompt"] == "You are a helpful assistant that produces valid results."
-            )
+            assert data["system_prompt"] == "You are a helpful assistant that produces valid results."
 
             # Node without system_prompt should return empty string
             resp2 = await client.get("/api/sessions/test_agent/graphs/primary/nodes/node_b")
@@ -1270,9 +1253,7 @@ class TestNodeCriteria:
             assert data["output_keys"] == ["result"]
 
     @pytest.mark.asyncio
-    async def test_criteria_with_log_enrichment(
-        self, nodes_and_edges, sample_session, tmp_agent_dir
-    ):
+    async def test_criteria_with_log_enrichment(self, nodes_and_edges, sample_session, tmp_agent_dir):
         """Criteria endpoint enriched with last execution from logs."""
         session_id, session_dir, state = sample_session
         tmp_path, agent_name, base = tmp_agent_dir
@@ -1293,8 +1274,7 @@ class TestNodeCriteria:
 
         async with TestClient(TestServer(app)) as client:
             resp = await client.get(
-                f"/api/sessions/test_agent/graphs/primary/nodes/node_b/criteria"
-                f"?session_id={session_id}"
+                f"/api/sessions/test_agent/graphs/primary/nodes/node_b/criteria?session_id={session_id}"
             )
             assert resp.status == 200
             data = await resp.json()
@@ -1311,9 +1291,7 @@ class TestNodeCriteria:
         app = _make_app_with_session(session)
 
         async with TestClient(TestServer(app)) as client:
-            resp = await client.get(
-                "/api/sessions/test_agent/graphs/primary/nodes/nonexistent/criteria"
-            )
+            resp = await client.get("/api/sessions/test_agent/graphs/primary/nodes/nonexistent/criteria")
             assert resp.status == 404
 
 
@@ -1388,9 +1366,7 @@ class TestLogs:
         app = _make_app_with_session(session)
 
         async with TestClient(TestServer(app)) as client:
-            resp = await client.get(
-                f"/api/sessions/test_agent/logs?session_id={session_id}&level=summary"
-            )
+            resp = await client.get(f"/api/sessions/test_agent/logs?session_id={session_id}&level=summary")
             assert resp.status == 200
             data = await resp.json()
             assert data["run_id"] == session_id
@@ -1411,9 +1387,7 @@ class TestLogs:
         app = _make_app_with_session(session)
 
         async with TestClient(TestServer(app)) as client:
-            resp = await client.get(
-                f"/api/sessions/test_agent/logs?session_id={session_id}&level=details"
-            )
+            resp = await client.get(f"/api/sessions/test_agent/logs?session_id={session_id}&level=details")
             assert resp.status == 200
             data = await resp.json()
             assert data["session_id"] == session_id
@@ -1435,9 +1409,7 @@ class TestLogs:
         app = _make_app_with_session(session)
 
         async with TestClient(TestServer(app)) as client:
-            resp = await client.get(
-                f"/api/sessions/test_agent/logs?session_id={session_id}&level=tools"
-            )
+            resp = await client.get(f"/api/sessions/test_agent/logs?session_id={session_id}&level=tools")
             assert resp.status == 200
             data = await resp.json()
             assert data["session_id"] == session_id

core/framework/skills/_default_skills/browser-automation/SKILL.md

@@ -12,25 +12,22 @@ metadata:
 
 All GCU browser tools drive a real Chrome instance through the Beeline extension and Chrome DevTools Protocol (CDP). That means clicks, keystrokes, and screenshots are processed by the actual browser's native hit testing, focus, and layout engines — **not** a synthetic event layer. Understanding this unlocks strategies that make hard sites easy.
 
-## Coordinates: always CSS pixels
+## Coordinates
 
-**Chrome DevTools Protocol `Input.dispatchMouseEvent` operates in CSS pixels, not physical pixels.**
-
-When you call `browser_coords(image_x, image_y)` after a screenshot, the returned dict has both `css_x/y` and `physical_x/y`. **Always use `css_x/y` for clicks, hovers, and key presses.**
+Every browser tool that takes or returns coordinates operates in **fractions of the viewport (0..1 for both axes)**. Read a target's proportional position off `browser_screenshot` — "this button is about 35% from the left and 20% from the top" → pass `(0.35, 0.20)`. Rect-returning tools (`browser_get_rect`, `browser_shadow_query`, and the `rect` inside `focused_element`) also return fractions. The tools convert to CSS pixels internally before dispatching to Chrome.
 
 ```
-browser_screenshot()          → image (downscaled to 800/900 px wide)
-browser_coords(img_x, img_y)  → {css_x, css_y, physical_x, physical_y}
-browser_click_coordinate(css_x, css_y)   ← USE css_x/y
-browser_hover_coordinate(css_x, css_y)   ← USE css_x/y
-browser_press_at(css_x, css_y, key)      ← USE css_x/y
+browser_screenshot()                  → image + cssWidth/cssHeight in meta
+browser_click_coordinate(x, y)        → x, y are fractions 0..1
+browser_hover_coordinate(x, y)        → fractions
+browser_press_at(x, y, key)           → fractions
+browser_get_rect(selector) → rect     → rect.cx / rect.cy are fractions
+browser_shadow_query(...)  → rect     → same
 ```
 
-Feeding `physical_x/y` on a HiDPI display overshoots by DPR× — on a DPR=1.6 laptop, clicks land 60% too far right and down. The ratio between `physicalScale` and `cssScale` tells you the effective DPR.
+**Why fractions:** every vision model (Claude ~1.15 MP target, GPT-4o 512-px tiles, Gemini, local VLMs) resizes or tiles images differently before the model sees the pixels. Proportions survive every such transform; pixel coordinates only "work" per-model and silently break when you swap backends. Four-decimal precision (`0.0001` ≈ 0.17 CSS px on a 1717-wide viewport) is more than enough for the tightest targets.
 
-`getBoundingClientRect()` already returns CSS pixels — feed those values straight through to click/hover tools without any DPR multiplication.
-
-**Exception for zoomed elements:** pages that use `zoom` or `transform: scale()` on a container (LinkedIn's `#interop-outlet`, some embedded iframes) render in a scaled local coordinate space. `getBoundingClientRect` there may not match CDP's hit space. Use `browser_shadow_query` which handles the math, or fall back to visually picking coordinates from a screenshot.
+**Exception for zoomed elements:** pages that use `zoom` or `transform: scale()` on a container (LinkedIn's `#interop-outlet`, some embedded iframes) render in a scaled local coordinate space. `getBoundingClientRect` there may not match CDP's hit space. Prefer `browser_shadow_query` (which handles the math and returns fractions) or visually pick coordinates from a screenshot. Avoid raw `browser_evaluate` + `getBoundingClientRect()` for coord lookup — that returns CSS px and will be wrong when fed to click tools.
 
