52 lines
6.7 KiB
Markdown
52 lines
6.7 KiB
Markdown
# STOPPED — row 332 (P3), T3 crash handoff
|
|
|
|
Stopped on 2026-10-24 under Mos mos-1630, relaying Jason's instruction: do not restart long jobs; commit/push safe work, leave a handoff, then stop. No further thread messages, tests, probes, queue operations, or implementation will run in this session.
|
|
|
|
## Branch and completed work
|
|
|
|
- Worktree: /home/jwoltje/.t3/worktrees/mosaic-stack/fethry-row332
|
|
- Branch: fethry/row332, based on refactor c8a9bcf94. No implementation commits, rebases, merges or production source edits.
|
|
- Read P3 brief, rules, full pi amendment, gate template, design and named source files. Detailed notes in BUILD.md beside this handoff.
|
|
- Root npm ci --ignore-scripts --no-audit --no-fund completed in this worktree only (128 packages). No canonical node_modules used.
|
|
- Initial test files written before implementation; none executed. Sage has not sent CLEAR. No proxy fetch, binary probe, offline turn, mutant, or suite has run.
|
|
- No real proxy, management key, host auth directory or live instance was accessed. No production service was started/stopped.
|
|
- Canonical queue next returned nothing during the assignment. Queue start op fethry-332-start refused on locks, then owner sage, including a retry after two minutes. Latest completed queue show still had owner sage, state briefed, after 331; it also warned that the rendered table was unknown. Did not repair or bypass it. Sage sage-4293 says an assign/after=none batch is running. Queue metadata identifies shared Gitea issue #1830.
|
|
|
|
## Latest accepted design
|
|
|
|
Sage sage-4293 supersedes all earlier route proposals: explicit route metadata, never catalog membership or model-prefix inference. Selected spelling: launch.models.<selection>.route = anthropic | glm | codex, required only with provider proxy. Missing route: proxy-route-missing; unknown/nonstring route: proxy-route-unknown. Other providers keep provider/model-only entries. Proposed launch.account.credential literal proxy; existing name/credential field names retained. GPT generated provider: mosaic-proxy-codex, never openai-codex. GPT wire API is still undecided pending the authorized pinned-binary requests. P2's seam stays exactly { baseUrl, key }.
|
|
|
|
Important implementation finding: launcher.mjs:571 serializes bundle.env into session.harnessEnv. Harness env will contain the session key in proxy mode, so credentials must instead reach spawnSession through transient environment variables and be omitted from serialized harnessEnv. runner.mjs:390 already inherits the spawn environment. Preserve ENV_ALLOW; filter instance provider variables in proxy mode only.
|
|
|
|
## Uncommitted work, intentionally left for the next session
|
|
|
|
These are unrun, incomplete tests/audit code, excluded from the documentation-only crash commit:
|
|
|
|
- packages/business/tests/proxy-launch.test.mjs — explicit routes and refusal codes, proxy account credential, existing nonproxy/account behavior.
|
|
- packages/plugins/tests/proxy-harness.test.mjs — Claude env/preflight, own-key isolation, pi preflight and OAuth-only refusal.
|
|
- packages/seat/tests/proxy-session-env.test.mjs — instance credential filtering and unchanged nonproxy env.
|
|
- packages/harness/tests/proxy-bundle.test.mjs — real bundle generation, all three providers, key reference/no-key/no-! invariants, file modes and launch freshness. Exact GPT API assertion deliberately pending probe evidence; add before its first run.
|
|
- agents/fethry/work/queue-332/import-run-list.mjs — non-evaluating static import audit using vm.SourceTextModule plus explicit computed loader edges. It ran successfully after correcting its own root-depth setup error. It is not a test runner.
|
|
|
|
IMPORT-RUN-LIST.txt is a historical 211-entry candidate impact list, generated before proxy-bundle.test.mjs was added. It includes case1-accept as explicitly EXCLUDED (mos-1612). Regenerate the list after resuming and report the actual authorized run list inline before any whole-file run. Do not treat the historical manifest as a current run authorization.
|
|
|
|
## Reporting status
|
|
|
|
T3 reporting repeatedly failed during GET with a 30-second timeout. fethry-0004 was confirmed delivered. Some later short numeric keys returned reused:true unexpectedly; do not rely on them as delivery evidence. A row-scoped detailed design resend and the inline 211-line import manifest also timed out, including the manifest's same-key retry. Sage may not have those messages. This handoff and BUILD.md are being pushed so they can be read with git show; no new thread message is sent under mos-1630.
|
|
|
|
## Next session, after restart authorization
|
|
|
|
1. Read this handoff/BUILD.md and recover queue state from canonical checkout. Wait for owner fethry and no after, then retry the same start op. Never bypass a refusal.
|
|
2. Recover Sage's slot status. Still NO tests or probes until Sage sends CLEAR. No job needs restarting merely to preserve current state.
|
|
3. Review the four uncommitted test files. Add the pinned-proxy API probe and exact GPT assertion before the first relevant run. Initial RED has not happened; production implementation must follow the authorized first RED.
|
|
4. Rebuild the import-derived run list and send it inline or in a reviewed pushed commit before runs. case1-accept remains off without Mos approval. Existing launch-settings.test.mjs proxy fixtures need explicit route metadata with their authorization assertions preserved; no old-test red has occurred.
|
|
5. Use P1's committed fetchPinned code under an owned fresh temporary root (8.0.42 at the inspected magica/row329 revision), never live proxy assets or another seat's scratch. After CLEAR, try pi's responses and completions requests under unshare -rn against stand-in upstream, record evidence, choose one GPT API at build time. Separately prove offline GLM and record z.ai compat survival. Real Codex auth proof remains row209 phase A step7.
|
|
6. Implement transient P2 context, model validation/route propagation, harness config, preflight, spawn env/serialization separation and tests. Named mutants: OAuth token leak; literal key in models.json. No policy or real credentials involved.
|
|
7. Land only after 329 and 331 land, rebasing on both, Gladstone first review, Dewey landing review and Sage's required gate. No force-push or merge authority is added by the crash instruction.
|
|
|
|
All future tests use a fresh shell-created short TMPDIR, absolute nice 19, and timeout -k 10 for scripts/test-*.sh. First new-test red is reportable afterward; old-test red or a second red goes to Sage before changes/reruns. No test outcomes are claimed here.
|
|
|
|
## Crash commit
|
|
|
|
Only documentation and the historical plain-text import manifest are committed. The final STOPPED reply records the exact pushed commit. The uncommitted files above remain deliberately available in this worktree because they have never run and test-slot authorization has not arrived.
|