c8e8cb3bf3
feat(tier4): Add patch generation for auto-patching
...
- Add TIER4_PATCH_PROMPT to mma_prompts.py with unified diff format
- Add run_tier4_patch_generation function to ai_client.py
- Import mma_prompts in ai_client.py
- Add unit tests for patch generation
2026-03-07 00:10:35 -05:00
bc606a8a8d
fix: Add minimax to tool call execution handler
2026-03-06 23:51:17 -05:00
a47ea47839
temp: disable tools for minimax to debug API issues
2026-03-06 23:48:41 -05:00
6cfe9697e0
fix: Use temperature=1.0 for MiniMax (required range is (0.0, 1.0])
2026-03-06 23:46:17 -05:00
ce53f69ae0
fix: Use correct MiniMax API endpoint (api.minimax.io not api.minimax.chat)
2026-03-06 23:43:41 -05:00
af4b716a74
fix: Use absolute path for credentials.toml
2026-03-06 23:42:01 -05:00
b79c1fce3c
feat(provider): Add MiniMax AI provider integration
...
- Add minimax to PROVIDERS lists in gui_2.py and app_controller.py
- Add minimax credentials template in ai_client.py
- Implement _list_minimax_models, _classify_minimax_error, _ensure_minimax_client
- Implement _send_minimax with streaming and reasoning support
- Add minimax to send(), list_models(), reset_session(), get_history_bleed_stats()
- Add unit tests in tests/test_minimax_provider.py
2026-03-06 23:36:30 -05:00
12dba31c1d
REGRESSSIOSSSOONNNNSSSS
2026-03-06 21:39:50 -05:00
f65e9b40b2
WIP: Regression hell
2026-03-06 21:22:21 -05:00
4c92817928
fixing regresssions
2026-03-06 20:12:35 -05:00
0e9f84f026
fixing
2026-03-06 19:54:52 -05:00
9d5b874c66
fix(ai_client): Restore AI text capture and fix tool declaration in Gemini generation loop.
2026-03-06 13:47:22 -05:00
87dbfc5958
feat(ai_client): Refactor tool dispatch to use asyncio.gather for parallel tool execution.
2026-03-06 13:14:27 -05:00
684a6d1d3b
feat(ai_client): isolation of current_tier using threading.local() for parallel agent safety
2026-03-06 12:59:18 -05:00
84de6097e6
chore(conductor): Finalize track 'Robust JSON Parsing for Tech Lead' and cleanup static analysis
2026-03-06 12:36:24 -05:00
03b68c9cea
fix(ai_client): Add missing response_received events for gemini streaming and non-streaming paths
2026-03-05 19:21:57 -05:00
c0ccaebcc5
fix(ai_client): Use send_message_stream for google-genai streaming
2026-03-05 16:48:57 -05:00
3d5773fa63
YET ANOTEHR BOTCHED TRACK.
2026-03-05 16:14:58 -05:00
8784d05db4
WIP: PAIN3
2026-03-05 15:10:53 -05:00
0e3b479bd6
WIP: PAIN
2026-03-05 14:24:03 -05:00
5e69617f88
WIP: I HATE PYTHON
2026-03-05 13:55:40 -05:00
35480a26dc
test(audit): fix critical test suite deadlocks and write exhaustive architectural report
...
- Fix 'Triple Bingo' history synchronization explosion during streaming
- Implement stateless event buffering in ApiHookClient to prevent dropped events
- Ensure 'tool_execution' events emit consistently across all LLM providers
- Add hard timeouts to all background thread wait() conditions
- Add thorough teardown cleanup to conftest.py's reset_ai_client fixture
- Write highly detailed report_gemini.md exposing asyncio lifecycle flaws
2026-03-05 01:42:47 -05:00
a0276e0894
feat(src): Move core implementation files to src/ directory
2026-03-04 09:55:44 -05:00