 ## Screenshot + coordinates is shadow-agnostic — prefer it on shadow-heavy sites
 
@@ -38,39 +35,39 @@ On sites that use Shadow DOM heavily (Reddit's faceplate Web Components, LinkedI
 
 Why:
 
-- **CDP hit testing walks shadow roots natively.** `browser_click_coordinate(css_x, css_y)` routes through Chrome's native hit tester, which traverses open shadow roots automatically. You don't need to know the shadow structure.
+- **CDP hit testing walks shadow roots natively.** `browser_click_coordinate(x, y)` routes through Chrome's native hit tester, which traverses open shadow roots automatically. You don't need to know the shadow structure.
 - **Keyboard dispatch follows focus** into shadow roots. After a click focuses an input (even one three shadow levels deep), `browser_press(...)` with no selector dispatches keys to `document.activeElement`'s computed focus target.
 - **Screenshots render the real layout** regardless of DOM implementation.
 
-Whereas `wait_for_selector`, `browser_click(selector=...)`, `browser_type(selector=...)` all use `document.querySelector` under the hood, which **stops at shadow boundaries**. They cannot see elements inside shadow roots.
+Whereas `wait_for_selector`, `browser_click(selector=...)`, `browser_type(selector=...)` all use `document.querySelector` under the hood, which **stops at shadow boundaries**. They cannot see elements inside shadow roots. For shadow-DOM inputs, use `browser_type_focused` after focusing via click-coordinate.
 
 ### Recommended workflow on shadow-heavy sites
 
-1. `browser_screenshot()` → visual image
-2. Identify the target visually → image pixel `(x, y)` (eyeball from the screenshot)
-3. `browser_coords(x, y)` → convert to CSS px
-4. `browser_click_coordinate(css_x, css_y)` → lands on the element via native hit testing; inputs get focused
-5. For typing:
-   - If the element was reachable via a selector → `browser_type(selector, text)`
-   - Otherwise → `browser_press(key)` per character (dispatches to focused element, no selector needed)
-6. Verify by reading element state via a targeted `browser_evaluate` that walks the shadow tree
+1. `browser_screenshot()` → JPEG; meta includes `cssWidth`/`cssHeight` for reference.
+2. Identify the target visually → estimate its proportional position `(fx, fy)` where each is in `0..1`.
+3. `browser_click_coordinate(fx, fy)` → tool converts to CSS px and dispatches; CDP native hit testing focuses the element. **The response includes `focused_element: {tag, id, role, contenteditable, rect, inFrame?, ...}`** — use it to verify you actually focused what you intended. `rect` is in fractions (same space as your input). When focus is inside a same-origin iframe, the descriptor reports the inner element and adds `inFrame: [...]` breadcrumbs.
+4. `browser_type_focused(text="...")` → inserts text into `document.activeElement` (traverses into same-origin iframes automatically). Shadow roots, iframes, Lexical, Draft.js, ProseMirror all just work. Use `browser_type(selector, text)` instead when you have a reliable CSS selector for a light-DOM element.
+5. Verify via `browser_screenshot` OR `browser_get_attribute` on a known-reachable marker (e.g. check that the Send button's `aria-disabled` flipped to `false`).
+
+### The click→type loop (canonical pattern)
+
+1. Call `browser_click_coordinate(x, y)` to click the target element.
+2. Check the `focused_element` field in the response — it tells you what actually received focus (tag, id, role, contenteditable, rect).
+3. If the focused element is editable, call `browser_type_focused(text="...")` to insert text. Use tools to verify the text took effect — prefer checking the underlying `.value` / `innerText` via `browser_evaluate` or confirming the submit button enabled. A screenshot alone can mislead: narrow input boxes visually clip long text, so only a portion may appear on screen even though the full string was accepted.
+4. If it is NOT editable, your click landed on the wrong thing — refine coordinates and retry. Do NOT reach for `browser_evaluate` + `execCommand('insertText')` or shadow-root traversals. The problem is the click target, not the typing method.
+
+`browser_click` (selector-based) also returns `focused_element`, so the same check works whether you clicked by selector or coordinate.
 
 ### Empirically verified (2026-04-11)
 
 Tested against `https://www.reddit.com/r/programming/` whose search input lives at:
+
 ```
 document > reddit-search-large [shadow]
          > faceplate-search-input#search-input [shadow]
          > input[name="q"]
 ```
 
-- `document.querySelector('input')` → **0 visible inputs** on the page (all in shadow)
-- `browser_type('faceplate-search-input input', 'python')` → "Element not found"
-- `browser_click_coordinate(617, 28)` → focus trail: `REDDIT-SEARCH-LARGE > FACEPLATE-SEARCH-INPUT > INPUT` ✓
-- Char-by-char key dispatch after the click → `input.value === 'python'` ✓
-
-Coordinate pipeline: works perfectly. Selector pipeline: unusable without shadow-piercing syntax.
-
 ### Shadow-piercing selectors
 
 When you DO want a selector-based approach and know the shadow structure, `browser_shadow_query` and `browser_get_rect` support `>>>` shadow-piercing syntax:
@@ -80,7 +77,7 @@ browser_shadow_query("reddit-search-large >>> #search-input")
 browser_get_rect("#interop-outlet >>> #ember37 >>> p")
 ```
 
-Returns the element's rect in **CSS pixels** (feed directly to click tools). Remember: `browser_type` and `wait_for_selector` do **not** support `>>>` — only shadow_query and get_rect do.
+Returns the element's rect as **fractions of the viewport** (feed `rect.cx` / `rect.cy` directly to click tools). Remember: `browser_type` and `wait_for_selector` do **not** support `>>>` — only shadow_query and get_rect do.
 
 ## Navigation and waiting
 
@@ -88,8 +85,8 @@ Returns the element's rect in **CSS pixels** (feed directly to click tools). Rem
 
 ```
 browser_navigate(url, wait_until="load")   # "load" | "domcontentloaded" | "networkidle"
-browser_wait_for_selector("h1", timeout_ms=5000)
-browser_wait_for_text("Some text", timeout_ms=5000)
+browser_wait_for_selector("h1", timeout_ms=2000)
+browser_wait_for_text("Some text", timeout_ms=2000)
 browser_go_back()
 browser_go_forward()
 browser_reload()
@@ -99,15 +96,15 @@ All return real URLs and titles. On a fast page `navigate(wait_until="load")` re
 
 ### Timing expectations (measured against real sites)
 
-| Site | Navigate load time |
-|---|---|
-| example.com | 100–400 ms |
-| wikipedia.org | 200–500 ms |
-| reddit.com | 1.5–2 s |
-| x.com/twitter | 1.2–1.6 s |
-| linkedin.com (logged in) | 4–5 s |
+| Site                     | Navigate load time |
+| ------------------------ | ------------------ |
+| example.com              | 100–400 ms         |
+| wikipedia.org            | 200–500 ms         |
+| reddit.com               | 1.5–2 s            |
+| x.com/twitter            | 1.2–1.6 s          |
+| linkedin.com (logged in) | 4–5 s              |
 
-Use `timeout_ms=20000` for LinkedIn and other heavy SPAs to give them margin.
+For LinkedIn and other heavy SPAs, rely on `sleep()` after navigation to let the page hydrate.
 
