Merge pull request #4304 from adenhq/fix/init-config

model selection + max_tokens in quickstart

.claude/skills/hive-create/examples/deep_research_agent/config.py

@@ -1,33 +1,8 @@
 """Runtime configuration."""
 
-import json
+from dataclasses import dataclass
-from dataclasses import dataclass, field
-from pathlib import Path
-
-
-def _load_preferred_model() -> str:
-    """Load preferred model from ~/.hive/configuration.json."""
-    config_path = Path.home() / ".hive" / "configuration.json"
-    if config_path.exists():
-        try:
-            with open(config_path) as f:
-                config = json.load(f)
-            llm = config.get("llm", {})
-            if llm.get("provider") and llm.get("model"):
-                return f"{llm['provider']}/{llm['model']}"
-        except Exception:
-            pass
-    return "anthropic/claude-sonnet-4-20250514"
-
-
-@dataclass
-class RuntimeConfig:
-    model: str = field(default_factory=_load_preferred_model)
-    temperature: float = 0.7
-    max_tokens: int = 40000
-    api_key: str | None = None
-    api_base: str | None = None
 
+from framework.config import RuntimeConfig
 
 default_config = RuntimeConfig()
 

core/framework/config.py

@@ -0,0 +1,64 @@
+"""Shared Hive configuration utilities.
+
+Centralises reading of ~/.hive/configuration.json so that the runner
+and every agent template share one implementation instead of copy-pasting
+helper functions.
+"""
+
+import json
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any
+
+from framework.graph.edge import DEFAULT_MAX_TOKENS
+
+# ---------------------------------------------------------------------------
+# Low-level config file access
+# ---------------------------------------------------------------------------
+
+HIVE_CONFIG_FILE = Path.home() / ".hive" / "configuration.json"
+
+
+def get_hive_config() -> dict[str, Any]:
+    """Load hive configuration from ~/.hive/configuration.json."""
+    if not HIVE_CONFIG_FILE.exists():
+        return {}
+    try:
+        with open(HIVE_CONFIG_FILE) as f:
+            return json.load(f)
+    except (json.JSONDecodeError, OSError):
+        return {}
+
+
+# ---------------------------------------------------------------------------
+# Derived helpers
+# ---------------------------------------------------------------------------
+
+
+def get_preferred_model() -> str:
+    """Return the user's preferred LLM model string (e.g. 'anthropic/claude-sonnet-4-20250514')."""
+    llm = get_hive_config().get("llm", {})
+    if llm.get("provider") and llm.get("model"):
+        return f"{llm['provider']}/{llm['model']}"
+    return "anthropic/claude-sonnet-4-20250514"
+
+
+def get_max_tokens() -> int:
+    """Return the configured max_tokens, falling back to DEFAULT_MAX_TOKENS."""
+    return get_hive_config().get("llm", {}).get("max_tokens", DEFAULT_MAX_TOKENS)
+
+
+# ---------------------------------------------------------------------------
+# RuntimeConfig – shared across agent templates
+# ---------------------------------------------------------------------------
+
+
+@dataclass
+class RuntimeConfig:
+    """Agent runtime configuration loaded from ~/.hive/configuration.json."""
+
+    model: str = field(default_factory=get_preferred_model)
+    temperature: float = 0.7
+    max_tokens: int = field(default_factory=get_max_tokens)
+    api_key: str | None = None
+    api_base: str | None = None

core/framework/graph/__init__.py

@@ -9,7 +9,7 @@ from framework.graph.client_io import (
 from framework.graph.code_sandbox import CodeSandbox, safe_eval, safe_exec
 from framework.graph.context_handoff import ContextHandoff, HandoffContext
 from framework.graph.conversation import ConversationStore, Message, NodeConversation
-from framework.graph.edge import EdgeCondition, EdgeSpec, GraphSpec
+from framework.graph.edge import DEFAULT_MAX_TOKENS, EdgeCondition, EdgeSpec, GraphSpec
 from framework.graph.event_loop_node import (
     EventLoopNode,
     JudgeProtocol,
@@ -58,6 +58,7 @@ __all__ = [
     "EdgeSpec",
     "EdgeCondition",
     "GraphSpec",
+    "DEFAULT_MAX_TOKENS",
     # Executor (fixed graph)
     "GraphExecutor",
     # Plan (flexible execution)

