Commit Graph

  • 96c7e6deae [loop-cycle-52] fix: remove all qwen3.5 references (#182) (#190) hermes 2026-03-15 12:34:21 -04:00
  • efef0cd7a2 fix: exclude backfilled data from success rate calculations (#189) hermes 2026-03-15 12:29:27 -04:00
  • 766add6415 [loop-cycle-52] test: comprehensive session_logger.py coverage (#175) (#187) hermes 2026-03-15 12:26:50 -04:00
  • 56b08658b7 feat: workspace isolation + honest success metrics (#186) hermes 2026-03-15 12:25:27 -04:00
  • f6d74b9f1d [loop-cycle-51] refactor: remove dead code from memory_system.py (#173) (#185) hermes 2026-03-15 12:18:11 -04:00
  • e8dd065ad7 [loop-cycle-51] perf: mock subprocess in slow introspection test (#172) (#184) hermes 2026-03-15 12:17:50 -04:00
  • 5b57bf3dd0 [loop-cycle-50] fix: agent retry uses exponential backoff instead of fixed 1s delay (#174) (#181) hermes 2026-03-15 12:08:30 -04:00
  • bcd6d7e321 [loop-cycle-50] refactor: replace bare sqlite3.connect() with context managers batch 2 (#157) (#180) hermes 2026-03-15 11:58:43 -04:00
  • bea2749158 [loop-cycle-49] refactor: narrow broad except Exception catches — batch 1 (#158) (#178) hermes 2026-03-15 11:48:54 -04:00
  • ca01ce62ad [loop-cycle-49] fix: mock _warmup_model in agent tests to prevent Ollama network calls (#159) (#177) hermes 2026-03-15 11:46:20 -04:00
  • b960096331 feat: triage scoring, cycle retros, deep triage, and LOOPSTAT panel (#162) hermes 2026-03-15 11:24:01 -04:00
  • 204a6ed4e5 refactor: decompose _maybe_distill() into focused helpers (#151) (#160) hermes 2026-03-15 11:23:45 -04:00
  • f15ad3375a [loop-cycle-47] feat: add confidence signaling module (#143) (#161) hermes 2026-03-15 11:20:30 -04:00
  • 5aea8be223 [loop-cycle-47] refactor: replace bare sqlite3.connect() with context managers (#148) (#155) hermes 2026-03-15 11:05:39 -04:00
  • 717dba9816 [loop-cycle-46] refactor: break up oversized functions in tools.py (#151) (#154) hermes 2026-03-15 10:56:33 -04:00
  • 466db7aed2 [loop-cycle-44] refactor: remove dead code batch 2 — agent_core + test_agent_core (#147) (#150) hermes 2026-03-15 10:22:41 -04:00
  • d2c51763d0 [loop-cycle-43] refactor: remove 1035 lines of dead code (#136) (#146) hermes 2026-03-15 10:10:12 -04:00
  • 16b31b30cb fix: shell hand returncode bug, delete worthless python-exec test (#140) hermes 2026-03-15 09:56:50 -04:00
  • 48c8efb2fb [loop-cycle-40] fix: use get_system_prompt() in cloud backends (#135) (#138) hermes 2026-03-15 09:44:43 -04:00
  • d48d56ecc0 [loop-cycle-38] fix: add soul identity to system prompts (#127) (#134) hermes 2026-03-15 09:42:57 -04:00
  • 76df262563 [loop-cycle-38] fix: add retry logic for Ollama 500 errors (#131) (#133) hermes 2026-03-15 09:38:21 -04:00
  • f4e5148825 policy: ban --no-verify, fix broken PRs before new work (#139) hermes 2026-03-15 09:36:02 -04:00
  • 92e123c9e5 [loop-cycle-36] fix: create soul.md and wire into system context (#125) (#130) hermes 2026-03-15 08:37:24 -04:00
  • 466ad08d7d [loop-cycle-34] fix: mock Ollama model resolution in create_timmy tests (#121) (#126) hermes 2026-03-15 08:20:00 -04:00
  • cf48b7d904 [loop-cycle-1] fix: lint errors — ambiguous vars + unused import (#123) (#124) hermes 2026-03-15 08:07:19 -04:00
  • aa01bb9dbe [loop-cycle-30] fix: gitea-mcp binary name + test stabilization (#118) hermes 2026-03-14 21:57:23 -04:00
  • 082c1922f7 policy: enforce squash-only merges with linear history (#122) hermes 2026-03-14 21:56:59 -04:00