 ### After navigate, always let SPA hydrate
 
@@ -116,7 +113,7 @@ Even after `wait_until="load"`, React/Vue SPAs often render their real chrome in
 ### Reading pages efficiently
 
 - **Prefer `browser_snapshot` over `browser_get_text("body")`** — returns a compact ~1–5 KB accessibility tree vs 100+ KB of raw HTML.
-- Interaction tools (`browser_click`, `browser_type`, `browser_fill`, `browser_scroll`, etc.) return a page snapshot automatically in their result. Use it to decide your next action — do NOT call `browser_snapshot` separately after every action. Only call `browser_snapshot` when you need a fresh view without performing an action, or after setting `auto_snapshot=false`.
+- Interaction tools (`browser_click`, `browser_type`, `browser_type_focused`, `browser_fill`, `browser_scroll`, etc.) return a page snapshot automatically in their result. Use it to decide your next action — do NOT call `browser_snapshot` separately after every action. Only call `browser_snapshot` when you need a fresh view without performing an action, or after setting `auto_snapshot=false`.
 - Complex pages (LinkedIn, Twitter/X, SPAs with virtual scrolling) have DOMs that don't match what's visually rendered — snapshot refs may be stale, missing, or misaligned with visible layout. On these pages, `browser_screenshot` is the only reliable way to orient yourself.
 - Only fall back to `browser_get_text` for extracting specific small elements by CSS selector.
 
@@ -128,7 +125,7 @@ Even after `wait_until="load"`, React/Vue SPAs often render their real chrome in
 
 Why this is necessary:
 
-- **React / Vue controlled components** don't trust JS-sourced `.focus()`. React uses event delegation and watches for *native* pointer/focus events — a `click` dispatched via CDP fires the real `pointerdown`/`pointerup`/`click`/`focus` sequence that React listens to, and updates its internal state. A JS-only `.focus()` sets `document.activeElement` but the framework's controlled state doesn't see it.
+- **React / Vue controlled components** don't trust JS-sourced `.focus()`. React uses event delegation and watches for _native_ pointer/focus events — a `click` dispatched via CDP fires the real `pointerdown`/`pointerup`/`click`/`focus` sequence that React listens to, and updates its internal state. A JS-only `.focus()` sets `document.activeElement` but the framework's controlled state doesn't see it.
 - **Draft.js** (X/Twitter compose) and **Lexical** (Gmail, LinkedIn DMs) use contenteditable divs with immutable editor state. They only enter "edit mode" after a real click on the editor surface. Typing at them without clicking routes keys to `document.body` or gets silently discarded.
 - **Send/submit buttons are bound to framework state**, not DOM state. They're typically `disabled={!hasRealContent}` where `hasRealContent` is computed from React/Vue/Svelte state. The input field can have characters in the DOM but the button stays disabled because the framework never saw a real input event.
 
@@ -136,44 +133,15 @@ The symptom is always the same: **you type, the characters appear visually, and
 
 ### Safe "click-then-type-then-verify" pattern
 
-```
-# 1. Focus the real element via a real click (not JS .focus()).
-rect = browser_get_rect(selector)             # or browser_shadow_query for shadow sites
-browser_click_coordinate(rect.cx, rect.cy)
-sleep(0.5)                                     # let the editor open / focus settle
+1. **Focus** the real element via a real click (not JS `.focus()`). Use `browser_get_rect(selector)` (or `browser_shadow_query` for shadow sites) to get coordinates, then `browser_click_coordinate(cx, cy)`. Wait ~0.5 s for the editor to open and focus to settle.
 
-# 2. Type. browser_type now uses CDP Input.insertText by default, which is
-#    the most reliable way to insert text into rich editors (Lexical,
-#    Draft.js, ProseMirror, any React-controlled contenteditable).
-browser_type(selector, text)
-sleep(1.0)                                     # let framework state commit
+2. **Type** the text. Use `browser_type(selector, text)` for light-DOM inputs, or `browser_type_focused(text=...)` for shadow-DOM / already-focused inputs. Both use CDP `Input.insertText` by default, which is the most reliable method for rich editors (Lexical, Draft.js, ProseMirror). Wait ~500 ms for framework state to commit.
 
-# 3. BEFORE clicking send, verify the submit button is actually enabled.
-#    Don't trust that typing worked — check state.
-state = browser_evaluate("""
-    (function(){
-      const btn = document.querySelector('[data-testid="tweetButton"]');
-      if (!btn) return {exists: false};
-      return {
-        exists: true,
-        disabled: btn.disabled || btn.getAttribute('aria-disabled') === 'true',
-        text: btn.textContent.trim(),
-      };
-    })()
-""")
+3. **Verify** the submit button is enabled before clicking it. Use `browser_evaluate` to check the button's `disabled` or `aria-disabled` attribute. Do NOT trust that typing worked — always check state.
 
-# 4. Only click send if the button is enabled.
-if not state['disabled']:
-    browser_click(submit_selector)
-else:
-    # Recovery: sometimes a click-again + one extra keystroke nudges
-    # React into recomputing hasRealContent.
-    browser_click_coordinate(rect.cx, rect.cy)
-    browser_press("End")
-    browser_press(" ")
-    browser_press("Backspace")
-    # re-check state
-```
+   **Partial visibility is fine.** Small single-line inputs, chat boxes with fixed width, and search fields commonly clip or truncate long text visually — only the tail or head may be shown on screen. Don't treat that as failure. What matters is that the framework accepted the input: the submit button enabled, or `element.value` / `innerText` read via `browser_evaluate` contains the full string. If the visible pixels don't match what you typed but the button is enabled and the underlying value is correct, typing succeeded — proceed.
+
+4. **Only click send if the button is enabled.** If the button is still disabled, try the recovery dance: click the textarea again, press `End`, press a space, press `Backspace` — this forces React to recompute `hasRealContent`. Then re-check the button state.
 