core/framework/graph/edge.py

@@ -24,10 +24,12 @@ given the current goal, context, and execution state.
 from enum import StrEnum
 from typing import Any
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, model_validator
 
 from framework.graph.safe_eval import safe_eval
 
+DEFAULT_MAX_TOKENS = 8192
+
 
 class EdgeCondition(StrEnum):
     """When an edge should be traversed."""
@@ -424,7 +426,7 @@ class GraphSpec(BaseModel):
 
     # Default LLM settings
     default_model: str = "claude-haiku-4-5-20251001"
-    max_tokens: int = 1024
+    max_tokens: int = Field(default=None)  # resolved by _resolve_max_tokens validator
 
     # Cleanup LLM for JSON extraction fallback (fast/cheap model preferred)
     # If not set, uses CEREBRAS_API_KEY -> cerebras/llama-3.3-70b or
@@ -447,6 +449,16 @@ class GraphSpec(BaseModel):
 
     model_config = {"extra": "allow"}
 
+    @model_validator(mode="before")
+    @classmethod
+    def _resolve_max_tokens(cls, values: Any) -> Any:
+        """Resolve max_tokens from the global config store when not explicitly set."""
+        if isinstance(values, dict) and values.get("max_tokens") is None:
+            from framework.config import get_max_tokens
+
+            values["max_tokens"] = get_max_tokens()
+        return values
+
     def get_node(self, node_id: str) -> Any | None:
         """Get a node by ID."""
         for node in self.nodes:

core/framework/runner/runner.py

@@ -8,8 +8,15 @@ from dataclasses import dataclass, field
 from pathlib import Path
 from typing import TYPE_CHECKING, Any
 
+from framework.config import get_hive_config, get_preferred_model
 from framework.graph import Goal
-from framework.graph.edge import AsyncEntryPointSpec, EdgeCondition, EdgeSpec, GraphSpec
+from framework.graph.edge import (
+    DEFAULT_MAX_TOKENS,
+    AsyncEntryPointSpec,
+    EdgeCondition,
+    EdgeSpec,
+    GraphSpec,
+)
 from framework.graph.executor import ExecutionResult, GraphExecutor
 from framework.graph.node import NodeSpec
 from framework.llm.provider import LLMProvider, Tool
@@ -28,9 +35,6 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger(__name__)
 
-# Configuration paths
-HIVE_CONFIG_FILE = Path.home() / ".hive" / "configuration.json"
-
 
 def _ensure_credential_key_env() -> None:
     """Load HIVE_CREDENTIAL_KEY from shell config if not already in environment.
@@ -60,17 +64,6 @@ def _ensure_credential_key_env() -> None:
 CLAUDE_CREDENTIALS_FILE = Path.home() / ".claude" / ".credentials.json"
 
 
-def get_hive_config() -> dict[str, Any]:
-    """Load hive configuration from ~/.hive/configuration.json."""
-    if not HIVE_CONFIG_FILE.exists():
-        return {}
-    try:
-        with open(HIVE_CONFIG_FILE) as f:
-            return json.load(f)
-    except (json.JSONDecodeError, OSError):
-        return {}
-
-
 def get_claude_code_token() -> str | None:
     """
     Get the OAuth token from Claude Code subscription.
@@ -268,11 +261,7 @@ class AgentRunner:
     @staticmethod
     def _resolve_default_model() -> str:
         """Resolve the default model from ~/.hive/configuration.json."""
-        config = get_hive_config()
+        return get_preferred_model()
-        llm = config.get("llm", {})
-        if llm.get("provider") and llm.get("model"):
-            return f"{llm['provider']}/{llm['model']}"
-        return "anthropic/claude-sonnet-4-20250514"
 
     def __init__(
         self,
@@ -425,7 +414,11 @@ class AgentRunner:
                 if agent_config and hasattr(agent_config, "model"):
                     model = agent_config.model
 