  • 9220732581 Merge pull request '[loop-cycle-31] feat: workspace heartbeat monitoring (#28)' (#120) from feat/workspace-heartbeat into main hermes 2026-03-14 21:52:24 -04:00
  • 66544d52ed feat: workspace heartbeat monitoring for thinking engine (#28) Kimi Agent 2026-03-14 21:51:36 -04:00
  • 5668368405 Merge pull request 'feat: Timmy authenticates to Gitea as himself' (#119) from feat/timmy-gitea-identity into main hermes 2026-03-14 21:46:05 -04:00
  • a277d40e32 feat: Timmy authenticates to Gitea as himself Kimi Agent 2026-03-14 21:45:54 -04:00
  • 564eb817d4 Merge pull request 'policy: QA philosophy + dogfooding mandate' (#117) from policy/qa-dogfooding-philosophy into main hermes 2026-03-14 21:33:08 -04:00
  • 874f7f8391 policy: add QA philosophy and dogfooding mandate to AGENTS.md Kimi Agent 2026-03-14 21:32:54 -04:00
  • a57fd7ea09 [loop-cycle-30] fix: gitea-mcp binary name + test stabilization Kimi Agent 2026-03-14 21:29:11 -04:00
  • 7546a44f66 Merge pull request 'policy: enforce PR-only merges to main + fix broken repl tests' (#116) from policy/pr-only-main into main rockachopa 2026-03-14 21:15:00 -04:00
  • 2fcaea4d3a fix: exclude slow tests from all tox envs (ci, pre-push, coverage) Kimi Agent 2026-03-14 21:14:36 -04:00
  • 750659630b policy: enforce PR-only merges to main + fix broken repl tests Kimi Agent 2026-03-14 21:14:34 -04:00
  • 24b20a05ca Merge pull request '[loop-cycle-29] perf: eliminate redundant LLM calls in agentic loop (#24)' (#115) from fix/perf-redundant-llm-calls-24 into main hermes 2026-03-14 20:56:33 -04:00
  • b9b78adaa2 perf: eliminate redundant LLM calls in agentic loop (#24) Kimi Agent 2026-03-14 20:54:33 -04:00
  • bbbbdcdfa9 fix: remove unused variable in repl test Kimi Agent 2026-03-14 19:25:19 -04:00
  • 65e5e7786f feat: REPL mode, stdin support, multi-word fix for CLI (#26) Kimi Agent 2026-03-14 19:25:10 -04:00
  • 9134ce2f71 Merge pull request '[loop-cycle-28] fix: smart_read_file accepts path= kwarg (#113)' (#114) from fix/smart-read-file-113 into main hermes 2026-03-14 20:41:39 -04:00
  • 547b502718 fix: smart_read_file accepts path= kwarg from LLMs (#113) Kimi Agent 2026-03-14 20:40:19 -04:00
  • 3e7a35b3df Merge pull request '[loop-cycle-12] feat: Kimi delegation tool for coding tasks (#67)' (#112) from fix/kimi-delegation-67 into main hermes 2026-03-14 20:31:08 -04:00
  • 1c5f9b4218 Merge pull request '[loop-cycle-12] feat: self-test tool for sovereign integrity verification (#65)' (#111) from fix/self-test-65 into main hermes 2026-03-14 20:31:07 -04:00
  • 453c9a0694 feat: add delegate_to_kimi() tool for coding delegation (#67) Kimi Agent 2026-03-14 20:29:03 -04:00
  • 2fb104528f feat: add run_self_tests() tool for self-verification (#65) Kimi Agent 2026-03-14 20:28:24 -04:00
  • c164d1736f Merge pull request '[loop-cycle-11] fix: enrich self-knowledge with architecture map and self-modification (#81, #86)' (#110) from fix/self-knowledge-depth into main hermes 2026-03-14 20:16:48 -04:00
  • ddb872d3b0 fix: enrich self-knowledge with architecture map and self-modification pathway Kimi Agent 2026-03-14 20:15:30 -04:00
  • f8295502fb Merge pull request '[loop-cycle-10] fix: memory consolidation dedup (#105)' (#109) from fix/memory-consolidation-dedup-105 into main hermes 2026-03-14 20:05:39 -04:00
  • b12e29b92e fix: dedup memory consolidation with existing memory search (#105) Kimi Agent 2026-03-14 20:04:18 -04:00
  • 825f9e6bb4 Merge pull request '[loop-cycle-10] feat: codebase self-knowledge in system prompts (#78, #80)' (#108) from fix/self-awareness-78-80 into main hermes 2026-03-14 19:59:39 -04:00
