loki-mode 10.6.7 → 10.6.9

package/docs/v10/PROGRESS.md

@@ -1898,3 +1898,66 @@ The swarm is stopped: .loki/V10-STOP exists, the loop has no wake-ups, and the c
 - NPM-LAG guard row: publish, smoke and promote wait up to 45 min for the version and re-trigger promote; train-cycle merges origin/main back after each release (it stalled at 16:20Z, merged by hand as cc3e1392).
 - E-160 (D55, train verdict reuse on main; CodeQL always runs; kill switch LOKI_E160_REUSE=0) merged locally after an opus APPROVE.
 - D56 Control Plane: design (docs/v10/CONTROL-PLANE.md, 19 slices), CP-00 corpus, CP-01 service (Hono, Drizzle, bun:sqlite; idempotent ingest, 409 on conflict, fold-derived runs), CP-02 shipper (no-op unless LOKI_CONTROL_URL; exactly-once backfill; redaction) and CP-03 UI (runs list and detail; unpriced never shown as 0) merged locally. CP-04 (wire loki control, packaging, CI, test isolation) and BUN-OPT (npm 11 allow-scripts warning: per-platform @oven/bun packages) building.
+
+## 2026-10-02T23:24Z D60 sprint: v10.6.7 cut with all five slices; D61 paused by the governor
+- v10.6.7 (release commit bfce1db12, train/79 at 1917333e1): `loki start owner/repo#N` runs Loki 10 (D60-1, merge 1e6cbeb65, moat P9 probe ported, moat run rc=0 "no rule failed (4 of 9 proven)"), dashboard prints the port it bound (D60-2, test-ui-bare-loki rc=0), reviewer-first PR body (D60-3, merge 6cfabcf8b), issue-to-PR Action on Loki 10 plus nightly `loki backlog` example (D60-4, test-issue-to-pr-action rc=0), visible cost cap with $20 default and BUDGET_STOP exit 3 (D60-5, merge 34c007e9e).
+- train/79 CI: Tier A, Bun Parity, First-run gate, Coverage, Security Audit, Tests all success. train-cycle phase B "PROMOTED train/79 -> main" 23:21:15Z; phase C "RELEASED v10.6.7" 23:21:26Z. On bfce1db12 so far: Bun Parity, First-run gate, SBOM success; Release and npm `next` pending.
+- train/78 (4da502a47) was red on Tier A "emoji/dash on changes" (literal dashes in reviewer_body.test.ts regex); fixed forward with unicode escapes (1917333e1). e10ext budget 1520 > 1500 fixed by trimming blank lines in assert_delta.ts (4da502a47; engine10 1032 pass, 0 fail).
+- Not done: a real end-to-end exit 3 run for the cost cap (unit-tested only); the root action.yml still uses `loki start --simple`.
+- D61 (speed, docs/v10/D61-SPEED.md): paused, governor max engineers 0 (weekly projected 167.8%). Slice 17 engineer stopped; partial work in worktree agent-ad890c5afa3648ae6.
+- 23:51Z: Post-Release Smoke and Promote success on bfce1db12; npm latest and next both 10.6.7. Sprint closed. (The pause was lifted by D62 at about 00:05Z on 2026-10-03.)
+
+## 2026-10-03T01:56Z D62 resume, D63 roadmap, D64 withdrawn; 4 builders on D63 order
+- D62 (resume now) and D63 (roadmap, docs/v10/ROADMAP-D63.md) recorded and pushed (main 49a940d81). D64 (max pace, all Vorflux rows) arrived at 00:20Z and was withdrawn at 00:25Z; recorded as WITHDRAWN, no builder started.
+- Building (sonnet, worktrees): D61-17 large eval tier, D61-01 pre-model timer, D61-08 decomposer, D62-FIX (action.yml to Loki 10 plus real BUDGET_STOP exit 3 test). Ready next: D61-02, D61-07, D62-VIS, D62-JIRA.
+- Governor: weekly projected 57.4% at 01:55Z; pace target about 0.5% of the week per hour at 4 engineers.