 ### Why `browser_type` uses `Input.insertText` by default
 
@@ -206,16 +174,16 @@ Always include an equivalent cleanup block in any script that types into a compo
 
 ### Verified site-specific quirks
 
-| Site | Editor | Workaround |
-|---|---|---|
-| **X / Twitter** compose | Draft.js | Click `[data-testid='tweetTextarea_0']` first, then type with `delay_ms=20`. First 1-2 chars may be eaten — accept truncation or prepend a throwaway char. Verify `[data-testid='tweetButton']` has `disabled: false` before clicking. |
-| **LinkedIn** messaging | contenteditable (inside `#interop-outlet` shadow root) | Use `browser_shadow_query` to find the rect, click-coordinate to focus, then type via focus-based key dispatch (selector-based type can't reach shadow). Send button is `.msg-form__send-button`. |
-| **LinkedIn** feed post composer | Quill/LinkedIn custom | Click the "Start a post" trigger first, wait 1s for modal, click the textarea, type. |
-| **Reddit** comment/post box | ProseMirror | Click the textarea, wait 0.5s for the toolbar to mount, then type. Submit is `button[slot="submit-button"]` inside a shreddit-composer. |
-| **Gmail** compose | Lexical | Click the body first. Gmail has a visible `div[contenteditable=true][aria-label*='Message Body']` after opening a compose window. |
-| **Slack** message box | contenteditable | Click first, then type. Send is a paper-plane button with `data-qa='texty_send_button'`. |
-| **Discord** | Slate | Click first. Discord's send is implicit on Enter (no button), so just press Enter after typing. |
-| **Monaco** editors (GitHub code review, CodeSandbox) | Monaco | Click first, type with `delay_ms=10`. Monaco listens for `textarea` input events on a hidden textarea — requires focus to be on that textarea. |
+| Site                                                 | Editor                                                 | Workaround                                                                                                                                                                                                                             |
+| ---------------------------------------------------- | ------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **X / Twitter** compose                              | Draft.js                                               | Click `[data-testid='tweetTextarea_0']` first, then type with `delay_ms=20`. First 1-2 chars may be eaten — accept truncation or prepend a throwaway char. Verify `[data-testid='tweetButton']` has `disabled: false` before clicking. |
+| **LinkedIn** messaging                               | contenteditable (inside `#interop-outlet` shadow root) | Use `browser_shadow_query` to find the rect, click-coordinate to focus, then `browser_type_focused(text=...)` (selector-based `browser_type` can't reach shadow). Send button is `.msg-form__send-button`.                             |
+| **LinkedIn** feed post composer                      | Quill/LinkedIn custom                                  | Click the "Start a post" trigger first, wait 1s for modal, click the textarea, type.                                                                                                                                                   |
+| **Reddit** comment/post box                          | ProseMirror                                            | Click the textarea, wait 0.5s for the toolbar to mount, then type. Submit is `button[slot="submit-button"]` inside a shreddit-composer.                                                                                                |
+| **Gmail** compose                                    | Lexical                                                | Click the body first. Gmail has a visible `div[contenteditable=true][aria-label*='Message Body']` after opening a compose window.                                                                                                      |
+| **Slack** message box                                | contenteditable                                        | Click first, then type. Send is a paper-plane button with `data-qa='texty_send_button'`.                                                                                                                                               |
+| **Discord**                                          | Slate                                                  | Click first. Discord's send is implicit on Enter (no button), so just press Enter after typing.                                                                                                                                        |
+| **Monaco** editors (GitHub code review, CodeSandbox) | Monaco                                                 | Click first, type with `delay_ms=10`. Monaco listens for `textarea` input events on a hidden textarea — requires focus to be on that textarea.                                                                                         |
 
 ### Plain text into a real input
 
@@ -229,7 +197,7 @@ browser_type(selector, text)
 - Fires real `keydown` / `keypress` / `input` / `keyup` events — frameworks that branch on `event.key` or `event.code` see the right values
 - Matches what Playwright and Puppeteer send
 
-Works on real `<input>`, `<textarea>`, and `contenteditable` elements. For shadow-DOM inputs, see the "shadow-heavy sites" section above — `type_text(selector=)` can't see past shadow boundaries.
+Works on real `<input>`, `<textarea>`, and `contenteditable` elements. For shadow-DOM inputs, see the "shadow-heavy sites" section above — `browser_type(selector=)` can't see past shadow boundaries; use `browser_type_focused` after click-coordinate focus.
 
 ### Keyboard shortcuts (Ctrl+A, Shift+Tab, Cmd+Enter)
 
@@ -251,25 +219,15 @@ Recognized without modifiers: `Enter`, `Tab`, `Escape`, `Backspace`, `Delete`, `
 ## Screenshots
 
 ```
-browser_screenshot()                    # viewport, 900 px wide by default
-browser_screenshot(full_page=True)      # full scrollable page
+browser_screenshot()                    # viewport, 800 px wide JPEG
+browser_screenshot(full_page=True)      # full scrollable page (overview only — don't click off a full-page shot)
 browser_screenshot(selector="#header")  # clip to element's rect
 ```
 
-Returns a PNG with automatic downscaling to a target width (default 900 px) plus a JSON metadata block containing `cssWidth`, `devicePixelRatio`, `physicalScale`, `cssScale`, and a `scaleHint` string. The image is also annotated with a highlight rectangle/dot showing the last interaction (click, hover, type) if one happened on this tab.
+Returns a JPEG (quality 75, ~50–120 KB) at 800 px wide. The pixel width is purely a bandwidth choice; all tool coordinates are fractions of the viewport and are invariant to image size. Metadata includes `imageWidth` (800), `cssWidth`, `cssHeight` (for reference), and `physicalScale`. The image is annotated with a highlight rectangle/dot showing the last interaction (click, hover, type) if one happened on this tab.
 
 The highlight overlay stays visible on the page for **10 seconds** after each interaction, then fades. Before a screenshot is likely, make sure your click / hover / type happens <10 s before the screenshot.
 
-### Anatomy of the scale fields
-
-- `cssWidth` = `window.innerWidth` (CSS px)
-- `devicePixelRatio` = `window.devicePixelRatio` (often 1.6, 2, or 3 on modern displays)
-- `physicalScale = png_width / image_width` (how many physical-px per image-px)
-- `cssScale = cssWidth / image_width` (how many CSS-px per image-px)
-- Effective DPR = `physicalScale / cssScale` (should match `devicePixelRatio`)
-
-When converting image coordinates for clicks, always use `cssScale`. The `physicalScale` field is there for debugging HiDPI displays, not for inputs.
-
 ## Scrolling
 
 - Use large scroll amounts (~2000) when loading more content — sites like Twitter and LinkedIn have lazy loading for paging.
@@ -292,6 +250,7 @@ When converting image coordinates for clicks, always use `cssScale`. The `physic
 - Popup appeared that you didn't need? Close it immediately
 
 `browser_tabs` returns an `origin` field for each tab:
+
 - `"agent"` — you opened it; you own it; close it when done
 - `"popup"` — opened by a link or script; close after extracting what you need
 - `"startup"` or `"user"` — leave these alone unless the task requires it
@@ -304,41 +263,41 @@ The bridge automatically evicts per-tab state (`_cdp_attached`, `_interaction_hi
 
 ### LinkedIn
 
-| Target | Selector |
-|---|---|
-| Global search input | `input[data-testid='typeahead-input']` |
-| Own profile link | `a[href*='linkedin.com/in/']` |
-| Messaging overlay | `#interop-outlet >>> [aria-label]` (use shadow_query) |
+| Target              | Selector                                              |
+| ------------------- | ----------------------------------------------------- |
+| Global search input | `input[data-testid='typeahead-input']`                |
+| Own profile link    | `a[href*='linkedin.com/in/']`                         |
+| Messaging overlay   | `#interop-outlet >>> [aria-label]` (use shadow_query) |
 
 LinkedIn enforces **strict Trusted Types CSP**. Any script you inject via `browser_evaluate` that uses `innerHTML = "<...>"` will be **silently dropped** — the wrapper element gets added but its content is empty, no console error. Always use `createElement` + `appendChild` + `setAttribute` for DOM injection on LinkedIn. `style.cssText`, `textContent`, and `.value` assignments are fine (they don't go through the Trusted Types sink).
 
