feat(intake): dashboard Bundles section + start_bundle skill - #310
Merged
Conversation
Adds a Bundles view to the PyAutoMind dashboard: sets of independent prompts that make sense in one Fable-orchestrated session with Opus subagents. Every task still renders in its usual section; the bundle is an extra view, never a replacement, and no existing section changes. - `Bundle:` header key (mirrors `Epic:`); `parse_bundles()` reads the human-pinned registry `PyAutoMind/bundles.md`. - `auto_bundles()`: deterministic, render-only proposals — grouped by Target; excludes epic members, `Blocked-by:`, `Autonomy: human-required`, `Difficulty: too-large` and pinned members; first-fit under 8 size points (small=1/medium=2/large=4), <=4 members, <=1 large, min 2. - Renders between Backlog and Recent in md + html: members table, total size, one-tap orchestration prompt (copy button in HTML); pinned first, auto capped at 8 with a "showing N of M" footer; unknown slug warns on the card like epics. - New `skills/start_bundle` (one issue + one PR per member, one shared worktree per repo, architect plans / subagents implement) and a WORKFLOW.md paragraph under the delegation ladder. - 22 tests in test_intake_dashboard.py. Closes #309 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Px3t8Ggy1PUmL9JdiLGip3
3 tasks
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds a Bundles section to the PyAutoMind dashboard for Fable-orchestrated multi-task sessions, plus the
start_bundleskill that defines the orchestration contract. Closes #309.A bundle is a set of independent prompts worked in one session: the architect (Fable) plans, Opus subagents implement, and every member keeps its own issue and PR so
/prmis unchanged. Distinct from an epic (ordered, phase-gated). All existing dashboard sections render byte-identically — the diff to the live pages is one added hunk per page.Changes
agents/conductors/intake/_intake.py:Bundle:header key;parse_bundles()for the human-pinnedPyAutoMind/bundles.md; deterministic render-onlyauto_bundles()(group by Target; exclude epic members /Blocked-by:/human-required/too-large/ pinned; first-fit under 8 pts with small=1, medium=2, large=4; ≤4 members, ≤1 large, min 2);bundle_prompt(); md + html renderers between Backlog and Recent; auto cards capped at 8 (BUNDLE_LIST_MAX) ranked by most-urgent member then size, with a "Showing N of M" footer; unknown-slugskills/start_bundle/(new; symlinked into~/.claudelike siblings) +skills/WORKFLOW.mdparagraph under the delegation ladder; intakeAGENTS.mddocuments the section.tests/test_intake_dashboard.py: 22 new tests (grouping, every exclusion, cap shapes, determinism, ranking, footer, pinned-before-auto, unknown slug, placement,--checkidempotence).API Changes
None — internal renderer and skills only. Prompt headers gain an optional
Bundle: <slug>key.Downstream
Companion PyAutoMind PR adds
bundles.md,REFERENCE.mddocs, workflow path triggers and the regenerated dashboard. Merge this PR first — the Mind PR's dashboard check renders with Brainmain.Test plan
pytest tests/test_intake_dashboard.py -q→ 84 passedPyAutoBrain/tests→ 601 passed_intake.py dashboard --applythen--checkclean on the real Mind; old vs new renderer diff = one added hunk per pageHeart readiness was RED for unrelated reasons (release
integratefailure,shared_preloads.pytimeout, hook-manifest drift, stale PyAutoFit PR); shipped on explicit human acknowledgement.🤖 Generated with Claude Code
https://claude.ai/code/session_01Px3t8Ggy1PUmL9JdiLGip3