Repository navigation
feat(folders): folder-level additional steering directories, delivered for every provider - #11827
Conversation
|
👋 Hi! This PR's description is missing some required sections from our PR template. Workflow runs won't be auto-approved until the description is updated. Missing sections:
Please update your PR description to include these sections, then push or re-save the description. The workflows will be approved on the next cycle. |
f95a43f to
22c0961
Compare
Design Review (Fable 5, fork) — 🟡 CONCERNSDesign-level review of Design-Verdict: CONCERNS A stored steering root that vanishes or becomes refused drops out log-only: the modal still lists it and the prompt carries no omission notice. WatchThe PR's own honesty principle ("a capped tree never reads like a complete one") stops at root granularity: every fired ceiling and the degraded fence get an in-band [DESIGN-REVIEWED] 967f2ec |
UX Review (Fable 5, fork) — 🟡 CONCERNSUX-level review of UX-Verdict: CONCERNS "Add directory" opens a picker that speaks only "project" vocabulary, and no first-time reader has cold-read the new "Additional steering" section. Watch
Suggestions
[UX-REVIEWED] 967f2ec |
First Principles Review (Fable 5, fork) — 🟡 CONCERNSPremise-level review of First-Principles-Verdict: CONCERNS
Not justified as shipped
What this change shipsInventory (10 items, capped — plus i18n keys, a capture script among 609 siblings, an error-baseline bump) — 6 justifiedIntent: let a folder attach shared, out-of-project steering directories that every chat filed under it inherits, on every backend — an ADDITION (issues #631, #4900, #7837).
[FIRST-PRINCIPLES-REVIEWED] 967f2ec |
Opus 5 Review (fork) — ✅ no blocking findingsReviewed Review detailsNothing blocks; the sharpest advisory issue is a FINDING — src/kiro_crew/folder_steering.py:266 — FINDING — src/kiro_crew/dashboard/chat_folders.py:701 — FINDING — src/kiro_crew/dashboard/chat_folders.py:711 — the read path reuses the write-site auditor, so once the [OPUS-REVIEWED] 967f2ec |
GPT 5.6 Review (fork) — ✅ no blocking findingsReviewed Review detailsFINDING -- src/kiro_crew/context.py:941 -- “ |
22c0961 to
1cb7de7
Compare
1cb7de7 to
7ec8074
Compare
7ec8074 to
cd0bc49
Compare
cd0bc49 to
4380dd2
Compare
|
Disposition for the GPT round on BLOCKING -- omission notices could push the bounded section past FINDING -- function-local imports in Also on |
|
Disposition for the GPT round on BLOCKING -- alternate-case path bypasses the memory-silo fence on a case-insensitive filesystem. Confirmed: |
|
Disposition for the GPT round on BLOCKING -- entry-ceiling notice states a fabricated exact count. Partly confirmed. The count itself is not fabricated: it is the one directory mid-listing when the ceiling fired, plus every sibling still queued at every open level, plus every child that could not be opened -- all directories the walk demonstrably never listed. But it IS a lower bound (an unlisted directory's own subtree was never seen, so it cannot be counted), and the notice rendered it as if exact. Fixed at the notice, not the count: it now reads "at least N directory(ies) ... were not listed ... The count is a lower bound: an unlisted directory's own subtree was never seen." The BLOCKING -- channel folder behaviour documented incorrectly. Confirmed, and my previous wording was wrong in the other direction. Verified in source: Also on |
|
Disposition for the GPT round on BLOCKING F2 -- a full essentials envelope silently loses folder steering. Confirmed: when a member's own essentials occupied every document slot (or nearly every character), F1 (app-owned folder reads host Markdown into that app's own slots) is the fifth spelling of a finding rebutted in the dispositions for Head is rebased onto main and carries all six flake fixes (#13121-#13126, all merged). |
|
Disposition for the GPT round on BLOCKING F1 -- inherited steering list ignored principal filtering. Confirmed: the backend delivery gate skips an ancestor whose |
|
Disposition for the GPT round on BLOCKING F1 -- a degraded F2 -- document-ceiling notice overclaimed. Reworded: "N more Markdown file(s) under were not examined -- the 64-document ceiling was reached, so whether they hold steering is unknown", since candidates past the ceiling are never opened. Pins updated. |
|
Disposition for the GPT round on BLOCKING F1 -- the project/global steering dedup assumed every provider delivers those trees. Confirmed: Also on this head: Linux shard 2 red was mine -- |
