Alex Newman
6c1ecb54ad
* docs(plans): mirror plan-12…25 masters as design docs The 13 open plan masters each name a `plans/NN-*.md` design doc in their body (e.g. `plans/12-provider-and-extensibility-roadmap.md`), and none of those files existed — the docs half of the issue/doc pair was never written, so the only copy of each architectural defect lived in a GitHub issue body. Mirror each master as its doc at the path the master already references, add a `plans/README.md` index mapping plan → master → doc with the routing rules and health checks, and record the 2026-09-12 oh-my-issues round on the seven masters that took children: - plan-12 (#2785) ← #4060 tool_uses FTS, #3833 prompt caching, #3845 brainbeats - plan-15 (#3603) ← #4059 stale-worker reclaim, #4063 logger filename latch - plan-18 (#3606) ← #4066 budget/recycle race, #3897 unhedged observations - plan-19 (#3607) ← #4065 CLAUDE_MEM_LLM_TIMEOUT_MS unreachable from settings - plan-20 (#3608) ← #4061 SessionStart injects on resume, fires twice - plan-21 (#3609) ← #4062 NULL memory_session_id cascade (fixed in 13.24.16) - plan-23 (#3611) ← #4057 Antigravity agy 1.2.1 contract mismatch Docs only; no source changes. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BrHC7gNievhm4yafkxo25S * docs(agent-jobs): oh-my-issues run report Counts, cluster routing, the 11 PR closures with their evidence, the per-cluster next-PR list, and five escalations that need a maintainer decision. Per-batch PR triage detail under .agent-jobs/pr-results/. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BrHC7gNievhm4yafkxo25S --------- Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Plan masters
Every open bug in this repo belongs to exactly one plan master — an architectural defect, not a symptom. Symptoms get filed, routed to their master with a redirect comment, and closed as not planned. The unit of work is the master; one PR per cluster closes its children atomically.
The GitHub issue is the public tracker. The doc here is the design. They reference each other, and when they drift the doc is canonical for design and the issue for status.
| Plan | Master | Doc | Architectural defect |
|---|---|---|---|
| plan-12 | #2785 | 12-provider-and-extensibility-roadmap.md | Net-new capabilities, not defects — providers, ingestion, integrations, UX |
| plan-14 | #3602 | 14-child-process-ownership.md | Every process the worker spawns dies with the worker |
| plan-15 | #3603 | 15-worker-port-and-liveness-authority.md | One verified answer to "is a worker serving this port?" |
| plan-16 | #3604 | 16-canonical-install-identity-and-bundle-integrity.md | One resolvable, dependency-complete plugin root; recycles that cannot kill a working worker |
| plan-17 | #3605 | 17-hook-wrapper-contract.md | Hook wrapper: thin, cheap, fail-open on every host |
| plan-18 | #3606 | 18-observer-response-pipeline.md | Classify every output, never confirm a batch on failure, bound every history |
| plan-19 | #3607 | 19-observer-subprocess-isolation.md | Explicit env, cwd, config, tool set and auth source for the headless generator |
| plan-20 | #3608 | 20-project-identity-and-injection-scope.md | One project resolver shared by capture, sync and retrieval; injection config that reaches the query |
| plan-21 | #3609 | 21-sqlite-schema-evolution-and-queue-state.md | One DDL path guarded by introspection, immutable session keys, transitionable queue states |
| plan-22 | #3610 | 22-chroma-sidecar-contract.md | Host-safe sidecar spawn, single-writer upsert sync, honest fallback — or retire the sidecar |
| plan-23 | #3611 | 23-host-integration-contracts.md | Every non-Claude-Code adapter validated by contract tests against the host's actual schema |
| plan-24 | #3618 | 24-server-runtime-generation-and-sync-contract.md | One generation pipeline shared by worker and server; session linkage on every write path |
| plan-25 | #3982 | 25-search-read-path-fts-cjk.md | CJK-aware matching when FTS5 unicode61 returns 0 |
Earlier plans (01–11, 13) shipped or were folded into the masters above; 02, 04 and 08 remain
here as historical design docs.
Routing a new bug
Pattern-match the symptom against the masters above and ask: would the fix described there also fix this? If yes, add a Round-N comment to the master naming the child, the one-line symptom, a 1–3 line fix sketch and any new test-matrix cell, then close the child as not planned with:
Consolidating into #<MASTER> (plan-XX). The root cause and fix sequencing are tracked there alongside the rest of the cluster — please follow that issue for progress.
Resist opening a new master. Most bugs are children of an existing plan. Two things legitimately stay out of this scheme: genuine feature requests with no shared root cause (those go to plan-12), and support questions, which are answered rather than routed.
Health checks
- Graveyard master — 5+ Round-N comments with no shipping PR. Force a PR or split the plan.
- Over-broad master — the children's fixes cannot fit one PR. Split into two narrower plans.
- Surface-clustered master — the children share a topic but not a fix. Re-cluster by root cause.
- Drift — the master body and the doc disagree. Regenerate the doc's mirror from the issue.