0
代码
代码
Issues
Pull Requests
讨论
Wiki
分析
0
xchang1121xchang1121fix(autoresearch): address PR #1912 review
63089bb2创建于 4月21日历史提交
文件最后提交记录最后更新时间
__init__.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_acknowledge_skill.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_autoresearch_cleanup.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_autoresearch_layering.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_autoresearch_postrefactor_fixes.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_autoresearch_refactor.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_compact_pipeline.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_conversation_buffer.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_edit_tool.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_fundamentals_layout.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_git_repo.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_patch_file_diagnostics.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_patch_validator.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_run_counters.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_runtime_skill_binding.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_scaffold_roundtrip.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_session_persistence.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_skill_builder.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_skill_pipeline.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前
test_skill_prompt_injection.py
fix(autoresearch): address PR #1912 review - .gitignore: scope scratch patterns under .akg/ so the unqualified reference.py / *_kernel.py / *_ref.py globs stop masking legit files; drop the stale RemoteWorker_AutoResearch.md entry. - op/autoresearch/agent/llm_client.py (ConversationAdapter) removed; the agent loop now drives LLM access exclusively through AkgLLMAdapter on top of LLMClient. Retry + backoff logic moved into the adapter so long-running runs stay resilient; loop.py's __init__ tightened to a single llm_adapter injection path, and the debug __main__ entry builds its client via create_llm_client with CLI overrides mapped onto AKG_AGENTS_* env vars. - Drop the suppress_extra_body kwarg from LLMProvider; compact / keyword-generation calls route to a fast_client bound to the "fast" model level via create_llm_client, keeping "no thinking" as a settings.json concern. - Add Apache 2.0 copyright headers to the new py / yaml files. - tests/op/ut/autoresearch/: move the 19 autoresearch-specific unit suites into their own package so tests/op/ut/ stays for shared op/skill / verifier / adapter coverage. - Autopep8 pass on op/autoresearch/ and tests/op/ut/autoresearch/. 1 个月前