 ### Reddit (new reddit / shreddit)
 
-| Target | Selector |
-|---|---|
+| Target                | Selector                                                                     |
+| --------------------- | ---------------------------------------------------------------------------- |
 | Search input (shadow) | `reddit-search-large >>> #search-input` (rect only; type via click-to-focus) |
-| Reddit logo (home) | `#reddit-logo` |
-| Subreddit posts | `shreddit-post` custom elements |
-| Create post button | `a[href*='/submit']` |
+| Reddit logo (home)    | `#reddit-logo`                                                               |
+| Subreddit posts       | `shreddit-post` custom elements                                              |
+| Create post button    | `a[href*='/submit']`                                                         |
 
 Reddit's search input lives **two shadow levels deep** inside `reddit-search-large > faceplate-search-input`. You cannot reach it with `browser_type(selector=)`. The working pattern:
 
 1. `browser_shadow_query("reddit-search-large >>> #search-input")` → rect
 2. `browser_click_coordinate(rect.cx, rect.cy)` → click lands on the real shadow input via native hit testing; input becomes focused
-3. `browser_press(c)` for each character → dispatches to focused element
+3. `browser_type_focused(text="query")` → dispatches to focused element via `Input.insertText`
 4. Verify by reading `.value` via `browser_evaluate` walking the shadow path
 
 ### X / Twitter
 
-| Target | Selector |
-|---|---|
-| Main search input | `input[data-testid='SearchBox_Search_Input']` |
-| Home nav link | `a[data-testid='AppTabBar_Home_Link']` |
-| Post text area (compose) | `[data-testid='tweetTextarea_0']` |
-| Reply buttons on feed | `[data-testid='reply']` |
-| Post / Tweet submit button | `[data-testid='tweetButton']` |
-| Caret (⋯) menu on a post | `[data-testid='caret']` |
-| Confirmation sheet button | `[data-testid='confirmationSheetConfirm']` |
+| Target                     | Selector                                      |
+| -------------------------- | --------------------------------------------- |
+| Main search input          | `input[data-testid='SearchBox_Search_Input']` |
+| Home nav link              | `a[data-testid='AppTabBar_Home_Link']`        |
+| Post text area (compose)   | `[data-testid='tweetTextarea_0']`             |
+| Reply buttons on feed      | `[data-testid='reply']`                       |
+| Post / Tweet submit button | `[data-testid='tweetButton']`                 |
+| Caret (⋯) menu on a post   | `[data-testid='caret']`                       |
+| Confirmation sheet button  | `[data-testid='confirmationSheetConfirm']`    |
 
 **X uses Draft.js for the compose text editor**, which does NOT accept synthetic input reliably. Working workaround: `browser_type(selector='[data-testid="tweetTextarea_0"]', text="...", delay_ms=20)`. The delay gives Draft.js time to process each keystroke. The first 1–2 characters may still get eaten — accept minor truncation or prepend a throwaway character. After typing, check `[data-testid="tweetButton"]` has `disabled: false` before clicking submit.
 
@@ -394,11 +353,12 @@ Then pass the most specific selector that uniquely identifies the right input (e
 - **Typing into a rich-text editor without clicking first → send button stays disabled.** Draft.js (X), Lexical (Gmail, LinkedIn DMs), ProseMirror (Reddit), and React-controlled `contenteditable` elements only register input as "real" when the element received a native focus event — JS-sourced `.focus()` is not enough. `browser_type` now does this automatically via a real CDP pointer click before inserting text, but always verify the submit button's `disabled` state before clicking send. See the "ALWAYS click before typing" section above.
 - **Using per-character `keyDown` on Lexical / Draft.js editors → keys dispatch but text never appears.** Those editors intercept `beforeinput` and route insertion through their own state machine; raw keyDown events are silently dropped. `browser_type` now uses `Input.insertText` by default (the CDP IME-commit method) which these editors accept cleanly. Only set `use_insert_text=False` when you explicitly need per-keystroke dispatch.
 - **Leaving a composer with text then trying to navigate → `beforeunload` dialog hangs the bridge.** LinkedIn and several other sites pop a native "unsent message" confirm. `browser_navigate` and `close_tab` both time out against this. Always strip `window.onbeforeunload = null` via `browser_evaluate` before any navigation after typing in a composer, or wrap your logic in a `try/finally` that runs the cleanup block.
-- **Clicking at physical pixels.** CDP uses CSS px. `browser_coords` returns both for debugging, but always feed `css_x/y` to click tools.
+- **Click landed in the wrong region (sidebar / header instead of target).** Check `focused_element` in the click response — it's ground truth for what actually got focused, including the `inFrame` breadcrumb when focus ends up inside a same-origin iframe. If it isn't the target (e.g. `className: "msg-conversation-listitem__link"` when you meant to hit a composer), adjust the fraction and retry. Coordinates you pass are fractions of the viewport; the tool multiplies by `cssWidth` / `cssHeight` internally, so a wrong result means your estimated proportion was off — not that any scale went sideways.
+- **Accidentally passing pixels to click / hover / press_at.** The tools reject any coord outside `[-0.1, 1.5]` with a clear error. If you see that error, you passed a pixel (like 815) instead of a fraction (like 0.475). Use `browser_get_rect` to get exact fractional cx/cy, or read proportions off `browser_screenshot`.
 - **Calling `wait_for_selector` on a shadow element.** It'll always time out. Use `browser_shadow_query` or the screenshot + coordinate strategy.
 - **Relying on `innerHTML` in injected scripts on LinkedIn.** Silently discarded. Use `createElement` + `appendChild`.
 - **Not waiting for SPA hydration.** `wait_until="load"` fires before React/Vue rendering on many sites. Add a 2–3 s sleep before querying for chrome elements.
-- **Using `browser_type(selector)` on LinkedIn DMs or any shadow-DOM input.** Won't find the element. Fall back to click-to-focus + `browser_press` per character.
+- **Using `browser_type(selector)` on LinkedIn DMs or any shadow-DOM input.** Won't find the element. Use `browser_click_coordinate` to focus, then `browser_type_focused(text=...)` to type.
 - **Clicking a "Photo" / "Attach" / "Upload" button to pick a file.** This opens Chrome's NATIVE OS file picker, which is rendered outside the web page and cannot be interacted with via CDP. Your automation will hang staring at an unreachable dialog. ALWAYS use `browser_upload(selector, file_paths)` against the underlying `<input type='file'>` element — see the "File uploads" section above for the full pattern. This is the single most common way to wedge a browser session on compose-with-media flows (X/LinkedIn/Gmail).
 - **Keyboard shortcuts without the `code` field.** Chrome's shortcut dispatcher ignores keyboard events that lack a `code` or `windowsVirtualKeyCode`. `browser_press(..., modifiers=[...])` populates these automatically; raw `Input.dispatchKeyEvent` calls from `browser_evaluate` may not.
 - **Taking a screenshot more than 10s after the last interaction** and expecting the highlight to still be visible. The overlay fades after 10s. Take the screenshot sooner, or re-trigger the interaction.
@@ -410,21 +370,39 @@ If Chrome detaches the debugger for its own reasons (tab closed, user opened Dev
 
 If reattach also fails, you'll get the underlying CDP error string — that's a real problem, usually the tab is gone.
 
