Skip to content

feat(pi): mount the crew member panel on pi member threads - #22813

Merged
iamwhatever merged 1 commit into
mainfrom
feat/pi-member-parity
Oct 21, 2026
Merged

iamwhatever merged 1 commit into
mainfrom
feat/pi-member-parity

Conversation

@kyleseaman

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: A crew member's DM thread on pi gets its own panel, like it does on claude, opencode, goose or deepseek.

pi already held a member session key and the session-control tools (ACP_BACKENDS_MEMBER_DISPATCH), but ACP_BACKENDS_MEMBER_PANEL left it out because no panel mount had been driven on it (harness-parity H6 asks for each capability on its own evidence). So a pi member could not publish its webview, and the set's own comment in backend_cards.OFF_CARD_SETS ("same as ACP_BACKENDS_MEMBER_DISPATCH's") was untrue for pi.

Why it matters

pi is the only member-dispatch harness without the panel. A member running there loses the one surface an operator reads to see what it is holding and what needs them.

Not a goal

What changed (motivation → approach → change)

  • pi joins ACP_BACKENDS_MEMBER_PANEL in agent_sdk/backends_members.py. Both preconditions the set is argued on hold for pi: the array is client-composed (the mirror-less branch builds it and the gate extension's sealed handoff carries it, identity env intact), and the routing (VERIFIED_GATE_EXTENSION) is enforced. No code path changes: the panel append already runs on the mirror-less branch, gated by this set.
  • The evidence is a new live capture, test/fixtures/acp_frames/pi/member-panel-mount-live.jsonl (+ replay snapshot), off pi-acp 0.0.34 over pi 1.2.0: the client's own resolver composed kirocrew-dashboard + kirocrew-panel for a member key on pi, pi registered both and listed all ten panel tools, a panel_publish call raised session/request_permission through the gate, and the panel server's own answer reached the turn.
  • ACP_BACKENDS_MEMBER_CAPABILITIES's comment now says why pi is not a member: no mirror means _session_agent_spec is never recorded, so confirming would refuse every saved-spec member; a saved spec's own servers reach pi only as pooled stubs; and "tools": [] is not enforced on pi. So a saved-spec member on pi is refused before spawn (capability_harness_unsupported), never run narrower or wider than saved.

Backwards compatibility

Compatible: one backend joins a set; nothing that works today stops working.

Removes nothing: the diff only adds a set member, comments, tests and a fixture.

Tests

  • test/test_member_mount_pi.py: pi is in the panel set; the live capture shows the panel tool called, gated once by the gate envelope (nonce matches the header), and answered by kirocrew-panel; the captured array is what the resolver composes; a member array now carries dispatch + panel, both with identity in the sealed handoff; agent.crew_panel: false, a disabled panel server, and a narrowed panel tool each withhold the panel only; an ordinary session still carries nothing.
  • Same file, the capabilities exclusion and its three reasons: member_backend_gap refuses pi (deepseek passes the same input); a spec with its own MCP server does not place it on pi; pi is not in the zero-tool-ban set; and pi records no consumed spec, so confirm_consumed_projection would raise capability_runtime_unverified on a matching saved intent.
  • test/test_member_mount_deepseek.py: the pi branch test now expects dispatch + panel.
  • Determinism: both files 5/5 repeats, and the pi file in reversed order, green. prove.py: PROVEN (reverting the set change fails the tests).

Manual verification

  • HARNESS_BASE_REF=origin/main python3 scripts/check_harness_parity.py and --test: pass.
  • scripts/local-gate.py --base origin/main: related backend + frontend sets pass; flake ratchet passes. semgrep is not installed on this host; CI's SAST lane runs it.
  • Capture limits, also in the fixture note and pi/README.md: this host refuses user namespaces, so it has no sandbox backend and Crew refuses to spawn pi unsandboxed. No gateway-created pi session (and so no pi member turn in the dashboard) can run here. The capture was driven by a scratch stdio driver outside the product path, and the panel server's answer is identity_unattested: its token reached a disposable local gateway, which refused to vouch for a session it did not create. The publish route itself reads no backend.

Screenshots / video

N/A: the diff touches no frontend file. A screenshot of a pi member thread showing the panel would need a gateway-run pi session, which this host cannot start (see above).