-            max_tokens = getattr(agent_config, "max_tokens", 1024) if agent_config else 1024
+            if agent_config and hasattr(agent_config, "max_tokens"):
+                max_tokens = agent_config.max_tokens
+            else:
+                hive_config = get_hive_config()
+                max_tokens = hive_config.get("llm", {}).get("max_tokens", DEFAULT_MAX_TOKENS)
 
             # Build GraphSpec from module-level variables
             graph = GraphSpec(

docs/configuration.md

@@ -5,12 +5,31 @@ Aden Hive is a Python-based agent framework. Configuration is handled through en
 ## Configuration Overview
 
 ```
-Environment variables     (API keys, runtime flags)
+~/.hive/configuration.json  (global defaults: provider, model, max_tokens)
-Agent config.py           (per-agent settings: model, tools, storage)
+Environment variables        (API keys, runtime flags)
-pyproject.toml            (package metadata and dependencies)
+Agent config.py              (per-agent settings: model, tools, storage)
-.mcp.json                 (MCP server connections)
+pyproject.toml               (package metadata and dependencies)
+.mcp.json                    (MCP server connections)
 ```
 
+## Global Configuration (~/.hive/configuration.json)
+
+The `quickstart.sh` script creates this file during setup. It stores the default LLM provider, model, and max_tokens used by all agents unless overridden in an agent's own `config.py`.
+
+```json
+{
+  "llm": {
+    "provider": "anthropic",
+    "model": "claude-sonnet-4-5-20250929",
+    "max_tokens": 8192,
+    "api_key_env_var": "ANTHROPIC_API_KEY"
+  },
+  "created_at": "2026-01-15T12:00:00+00:00"
+}
+```
+
+The default `max_tokens` value (8192) is defined as `DEFAULT_MAX_TOKENS` in `framework.graph.edge` and re-exported from `framework.graph`. Each agent's `RuntimeConfig` reads from this file at startup. To change defaults, either re-run `quickstart.sh` or edit the file directly.
+
 ## Environment Variables
 
 ### LLM Providers (at least one required for real execution)
@@ -61,14 +80,16 @@ Each agent package in `exports/` contains its own `config.py`:
 ```python
 # exports/my_agent/config.py
 CONFIG = {
-    "model": "claude-haiku-4-5-20251001",  # Default LLM model
+    "model": "anthropic/claude-sonnet-4-5-20250929",  # Default LLM model
-    "max_tokens": 4096,
+    "max_tokens": 8192,  # default: DEFAULT_MAX_TOKENS from framework.graph
     "temperature": 0.7,
     "tools": ["web_search", "pdf_read"],   # MCP tools to enable
     "storage_path": "/tmp/my_agent",       # Runtime data location
 }
 ```
 
+If `model` or `max_tokens` are omitted, the agent loads defaults from `~/.hive/configuration.json`.
+
 ### Agent Graph Specification
 
 Agent behavior is defined in `agent.json` (or constructed in `agent.py`):

examples/templates/deep_research_agent/config.py

@@ -1,33 +1,8 @@
 """Runtime configuration."""
 
-import json
+from dataclasses import dataclass
-from dataclasses import dataclass, field
-from pathlib import Path
-
-
-def _load_preferred_model() -> str:
-    """Load preferred model from ~/.hive/configuration.json."""
-    config_path = Path.home() / ".hive" / "configuration.json"
-    if config_path.exists():
-        try:
-            with open(config_path) as f:
-                config = json.load(f)
-            llm = config.get("llm", {})
-            if llm.get("provider") and llm.get("model"):
-                return f"{llm['provider']}/{llm['model']}"
-        except Exception:
-            pass
-    return "anthropic/claude-sonnet-4-20250514"
-
-
-@dataclass
-class RuntimeConfig:
-    model: str = field(default_factory=_load_preferred_model)
-    temperature: float = 0.7
-    max_tokens: int = 40000
-    api_key: str | None = None
-    api_base: str | None = None
 
+from framework.config import RuntimeConfig
 
 default_config = RuntimeConfig()
 

examples/templates/tech_news_reporter/config.py

@@ -1,33 +1,8 @@
 """Runtime configuration."""
 
