Commit 17a466ba024e596f1c64114580ec74c5a081feb5
1 parent
4b293a8e
graphlemon: real agent-memory updates from self-hosting run 8
Showing
2 changed files
with
27 additions
and
0 deletions
.claude/agent-memory/planner/MEMORY.md
| 1 | 1 | - [loop_round bug already fixed](project_loop_round_bug_already_fixed.md) — off-by-one fix AND the REQ-05/REQ-09 comment above _LOOP_LIMIT are both already present in src/org_loop_route.py; re-verify before replanning either as open |
| 2 | 2 | - [scheduler.py busy-timeout comment missing](project_scheduler_busy_timeout_comment_missing.md) — as of 2026-08-03 _BUSY_TIMEOUT_MS (scheduler.py:78) has no inline comment; PL does not self-edit, packages as a Unit for Code Agent |
| 3 | +- [deploy_health_check.py startup-timeout comment missing](project_deploy_health_check_startup_timeout_comment_missing.md) — as of 2026-08-03 HEALTH_CHECK_STARTUP_TIMEOUT (line 24) has no inline comment (only module docstring); PH5-scoped, package as Unit, don't self-edit | ... | ... |
.claude/agent-memory/planner/project_deploy_health_check_startup_timeout_comment_missing.md
0 → 100644
| 1 | +--- | |
| 2 | +name: project-deploy-health-check-startup-timeout-comment-missing | |
| 3 | +description: supervisor/deploy_health_check.py's HEALTH_CHECK_STARTUP_TIMEOUT constant has no comment directly above it as of 2026-08-03; rationale only lives in the module docstring, far above the constant. | |
| 4 | +metadata: | |
| 5 | + type: project | |
| 6 | +--- | |
| 7 | + | |
| 8 | +As of 2026-08-03, `supervisor/deploy_health_check.py` line 24 | |
| 9 | +(`HEALTH_CHECK_STARTUP_TIMEOUT = 30`) has no comment directly above it — the lines immediately | |
| 10 | +preceding it are a blank line and `from supervisor import deploy_supervisor` (line 22). The | |
| 11 | +rationale ("MVP-fixed draft value from 05 §5.9, needs real-world calibration") exists only in | |
| 12 | +the module docstring at the top of the file (lines 1-11), which also covers the sibling | |
| 13 | +constants `HEALTH_CHECK_HTTP_TIMEOUT` and `HEALTH_CHECK_CANARY_TIMEOUT`. | |
| 14 | + | |
| 15 | +**Why:** Same verify-then-conditionally-edit request pattern as | |
| 16 | +[[project_scheduler_busy_timeout_comment_missing]] — check for an inline comment adjacent to a | |
| 17 | +specific constant, add exactly one line if missing. As PL I do not edit source code | |
| 18 | +(SOUL.md: "不写业务代码，不替 Code Agent 实现"), so the gap gets packaged as a one-line | |
| 19 | +Development Unit for Code Agent rather than fixed directly. | |
| 20 | + | |
| 21 | +**How to apply:** If asked again about this constant or its siblings | |
| 22 | +(`HEALTH_CHECK_HTTP_TIMEOUT`, `HEALTH_CHECK_CANARY_TIMEOUT`) in `deploy_health_check.py`, re-read | |
| 23 | +the file first — don't assume the module docstring counts as "directly above" the constant, and | |
| 24 | +don't assume a fix from a prior conversation already landed. This module is PH5-scoped | |
| 25 | +(Deploy Supervisor) and out of active development per CLAUDE.md's "PH5 is not in scope yet", so | |
| 26 | +any resulting Development Unit should be queued, not treated as urgent/blocking. | ... | ... |