+
+## 2026-10-03T03:04Z Train 82 in CI; HIGH re-review APPROVES contract and visual evidence
+- Train 82 (e072e47a9) carries every D61, D62 and D65 slice from trains 80 and 81 plus fixes: CI fixes dc1fa634f, contract spawn env 32b9db508, visual evidence B1-B3 e035e9929, P9 diagnostic capture e3b353e7a. Local gates: bun test 2905 pass 0 fail, dist guard 13/0, moat rc=0.
+- CI on train/82 so far: Bun Parity, First-run gate, Tier A, Coverage (baseline) success; Tests and Security Audit running.
+- HIGH re-review (opus, af6ddde5): APPROVE both. C1 and B1-B3 each reproduced on the pre-fix parent and shown fixed. Its release-gate item (stale dist) is already met: e072e47a9 dist contains "seal aborted", "keyword_match", "contract trace failed" (1 each) and no "untraced: " line.
+- Five non-blocking should-fixes filed as D65-SPEC-F1, D65-SPEC-F2 (HIGH, design) and D62-VIS-F1.
+- LOKI_CONTRACT and LOKI_VISUAL_EVIDENCE stay default off; flipping them is a separate decision.
+- Reviewer incident: a failed cd ran `loki contract` in the main checkout and wrote .loki/contract.json (gitignored); the reviewer removed it, confirmed absent at 03:04Z.
+
+## 2026-10-03T03:20Z train/83 red, P0-D66-FENCE
+- train/83 (1a63ad156) Coverage (baseline) failure: run 37092508809, `features size and import budget (D66)` fails on "speed/lean_select.ts imports ../../engine10/stages/plan.ts without a whole-statement 'import type'" (local repro: `bun test tests/engine10/budget.test.ts` 26 pass 1 fail).
+- Cause: D61-03 (999ea6af3) value-imports selectRelevantFiles from stages/plan.ts. Fix-forward slice P0-D66-FENCE dispatched (dependency injection, test untouched). Train 83 will not release; train 84 carries the fix.
+- Guard gap: the D61-03 engineer and TL did not run budget.test.ts. Every features/ slice prompt now names it as a required command.
+- Dispatched D63 cards C1 (HIGH), C2, C5, C8, C9, C12 and D61-10-F1; reviews: D61-04 (opus), D61-12 re-review (opus).
+
+## 2026-10-03T03:56Z v10.6.8 released, train 85 staged, train 86 reviewed
+- v10.6.8 released from main d95095d9d (train/82 tree e072e47a9; Tests, Bun Parity, Coverage, Security Audit, First-run green on that SHA). Peer told; D49 auto-promote pending (npm latest 10.6.7 at 03:46Z).
+- train/84 (b45cc902e, carries P0-D66-FENCE) CI running.
+- Train 85 on local main 52c3b0e02: C5, C9, C7, D61-10-F1, D61-16, C4 plus dist (dist guard 13/0). local-ci fast tier hit the 590s cap (rc 124) after 76 PASS, 0 FAIL, bun test PASS; train CI is the authority.
+- Train 86 fully reviewed: C2 00f6741d9 (opus) + C2-F 3177c28ba + C2-F2 3fca6590d (TL, preload mutation goes red), C3 e41381751 + C3-F 362e9c501 (TL, 20/0), C11a 50a75bcfa (TL; legs 1-2 PASS, positive control rc 1).
+- D61-12 round 4 opus BLOCK (B3: repo filter driver fooled the fresh verify checkout). Round 5 630772f97 fixes B3, N1, N5, N7 (integrate tests 68/0); opus round 5 running.
+- In review: C6 (HIGH), C1 (HIGH), C8, C12 (HIGH), D61-04, D61-11, D61-13, D61-16-F, VIS-F1. Next: BUG-C (slack --port 0) after C6, C10 after C1, C11b after train 86.
+
+## 2026-10-03T04:13Z Train 85 pushed (2cc94a548), C1 approved, C12 dropped
+- Train 84 went stale behind the v10.6.8 release commit (train-cycle B: TRAIN_STALE); merged origin/main into local main (dist conflict resolved by rebuild, dist guard 13/0) and pushed train/85 (train-cycle A: TRAIN_PUSHED).
+- Train 85 carries C2, C3, C4, C5, C7, C9, C11a, D61-10-F1, D61-16, D61-16-F (opus APPROVE round 3) and C8 (TL APPROVE). Main moat on bf3e42066: 4 of 9, rc 0. Local-ci hit the 590s cap at 43 PASS, 0 FAIL.