-import json
+from dataclasses import dataclass
-from dataclasses import dataclass, field
-from pathlib import Path
-
-
-def _load_preferred_model() -> str:
-    """Load preferred model from ~/.hive/configuration.json."""
-    config_path = Path.home() / ".hive" / "configuration.json"
-    if config_path.exists():
-        try:
-            with open(config_path) as f:
-                config = json.load(f)
-            llm = config.get("llm", {})
-            if llm.get("provider") and llm.get("model"):
-                return f"{llm['provider']}/{llm['model']}"
-        except Exception:
-            pass
-    return "anthropic/claude-sonnet-4-20250514"
-
-
-@dataclass
-class RuntimeConfig:
-    model: str = field(default_factory=_load_preferred_model)
-    temperature: float = 0.7
-    max_tokens: int = 40000
-    api_key: str | None = None
-    api_base: str | None = None
 
+from framework.config import RuntimeConfig
 
 default_config = RuntimeConfig()
 

examples/templates/twitter_outreach/config.py

@@ -1,33 +1,8 @@
 """Runtime configuration."""
 
-import json
+from dataclasses import dataclass
-from dataclasses import dataclass, field
-from pathlib import Path
-
-
-def _load_preferred_model() -> str:
-    """Load preferred model from ~/.hive/configuration.json."""
-    config_path = Path.home() / ".hive" / "configuration.json"
-    if config_path.exists():
-        try:
-            with open(config_path) as f:
-                config = json.load(f)
-            llm = config.get("llm", {})
-            if llm.get("provider") and llm.get("model"):
-                return f"{llm['provider']}/{llm['model']}"
-        except Exception:
-            pass
-    return "anthropic/claude-sonnet-4-20250514"
-
-
-@dataclass
-class RuntimeConfig:
-    model: str = field(default_factory=_load_preferred_model)
-    temperature: float = 0.7
-    max_tokens: int = 40000
-    api_key: str | None = None
-    api_base: str | None = None
 
+from framework.config import RuntimeConfig
 
 default_config = RuntimeConfig()
 

quickstart.sh

@@ -303,9 +303,9 @@ if [ "$USE_ASSOC_ARRAYS" = true ]; then
     )
 
     declare -A DEFAULT_MODELS=(
-        ["anthropic"]="claude-sonnet-4-5-20250929"
+        ["anthropic"]="claude-opus-4-6"
-        ["openai"]="gpt-4o"
+        ["openai"]="gpt-5.2"
-        ["gemini"]="gemini-3.0-flash-preview"
+        ["gemini"]="gemini-3-flash-preview"
         ["groq"]="moonshotai/kimi-k2-instruct-0905"
         ["cerebras"]="zai-glm-4.7"
         ["mistral"]="mistral-large-latest"
@@ -313,6 +313,65 @@ if [ "$USE_ASSOC_ARRAYS" = true ]; then
         ["deepseek"]="deepseek-chat"
     )
 
