Remove start command - #4
Merged
Merged
Conversation
Entire-Checkpoint: 013118c3a750
peyton-alt
added a commit
that referenced
this pull request
Apr 21, 2026
…rivation Covers issues #1-7 from the multi-agent PR review pass: 1-2. Settings-load errors no longer wipe user config. Both runReview and saveReviewConfig now distinguish "file missing" (settings.Load returns defaults) from "file malformed" (returns err). Malformed-file errors surface to the user with a friendly "fix .entire/settings.json" hint instead of silently opening the picker and overwriting unrelated settings with an empty EntireSettings{}. 3. Pending marker is now cleaned up on every spawn-path failure via a deferred best-effort ClearPendingReviewMarker. Previously it only fired on execCmd.Run() non-zero exit, so a clean agent exit without any UserPromptSubmit (e.g. /quit) would leave the marker behind to mis-tag the next unrelated session. 4. detectBaseBranch loop order now matches its docstring: all remote- tracking branches (origin/main, origin/master) are tried before any local branch. The doc-vs-code drift the comment-analyzer caught is fixed; a regression test pins the order. 5. HasReview derivation no longer lives as a hardcoded string literal in the checkpoint package. session.Kind.IsReview() is the single source of truth; manual_commit_condensation sets WriteCommittedOptions .HasReview via that helper. Future review-kind Kind values just add to the IsReview disjunction and HasReview keeps covering them — previously a typo of "agent_review" in committed.go would have silently broken the feature. 6. Context now threads through pendingMarkerPath, WritePendingReviewMarker, ReadPendingReviewMarker, ClearPendingReviewMarker. Previously they all used context.Background() internally, dropping cancellation and tracing from callers. 7. headHasReviewCheckpoint now logs at Debug on each failure step (locate worktree root, read HEAD, parse trailer, open repo, resolve summary, HasReview false) so users debugging "why didn't the review badge show up?" have breadcrumbs instead of a single silent false. Plus tests: - TestKindIsReview pins the IsReview invariant and forces future review kinds to be added to the disjunction. - TestSaveReviewConfig_ReturnsErrorOnMalformedSettings pins the data-loss regression fix. - TestDetectBaseBranch_PrefersAllRemotesOverLocals pins the #4 fix. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Entire-Checkpoint: 410590b32b74
7 tasks
suhaanthayyil
added a commit
that referenced
this pull request
Jun 30, 2026
Resolves the review packet on the Codex subagent change: - #1 Codex task-checkpoint UUID: documented that CheckpointUUID is Claude-format-specific (tool_result/UUID) and resolves to "" for Codex — rewind to a Codex task checkpoint restores files via the shadow tree but does not truncate the transcript (graceful fall-through; restore truncation is also Claude-only). Codex-aware line-offset truncation is a deferred follow-up. Comment at the call site + AGENT.md. - #2 Resumed-subagent token under-count: documented deliberate trade-off (chosen over the worse cross-turn double-count) + observability — logResumedOutOfRangeChildren debug-logs when a resume_agent targets a child spawned in a prior range. - #3 Regression tests: CalculateTotalTokenUsage nil-main-with-subagent-tokens unit test (guards the nil-deref); new integration test TestCodexSubagentEnd_SourcesFilesFromChildNotParent (+ SimulateCodexSubagentStart/Stop harness helpers) guarding handleLifecycleSubagentEnd's child-not-parent resolver. - #4 Debug logging across the discover→resolve→read→parse chain (readSubagentRolloutsUncached, CalculateTotalTokenUsage, spawn-output drop) so Codex wire-format drift is visible instead of silently zeroing attribution. - #5 isCodexSubagentRollout: nested source.subagent fallback for rollouts without thread_source + backward-compat test (missing marker → treated as parent turn). - #6 + nits: t.Parallel() on the pure-logic codex tests; AGENT.md PostToolUse line corrected (it IS consumed); StepTranscriptStart aligned to the resolved transcriptOffset (removes the exec/no-preState divergence; field is currently unconsumed by the strategy). go build (incl. integration tag), vet, unit + codex integration tests, lint (0) all green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
suhaanthayyil
added a commit
that referenced
this pull request
Jul 15, 2026
Resolves the review packet on the Codex subagent change: - #1 Codex task-checkpoint UUID: documented that CheckpointUUID is Claude-format-specific (tool_result/UUID) and resolves to "" for Codex — rewind to a Codex task checkpoint restores files via the shadow tree but does not truncate the transcript (graceful fall-through; restore truncation is also Claude-only). Codex-aware line-offset truncation is a deferred follow-up. Comment at the call site + AGENT.md. - #2 Resumed-subagent token under-count: documented deliberate trade-off (chosen over the worse cross-turn double-count) + observability — logResumedOutOfRangeChildren debug-logs when a resume_agent targets a child spawned in a prior range. - #3 Regression tests: CalculateTotalTokenUsage nil-main-with-subagent-tokens unit test (guards the nil-deref); new integration test TestCodexSubagentEnd_SourcesFilesFromChildNotParent (+ SimulateCodexSubagentStart/Stop harness helpers) guarding handleLifecycleSubagentEnd's child-not-parent resolver. - #4 Debug logging across the discover→resolve→read→parse chain (readSubagentRolloutsUncached, CalculateTotalTokenUsage, spawn-output drop) so Codex wire-format drift is visible instead of silently zeroing attribution. - #5 isCodexSubagentRollout: nested source.subagent fallback for rollouts without thread_source + backward-compat test (missing marker → treated as parent turn). - #6 + nits: t.Parallel() on the pure-logic codex tests; AGENT.md PostToolUse line corrected (it IS consumed); StepTranscriptStart aligned to the resolved transcriptOffset (removes the exec/no-preState divergence; field is currently unconsumed by the strategy). go build (incl. integration tag), vet, unit + codex integration tests, lint (0) all green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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.
This was added in initial experimenting to have a convenient way to start a new branch. It's mostly replicating what you would do with git so we remove this again.