Related Issues

No issue linked, by the owner's standing preference not to open tracking issues.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title
  • Existing tests pass and new tests added for new functionality
  • Self-review completed; code follows project style guidelines
  • Documentation updated (if applicable)
  • No secrets, credentials, or internal references in the diff

pi joins ACP_BACKENDS_MEMBER_PANEL on its own evidence (harness-parity H6):
the array is client-composed (mirror-less branch) and reaches pi through the
gate extension's sealed handoff, and the routing is the enforced
VERIFIED_GATE_EXTENSION. A live capture off pi-acp 0.0.34 over pi 1.2.0
(test/fixtures/acp_frames/pi/member-panel-mount-live.jsonl) shows the
resolver's own panel element registered, its tools listed, a panel_publish
call gated by session/request_permission, and the panel server's own answer.

pi stays out of ACP_BACKENDS_MEMBER_CAPABILITIES, and the set's comment now
says why: no mirror records a consumed spec, a saved spec's own servers reach
pi only as pooled stubs, and "tools": [] is not enforced there. Tests pin the
exclusion and each reason.
@kyleseaman
kyleseaman requested review from a team and KiroCrewCaptain as code owners October 21, 2026 15:55
@kyleseaman
kyleseaman requested a review from mbriones98 October 21, 2026 15:55
@github-actions

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 7b8aa00d68baf3f7edb2ad362501bf5cf911ec38 touches no user-facing surface (no changes under website/ or committed screenshots), so the UX review was skipped. Does not block merge.

@github-actions

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 7b8aa00d68baf3f7edb2ad362501bf5cf911ec38 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: pi joins one capability set on its own live capture, and no code path or frontend surface changes.

Notes

  • The live capture ran outside the product path, and the panel server refused it (identity_unattested). So no gateway-run pi member turn has yet shown the panel end to end. Capture one under acp_frames/pi/ once a sandboxed host can run it.

[DESIGN-REVIEWED] 7b8aa00

Description read

[DESCRIPTION-READ] 6439c33e6a41b8741b69dce9b1d56935956ee58a72b122dcc8c70f7bcf2678c5

That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with .github/scripts/pr-description-capture.sh over the same inputs; if it differs, the description or that evidence changed after this verdict was formed and any finding drawn from either is unproven.

@github-actions

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 7b8aa00d68baf3f7edb2ad362501bf5cf911ec38 — why this exists and whether the shipped surface is the smallest honest version. Updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

First-Principles-Verdict: PASS

Nothing to check.

What this change ships

Inventory (5 items) — 5 justified

Intent: let a crew member on the pi harness publish its own panel in its DM thread, as it already can on the other member-dispatch harnesses. This is an ADDITION.

  1. A crew member's DM thread on pi now mounts the member panel (pi joins ACP_BACKENDS_MEMBER_PANEL) — justified
  2. The existing refusal of saved-spec members on pi is pinned by tests and given a written reason, with no behaviour change — justified
  3. A new live pi capture of the panel mount, with its replay snapshot, as the evidence harness-parity H6 asks for — justified
  4. The deepseek member-mount test's pi branch now expects dispatch + panel — justified
  5. The backend_cards.OFF_CARD_SETS statement that panel membership is "the same as ACP_BACKENDS_MEMBER_DISPATCH's" becomes true again for pi — justified

[FIRST-PRINCIPLES-REVIEWED] 7b8aa00

Description read

[DESCRIPTION-READ] 71a8728fbdbe0dd791c41286ca1e314a9247403b3af15b76e9a0c2f4567f6355

That sha256 names the PR description this verdict read. Recompute it with .github/scripts/pr-description-capture.sh; if it differs, the description changed after this verdict was formed and any finding drawn from the description is unproven.

@github-actions

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 7b8aa00d68baf3f7edb2ad362501bf5cf911ec38 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 7b8aa00

Verdict parsed from the review's SHA-scoped output markers for commit 7b8aa00d68baf3f7edb2ad362501bf5cf911ec38.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 7b8aa00d68baf3f7edb2ad362501bf5cf911ec38: <one-sentence reason>

@github-actions

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 7b8aa00d68baf3f7edb2ad362501bf5cf911ec38 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 7b8aa00

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 7b8aa00d68baf3f7edb2ad362501bf5cf911ec38: <one-sentence reason>

@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running labels Oct 21, 2026
@iamwhatever
iamwhatever merged commit a247d03 into main Oct 21, 2026
104 checks passed
@iamwhatever
iamwhatever deleted the feat/pi-member-parity branch October 21, 2026 17:46
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Oct 21, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants