Repository navigation
Mission loop drives the goal commands (M9.28) - #87
Merged
Merged
Conversation
A goal counts only with its goal.derived (or goal.approved) ledger record and is closed by goal.met, as mission evaluate reads them. Each handout names its command: goal derive, spoon-fed goal options and derive --pick, goal intents, goal next, goal close --eval. An eval narrowed to a closed goal asks for a whole-mission eval. A goal sprinted with gaps open, or a hard-lined goal evaluate still narrows to, goes to the human (gaps M9.29, M9.30). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Aw6CiQcdpzdzZZXKf8WbUM
…#86) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Aw6CiQcdpzdzZZXKf8WbUM
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Aw6CiQcdpzdzZZXKf8WbUM
…87 M9.28-30, #74 M9.40-42, #86 M9.50+) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Aw6CiQcdpzdzZZXKf8WbUM
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Aw6CiQcdpzdzZZXKf8WbUM
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Aw6CiQcdpzdzZZXKf8WbUM
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018RxETAY6S1gcmdctBK8a8Z
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
…eval (#87) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018RxETAY6S1gcmdctBK8a8Z
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
…M9.24/M9.25) into the dsh host README takes the new front page and adds DeepSeek Harness to its host list, install notes, harness table, CI notes and limitations. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AiLhAWTRtwbgMCDQNJUbea
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
62AF
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:
mission tickread goal files and their status field. That caused three problems:goal_metwas read as "the mission is met", which sent the loop toRESEARCH.After: tick reads goals the way
mission evaluateandmission goaldo, and each handout names the command to run. A real goal run passes end to end on the real clock: derive, then review, then intents, thennextand a sprint per intent, then the narrowed eval, thenclose, then a whole-mission eval, thenRESEARCH.How (
plugin/mission/tick.py):goal.derived(orgoal.approved) ledger row for its content. A latergoal.metrow closes it.DERIVE_GOAL→aloop mission goal derive.OFFER_OPTIONS→goal options, thengoal derive --pick … --by.PLAN_INTENTS→goal intents.SPRINT→goal next, then/aladdin.EVALUATE:goal close G --eval E.mission evaluate.goal closerefuses an unmet goal, andgoal nexthas no intent left. (Numbered M9.50 because Core agent principles and the one-way / two-way door rule (M9.30, M9.38); hard-lined goals retire (M9.29) #86 holds M9.30–M9.38 and Mission layer M9.9: the six fixed roles, their wiring and two gates #74 holds M9.40–M9.42.)evaluatestill narrows to deadlocksgoal derive. I reproduced it and reported it to the goals thread, which is taking the fix after Core agent principles and the one-way / two-way door rule (M9.30, M9.38); hard-lined goals retire (M9.29) #86./aloop:missionrows,plugin/mission/README.md, the tick docstring, ROADMAP (M9.28 done; M9.29 and M9.50 open), TRACKING and CHANGELOG are updated.Evidence.
mission-tick.test.py: 29 checks. New section 27 drivesaloop mission goal derive / intents / next / closewith realassessandevaluate. It also covers:goal options.mission-*.test.pysuites,make pycheck test-hostsandscripts/check-tracking.py(80 requirements) pass locally, and CI is green on the head.🤖 Generated with Claude Code
https://claude.ai/code/session_01Aw6CiQcdpzdzZZXKf8WbUM