|
Disposition for the GPT round on BLOCKING F1 -- the entry-ceiling notice reported a placeholder count and the wrong kind. Confirmed: past |
|
Disposition for the GPT round on BLOCKING F1 -- feature-map row overstated delivery for Temporary private-member chats. Confirmed: the member seam gates folder steering on |
|
Disposition for the GPT round on BLOCKING F1 -- folder permission granted host-file reads. Accepted the proposed fix: only the person may declare steering directories. Also on that head: |
A sidebar folder can declare extra steering directories. Every dashboard chat filed under it (or under a descendant folder) receives the always-inclusion markdown from those directories as session-start context, in addition to the project's own steering. Delivery happens once, in the context builder, the one layer every provider passes through: kiro-cli, Claude Code, Codex, KAS and any config-authored harness receive it identically as prompt text. Harnesses, SpawnContext and AcpRuntime carry no folder-steering field. The effective directories are resolved live from the committed folder tree at every fresh session and post-compaction reinjection turn, so a folder edit applies to existing chats with no cache to invalidate. Spec: .kiro/specs/folder-steering-dirs (requirements, design, tasks).
|
Disposition for the GPT round on BLOCKING F1 -- the silo fence mixed config snapshots. Confirmed: |
Problem / Motivation
A sidebar folder can scope a
project_dir(file search, @-mentions, and the project's own.kiro/steering), but there is no way to attach additional steering directories that live outside the project — e.g. a shared standards/planning repo that applies across many project folders. This is upstream issue #631 ("Folder-level rules/instructions and attached sources"), and the recurring IDE-"workspace-folders" ask (#4900, #7837). Users today must hand-edit an agent template'sresourcesper repo, which is undiscoverable and does not inherit.Why it matters
Anyone maintaining a shared standards/planning repo (steering, checklists, decision records) that applies across many project folders currently has no way to attach it in Crew:
project_dirscopes only one directory's own.kiro/steering, so the shared rules must be duplicated per repo or wired by hand-editing an agent template'sresources— undiscoverable and non-inheriting. This is a recurring, multiply-requested gap (#631 plus the workspace-folders asks #4900/#7837). Delivering it at the universal context seam also means every current and future backend — including config-authored harnesses — inherits the capability with no per-provider work.What changed (motivation → approach → change)
A folder gains an Additional steering directory list, resolved up the folder tree and delivered to the model at session start — for every backend, not just one.
src/kiro_crew/folder_steering.py) and placed into session-start context by the Context_Builder, so kiro-cli, Claude Code, Codex, KAS, and any future config-authored harness all receive it identically. No per-harness wiring — the harness/runtime/slot layers carry no steering field, which avoids the "one hole per host" gap where a provider silently drops it.parent_idchain, de-duplicated and cycle-guarded, matching the existing project-directory resolver's walk contract.slot.folder_id— so editing a folder applies to existing chats at their next session, with no cachedslot.steering_dirs..kiro/steering,~/.kiro/steering) are skipped to avoid double-injection.Tests
test_folder_steering.py,test_context_folder_steering.py,test_chat_folder_steering_dirs.py,test_chat_runner_folder_steering.py,test_harness_steering_invariant.py(property tests for the resolver + the identical-SpawnPlan invariant). 64 feature + 293 neighboring regression tests pass at-n 2.Manual verification
Verified end-to-end on a pod: a chat filed into a folder with an external standards dir quoted a marker string and rule ID that exist only in that external directory; a chat outside the folder could not. Authored via the spec workflow (
.kiro/specs/folder-steering-dirs/).Screenshots / video
— PR #11827 UX evidence 2/2: Creating a child folder, showing the read-only "Inherited from parent folders" steering group — the second frame the UX Review asks for
— PR #11827 UX evidence 1/2: Folder settings with the steering-directory list filled (two rows, each with × remove) — the "filled list" frame the UX Review asks for
Related Issues
Closes #631. Related: #4900, #7837.