  • ffae5aa7c6 feat: add codebase self-knowledge to system prompts (#78, #80) Kimi Agent 2026-03-14 19:58:10 -04:00
  • 0204ecc520 Merge pull request '[loop-cycle-9] fix: CLI multi-word messages (#26)' (#107) from fix/cli-multiword-messages into main hermes 2026-03-14 19:48:28 -04:00
  • 2b8d71db8e Merge pull request '[loop-cycle-9] feat: session identity awareness (#64)' (#106) from fix/session-identity-awareness into main hermes 2026-03-14 19:48:16 -04:00
  • 9171d93ef9 fix: CLI chat accepts multi-word messages without quotes Kimi Agent 2026-03-14 19:43:52 -04:00
  • f8f3b9b81f feat: inject session_id into system prompt for session identity awareness Kimi Agent 2026-03-14 19:43:11 -04:00
  • a728665159 Merge pull request 'fix: python3 compatibility in shell hand tests (#56)' (#104) from fix/test-infra into main hermes 2026-03-14 19:24:49 -04:00
  • 343421fc45 Merge remote-tracking branch 'origin/main' into fix/test-infra Kimi Agent 2026-03-14 19:24:32 -04:00
  • 4b553fa0ed Merge pull request 'fix: word-boundary routing + debug route command (#31)' (#102) from fix/routing-patterns into main hermes 2026-03-14 19:24:16 -04:00
  • 342b9a9d84 Merge pull request 'feat: JSON status endpoints for briefing, memory, swarm (#49, #50)' (#101) from fix/api-consistency into main hermes 2026-03-14 19:24:15 -04:00
  • b3809f5246 feat: add JSON status endpoints for briefing, memory, swarm (#49, #50) Kimi Agent 2026-03-14 19:23:32 -04:00
  • 2ffee7c8fa fix: python3 compatibility in shell hand tests (#56) Kimi Agent 2026-03-14 19:22:21 -04:00
  • 67497133fd fix: word-boundary routing + debug route command (#31) Kimi Agent 2026-03-14 19:21:30 -04:00
  • 970a6efb9f Merge pull request '[loop-cycle-8] test: add 86 tests for semantic_memory.py (#54)' (#100) from test/semantic-memory-coverage into main hermes 2026-03-14 19:17:19 -04:00
  • 415938c9a3 test: add 86 tests for semantic_memory.py (#54) Kimi Agent 2026-03-14 19:15:55 -04:00
  • c1ec43c59f Merge pull request '[loop-cycle-8] fix: replace 59 bare except clauses with proper logging (#25)' (#99) from fix/bare-except-clauses into main hermes 2026-03-14 19:08:40 -04:00
  • fdc5b861ca fix: replace 59 bare except clauses with proper logging (#25) Kimi Agent 2026-03-14 19:07:14 -04:00
  • ad106230b9 Merge pull request '[loop-cycle-7] feat: add OLLAMA_NUM_CTX config (#83)' (#98) from fix/num-ctx-remaining into main rockachopa 2026-03-14 19:00:40 -04:00
  • f51512aaff Merge pull request '[loop-cycle-7] chore: Docker cleanup - remove taskosaur (#32)' (#97) from fix/docker-cleanup into main hermes 2026-03-14 18:56:42 -04:00
  • 9c59b386d8 feat: add OLLAMA_NUM_CTX config to cap context window (#83) Kimi Agent 2026-03-14 18:54:43 -04:00
  • e6bde2f907 chore: remove dead taskosaur/postgres/redis services, fix root user (#32) Kimi Agent 2026-03-14 18:52:44 -04:00
  • b01c1cb582 Merge pull request '[loop-cycle-6] fix: Ollama disconnect logging and error handling (#92)' (#96) from fix/ollama-disconnect-logging into main hermes 2026-03-14 18:41:25 -04:00
  • bce6e7d030 fix: log Ollama disconnections with specific error handling (#92) Kimi Agent 2026-03-14 18:40:15 -04:00
  • 8a14bbb3e0 Merge pull request '[loop-cycle-5] fix: warmup model on cold load (#82)' (#95) from fix/warmup-cold-model into main hermes 2026-03-14 18:26:48 -04:00
  • d1a8b16cd7 Merge pull request '[loop-cycle-5] test: skip voice_loop tests when numpy missing (#48)' (#94) from fix/skip-voice-tests-no-numpy into main hermes 2026-03-14 18:26:40 -04:00
