Repository navigation
targets: a later task may modify a symbol another task plans - #81
Merged
Merged
Conversation
Live run 46: T2 extended src/main.rs with parse_args and run, T3 modified them, and targets check blocked the planner 4 times with "not defined". Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015QxyVf3NgwsgRyYpBgDDTC
adeelahmad
marked this pull request as ready for review
October 20, 2026 03:42
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
…rgery paths PR #82 (M9.17) makes a mission grant need the human's own words: a prompt line the UserPromptSubmit hook captured. gate-mission-scope now denies the ways around that, for every agent and the supervisor: - a write (Write/Edit/patch or a Bash write) under <run data>/transcripts/, the captured prompts; - a Bash `transcripts prompt|record|snapshot|stop|stage-in`, the hooks' own commands; - where a mission is set, a host session started from a tool call (`claude -p`, `codex exec`, `opencode run`, or any prompt), since its prompt fires UserPromptSubmit too. A host's tools (`claude plugin validate`, `--version`, `opencode models`) stay allowed; no mission, no rule. Test: mission-scope-bash.test.py (220 rows; 13 of the 18 new ones fail on the previous gate), mission-roles.test.py (32 checks); make ci, conformance 78/78 and plugin validate --strict pass. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0197nSutKR1QAAqgJhFZ8fPj
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015QxyVf3NgwsgRyYpBgDDTC
adeelahmad
added a commit
that referenced
this pull request
Oct 20, 2026
Run 47: cli on #81, 13/13, 2 blocks
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
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.
Requested by Adeel · project thread
Before:
targets checkrefused amodifywhose symbol was not yet in the tree, even when another task's target plans that symbol in the same file. In live run 46, T2 extendedsrc/main.rswithparse_argsandrun, and T3 modified both of them. The planner was blocked 4 times with "symbol … is not defined in src/main.rs".After: a
modify/refactor/replace/deleteof a symbol that another target plans (as itsplanned_symbol, same path) passes the check.targets targetshows it as(planned, shadow). A symbol that no target plans is still "not defined".How:
plugin/bin/targetscollects the planned(path, symbol)pairs and accepts a match from a different change_ref.semantic-targets.test.pycase 8 covers both the pass and the still-blocked case. It was RED before the fix.make ciis green locally (78/78).Generated by Claude Code