kimi f563f76eab fix: implement source distinction in agent responses ...

Add SOURCE DISTINCTION instructions to both lite and full system prompts,
requiring Timmy to cite grounded sources (memory/retrieval) and hedge
appropriately when inferring. Label memory context as "GROUNDED CONTEXT"
so the model can distinguish retrieved facts from pattern-matching.

Fixes #463

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-19 14:50:18 -04:00

..

adapters

feat: time adapter — circadian awareness for Timmy (#315)

2026-03-18 18:47:09 -04:00

agents

test: add unit tests for agents/loader.py (#349)

2026-03-18 21:13:01 -04:00

__init__.py

refactor: Phase 3 — reorganize tests into module-mirroring subdirectories

2026-02-26 21:21:28 +00:00

test_agent_retry.py

[loop-cycle-60] fix: retry with backoff on Ollama GPU contention (#70) (#238)

2026-03-15 14:28:47 -04:00

test_agent.py

[loop-cycle-49] fix: mock _warmup_model in agent tests to prevent Ollama network calls (#159) (#177)

2026-03-15 11:46:20 -04:00

test_agentic_loop.py

[loop-cycle-522] test: add unit tests for agentic_loop.py (#421) (#441)

2026-03-19 14:10:16 -04:00

test_agents_base.py

[loop-cycle-150] test: add 22 unit tests for agents/base.py — BaseAgent and SubAgent (#350)

2026-03-18 21:10:08 -04:00

test_api_rate_limiting.py

ruff (#169)

2026-03-11 12:23:35 -04:00

test_approvals.py

[loop-cycle-50] refactor: replace bare sqlite3.connect() with context managers batch 2 (#157) (#180)

2026-03-15 11:58:43 -04:00

test_audit_trail.py

[loop-cycle-57] fix: wire confidence estimation into chat flow (#231) (#232)

2026-03-15 13:58:35 -04:00

test_autoresearch_perplexity.py

Claude/angry cerf (#173)

2026-03-11 16:55:27 -04:00

test_autoresearch.py

ruff (#169)

2026-03-11 12:23:35 -04:00

test_backends.py

[loop-cycle-40] fix: use get_system_prompt() in cloud backends (#135) (#138)

2026-03-15 09:44:43 -04:00

test_briefing.py

[loop-cycle] test: add unit tests for briefing.py (#422) (#438)

2026-03-19 10:50:21 -04:00

test_calculator.py

refactor: Phase 3 — reorganize tests into module-mirroring subdirectories

2026-02-26 21:21:28 +00:00

test_cli_multiword.py

fix: CLI chat accepts multi-word messages without quotes

2026-03-14 19:43:52 -04:00

test_cli.py

[loop-cycle-30] fix: gitea-mcp binary name + test stabilization

2026-03-14 21:32:39 -04:00

test_cognitive_state.py

fix: wire cognitive state to sensory bus (presence loop) (#414)

2026-03-19 03:23:03 -04:00

test_confidence.py

[loop-cycle-47] feat: add confidence signaling module (#143) (#161)

2026-03-15 11:20:30 -04:00

test_conversation.py

feat: tick prompt arg + fix name extraction learning verbs as names

2026-03-11 21:11:53 -04:00

test_event_bus.py

feat: SensoryEvent model + SensoryBus dispatcher (#318)

2026-03-18 19:02:12 -04:00

test_events.py

feat: SensoryEvent model + SensoryBus dispatcher (#318)

2026-03-18 19:02:12 -04:00

test_familiar.py

feat: Pip the Familiar — behavioral state machine (#367)

2026-03-18 21:50:36 -04:00

test_focus.py

fix: deep focus mode — single-problem context for Timmy (#409)

2026-03-19 02:54:19 -04:00

test_gematria.py

[loop-cycle-60] fix: retry with backoff on Ollama GPU contention (#70) (#238)

2026-03-15 14:28:47 -04:00

test_grok_backend.py

[loop-cycle-40] fix: use get_system_prompt() in cloud backends (#135) (#138)