  • bf30d26dd1 test: skip voice_loop tests gracefully when numpy unavailable Kimi Agent 2026-03-14 18:24:56 -04:00
  • 86956bd057 fix: warmup model on cold load to prevent first-request disconnect Kimi Agent 2026-03-14 18:24:00 -04:00
  • 23ed2b2791 Merge pull request '[loop-cycle-4] fix: prune dead web_search tool (#87)' (#93) from fix/prune-dead-web-search into main hermes 2026-03-14 18:15:25 -04:00
  • b3a1e0ce36 fix: prune dead web_search tool — ddgs never installed (#87) Kimi Agent 2026-03-14 18:13:51 -04:00
  • 7ff012883a Merge pull request '[loop-cycle-3] fix: model introspection prefix-match collision (#77)' (#91) from fix/model-introspection-prefix-match into main hermes 2026-03-14 18:04:40 -04:00
  • 7132b42ff3 fix: model introspection uses exact match, queries /api/ps first Kimi Agent 2026-03-14 18:02:14 -04:00
  • 1f09323e09 Merge pull request '[loop-cycle-2] test: regression tests for confirmation warning spam (#79)' (#90) from fix/confirmation-warning-spam into main hermes 2026-03-14 17:55:16 -04:00
  • 74e426c63b [loop-cycle-2] fix: suppress confirmation tool WARNING spam (#79) (#89) hermes 2026-03-14 17:54:58 -04:00
  • 586c8e3a75 fix: remove unused variable lint warning Kimi Agent 2026-03-14 17:54:27 -04:00
  • e09ca203dc Merge pull request '[loop-cycle-1] feat: tool allowlist for autonomous operation (#69)' (#88) from fix/tool-allowlist-autonomous into main hermes 2026-03-14 17:41:56 -04:00
  • 09fcf956ec Merge pull request '[loop-cycle-1] feat: tool allowlist for autonomous operation (#69)' (#88) from fix/tool-allowlist-autonomous into main hermes 2026-03-14 17:41:56 -04:00
  • d28e2f4a7e [loop-cycle-1] feat: tool allowlist for autonomous operation (#69) Kimi Agent 2026-03-14 17:39:48 -04:00
  • 0b0251f702 Merge pull request '[loop-cycle-13] fix: configurable model fallback chains (#53)' (#76) from fix/configurable-fallback-models into main hermes 2026-03-14 17:28:34 -04:00
  • 94cd1a9840 fix: make model fallback chains configurable (#53) Kimi Agent 2026-03-14 17:26:47 -04:00
  • f097784de8 Merge pull request '[loop-cycle-12] fix: brevity tuning — Timmy speaks plainly (#71)' (#75) from fix/brevity-tuning into main hermes 2026-03-14 17:18:06 -04:00
  • 061c8f6628 fix: brevity tuning — plain text prompts, markdown=False, front-loaded brevity Kimi Agent 2026-03-14 17:15:56 -04:00
  • 3c671de446 Merge pull request '[loop-cycle-9] fix: thinking engine skips MCP tools to avoid cancel-scope errors (#72)' (#74) from fix/thinking-mcp-cancel-scope into main hermes 2026-03-14 16:51:07 -04:00
  • 927e25cc40 Merge pull request 'fix: replace print() with proper logging (#29, #51)' (#59) from fix/print-to-logging into main rockachopa 2026-03-14 16:34:48 -04:00
  • 2d2b566e58 Merge pull request 'fix: replace print() with proper logging (#29, #51)' (#59) from fix/print-to-logging into main rockachopa 2026-03-14 16:34:48 -04:00
  • 64fd1d9829 voice: reinforce brevity at top of system prompt Kimi Agent 2026-03-14 16:32:47 -04:00
  • f0b0e2f202 fix: WebSocket 403 spam and missing /swarm endpoints Kimi Agent 2026-03-14 16:29:35 -04:00
  • b30b5c6b57 [loop-cycle-6] Break thinking rumination loop — semantic dedup (#38) Kimi Agent 2026-03-14 16:21:16 -04:00
  • 0d61b709da Merge pull request '[loop-cycle-5] Persist chat history in SQLite (#46)' (#63) from fix/issue-46-chat-persistence into main rockachopa 2026-03-14 16:10:55 -04:00
  • 79edfd1106 feat: persist chat history in SQLite — survives server restarts Kimi Agent 2026-03-14 16:09:26 -04:00