-## When to reach for `browser_evaluate`
+## `browser_evaluate` is a last-resort escape hatch
 
-Use it when:
-- You need to read state from inside a shadow root that `browser_get_rect` doesn't handle
-- You need a one-shot JS snippet to trigger a site-specific action (scroll a specific container, open a menu, set a form field value directly)
-- You need to walk an AX tree or measure layout that the standard tools don't expose
+**Before using `browser_evaluate`, try these first — in this order:**
 
-Avoid it when:
-- A standard tool (`browser_click_coordinate`, `browser_type`, `browser_press`) already does what you need. Those go through CDP's native event pipeline, which real sites trust more than synthetic JS dispatch.
-- You're on a strict-CSP site and want to inject DOM — stick to `createElement` + `appendChild`, never `innerHTML`.
-- You need to trigger React / Vue / framework state changes — those frameworks watch for real browser events (`input`, `change`, `click`), not scripted `dispatchEvent` calls. Native-event tools are more reliable.
+1. **`browser_screenshot` + `browser_click_coordinate`** — works on every site regardless of shadow DOM, iframes, obfuscated classes. This is the default path for "click a thing you can see."
+2. **`browser_type(use_insert_text=True, text=...)`** — for typing into ANY input/contenteditable, including Lexical and Draft.js. Handles click-focus-insert with built-in retries. Do **not** call `document.execCommand('insertText')` via evaluate; this tool already does it correctly.
+3. **`browser_shadow_query`** or **`browser_get_rect(selector)`** with the `>>>` shadow-piercing syntax — for selector-based lookups across shadow roots.
+4. **`browser_get_text` / `browser_get_attribute`** — for reading element state by selector.
+5. **`browser_snapshot`** — for dumping the accessibility tree of the page.
+
+If all five of those fit your goal, **do not use `browser_evaluate`.** Each evaluate call is a small LLM round-trip of ~30-100 tokens of JS plus a JSON response; five of them burn more context than a single screenshot-and-coordinate does, with less reliability.
+
+### Anti-patterns — stop immediately if you catch yourself doing these
+
+- **Trying multiple `querySelectorAll` variants when the first returned `[]`.** Different selectors on the same page rarely work if the first guess failed — modern SPAs obfuscate class names at build time. After one empty result, switch to `browser_screenshot` + `browser_click_coordinate`. Do not write `.artdeco-list__item`, then `[data-test-incoming-invitation-card]`, then `[class*="invitation"]` — you are already on the wrong path.
+- **Writing `walk(root)` recursive shadow-DOM traversal functions.** Use `browser_shadow_query` — it traverses at the CDP level (native C++), not by re-running a recursive JS function every call.
+- **Calling `document.execCommand('insertText', ...)` to type into a contenteditable.** Use `browser_type(use_insert_text=True, text='...')`. The high-level tool handles the exact same Lexical/Draft.js case but with click-focus-retry logic built in.
+- **Accessing `iframe.contentDocument`.** Rarely works (cross-origin, late hydration) and when it does, the code is brittle. Use `browser_screenshot` to see the iframe, then `browser_click_coordinate` to interact.
+- **Using `innerHTML = "<...>"` on a Trusted Types site (LinkedIn, GitHub).** The assignment is silently dropped. Use `createElement` + `appendChild` if you must inject DOM — but first, ask whether you really need to.
+- **Triggering React/Vue state via synthetic `dispatchEvent`.** Frameworks watch for real browser events. Use `browser_click_coordinate`, `browser_press`, or `browser_type` — all go through CDP's native event pipeline.
+
+### Legitimate uses (when nothing semantic fits)
+
+- Reading a computed style, `window.innerWidth/Height`, `document.scrollingElement.scrollTop`, or other layout values the tools don't expose.
+- Firing a one-shot site-specific API call (analytics beacon, feature-flag toggle).
+- Stripping `onbeforeunload` before navigating away from a page with an unsent draft (LinkedIn, Gmail).
+- Detecting whether a specific shadow-root host exists before a follow-up screenshot.
+
+In all of these cases the script is SHORT (< 10 lines) and the result is CONSUMED (read, then acted on), not further probed.
 
 ## Login & auth walls
 
-- If you see a "Log in" or "Sign up" prompt, report the auth wall immediately — do NOT attempt to log in.
+- If you see a "Log in" or "Sign up" prompt, report the auth wall to user immediately — do NOT attempt to log in.
 - Check for cookie consent banners and dismiss them if they block content.
 
 ## Error recovery
@@ -461,9 +439,8 @@ sleep(2)
 # Shadow-pierce the nested search input
 sq = browser_shadow_query("reddit-search-large >>> #search-input")
 browser_click_coordinate(sq.rect.cx, sq.rect.cy)
-# Typing can't use selector (shadow); focused input receives raw key presses
-for c in "python":
-    browser_press(c)
+# Typing can't use selector (shadow); use browser_type_focused on the focused input
+browser_type_focused(text="python")
 browser_screenshot()
 browser_press("Escape")
 ```
@@ -471,7 +448,7 @@ browser_press("Escape")
 ### Search LinkedIn and dismiss without submitting
 
 ```
-browser_navigate("https://www.linkedin.com/feed/", wait_until="load", timeout_ms=20000)
+browser_navigate("https://www.linkedin.com/feed/", wait_until="load")
 sleep(3)
 browser_wait_for_selector("input[data-testid='typeahead-input']", timeout_ms=5000)
 rect = browser_get_rect("input[data-testid='typeahead-input']")

core/framework/skills/_default_skills/colony-progress-tracker/SKILL.md

@@ -4,6 +4,7 @@ description: Claim tasks, record step progress, and verify SOP gates in the colo
 metadata:
   author: hive
   type: default-skill
+  visibility: [worker]
 ---
 
 ## Operational Protocol: Colony Progress Tracker

core/framework/skills/_default_skills/context-preservation/SKILL.md

@@ -4,6 +4,7 @@ description: Proactively extract critical values from tool results into working
 metadata:
   author: hive
   type: default-skill
+  visibility: [worker]
 ---
 
 ## Operational Protocol: Context Preservation

core/framework/skills/_default_skills/error-recovery/SKILL.md

@@ -4,6 +4,7 @@ description: Follow a structured recovery decision tree when tool calls fail ins
 metadata:
   author: hive
   type: default-skill
+  visibility: [worker]
 ---
 
 ## Operational Protocol: Error Recovery

core/framework/skills/_default_skills/linkedin-automation/SKILL.md

@@ -13,15 +13,37 @@ metadata:
 
 LinkedIn is the hardest mainstream site to automate because it combines **shadow DOM** (`#interop-outlet` for messaging), **strict Trusted Types CSP** (silently drops `innerHTML`), **heavy React reconciliation** (injected nodes get stripped on re-render), **native `beforeunload` draft dialogs** (hang the bridge), and **aggressive spam filters**. Every one of those has bit us at least once. This skill documents what actually works.
 
