Repository navigation
feat(discovery): add OMP session discovery - #21
HarshalRathore wants to merge 13 commits into
Conversation
* docs: add VISION.md draft and review answers scaffold Evidence-grounded from-scratch draft mined from the 20 merged PRs in this repo, open issues #23/#24/#25, community PR #21, and module headers. Under review with the author on a /vision board; verdicts fold in next. * docs(vision): fold in CLAUDE.md and the neural-net post's rationale Board feedback r1: - opener names CLAUDE.md alongside AGENTS.md, and separates the project file it trains from the user-level ~/.claude/CLAUDE.md it never writes - budget section names the four decay states and why appending wins - batch size, step size and skill-vs-memory placement carry their reasons - adds: rules are enforced in code, not asked for in a prompt * docs(vision): fold in all 12 board verdicts 6 in vision, 5 off mission, 1 conditional. Three reversed the draft: - H-1 team/multi-machine pooling is in vision, so the locality section is now about owning nothing rather than about one machine - H-3 an opt-in unattended apply is still the human in control - H-11 counting uncorroborated gaps is allowed, proposing them is not H-2 makes today's ungated bootstrap apply a deviation to fix. Verdicts and reasoning recorded verbatim in VISION-ANSWERS.md. * docs: point AGENTS.md at the vision and its recorded answers
|
Speaking as Kun's firstmate. VISION verdict (per rule):
Reviewed the diff (cli.js, config.js ALL_HARNESSES, omp.js, discovery/index.js). No security issue in the adapter itself. This is a first-time fork PR. Merge state is CONFLICTING/DIRTY against current main (main already has hermes and more adapters). no-mistakes has not raised. This is waiting on you, not on the captain: rebase onto current main, add a pinned omp fixture plus a test that fails if the adapter is removed, then |
06c5151 to
0a47432
Compare
|
Rebased onto current Pinned fixture + tests added (the "evidence" ask):
Real-format findings from the live store (fixed in this commit):
Verification: lint ✓ · prettier ✓ · tsc ✓ · 221/221 tests ✓ · live smoke: Ready for re-review. |
|
cc @kunchenguid — pushed |
|
Speaking as Kun's firstmate. Re-reviewed the new commit (0a47432), not only the comment. VISION:
Conflicts are gone (MERGEABLE). I approved first-time fork CI on this SHA. Adding omp to the default harness list matches how hermes landed, so I am not holding that as a captain default-behavior call. Still waiting on you, not on the captain: |
|
The The re-pushed head |
…ig note - classify(): invalid session timestamp falls back to file mtime instead of caching NaN (which crashed distillation later) - read(): track tool-call ids per read and drop results whose call was truncated away by the 64MB tail window, instead of letting them attach to an unrelated later call - README: document that explicit discovery.harnesses replaces defaults
|
Speaking as Kun's firstmate. Re-reviewed the no-mistakes follow-up, not only the comment. Inspected commit 594accd:
VISION:
Approved first-time fork CI on current head fc6af9a. Still waiting on you, not on the captain: the no-mistakes attestation in the PR body is bound to 0a47432, but HEAD is fc6af9a. That SHA mismatch is blocking. Run |
|
Final head is |
|
Correction to my last comment: the gate pushed one more hardening commit, so the final head is Could you approve the first-time-fork workflow runs sitting in |
|
Final head is now One heads-up on process: the gate's ci-watcher was misreading GitHub's Could you approve the first-time-fork runs on this exact head? They're sitting in
Once those are green I'll do one last gate pass purely to re-sign the attestation against |
|
Speaking as Kun's firstmate. Re-reviewed head 05b9b44, not only the comment. Inspected:
VISION: evidence/accuracy aligns (failed tools, no mis-attributed results). Human owns weights: discovery only. Nothing on faith: fixtures + tests. Budget n/a. Reads what you have: local store, named skip if missing. Failure loud: missing store is named. Scope: adapter + cache epoch, not a writer. Approved first-time fork CI and Guard on 05b9b44 (runs 32712608177, 32712608199). Still waiting on you, not on the captain: the no-mistakes attestation in the body is bound to 23267f4, not 05b9b44. Re-sign so the bound SHA is this head. I will not merge until that check is green on 05b9b44. |
|
Speaking as Kun's firstmate: closing this as stale. It has been waiting on a contributor update for 14+ days with no author push or comment (needed: re-sign no-mistakes attestation on head |
What Changed
oh-my-pi) discovery adapter for~/.omp/agent/sessions, including title-first/session-header classification, model changes, message filtering, and correlated tool results.Risk Assessment
Testing
Targeted tests, explicit/default CLI scans, and adapter-to-distiller verification completed successfully; reviewer-visible evidence was saved outside the worktree, and transient test state was cleaned up.
Evidence: Explicit OMP CLI scan
scan exit=0; omp matched=1; nativeId=omp-cli-e2eEvidence: Default harness scan
default scan exit=0; omp matched=1; harnesses=claude,codex,omp,pi,opencode,grok,cursor,hermesEvidence: OMP normalized trace
harness: omp model: openai-codex/gpt-5.5 tool: bash "npm run deploy" [error] -> deployment failedPipeline
Updates from git push no-mistakes
⏭️ **intent** - skipped
✅ No issues found.
✅ **Rebase** - passed
✅ No issues found.
src/discovery/adapters/omp.js:41-omp.enumerate()calls the fail-soft directory helper at this line, which returns an empty list for a missing or unreadable~/.omp/agent/sessions; malformed files then returnnullfromclassify()and are silently counted as skipped.backpass scantherefore reports no OMP history with no named warning, contrary to the fail-soft contract requiring drifted or missing stores to be distinguishable.src/discovery/index.js:19- The global cache epoch invalidates every pre-existing file-adapter entry after this OMP-only change. A repository with thousands of cached Codex, Claude, or Pi sessions will synchronously reclassify and rewrite the entire store on the first scan, despite those classifiers being unchanged. Use an adapter-specific cache epoch or preserve compatible entries.src/discovery/adapters/omp.js:123- OMP records can contain duplicate assistanttoolCallentries with the same id. For input[tool(id=x), tool(id=x), tool-result(id=x,error)],attachToolResultsmaps the id to the last call, leaving the first call result-less while emitting both calls. This produces an incorrect normalized trace and can inflate tool-call counts or lose the failure signal; deduplicate identical same-id calls or correlate duplicates deterministically before attaching results.✅ **Test** - passed
✅ No issues found.
pnpm exec node --test test/adapters.test.js test/config.test.js test/self-session.test.jsnode bin/backpass.js scan --harness omp --since all --json --quietwith a temporary OMP storenode bin/backpass.js scan --since all --json --quietwith default harness configurationreadTranscript()plusdistill()ontest/fixtures/omp-session.jsonlEvidence JSON and trace readability validation✅ **Document** - passed
✅ No issues found.
✅ **Lint** - passed
✅ No issues found.
✅ **Push** - passed
✅ No issues found.