+- C1 round 2 opus APPROVE (7ca8f9832); held until C10 so the Dockerfile and Helm chart do not exit 2 on a tokenless 0.0.0.0 bind. C10 builder dispatched on top of C1.
+- C12 dropped (D72). D61-12 round 6 BLOCK; round 7 fix running. Opus round 2 reviews running for D61-04, D61-13, C6, D61-11.
+- Deferred cleanup (no compound rm mid-window): review scratch dirs rev-d61-16-f-r3, rev-d61-12-r6, and 12 git-home dirs leaked by the D61-12 tests (reviewer removed 2 it owned).
+
+
+## 2026-10-03T04:40Z CoS tick
+- Train 85 Tests red twice in full (run 37095579466): control_default "serve needs no flag; instance.json is 0600" times out on ubuntu only (passes on macOS 13/0). Real cause, so P0-CONTROL-LINUX dispatched (D68). Train 85 will not promote; train 86 supersedes it once green.
+- Merged to local main: C1, C10, INTEL-2, C6, C6-F (TL APPROVE e8837ffa4), D61-13 (opus r3 APPROVE a2c3d9cb2); dist 7ad4a44e9.
+- Core engine10 at 5001 after D61-13 (budget.test needs < 5000): P0-CORE-BUDGET dispatched. Train 86 waits on it and on P0-CONTROL-LINUX.
+- D61-04 r3 BLOCK (live-tree read), r4 fix 9d2bbf4b9 in opus review. D61-12 r7 BLOCK, r8 fix 35a7b0c32 in opus review (final round, else drop). P0-VERIFY-ARG r2 BLOCK (core budget, unguarded unknown-option check, autonomy/loki routes --pubkey= to legacy), r3 fix running. D61-11 r3 fix running.
+- Deferred cleanup adds: scratchpad rev-d61-04-r3, rev-d61-12-r7, rev-d61-13-r3; 13 pre-existing loki-run.git-home-* dirs in TMPDIR (record exact list at end-of-window pass).
+
+## 2026-10-03T04:57Z CoS tick
+- D73 logged: D61-12 integrator dropped from this window (r8 reproduced C1-C4, S3, E6); D61 ships without it, flag-gated, named in handoff. BOARD a1f83c7a9.
+- Merged to local main: D51-B11 (933ecc9fc, test-workspace 14/0), D51-B05/B06 (c1095889f, backlog 49/0, api_start_prep 2 passed). D51-B02/03/04/07/08/09/10/12 parked as already delivered (99aaa6d2b).
+- P0-CONTROL-LINUX opus APPROVE: root cause reproduced in oven/bun:1.3.13 (repo-root node_modules disables bun auto-install, hono missing); npm tarball uses bundled dist/server.js so no runtime fetch. Cherry-picked 2d6e4a77d, dist 377871c88, dist guard 13/0.
+- Train 86 now waits only on P0-CORE-BUDGET TL verdict. In flight: P0-VERIFY-ARG r3 opus, D61-04 r5 fix, D61-11 test fix, P1-DISCARD-PROTO build (HIGH), D50-F4b build.
+- Deferred cleanup adds: scratchpad rev-d61-04-r4, rev-d61-12-r8.
+
+## 2026-10-03T05:27Z tick (CoS)
+- Merged to local main since 04:57Z: P0-VERIFY-ARG (dist 7bfa73a64), P1-DISCARD-PROTO (dist 4d8d1db59), D50-F4b (dist 159abf6d6), D61-04 off-path already-done check under LOKI_SPEED=1 (dist 588658b36, main bun test 1338/0 on rerun after one load flake). Core budget now passes on main, so train 86 no longer waits on P0-CORE-BUDGET.
+- Train 86 first push failed: gitleaks github-pat on the synthetic token fixture tests/workspace/80-comment.sh:7 (D51-B11). Fingerprint baselined with a reason line in .gitleaksignore (acb4ee58f). Rerun: TRAIN_PUSHED train/86 at acb4ee58f, 05:25:53Z; CI pending.