-**Always activate `browser-automation` first.** This skill assumes you already know about CSS-px coordinates, `browser_type`'s click-first behavior, and `browser_shadow_query`. The guidance below is LinkedIn-specific; general browser rules are there.
+**Always activate `browser-automation` first.** This skill assumes you already know about CSS-px coordinates, `browser_type`/`browser_type_focused`, and `browser_shadow_query`. The guidance below is LinkedIn-specific; general browser rules are there.
+
+## Rule #0: screenshot + coordinates, not selectors
+
+LinkedIn changes class names aggressively and hides composers inside shadow roots AND iframes. **Selectors break constantly.** Your default strategy on every LinkedIn page should be:
+
+1. `browser_screenshot()` — see the page visually
+2. Pick the target's position from the image
+3. `browser_coords(image_x, image_y)` → get CSS pixels
+4. `browser_click_coordinate(css_x, css_y)` — reaches shadow DOM, iframes, and React elements indifferently
+5. `browser_type(use_insert_text=True, text=...)` — types into whatever is focused, including Lexical composers
+
+**If `browser_evaluate(...querySelectorAll...)` returns `[]` even once, do not try a different selector.** Stop, screenshot, and click. The "what if I try `.artdeco-list__item` next" instinct has burned ~50 tool calls in real sessions before the agent pivoted. Don't fall into that loop.
+
+The selectors in the table below are **only** for when you already know the target is in the light DOM and you want a faster path than screenshot+coord. **When in doubt, default to coordinates.**
+
+## Invitation manager — inline message button path is BROKEN
+
+If the user asks to message a connection request **from the invitation manager page without accepting first**, the inline "Message" button opens a composer inside a nested **iframe overlay** (not a shadow root). The iframe's `contentDocument` is either cross-origin-blocked or not hydrated at access time. This path is **not reliably automatable today.**
+
+**Redirect:** click the person's name/profile link on the card, go to the profile page, and use the standard Profile Message flow below. The profile flow is battle-tested; the inline-iframe flow isn't.
+
+If you end up writing `document.activeElement.tagName === 'IFRAME'` inside a `browser_evaluate`, you've hit this trap. Stop and go to the profile page.
 
 ## Timing expectations
 
-- `browser_navigate(wait_until="load", timeout_ms=20000)` — LinkedIn takes **4–5 seconds** to load the feed cold. Default 30s timeout is fine; use 20s as a floor.
+- `browser_navigate(wait_until="load")` — LinkedIn takes **4–5 seconds** to load the feed cold.
 - After navigation, **always `sleep(3)`** to let React hydrate the profile/feed chrome before querying selectors. Without the sleep `wait_for_selector` will flake on elements that exist moments later.
 - Composer modal slide-in takes **~2 seconds** after you click the Message button.
 
-## Verified selectors (2026-04-11)
+## Verified selectors
 
 | Target | Selector | Notes |
 |---|---|---|
@@ -34,14 +56,14 @@ LinkedIn is the hardest mainstream site to automate because it combines **shadow
 | Pending connection card | `.invitation-card, .invitations-card, [data-test-incoming-invitation-card]` | Filter out "invited you to follow" / "subscribe" cards |
 | Accept button | `button[aria-label*="Accept"]` within the card scope | Per-card scoping is critical — there are many Accept buttons on the page |
 
-LinkedIn changes class names aggressively. If a class-based selector breaks, fall back to **`browser_screenshot` → visual identification → `browser_coords` → `browser_click_coordinate`**. The screenshot + coord path works regardless of class-name churn and regardless of shadow DOM.
+LinkedIn changes class names aggressively. If a class-based selector breaks, fall back to **`browser_screenshot` → visual identification → `browser_click_coordinate`** with the pixel you read straight off the image (screenshots are CSS-sized, no conversion). The screenshot + coord path works regardless of class-name churn and regardless of shadow DOM.
 
 ## Profile Message flow (verified end-to-end 2026-04-11)
 
 ```
 # 1. Load the profile
-browser_navigate("https://www.linkedin.com/in/<username>/", wait_until="load", timeout_ms=20000)
-sleep(4)
+browser_navigate("https://www.linkedin.com/in/<username>/", wait_until="load")
+sleep(3)
 
 # 2. Strip onbeforeunload before any state-mutating work — prevents draft-dialog deadlock later
 browser_evaluate("""
@@ -98,19 +120,18 @@ textarea = browser_evaluate("""
 browser_click_coordinate(textarea['cx'], textarea['cy'])
 sleep(0.6)
 
-# 6. Insert text via document.execCommand('insertText') through browser_evaluate.
-#    This is the ONLY reliable approach for LinkedIn's Lexical composer.
-#    See the "Lexical composer quirks" section below for why browser_type
-#    with a selector does NOT work here (the contenteditable lives inside
-#    the #interop-outlet shadow root which document.querySelector can't
-#    reach). The click in step 5 already put Lexical into edit mode, so
-#    execCommand injects straight into the focused editor's state.
-browser_evaluate("""
-  (function(){
-    document.execCommand('insertText', false, %s);
-    return true;
-  })();
-""" % json.dumps(message_text))   # json.dumps gives you a safely-escaped JS string literal
+# 6. Insert text via browser_type_focused. This dispatches CDP
+#    Input.insertText to document.activeElement — the same underlying
+#    mechanism as execCommand('insertText') but with no JSON escaping,
+#    no browser_evaluate round trip, and built-in retry. The click in
+#    step 5 already focused Lexical, so insertText lands in the editor
+#    regardless of the shadow wrapping around #interop-outlet.
+#
+#    Use browser_type_focused (not browser_type) here — browser_type
+#    requires a selector, which cannot see past the #interop-outlet
+#    shadow root. browser_type_focused targets document.activeElement
+#    directly, sidestepping shadow boundaries entirely.
+browser_type_focused(text=message_text)
 sleep(1.0)   # let Lexical commit state + enable Send button
 
 # 7. Find the modal Send button (filter by in-viewport, reject pinned bar)
@@ -143,20 +164,21 @@ send = browser_evaluate("""
   })();
 """)
 
-# 8. ONLY click Send if it's enabled — if disabled, the execCommand
+# 8. ONLY click Send if it's enabled — if disabled, the insertText
 #    didn't land. DO NOT retry with a different tool; the fix is
-#    always: re-click the composer rect, re-run execCommand, re-check.
-#    The Send button's `disabled` state IS the ground truth — if
-#    Lexical registered your text, it enables the button. If it's
+#    always: re-click the composer rect, re-run browser_type_focused(text=...),
+#    re-check. The Send button's `disabled` state IS the ground truth —
+#    if Lexical registered your text, it enables the button. If it's
 #    still disabled, your text did not reach the editor, regardless
 #    of what any tool call claims.
 if send['disabled']:
     # The editor didn't receive your text. Do NOT click Send. Do NOT
-    # fall back to browser_type with a dummy selector (see anti-pattern
-    # in Common Pitfalls). Instead: re-click the textarea rect from
-    # step 4, wait a beat, re-run the execCommand insertText from step
-    # 6. If that still fails after 2 retries, bail and surface — the
-    # modal may have been reclaimed by a stale state or auth wall.
+    # fall back to browser_type with a selector (see anti-pattern in
+    # Common Pitfalls — selector-based type can't reach the shadow-DOM
+    # composer). Instead: re-click the textarea rect from step 4, wait
+    # a beat, re-run browser_type_focused(text=message_text) from
+    # step 6. If that still fails after 2 retries, bail and surface —
+    # the modal may have been reclaimed by a stale state or auth wall.
     raise Exception("Send button disabled after insertText — editor did not receive input")
 
 browser_click_coordinate(send['cx'], send['cy'])
@@ -171,7 +193,7 @@ Daily outbound pattern — accept pending connection requests and send a templat
 
