mirror of https://github.com/thedotmack/claude-mem.git synced 2026-07-03 12:32:32 +08:00

Files

Alex Newman cf450cec00 fix(build): enforce shipped dependency-closure boundary (plan-10, closes #2783 ) (#2800 )

* plan-10 Phase 1: ship deterministic plugin runtime dependency closure

Approach A — commit & ship plugin/bun.lock so the plugin's runtime
node_modules install is deterministic, fixing the recurring
`Cannot find module 'zod/v3'` (#2730).

- align generated plugin zod range to root (^4.4.3) in build-hooks.js
- new scripts/gen-plugin-lockfile.cjs generates plugin/bun.lock as a
  build artifact after build-hooks.js writes plugin/package.json
- track & ship plugin/bun.lock (.gitignore negation, .npmignore, files allowlist)
- install with `bun install --frozen-lockfile --ignore-scripts` at runtime

Refs #2783, #2730

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* plan-10 Phase 2: fail loud at install time on a broken dependency closure

Strengthen verifyCriticalModules to assert each dependency is actually
importable via require.resolve (not merely a directory), and assert the
worker-required zod subpaths resolve: zod/v3, zod/v4, zod/v4-mini.
A partial/stale install now fails `npx claude-mem install` immediately
instead of surfacing later as a Stop-hook `Cannot find module 'zod/v3'`.

Bin-only packages (e.g. tree-sitter-cli, which has no bare-name entry
point) fall back to resolving <dep>/package.json so a healthy install
isn't falsely rejected.

Adds tests/cli/verify-critical-modules.test.ts covering a missing zod/v3
subpath (throws), a complete zod (passes), and a bin-only dep (passes).

Refs #2783, #2730

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* plan-10 Phase 3: clean-room install + import smoke test (#2730 backstop)

Add scripts/smoke-clean-room.cjs and a `smoke:clean-room` npm script.
Against fresh temp dirs (never the repo's node_modules) it:
- copies plugin/, runs `bun install --frozen-lockfile --ignore-scripts`,
  asserts zod, zod/v3, zod/v4, zod/v4-mini resolve, and boots the bundled
  worker asserting no `Cannot find module` — the direct #2730 regression guard;
- `npm pack`s, installs the tarball into a second temp dir, and load-tests
  the published bin entrypoint, warning loudly on any declared main/exports
  target missing from the tarball (latent #2537 gap).

Exits non-zero naming the missing module on any failure; cleans up all
temp dirs and the tarball in a finally.

Refs #2783, #2730

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* plan-10 Phase 4: gate CI and publish on the clean-room dependency closure

- ci.yml: new `clean-room-deps` job (between build and the docker e2e job)
  runs a frozen-lockfile drift check on the committed plugin lockfile, then
  `npm run build` + `npm run smoke:clean-room`. The drift step catches a
  contributor who changed plugin deps without regenerating plugin/bun.lock.
- npm-publish.yml: add setup-bun and run `npm run smoke:clean-room` between
  build and `npm publish`, so a broken runtime closure cannot be published
  on a tag push (ci.yml does not run on tags). Secrets block untouched.

Refs #2783, #2730

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* plan-10: doc recluster note + Phase 0 execution slice for #2730

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* plans: backlog recluster (2026-06-04) — cross-cluster execution order + plan-13 doc

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* plan-10: gen-plugin-lockfile degrades gracefully when bun is absent

The Windows build CI job has no bun on PATH; regenerating the lockfile there
threw and failed the build. The committed plugin/bun.lock is already the
deterministic closure, so skip regeneration (non-fatal) when bun is missing
and a lockfile exists; fail loud only when neither is available.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-05 20:27:34 -07:00

1.9 KiB

Raw Permalink Blame History

[plan-11] Observer / Summarizer Output Fidelity & Resilience — trust what the agent emits, or recover

Defect

claude-mem's quality depends on the observer/summarizer emitting truthful, parseable output, but nothing enforces either property. The observer SDK sometimes never receives tool results (only the calls) and then poisons; it poison-loops on prose like "No observations to record"; and provider history truncation (OpenRouter/Gemini) can drop the init prompt and the XML-output instructions, so the model emits non-XML and the parser silently drops the batch — observations stay at zero with no recovery and no signal. The fix is an output-fidelity contract: classify the observer's output (valid XML / idle-empty / prose / poisoned), recover by killing and respawning a poisoned session while preserving pending work, and protect the init/XML instructions from truncation.

Children

#2758 — Observations never generate — observer SDK gets tool calls but not tool results, then poisons (v13.4.0)
#2749 — Regression (v13.4.0, Windows): observer poison-loops on 'No observations to record' prose
#2738 — OpenRouter/Gemini history truncation can drop the init prompt and XML-output instructions

Fix sequence

Design doc: plans/11-observer-output-fidelity.md. Ensure tool results reach the observer; classify output and treat idle-empty/prose as non-fatal; respawn poisoned sessions preserving pending work; pin init + XML-instruction messages so truncation cannot drop them.

Test matrix

Input	Required behavior
idle batch	classified idle-empty, not poison
prose "no observations"	no poison loop
truncating provider	XML instructions retained; output parses
missing tool results	detected; session recovered

Out of scope

Tool permissions of the observer (plan-05, shipped); write-path persistence (plan-09).

1.9 KiB Raw Permalink Blame History