2026-03-15 09:44:43 -04:00

test_interview.py

fix: repair broken test patch target and add interview transcript (#156)

2026-03-10 15:26:29 -04:00

test_introspection.py

[loop-cycle-52] fix: remove all qwen3.5 references (#182) (#190)

2026-03-15 12:34:21 -04:00

test_loop_qa.py

feat: add Loop QA self-testing framework

2026-03-11 22:33:16 -04:00

test_mcp_tools.py

fix: add update_gitea_avatar capability (#368)

2026-03-18 22:04:57 -04:00

test_memory_system.py

test: add unit tests for jot_note and log_decision artifact tools (#341)

2026-03-18 20:47:38 -04:00

test_ollama_disconnect.py

[loop-cycle-66] fix: replace language-model with inference-backend in error messages (#334)

2026-03-18 20:27:06 -04:00

test_ollama_timeout.py

[loop-cycle-34] fix: mock Ollama model resolution in create_timmy tests (#121) (#126)

2026-03-15 08:20:00 -04:00

test_prompts.py

fix: implement source distinction in agent responses

2026-03-19 14:50:18 -04:00

test_routing.py

fix: word-boundary routing + debug route command (#31)

2026-03-14 19:21:30 -04:00

test_self_awareness.py

fix: enrich self-knowledge with architecture map and self-modification pathway

2026-03-14 20:15:30 -04:00

test_semantic_memory.py

[loop-cycle-56] fix: resolve 5 lint errors on main (#203) (#224)

2026-03-15 13:40:40 -04:00

test_session_identity.py

feat: inject session_id into system prompt for session identity awareness

2026-03-14 19:43:11 -04:00

test_session_logger.py

fix: add self_reflect tool for past behavior review (#417)

2026-03-19 09:39:14 -04:00

test_session_logging.py

ruff (#169)

2026-03-11 12:23:35 -04:00

test_session.py

[loop-cycle-154] refactor: extract _annotate_confidence helper — DRY 3x duplication (#369) (#376)

2026-03-18 22:01:51 -04:00

test_thinking.py

[loop-cycle-65] fix: validate file paths before filing thinking-engine issues (#327) (#329)

2026-03-18 20:07:19 -04:00

test_timmy_serve_app.py

Operation Darling Purge: slim to wealth core (-33,783 lines) (#121)

2026-03-02 13:17:38 -05:00

test_timmy_serve_cli.py

Operation Darling Purge: slim to wealth core (-33,783 lines) (#121)

2026-03-02 13:17:38 -05:00

test_timmy_tools.py

fix: prune dead web_search tool — ddgs never installed (#87)

2026-03-14 18:13:51 -04:00

test_tool_safety.py

fix: prune dead web_search tool — ddgs never installed (#87)

2026-03-14 18:13:51 -04:00

test_tools_calculator.py

fix: replace eval() with AST-walking safe evaluator in calculator

2026-03-14 15:51:35 -04:00

test_tools_delegation.py

feat: add delegate_to_kimi() tool for coding delegation (#67)

2026-03-14 20:29:03 -04:00

test_tools_extended.py

Claude/angry cerf (#173)

2026-03-11 16:55:27 -04:00

test_tools_unit.py

fix: add unit tests for tools.py (#428)

2026-03-19 10:17:36 -04:00

test_vector_store.py

[loop-cycle-54] refactor: consolidate three memory stores into single table (#37) (#223)

2026-03-15 13:33:24 -04:00

test_voice_loop.py

test: skip voice_loop tests gracefully when numpy unavailable

2026-03-14 18:24:56 -04:00

test_welcome.py

fix: add real-time data disclaimer to welcome message (#304)

2026-03-18 16:56:21 -04:00

test_workshop_state.py

feat: Workshop Phase 1 — State Schema v1 (#404)

2026-03-19 02:24:13 -04:00

test_workspace.py

[loop-cycle-1] fix: lint errors — ambiguous vars + unused import (#123) (#124)

2026-03-15 08:07:19 -04:00