docs(spx-v2): verification pass, queue state, and self-refinement record - #13
Merged
thomaswillner merged 4 commits intoAug 29, 2026
Merged
Conversation
No code written this session — a verification pass over already-delivered work plus the queue-state answer. Records, so future sessions do not repeat them: - The audit-challenge / V1-coverage / rag-tot-cot-challenge / corrected-input deliverable ALREADY EXISTS (AUDIT_CHALLENGE sections A-D and PRIME_AGENT_INPUT_SPX_V2). An operator prompt has now asked for it in at least two sessions; redoing it is inventing work. - Verified queue state from GitHub: PrimeIntellect-ai#266/PR PrimeIntellect-ai#268 merged (and PrimeIntellect-ai#263 with it, now main f64029a); PrimeIntellect-ai#265/PR PrimeIntellect-ai#269 and PrimeIntellect-ai#264/PR PrimeIntellect-ai#270 open with CI in flight; PrimeIntellect-ai#272 and PrimeIntellect-ai#271 filed, unstarted, no lane. - Errors and corrections: settle elapsed time from GitHub workflow-run timestamps, never the container clock; add_repo push access was classifier-denied so a remote session may hold read-only and cannot push; register_repo_root denial falls back to reading CLAUDE.md directly. - MATS/superpowers/routing settled empirically with the exact commands used, so the search is not repeated: they are Mac-harness resident, and PrimeIntellect-ai#272/PrimeIntellect-ai#271 already carry auto-dispatch, which is what routes them to the maker fleet. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01G5B7QM1QLQuWSBMCxiCzS6
…age, self-review Appends the second half of the session to the notes: implementing PrimeIntellect-ai#272 after the operator corrected two access assumptions. The corrections matter more than the code: - push DOES work; "I cannot push" was inferred from add_repo's access label rather than tested. A dry-run push proved it. Also: the refspec push form is classifier-denied while `git push -u origin <branch>` succeeds. - this host is not the MacBook (uname, no /Users, no ~/.prime). Also records the environment setup the Makefile assumes (venv before v2-install, ruff 0.15.22 via python -m, seeding the gitignored account.yaml, and proving PYTHONPATH beats editable installs in a worktree), the method that diagnosed the repo-wide CI outage in two calls (zero recorded steps, then the same workflow red on main), and two test defects self-review caught before pushing. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01G5B7QM1QLQuWSBMCxiCzS6
…rimeIntellect-ai#271 remains Closes the record for this session. - All five briefed PRs merged (PrimeIntellect-ai#268, PrimeIntellect-ai#263, PrimeIntellect-ai#270, PrimeIntellect-ai#269, PrimeIntellect-ai#273); main is c84855d. Issues PrimeIntellect-ai#266 and PrimeIntellect-ai#272 closed by their PRs. PrimeIntellect-ai#271 is the only open brief and was never authorised, so never started. Runtime testing is unblocked. - The CI outage (13:51Z-15:47Z) was account-level and hit main identically; recovery was visible as `changes` taking 9s with real steps instead of 2s with none. Nothing in the diff ever needed changing. - Records the scope misjudgement worth carrying forward: a Codex P1 mapped directly to an acceptance checkbox I had deferred as out of scope. When a finding maps to an acceptance criterion it is in scope by definition. - Records the auto-merge hazard: squash composes the commit message from the PR body, so a body left stale after a review round writes false claims into main permanently. Rewrite the body before merge; keep corrections visible. - Records a published test claim that had not been executed, and the rule that follows from it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01G5B7QM1QLQuWSBMCxiCzS6
