112b1baf2e
fix(memory): patch ConcurrentStorage leak with WeakValueDictionary (Isolated Logic)
2026-01-27 20:28:22 +05:00
6acdb65c1c
Merge pull request #948 from TanujaNair03/refactor/provider-agnostic-prompts
...
Refactor/provider agnostic prompts
2026-01-27 14:18:59 +08:00
a4b0c66564
Merge pull request #558 from Hundao/feature/csv-tools
...
feat(tools): add CSV tools with DuckDB SQL support
2026-01-27 14:02:06 +08:00
bc8cdfd6da
Merge pull request #941 from vakrahul/fix/graph-retry-backoff
...
Fix/graph retry backoff
2026-01-26 19:20:35 -08:00
500876d65e
style: add required trailing newline to prompts.py
2026-01-27 07:35:54 +05:30
e59bb2d83f
style: fix linting issues (whitespace and newline)
2026-01-27 07:29:48 +05:30
03910d531f
Merge branch 'main' into fix/graph-retry-backoff
2026-01-27 07:28:22 +05:30
a122345f9c
fix(graph): restore node.max_retries and fix type check per review
2026-01-27 07:26:40 +05:30
6d025c808a
Merge pull request #946 from not-anas-ali/fix/callable-type-annotations
...
fix(types): correct type annotation from lowercase 'callable' to 'Callable'
2026-01-26 17:52:00 -08:00
8525aec49c
Merge pull request #934 from adionit7/fix/validate-exports-skip-when-empty
...
ci: make Validate Agent Exports skip clearly when exports/ is missing or empty
2026-01-26 17:48:44 -08:00
b0435a188f
Merge branch 'adenhq:main' into refactor/provider-agnostic-prompts
2026-01-27 07:07:01 +05:30
3eb964eff2
Merge pull request #933 from adionit7/docs/fix-execute-command-tool-name-readme
...
docs(tools): fix tool name in README table (execute_command → execute_command_tool)
2026-01-26 17:36:24 -08:00
ed88129b00
Merge pull request #927 from saboor2632/fix/worker-node-json-logging
...
fix(graph): add logging for JSON parsing failures in worker_node
2026-01-26 17:36:13 -08:00
68264b54d9
style: fix linting issues in output_cleaner.py
2026-01-27 07:02:43 +05:30
1631d01dd2
merge: resolve conflicts in executor.pyx
2026-01-27 06:52:07 +05:30
e846ad6ea7
refactor: implement provider-agnostic logic for test templates
...
Centralized _get_api_key in prompts.py to support OpenAI, Cerebras, and Groq via environment variables while maintaining Anthropic support through CredentialManager.
2026-01-27 06:39:55 +05:30
e57cad7159
ci: make Validate Agent Exports skip clearly when exports/ is missing or empty
...
Previously, when exports/ was missing or empty, the bash glob
`exports/*/` would not match anything and the loop would silently
do nothing. The job would pass without actually validating anything,
which was misleading.
Now the job:
- Explicitly checks if exports/ directory exists
- Uses nullglob to handle empty directories properly
- Logs clear messages when skipping validation
- Reports the number of agents validated when successful
Fixes #887
2026-01-27 05:59:43 +05:30
0cf9e39f6f
docs(tools): fix tool name in README table (execute_command → execute_command_tool)
...
The "Available Tools" table listed `execute_command` but the actual
registered name is `execute_command_tool`. This aligns the docs with
the runtime name in __init__.py and the tool's own README.
Fixes #901
2026-01-27 05:58:59 +05:30
852332483a
fix(graph): add logging for JSON parsing failures in worker_node
2026-01-27 05:10:34 +05:00
2b8604610c
fix(types): correct type annotation from lowercase 'callable' to 'Callable'
...
Fixes #922
2026-01-27 05:06:27 +05:00
9230ac6c20
Merge pull request #871 from pradyten/feat/llm-judge-configurable-provider
...
feat(testing): add configurable LLM provider to LLMJudge
2026-01-26 14:53:12 -08:00
5cf25c6f10
Merge pull request #906 from adenhq/fix/ruff-tests
...
fixed linter
2026-01-26 14:49:45 -08:00
d064c98998
fixed linter
2026-01-26 14:47:56 -08:00
25fabd8068
Merge pull request #576 from savankansagara1/fix/mock-mode-llm-provider
...