+    # Model choices per provider: composite-key associative arrays
+    # Keys: "provider:index" -> value
+    declare -A MODEL_CHOICES_ID=(
+        ["anthropic:0"]="claude-opus-4-6"
+        ["anthropic:1"]="claude-sonnet-4-5-20250929"
+        ["anthropic:2"]="claude-sonnet-4-20250514"
+        ["anthropic:3"]="claude-haiku-4-5-20251001"
+        ["openai:0"]="gpt-5.2"
+        ["openai:1"]="gpt-5-mini"
+        ["openai:2"]="gpt-5-nano"
+        ["gemini:0"]="gemini-3-flash-preview"
+        ["gemini:1"]="gemini-3-pro-preview"
+        ["groq:0"]="moonshotai/kimi-k2-instruct-0905"
+        ["groq:1"]="openai/gpt-oss-120b"
+        ["cerebras:0"]="zai-glm-4.7"
+        ["cerebras:1"]="qwen3-235b-a22b-instruct-2507"
+    )
+
+    declare -A MODEL_CHOICES_LABEL=(
+        ["anthropic:0"]="Opus 4.6 - Most capable (recommended)"
+        ["anthropic:1"]="Sonnet 4.5 - Best balance"
+        ["anthropic:2"]="Sonnet 4 - Fast + capable"
+        ["anthropic:3"]="Haiku 4.5 - Fast + cheap"
+        ["openai:0"]="GPT-5.2 - Most capable (recommended)"
+        ["openai:1"]="GPT-5 Mini - Fast + cheap"
+        ["openai:2"]="GPT-5 Nano - Fastest"
+        ["gemini:0"]="Gemini 3 Flash - Fast (recommended)"
+        ["gemini:1"]="Gemini 3 Pro - Best quality"
+        ["groq:0"]="Kimi K2 - Best quality (recommended)"
+        ["groq:1"]="GPT-OSS 120B - Fast reasoning"
+        ["cerebras:0"]="ZAI-GLM 4.7 - Best quality (recommended)"
+        ["cerebras:1"]="Qwen3 235B - Frontier reasoning"
+    )
+
+    # NOTE: 8192 should match DEFAULT_MAX_TOKENS in core/framework/graph/edge.py
+    declare -A MODEL_CHOICES_MAXTOKENS=(
+        ["anthropic:0"]=8192
+        ["anthropic:1"]=8192
+        ["anthropic:2"]=8192
+        ["anthropic:3"]=8192
+        ["openai:0"]=16384
+        ["openai:1"]=16384
+        ["openai:2"]=16384
+        ["gemini:0"]=8192
+        ["gemini:1"]=8192
+        ["groq:0"]=8192
+        ["groq:1"]=8192
+        ["cerebras:0"]=8192
+        ["cerebras:1"]=8192
+    )
+
+    declare -A MODEL_CHOICES_COUNT=(
+        ["anthropic"]=4
+        ["openai"]=3
+        ["gemini"]=2
+        ["groq"]=2
+        ["cerebras"]=2
+    )
+
     # Helper functions for Bash 4+
     get_provider_name() {
         echo "${PROVIDER_NAMES[$1]}"
@@ -325,6 +384,22 @@ if [ "$USE_ASSOC_ARRAYS" = true ]; then
     get_default_model() {
         echo "${DEFAULT_MODELS[$1]}"
     }
+
+    get_model_choice_count() {
+        echo "${MODEL_CHOICES_COUNT[$1]:-0}"
+    }
+
+    get_model_choice_id() {
+        echo "${MODEL_CHOICES_ID[$1:$2]}"
+    }
+
+    get_model_choice_label() {
+        echo "${MODEL_CHOICES_LABEL[$1:$2]}"
+    }
+
+    get_model_choice_maxtokens() {
+        echo "${MODEL_CHOICES_MAXTOKENS[$1:$2]}"
+    }
 else
     # Bash 3.2 - use parallel indexed arrays
     PROVIDER_ENV_VARS=(ANTHROPIC_API_KEY OPENAI_API_KEY GEMINI_API_KEY GOOGLE_API_KEY GROQ_API_KEY CEREBRAS_API_KEY MISTRAL_API_KEY TOGETHER_API_KEY DEEPSEEK_API_KEY)
@@ -333,7 +408,7 @@ else
 
     # Default models by provider id (parallel arrays)
     MODEL_PROVIDER_IDS=(anthropic openai gemini groq cerebras mistral together_ai deepseek)
-    MODEL_DEFAULTS=("claude-sonnet-4-5-20250929" "gpt-4o" "gemini-3.0-flash-preview" "moonshotai/kimi-k2-instruct-0905" "zai-glm-4.7" "mistral-large-latest" "meta-llama/Llama-3.3-70B-Instruct-Turbo" "deepseek-chat")
+    MODEL_DEFAULTS=("claude-opus-4-6" "gpt-5.2" "gemini-3-flash-preview" "moonshotai/kimi-k2-instruct-0905" "zai-glm-4.7" "mistral-large-latest" "meta-llama/Llama-3.3-70B-Instruct-Turbo" "deepseek-chat")
 