 ```
 browser_navigate("https://www.linkedin.com/mynetwork/invitation-manager/received/",
-                 wait_until="load", timeout_ms=20000)
+                 wait_until="load")
 sleep(4)
 browser_evaluate("(function(){window.onbeforeunload=null;})()")
 
@@ -215,7 +237,7 @@ for card in cards[:25]:
 ## Feed post composer flow
 
 ```
-browser_navigate("https://www.linkedin.com/feed/", wait_until="load", timeout_ms=20000)
+browser_navigate("https://www.linkedin.com/feed/", wait_until="load")
 sleep(4)
 browser_evaluate("(function(){window.onbeforeunload=null;})()")
 
@@ -302,7 +324,7 @@ If the image isn't already on disk, write it first with `write_file(absolute_pat
 
 ## Rate limits and safety
 
-LinkedIn's abuse detection is aggressive. Respect these limits:
+LinkedIn's abuse detection is aggressive. Beware of the limits, let user know but dare to break them if user confirms.:
 
 | Action | Limit |
 |---|---|
@@ -310,8 +332,7 @@ LinkedIn's abuse detection is aggressive. Respect these limits:
 | Outbound messages to new 1st-degree connections | **25/day max**, 5–10s randomized delays |
 | Connection request sends | **100/week max**, spread across days, warm intros preferred |
 | Profile views | Several hundred/day is usually fine but varies by account age |
-| Post publications | 1–3/day, no URL-only posts |
-| Feed reactions | Dozens/day is fine; vary your activity mix |
+| Post publications | 1–5/day, no URL-only posts |
 
 Signals you're being throttled:
 - "Message failed to send" with no error detail
@@ -324,9 +345,8 @@ If any of those show up, **stop the run, screenshot the state, and surface the i
 ## Common pitfalls
 
 - **`innerHTML` injection is silently dropped** — LinkedIn's Trusted Types CSP discards any `innerHTML = "<...>"` from injected scripts, no console error. Always use `createElement` + `appendChild` + `setAttribute` for DOM injection. `textContent`, `style.cssText`, and `.value` assignments are fine.
-- **Do NOT use `browser_type` on the message composer — use `document.execCommand('insertText', false, text)` via `browser_evaluate` instead.** The Lexical contenteditable lives inside the `#interop-outlet` shadow root which `document.querySelector` (what `browser_type` uses under the hood) cannot see. Attempts to work around this with `browser_shadow_query` fail because `browser_type` doesn't support the `>>>` shadow-pierce syntax. The ONLY reliable insert path is: (1) `browser_click_coordinate` on the composer rect (put Lexical in edit mode via a real CDP pointer click) → (2) `browser_evaluate` with `document.execCommand('insertText', false, <message>)` against the focused editor. This pattern is verified end-to-end across 15+ successful sends in session `session_20260414_113244_a98cfd66` (2026-04-14).
-- **Per-char keyDown on the message composer produces empty text** — Lexical intercepts `beforeinput` and drops raw keys. Ignore `browser_type` entirely for LinkedIn DMs; use the `execCommand('insertText')` path above.
-- **ANTI-PATTERN: "inject a dummy `<div id='dummy-target'>` and pass it as the `selector` arg to `browser_type`".** This looks tempting but fails compoundingly: `browser_type` clicks the **dummy div's** rect (not the editor's), the click lands on the Lexical wrapper's non-editable chrome, the contenteditable never receives focus, and `Input.insertText` fires against nothing. The bridge will still return `{"ok": true, "action": "type", "length": N}` because it has no way to verify the text actually landed. Symptom: Send button stays `disabled: true` forever. Fix: use `execCommand('insertText')` exactly as shown in the profile-message flow above. (See `session_20260414_114820_08bd3c4d` for the failed attempt.)
+- **Use `browser_type_focused` (not `browser_type`) on the message composer.** The Lexical contenteditable lives inside the `#interop-outlet` shadow root which `document.querySelector` (what `browser_type`'s selector path uses under the hood) cannot see. `browser_type` requires a selector and will fail with "Element not found". The reliable insert path is: (1) `browser_click_coordinate` on the composer rect — the response's `focused_element` confirms Lexical received focus → (2) `browser_type_focused(text=message_text)` — CDP `Input.insertText` dispatches to `document.activeElement` regardless of shadow wrapping.
+- **Per-char keyDown on the message composer produces empty text** — Lexical intercepts `beforeinput` and drops raw keys. Use `browser_type_focused(text=..., use_insert_text=True)` after click-coordinate focused the composer. The CDP `Input.insertText` method commits as if IME fired, which Lexical accepts cleanly.
 - **Multiple Send buttons on the page** — the pinned bottom-right messaging bar has its own `msg-form__send-button` that's usually below `innerHeight`. Filter by in-viewport before clicking.
 - **`window.onbeforeunload` hangs navigation/close** — after typing in a composer, any `browser_navigate` or `close_tab` can pop a native "unsent message, leave?" confirm dialog that deadlocks the bridge. Always strip `onbeforeunload` before any navigation, and wrap composer flows in a `try/finally` that runs the cleanup block:
 
@@ -347,7 +367,7 @@ browser_evaluate("""
 
 ## Auth wall detection
 
-If you see a "Log in" / "Join LinkedIn" prompt instead of the logged-in feed, **stop immediately** and surface the issue. Do NOT attempt to log in via automation — LinkedIn's bot detection will flag the account.
+If you see a "Log in" / "Join LinkedIn" prompt instead of the logged-in feed, **stop immediately** and surface the issue to user. Do NOT attempt to log in via automation — LinkedIn's bot detection will flag the account.
 
 Check via:
 ```