Records, without editing the now-false text away, that sections 9 and 4 went stale five hours after they were written. The correction matters more than the content: this file exists to stop sessions trusting notes over GitHub, and it caught its own author. - main is 8d2139c. Between 16:12Z and 21:54Z the fleet merged PrimeIntellect-ai#279 (the PrimeIntellect-ai#58 alert-bridge race, FIXED — stop carrying it as a standing exception), PrimeIntellect-ai#278 (AGENTS.md invariants), PrimeIntellect-ai#283 (repo cleanup), and PrimeIntellect-ai#284, which delivered the last brief and closed PrimeIntellect-ai#165 with a keyword. - Section 3's routing conclusion was confirmed by events: PrimeIntellect-ai#271 was delivered by the Mac maker fleet via auto-dispatch, exactly as argued, and the remote session correctly declined to open a second lane. - Flags issue-state drift: PrimeIntellect-ai#271, PrimeIntellect-ai#276 and PrimeIntellect-ai#274 are delivered and merged yet still open, because a title reference is not a closing keyword. That is the mirror image of the hazard the V2 CLAUDE.md documents, and it leaves open-work disagreeing with main. Operator action, named as such. - Records the residual PrimeIntellect-ai#284 deferred on stated grounds (PrimeIntellect-ai#286), which is a known open edge on the LIVE path. - States the next slice: S4 / PrimeIntellect-ai#236, the first whose exit criteria need a real broker order. Certification stays 0/12; the system has never placed a trade. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01G5B7QM1QLQuWSBMCxiCzS6
thomaswillner
marked this pull request as ready for review
August 29, 2026 21:56
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
One orchestration-memory file:
orchestration/spx-v2/SESSION_NOTES_2026-08-29_VERIFICATION_AND_QUEUE_STATE.md. Docs only — nothing inspx-0dte-bot-v2is touched by this PR.Why
The operator's self-refinement standing instruction: errors and corrections go into MD files so future sessions read them instead of repeating the work. Four things were worth making durable.
1. A re-audit request that is already satisfied. A prompt asking to challenge the Codex GPT 5.6 SOL analysis, inspect V1 coverage, challenge the rag/tot/cot/self-refinement instructions, and produce a corrected input has now arrived in at least two sessions. All of it exists:
AUDIT_CHALLENGE_2026-08-28.md§A/§B, §C (V1 coverage verdict), §D (the prompt-instruction challenge), andPRIME_AGENT_INPUT_SPX_V2.mdas the corrected input. The three IBKR rules flagged as "already missing" are that document's §3 R1/R2/R3.2. Access and environment facts, corrected by testing rather than inferring. Push works — the earlier "I cannot push" was inferred from a tool's access label and was wrong; the push form is what the classifier gates. This is a Linux sandbox, not the MacBook. MATS, superpowers and Prime's route selection are Mac-harness resident, verified by enumeration rather than assumption.
3. Two self-review findings and two published-evidence corrections. Including a scope call I got wrong on PrimeIntellect-ai#273 — a Codex P1 mapped directly to an acceptance checkbox I had deferred as out of scope — and a test claim published without executing it in the form stated.
4. The file caught its own author. Sections 9 and 4 recorded "PrimeIntellect-ai#271 is the only open brief, unstarted". Five hours later the Mac maker fleet had delivered it (PrimeIntellect-ai#284, merged 21:51Z, also closing PrimeIntellect-ai#165). The correction is appended rather than edited in, because going stale is precisely the failure this file exists to prevent.
What the final section adds
mainis8d2139c. feat(coding-agent): first-party MCP extension PrimeIntellect-ai/prime-agent#279 fixed the feat(coding-agent): add system prompt note listing pre-installed Python packages PrimeIntellect-ai/prime-agent#58 alert-bridge race — future sessions must stop carrying "known-flaky feat(coding-agent): add system prompt note listing pre-installed Python packages PrimeIntellect-ai/prime-agent#58 excepted" as boilerplate.auto-dispatch, exactly as argued, and the remote session correctly declined to open a second lane.make open-workdisagreeing withmain.0/12; the system has never placed a trade.Scope
Within the operator's standing orders: orchestration memory and Prime Agent continuity. No V2 repository, runtime, scheduler, broker or provider state changed.
Testing
Docs-only; no lanes apply. Every claim was verified against GitHub rather than copied from prior notes — branch ancestry by
merge-base --is-ancestor, the PrimeIntellect-ai#264 no-intraday-CBOE grep re-run directly, workflow-run and merge timestamps read from the API,main's history read directly, and the skill roster enumerated viaListSkills/SearchSkillsand the filesystem.🤖 Generated with Claude Code
https://claude.ai/code/session_01G5B7QM1QLQuWSBMCxiCzS6