     # Helper: get provider display name for an env var
     get_provider_name() {
@@ -373,6 +448,82 @@ else
             i=$((i + 1))
         done
     }
+
+    # Model choices per provider - flat parallel arrays with provider offsets
+    # Provider order: anthropic(4), openai(3), gemini(2), groq(2), cerebras(2)
+    MC_PROVIDERS=(anthropic anthropic anthropic anthropic openai openai openai gemini gemini groq groq cerebras cerebras)
+    MC_IDS=("claude-opus-4-6" "claude-sonnet-4-5-20250929" "claude-sonnet-4-20250514" "claude-haiku-4-5-20251001" "gpt-5.2" "gpt-5-mini" "gpt-5-nano" "gemini-3-flash-preview" "gemini-3-pro-preview" "moonshotai/kimi-k2-instruct-0905" "openai/gpt-oss-120b" "zai-glm-4.7" "qwen3-235b-a22b-instruct-2507")
+    MC_LABELS=("Opus 4.6 - Most capable (recommended)" "Sonnet 4.5 - Best balance" "Sonnet 4 - Fast + capable" "Haiku 4.5 - Fast + cheap" "GPT-5.2 - Most capable (recommended)" "GPT-5 Mini - Fast + cheap" "GPT-5 Nano - Fastest" "Gemini 3 Flash - Fast (recommended)" "Gemini 3 Pro - Best quality" "Kimi K2 - Best quality (recommended)" "GPT-OSS 120B - Fast reasoning" "ZAI-GLM 4.7 - Best quality (recommended)" "Qwen3 235B - Frontier reasoning")
+    # NOTE: 8192 should match DEFAULT_MAX_TOKENS in core/framework/graph/edge.py
+    MC_MAXTOKENS=(8192 8192 8192 8192 16384 16384 16384 8192 8192 8192 8192 8192 8192)
+
+    # Helper: get number of model choices for a provider
+    get_model_choice_count() {
+        local provider_id="$1"
+        local count=0
+        local i=0
+        while [ $i -lt ${#MC_PROVIDERS[@]} ]; do
+            if [ "${MC_PROVIDERS[$i]}" = "$provider_id" ]; then
+                count=$((count + 1))
+            fi
+            i=$((i + 1))
+        done
+        echo "$count"
+    }
+
+    # Helper: get model choice id by provider and index (0-based within provider)
+    get_model_choice_id() {
+        local provider_id="$1"
+        local idx="$2"
+        local count=0
+        local i=0
+        while [ $i -lt ${#MC_PROVIDERS[@]} ]; do
+            if [ "${MC_PROVIDERS[$i]}" = "$provider_id" ]; then
+                if [ $count -eq "$idx" ]; then
+                    echo "${MC_IDS[$i]}"
+                    return
+                fi
+                count=$((count + 1))
+            fi
+            i=$((i + 1))
+        done
+    }
+
+    # Helper: get model choice label by provider and index
+    get_model_choice_label() {
+        local provider_id="$1"
+        local idx="$2"
+        local count=0
+        local i=0
+        while [ $i -lt ${#MC_PROVIDERS[@]} ]; do
+            if [ "${MC_PROVIDERS[$i]}" = "$provider_id" ]; then
+                if [ $count -eq "$idx" ]; then
+                    echo "${MC_LABELS[$i]}"
+                    return
+                fi
+                count=$((count + 1))
+            fi
+            i=$((i + 1))
+        done
+    }
+
+    # Helper: get model choice max_tokens by provider and index
+    get_model_choice_maxtokens() {
+        local provider_id="$1"
+        local idx="$2"
+        local count=0
+        local i=0
+        while [ $i -lt ${#MC_PROVIDERS[@]} ]; do
+            if [ "${MC_PROVIDERS[$i]}" = "$provider_id" ]; then
+                if [ $count -eq "$idx" ]; then
+                    echo "${MC_MAXTOKENS[$i]}"
+                    return
+                fi
+                count=$((count + 1))
+            fi
+            i=$((i + 1))
+        done
+    }
 fi
 
