This repository has been archived on 2026-03-24. You can view files and clone it. You cannot open issues or pull requests or push a commit.

kimi 919a011cae feat: adapt token rewards based on system stress signals (#714) ...

Implements adaptive token rewards that respond to system stress:

- StressDetector module (timmy/stress_detector.py):
  - Monitors 4 stress signals: flaky test rate, P1 backlog growth,
    CI failure rate, open bug count
  - Calculates weighted stress score (0-1) and determines mode:
    calm (<0.3), elevated (0.3-0.6), high (>0.6)
  - Applies quest-specific multipliers based on current mode

- Configuration (config/stress_modes.yaml):
  - Thresholds for mode transitions
  - Signal weights and thresholds
  - Multipliers per mode (e.g., test_improve: 1.5x in high stress)

- Quest system integration:
  - Rewards now include stress bonus/penalty in notification
  - Quest status API includes adjusted_reward and multiplier
  - Agent can see current stress mode and why rewards changed

- API endpoints:
  - GET /quests/api/stress - current stress mode and signals
  - POST /quests/api/stress/refresh - force refresh stress detection

Fixes #714

2026-03-21 17:26:40 -04:00

..

dashboard

[kimi] Add WebSocket authentication for Matrix connections (#682) (#744)

2026-03-21 16:14:05 +00:00

e2e

[loop-cycle-51] perf: mock subprocess in slow introspection test (#172) (#184)

2026-03-15 12:17:50 -04:00

fixtures

feat: code quality audit + autoresearch integration + infra hardening (#150)

2026-03-08 12:50:44 -04:00

functional

Claude/angry cerf (#173)

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

infrastructure

[kimi] test: add comprehensive tests for multimodal.py (#658) (#694)

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

integrations

[loop-cycle-956] refactor: break up _handle_message() into focused helpers (#553) (#574)

2026-03-19 21:42:01 -04:00

loop

[kimi] feat: pre-cycle state validation for stale cycle_result.json (#661) (#666)

2026-03-21 13:53:11 +00:00

security

Claude/angry cerf (#173)

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

spark

[kimi] test: add comprehensive tests for spark modules (#659) (#695)

2026-03-21 13:32:53 +00:00

timmy

[kimi] Add Golden Path generator for longer sessions (#717) (#785)

2026-03-21 19:41:34 +00:00

unit

feat: adapt token rewards based on system stress signals (#714)

2026-03-21 17:26:40 -04:00

__init__.py

feat: scaffold Timmy Time Mission Control (v1.0.0 Genesis)

2026-02-19 19:05:01 +00:00

conftest_markers.py

feat: code quality audit + autoresearch integration + infra hardening (#150)

2026-03-08 12:50:44 -04:00

conftest.py

[kimi] refactor: extract helpers from CSRFMiddleware.dispatch (#628) (#691)

2026-03-21 03:41:09 +00:00

test_agentic_loop.py

test: add comprehensive unit tests for agentic_loop.py (#345)

2026-03-18 20:54:02 -04:00

test_api_v1.py

feat: implement v1 API endpoints for iPad app (#312)

2026-03-18 18:20:14 -04:00

test_config_module.py

[kimi] test: add comprehensive tests for config.py (#648) (#693)

2026-03-21 03:54:54 +00:00

test_hands_git.py

feat: code quality audit + autoresearch integration + infra hardening (#150)

2026-03-08 12:50:44 -04:00

test_hands_shell.py

fix: shell hand returncode bug, delete worthless python-exec test (#140)

2026-03-15 09:56:50 -04:00

test_lazy_init.py

[loop-cycle-536] fix: validate_startup checks CORS wildcard in production (#472) (#478)

2026-03-19 15:29:26 -04:00

test_smart_read_file.py

fix: smart_read_file accepts path= kwarg from LLMs (#113)

2026-03-14 20:40:19 -04:00

test_smoke.py

cleanup: delete dead modules — ~7,900 lines removed

2026-03-14 09:49:24 -04:00