Fix: Add MockLLMProvider to enable mock mode execution
2026-01-26 14:41:13 -08:00
396e5c35a6
Merge pull request #528 from gaurav-code098/fix/web-scrape-content-type
...
fix(tools): validate Content-Type in web_scrape tool (Closes #487 )
2026-01-26 14:34:37 -08:00
0a8c30c3da
Merge pull request #788 from SoulSniper-V2/feat/add-deepseek-docs
...
docs(llm): add DeepSeek models support documentation and examples
2026-01-26 14:33:51 -08:00
798f3cfd36
Merge pull request #349 from Himanshu-ABES/feat/pydantic-llm-validation
...
feat(validation): add Pydantic model validation for LLM outputs
2026-01-26 14:14:12 -08:00
69ad0be5ff
Merge branch 'main' into feat/llm-judge-configurable-provider
2026-01-26 17:06:30 -05:00
60f2e674ec
feat(validation): add Pydantic model validation for LLM outputs
...
- Add output_model field to NodeSpec for specifying Pydantic model
- Add max_validation_retries field (default: 2) for retry configuration
- Add validation_errors field to NodeResult for error tracking
- Implement validate_with_pydantic() in OutputValidator
- Implement format_validation_feedback() for LLM retry prompts
- Auto-generate JSON schema from Pydantic model for response_format
- Add retry loop that feeds validation errors back to LLM
- Add 28 comprehensive tests covering all new functionality
2026-01-26 14:06:29 -08:00
81ad85db5e
Merge pull request #876 from adenhq/fix/ruff-tests
...
Fix/ruff tests
2026-01-26 13:41:15 -08:00
ed25ef7562
Merge pull request #762 from vishalharkal15/fix/concurrent-storage-race-condition
...
Fix race condition in ConcurrentStorage.stop() causing data loss
2026-01-26 13:38:17 -08:00
d9c696aa22
fixed all linter errors
2026-01-26 13:37:25 -08:00
22358a2d83
Merge branch 'main' into fix/ruff-tests
2026-01-26 13:37:12 -08:00
39a2a34380
Merge pull request #874 from TimothyZhang7/main
...
fix: git actions
2026-01-26 13:36:50 -08:00
07077dbb52
Merge branch 'adenhq:main' into main
2026-01-26 13:35:33 -08:00
e1346ae557
fix: include actual status check in pr requirements
2026-01-26 13:34:54 -08:00
4f3d34d01e
fix: consolidate dedupe and triage
2026-01-26 13:29:33 -08:00
8516eba7c5
feat(testing): add configurable LLM provider to LLMJudge
...
Allow LLMJudge to accept any LLMProvider instance instead of being
hardcoded to use Anthropic. This aligns with the framework's pluggable
LLM design and enables users to:
- Use the same LLM provider across their agent and tests
- Run tests with cheaper or local models
- Avoid requiring an Anthropic API key for testing
Backward compatible: existing code using LLMJudge() without arguments
continues to work by falling back to Anthropic.
Closes #477
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-26 16:27:08 -05:00
63010d45b2
Merge pull request #861 from TimothyZhang7/main
...
fix: explain the PR requirements
2026-01-26 12:43:30 -08:00
59db8f99d7
Merge branch 'adenhq:main' into main
2026-01-26 12:42:22 -08:00
236e8e8638
fix: explain the pr requirement
2026-01-26 12:41:16 -08:00
3279686342
Merge pull request #858 from TimothyZhang7/main
...
fix: PR requirements enforcement
2026-01-26 12:32:11 -08:00
b6a77ffd7e
Merge branch 'adenhq:main' into main
2026-01-26 12:31:25 -08:00
e0544a57f9
fix: pr requirements
2026-01-26 12:30:12 -08:00
a180d78d0c
Merge pull request #782 from ayush123-bit/docs/windows-environment-clarification
...
docs: clarify Windows environment expectations in setup guides
2026-01-26 12:22:43 -08:00
9be036aa37
Merge pull request #602 from Kira714/fix/callable-type-annotation-599
...
fix(llm): correct type annotation from lowercase `callable` to `Callable`
2026-01-26 12:22:34 -08:00
8c39dad22d
Merge pull request #605 from Kira714/fix/session-state-dict-validation-590
...
fix(executor): add type validation for session state memory
2026-01-26 12:22:21 -08:00
0a7aa62c45
Merge pull request #608 from Kira714/fix/agent-runtime-keyerror
...
fix(runtime): use safe dictionary access in trigger_and_wait()
2026-01-26 12:22:12 -08:00
cbd34db278
Merge pull request #665 from Ranxin2023/main
...
Make MCP tool registration idempotent to avoid conflicts with agent-generated tools
2026-01-26 12:22:02 -08:00
414d86f2f0
Merge pull request #672 from subham-panja/docs/fix-architecture-link
...
docs(readme): fix broken architecture documentation link
2026-01-26 12:21:34 -08:00
Tahir Yamin