+- In flight: P0-CORE-BUDGET TL r2, D61-11 test fix, D61-04-F leak fixes (MEDIUM, new BOARD row).
+- Carry-forward reviewer notes: P0-CONTROL-LINUX wants a frozen-lockfile install for packages/control-plane in CI; D50-F4b invalid-base reason unreachable in supervisor; D61-04 child env carries OLDPWD (informational).

package/docs/v10/ROADMAP-D63.md

@@ -0,0 +1,35 @@
+# Roadmap D63: the industry-standard autonomous software factory
+
+Founder directive D63 (2026-10-03 00:15Z, relayed by the autonomi-dev session). This page sets the roadmap that D50, D51, D56 and D61 slot into. The measurable bars below are the only claim we make. User-facing text makes no "superintelligence" or benchmark claims, and no row is done without a test or an eval row in METRICS.
+
+## Pillars: the bar to match, and how we beat it
+
+| # | Pillar | Bar to match | How we beat it | Done when (test or eval row) |
+|---|---|---|---|---|
+| 1 | Autonomy | Devin, Factory Droids: an issue, backlog or spec goes in; merge-ready PRs come out; no babysitting | Proof plus lift | D50 lift on the eval, never below raw on the same model; D61 speed targets; a BLOCKED run asks exactly one question |
+| 2 | Speed at scale | Factory: parallel units with an integrator; warm start | Same or fewer tokens than one sequential session | D61 large-arm eval holds (section 5 of D61-SPEED.md) before the default flips |
+| 3 | Evidence | Devin, Vorflux: PR bodies with tests, screenshots of changed pages, HTTP transcripts for APIs | A signed receipt covers all of it | Screenshots are generated locally (Playwright) and hashed into the receipt; `loki verify` fails if one is altered |
+| 4 | Control Plane UI | Devin web app, Factory dashboard | Every number links to its receipt | D56 is the default: live runs, history, PRs and issues, cost, compare, and a BLOCKED question answerable in the UI; one container with Helm and ECS examples; the old dashboard retired once at parity |
+| 5 | Connections | Devin, Factory integrations | Intake is the same v10 run with the same receipt | GitHub (PAT now, GitHub App next) and GitLab; Jira and Linear intake; two-way Slack (`@loki` in a thread starts a run, BLOCKED answers come back); issue-to-PR Action; an MCP server exposing run, status and verify; VS Code and JetBrains via ACP later |
+| 6 | Spec to software | 8090 | Every acceptance criterion traced to code and a check in the receipt | A spec or PRD file becomes a delivery contract, decomposed (D61) into units and then PRs; replaces the legacy PRD path (D57) |
+| 7 | Legacy and modernization | 8090, Factory | Proof of function on legacy code | `loki modernize` stays hidden until it passes a real-repo eval; not this week |
+| 8 | Claude Code parity | Claude Code | Runs inside it with a receipt | loki-seal plus a /loki command that runs the v10 engine on the current task; CLAUDE.md and .claude/skills honoured in the context pack |
+| 9 | Enterprise | Devin and Factory enterprise tiers | Audit from the receipt chain | An audit log of model calls; budgets per team; SSO for the Control Plane later; never certification claims |
+
+## Order this week (under the usage governor)
+1. D61 eval arm (slice 17), then warm start (slices 5 and 6), with slices 1, 2, 7 and 8 in parallel.
+2. Visual evidence in PRs (pillar 3).
+3. Control Plane as the default, with the BLOCKED answer UI (pillar 4).
+4. Two-way Slack (pillar 5).
+5. Jira and Linear intake (pillar 5).
+6. Spec to contract (pillar 6).
+7. Multi-repo workspaces (D51 Phase B, behind LOKI_WORKSPACES).
+8. MCP run, status and verify server (pillar 5).
+9. Containers (pillar 4).
+
+Also from D62: root action.yml routes to Loki 10; one real end-to-end BUDGET_STOP exit 3 test; project memory (D50 item 3). Later: merge queue, PR review with a risk score, REST API.
+
+## Rules
+- Each item ships on its own train, behind a flag where it changes defaults, with README and docs updated in the same slice.
+- Each release reports its version and what users can now do to the autonomi-dev session.
+- Pacing follows the governor (about 0.5% of the weekly window per hour); seats scale only with live /usage.