 # Configuration directory
@@ -411,12 +562,74 @@ detect_shell_rc() {
 SHELL_RC_FILE=$(detect_shell_rc)
 SHELL_NAME=$(basename "$SHELL")
 
+# Prompt the user to choose a model for their selected provider.
+# Sets SELECTED_MODEL and SELECTED_MAX_TOKENS.
+prompt_model_selection() {
+    local provider_id="$1"
+    local count
+    count="$(get_model_choice_count "$provider_id")"
+
+    if [ "$count" -eq 0 ]; then
+        # No curated choices for this provider (e.g. Mistral, DeepSeek)
+        SELECTED_MODEL="$(get_default_model "$provider_id")"
+        SELECTED_MAX_TOKENS=8192
+        return
+    fi
+
+    if [ "$count" -eq 1 ]; then
+        # Only one choice — auto-select
+        SELECTED_MODEL="$(get_model_choice_id "$provider_id" 0)"
+        SELECTED_MAX_TOKENS="$(get_model_choice_maxtokens "$provider_id" 0)"
+        return
+    fi
+
+    # Multiple choices — show menu
+    echo ""
+    echo -e "${BOLD}Select a model:${NC}"
+    echo ""
+
+    local i=0
+    while [ $i -lt "$count" ]; do
+        local label
+        label="$(get_model_choice_label "$provider_id" "$i")"
+        local mid
+        mid="$(get_model_choice_id "$provider_id" "$i")"
+        local num=$((i + 1))
+        echo -e "  ${CYAN}$num)${NC} $label  ${DIM}($mid)${NC}"
+        i=$((i + 1))
+    done
+    echo ""
+
+    local choice
+    while true; do
+        read -r -p "Enter choice [1]: " choice
+        choice="${choice:-1}"
+        if [[ "$choice" =~ ^[0-9]+$ ]] && [ "$choice" -ge 1 ] && [ "$choice" -le "$count" ]; then
+            local idx=$((choice - 1))
+            SELECTED_MODEL="$(get_model_choice_id "$provider_id" "$idx")"
+            SELECTED_MAX_TOKENS="$(get_model_choice_maxtokens "$provider_id" "$idx")"
+            echo ""
+            echo -e "${GREEN}⬢${NC} Model: ${DIM}$SELECTED_MODEL${NC}"
+            return
+        fi
+        echo -e "${RED}Invalid choice. Please enter 1-$count${NC}"
+    done
+}
+
 # Function to save configuration
 save_configuration() {
     local provider_id="$1"
     local env_var="$2"
-    local model
+    local model="$3"
-    model="$(get_default_model "$provider_id")"
+    local max_tokens="$4"
+
+    # Fallbacks if not provided
+    if [ -z "$model" ]; then
+        model="$(get_default_model "$provider_id")"
+    fi
+    if [ -z "$max_tokens" ]; then
+        max_tokens=8192
+    fi
 
     mkdir -p "$HIVE_CONFIG_DIR"
 
@@ -426,6 +639,7 @@ config = {
     'llm': {
         'provider': '$provider_id',
         'model': '$model',
+        'max_tokens': $max_tokens,
         'api_key_env_var': '$env_var'
     },
     'created_at': '$(date -u +"%Y-%m-%dT%H:%M:%S+00:00")'
@@ -449,6 +663,8 @@ FOUND_PROVIDERS=()      # Display names for UI
 FOUND_ENV_VARS=()       # Corresponding env var names
 SELECTED_PROVIDER_ID="" # Will hold the chosen provider ID
 SELECTED_ENV_VAR=""     # Will hold the chosen env var
+SELECTED_MODEL=""       # Will hold the chosen model ID
+SELECTED_MAX_TOKENS=8192 # Will hold the chosen max_tokens
 
 if [ "$USE_ASSOC_ARRAYS" = true ]; then
     # Bash 4+ - iterate over associative array keys
@@ -486,6 +702,8 @@ if [ ${#FOUND_PROVIDERS[@]} -gt 0 ]; then
 
