diff --git a/.torch/prompts/COMMON.md b/.torch/prompts/COMMON.md index 9a324e0..db9b900 100644 --- a/.torch/prompts/COMMON.md +++ b/.torch/prompts/COMMON.md @@ -82,6 +82,27 @@ enforcement; this is not permission to auto-assign arbitrary proposals, invent approval authority, launch providers, activate identities or enable wakes. The arbiter starts the assigned session. Other implementation remains gated. +## Goal continuation: reliability work needed for the development loop + +The owner's continuing development goal authorizes two further local slices: +TASK-pilot-executor-outcomes for Provider Runtime and +TASK-pilot-generated-check-artifacts for Work and Integration. Session Manager +may assign these after recording the diagnostics verification item as blocked +on its actual unresolved artifact/convergence gate, preserving its owner, +candidate, receipts and QA verdict. Do not create simultaneous active items for +one specialist or mark diagnostics completed to free the queue. + +Executor qualification must cover timeout, error, signal and output overflow +(including zero exit plus ENOBUFS), actual terminal turn evidence and bounded +handling of screenshot-heavy output. No false successful/idle receipt or exposed +private reasoning. Coordinate exact CLI-owned paths with Release and tests with +QA. Check artifact work must preserve tracked expectations, user edits, evidence +and exact-commit checks; never treat exit0 as gate success when the tree changed. +Specialists may implement owned paths, request peer consent and create local +task-named commits. Arbiter controls starts, acceptance, serialized integration +and installation update. Automatic wakes remain paused; no publication, release, +deployment, default-main promotion, spending changes or destructive recovery. + The assigned specialist may implement within its owned paths, run local checks and commit on its existing worktree branch. Ask the responsible owner before editing shared/other-owned files. Name the task in commits, preserve all existing diff --git a/reports/audit/first-development-pilot-2026-09-30.md b/reports/audit/first-development-pilot-2026-09-30.md index 791ef7b..e496594 100644 --- a/reports/audit/first-development-pilot-2026-09-30.md +++ b/reports/audit/first-development-pilot-2026-09-30.md @@ -158,3 +158,81 @@ Recovery is `ONE-DISK` for current rewrite HEAD: origin exists, but local remote-tracking references do not contain that commit. This is not proof of a live remote query. Off-machine synchronization requires an explicit owner publication/backup decision; no remote push or default-main promotion occurred. + +## Bounded coordination and reliability follow-through + +The owner clarified that ordinary peer coordination should not require human +relay. Live COMMON and Session Manager instructions now require own-inbox review, +named-approver decisions, durable unresolved waits and direct responsible-peer +follow-up. Spending, publication, releases, scope/ownership changes, destructive +recovery and owner-addressed approvals remain reserved. There are 44 backlog +items; `TASK-bounded-routine-coordination` carries this policy into fresh installs. + +Project Kernel committed candidate `d3a679849b0f5e55c2114223a2e56977c318391e`. +The arbiter independently ran its new routine-coordination test: **2/2 PASS**. +This covers generated instruction surfaces, acknowledgement not completing work, +and named-approver enforcement. It does not independently prove paused runtime +execution or full integration qualification. QA has a review request for that +coverage gap. Kernel reports test/check/lint evidence, but its dashboard gate is +blocked: root Playwright is 1.58.2, Kernel's installed dependency is 1.63.0, and +the latter expects absent `chromium_headless_shell-1243`. QA and manager were +asked to resolve reproducible setup, not waive assertions or use an unverified +browser substitution. + +Session Manager explicitly blocked the earlier runtime diagnostics task while +preserving its accepted candidate and incomplete dashboard receipt. It then +assigned `TASK-pilot-executor-outcomes` to Provider Runtime and +`TASK-pilot-generated-check-artifacts` to Work and Integration, one active item +per specialist. Named QA additive-test/output-plumbing consent and Release CLI +consent were requested through the control plane. The arbiter started their +review turns and both assigned implementation turns using separate owned +transient user services. A running service proves an active launch handle, not +task completion or successful native terminal output. + +All three named peer consents subsequently reached **approved revision 2**: +QA `e198e23b-772f-42d5-89df-5c4891df904f` and +`649f7e47-8b94-4b02-a1e6-962fde3e24a7`, and Release +`200dcdba-9337-4e6f-a218-d02c7bda458a`. The responsible peers sent their bounded +decisions directly to specialists and manager. Actual native Codex processes +were verified in the Provider Runtime and Work and Integration worktrees; +the Console subsequently showed both as working. These are successful peer +coordination outcomes, not completed implementation or independent acceptance. + +Owner Console is continuing its actual browser audit through a bounded temporary +diagnostic launcher. The launcher captures outcome metadata only, checks terminal +turn evidence and refuses false success. Its larger output buffer is diagnostic +recovery, **not an installed engine fix**. The permanent executor task must handle +timeouts, signals, errors, output overflow and uncertain captured identities. +Automatic wakes remain paused; no remote push, release, installation update or +default-main promotion has occurred. + +## Independent follow-up: completion evidence and review gaps + +The first temporary Console probe completed with status 0, no executor error or +signal, 64 valid protocol records and a final `turn.completed` event. It captured +141,317 stdout bytes. This proves that diagnostic turn completed, **not that its +audit task completed**; the audit addendum still records missing computer-use +coverage. A fresh arbiter browser connection and fresh tab subsequently produced +an actually viewed single-viewport Overview capture in about four seconds. The +same Console identity was resumed with that recovery evidence, without duplicate +launch or a claim that the earlier interruption was caused by output overflow. + +QA independently confirmed Kernel's focused 2/2 pass, but rejected full policy +acceptance because paused execution was only text-matched and manual test reports +were not durable TORCH check receipts. Kernel was resumed for an additive real +paused-dispatch boundary scenario. Both tracked lockfiles pin Playwright 1.58.2; +Kernel's 1.63.0 installation is an environment mismatch, not an intended upgrade. + +Work and Integration created candidate +`f46c713cc9e90697d02e3e29222b3eeb7cd71d99`. Arbiter independently ran its two new +artifact scenarios: **2/2 PASS**, covering sequential external hashed outputs +and an exit-zero source mutation remaining incomplete. Full dashboard, +convergence and independent acceptance remain outstanding. + +An early review of Provider Runtime's uncommitted executor draft found remaining +workflow gaps: status-zero success without terminal evidence, reducing scheduled +output capacity rather than safely handling screenshot-rich turns, discarding +initial runtime identity on large output, and insufficient public-boundary tests. +Specific evidence was routed to Provider Runtime, QA and Session Manager. This +is in-progress review feedback, not an accepted fix. The manager was resumed to +follow direct-report waits and task/evidence state; automatic wakes remain paused.