             echo ""
             echo -e "${GREEN}⬢${NC} Using ${FOUND_PROVIDERS[0]}"
+
+            prompt_model_selection "$SELECTED_PROVIDER_ID"
         fi
     else
         # Multiple providers found, let user pick one
@@ -498,28 +716,34 @@ if [ ${#FOUND_PROVIDERS[@]} -gt 0 ]; then
             echo -e "  ${CYAN}$i)${NC} $provider"
             i=$((i + 1))
         done
+        echo -e "  ${CYAN}$i)${NC} Other"
+        max_choice=$i
         echo ""
 
         while true; do
-            read -r -p "Enter choice (1-${#FOUND_PROVIDERS[@]}): " choice
+            read -r -p "Enter choice (1-$max_choice): " choice
-            if [[ "$choice" =~ ^[0-9]+$ ]] && [ "$choice" -ge 1 ] && [ "$choice" -le "${#FOUND_PROVIDERS[@]}" ]; then
+            if [[ "$choice" =~ ^[0-9]+$ ]] && [ "$choice" -ge 1 ] && [ "$choice" -le "$max_choice" ]; then
+                if [ "$choice" -eq "$max_choice" ]; then
+                    # Fall through to the manual provider selection below
+                    break
+                fi
                 idx=$((choice - 1))
                 SELECTED_ENV_VAR="${FOUND_ENV_VARS[$idx]}"
                 SELECTED_PROVIDER_ID="$(get_provider_id "$SELECTED_ENV_VAR")"
 
                 echo ""
                 echo -e "${GREEN}⬢${NC} Selected: ${FOUND_PROVIDERS[$idx]}"
+
+                prompt_model_selection "$SELECTED_PROVIDER_ID"
                 break
             fi
-            echo -e "${RED}Invalid choice. Please enter 1-${#FOUND_PROVIDERS[@]}${NC}"
+            echo -e "${RED}Invalid choice. Please enter 1-$max_choice${NC}"
         done
     fi
 fi
 
 if [ -z "$SELECTED_PROVIDER_ID" ]; then
-    echo "No API keys found. Let's configure one."
     echo ""
-
     prompt_choice "Select your LLM provider:" \
         "Anthropic (Claude) - Recommended" \
         "OpenAI (GPT)" \
@@ -595,11 +819,16 @@ if [ -z "$SELECTED_PROVIDER_ID" ]; then
     fi
 fi
 
+# Prompt for model if not already selected (manual provider path)
+if [ -n "$SELECTED_PROVIDER_ID" ] && [ -z "$SELECTED_MODEL" ]; then
+    prompt_model_selection "$SELECTED_PROVIDER_ID"
+fi
+
 # Save configuration if a provider was selected
 if [ -n "$SELECTED_PROVIDER_ID" ]; then
     echo ""
     echo -n "  Saving configuration... "
-    save_configuration "$SELECTED_PROVIDER_ID" "$SELECTED_ENV_VAR" > /dev/null
+    save_configuration "$SELECTED_PROVIDER_ID" "$SELECTED_ENV_VAR" "$SELECTED_MODEL" "$SELECTED_MAX_TOKENS" > /dev/null
     echo -e "${GREEN}⬢${NC}"
     echo -e "  ${DIM}~/.hive/configuration.json${NC}"
 fi
@@ -781,7 +1010,9 @@ echo ""
 
 # Show configured provider
 if [ -n "$SELECTED_PROVIDER_ID" ]; then
-    SELECTED_MODEL="$(get_default_model "$SELECTED_PROVIDER_ID")"
+    if [ -z "$SELECTED_MODEL" ]; then
+        SELECTED_MODEL="$(get_default_model "$SELECTED_PROVIDER_ID")"
+    fi
     echo -e "${BOLD}Default LLM:${NC}"
     echo -e "  ${CYAN}$SELECTED_PROVIDER_ID${NC} → ${DIM}$SELECTED_MODEL${NC}"
     echo ""