loki-mode 10.0.1 → 10.1.0

package/SKILL.md

@@ -3,7 +3,7 @@ name: loki-mode
 description: Autonomous spec-driven build system with a built-in trust layer. It does not call work done until it is verified (RARV-C closure loop, 8 quality gates, completion council, verified-completion evidence gate). Triggers on "Loki Mode". Takes a spec (PRD, GitHub issue, OpenAPI doc, etc.) to deployed product with minimal human intervention. Provider-agnostic. Requires --dangerously-skip-permissions flag.
 ---
 
-# Loki Mode v10.0.1
+# Loki Mode v10.1.0
 
 **You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
 
@@ -470,4 +470,4 @@ See `CHANGELOG.md` entries [7.5.7], [7.5.8], [7.5.13] for the per-fix list and r
 
 ---
 
-**v10.0.1 | [Autonomi](https://www.autonomi.dev/) flagship product | ~410 lines core**
+**v10.1.0 | [Autonomi](https://www.autonomi.dev/) flagship product | ~410 lines core**

package/VERSION

@@ -1 +1 @@
-10.0.1
+10.1.0

package/dashboard/__init__.py

@@ -7,7 +7,7 @@ Modules:
     control: Session control API (start/stop/pause/resume)
 """
 
-__version__ = "10.0.1"
+__version__ = "10.1.0"
 
 # Expose the control app for easy import
 try:

package/docs/INSTALLATION.md

@@ -2,7 +2,7 @@
 
 The flagship product of [Autonomi](https://www.autonomi.dev/). Loki Mode is a spec-driven autonomous builder with a built-in trust layer that takes any spec to a deployed product and verifies completion with evidence (quality gates plus a completion council), not just a "done" claim. Complete installation instructions for all platforms and use cases.
 
-**Version:** v10.0.1
+**Version:** v10.1.0
 
 ---
 

package/docs/v10/BOARD.md

@@ -344,28 +344,28 @@ set is declared to avoid overlap with those and with each other.
 | E-57 | Line reclaim: engine10 back to 4,700 or fewer by deleting dead exports and duplicated helpers, no behavior change | loki-ts/src/engine10/ (deletions only, no new files) | LOW | cd loki-ts && bun test tests/engine10/ && bunx tsc --noEmit; budget.test count at or below 4700 | released@2026-09-28T02:38Z | Source: train E10 hit 5,019 and needed a header trim; E-36, E-45 and E-52..E-56 need room. Merge after the gate-path slices to avoid conflicts. Dispatched after train E13. Merged 3ab2a8fa (train E14, rebased on main): engine10 404 pass 0 fail (402 pass 0 fail with claude removed from PATH), tsc exit 0, test-harness 86/0, test-local-ci-gitleaks 6/0, test-engine10-dist 18/0. Released v9.81.0 (npm view loki-mode time: 2026-09-28T02:38:54Z). |
 | EV-10 | Harness reaps arm descendants that escape the timeout process group: after the cap, KILL recorded PIDs under the run clone (.loki/**/*.pid) and processes whose cwd is inside that run-owned clone; guard in docs/v10/GUARDS.md | eval/loki10/harness.py (kill_orphans only), eval/loki10/test-harness.sh (one leg), docs/v10/GUARDS.md (one entry) | HIGH | bash eval/loki10/test-harness.sh; a fixture arm that setsid-spawns a sleeper leaves no live process after the cap | released@2026-09-28T02:38Z | Source: incident 00:08Z, pulse ORPHAN_WORKTREE caught 4 legacy /tmp/loki-run-*.sh loops (ppid 1, 30 min, 15-min cap) plus 2 sleep 300 children from run dir loki-run.u6ikBxCT; stopped by PID (kill -TERM 58249 58251 58633 58634 57049 56916, ps -p afterwards empty). Never match by name. Opus CONCERN: Linux /proc/<pid> mtime is not process start, so the age filter passes everything. Rework dispatched. Merged 3ab2a8fa (train E14, rebased on main): engine10 404 pass 0 fail (402 pass 0 fail with claude removed from PATH), tsc exit 0, test-harness 86/0, test-local-ci-gitleaks 6/0, test-engine10-dist 18/0. Released v9.81.0 (npm view loki-mode time: 2026-09-28T02:38:54Z). |
 | E-60 | Secret-scan guard before push: scripts/local-ci.sh fast tier runs gitleaks v8.30.0 with .gitleaksignore over origin/main..HEAD when the binary is present (SKIP line, not green, when absent); fixtures must build secret-shaped strings at runtime; entry in docs/v10/GUARDS.md | scripts/local-ci.sh (one step), tests/test-local-ci-gitleaks.sh, docs/v10/GUARDS.md | MEDIUM | bash tests/test-local-ci-gitleaks.sh: a commit adding a planted AKIA fixture fails the step; the same fixture built by concatenation passes | released@2026-09-28T02:38Z | Source: incident 00:45Z. Security Audit gitleaks failed on 9dc0b1d3 and 085306ae (3 findings: deep.test.ts aws-access-token, test-engine10-push-gitlab.sh gitlab-pat, rule_of_two.test.ts generic-api-key, all synthetic), so v9.79.0 and v9.80.0 never reached npm (npm view loki-mode version = 9.78.0). Baselined in 5190756f; local full-history scan shows only local-branch copies. Dispatched. Merged 3ab2a8fa (train E14, rebased on main): engine10 404 pass 0 fail (402 pass 0 fail with claude removed from PATH), tsc exit 0, test-harness 86/0, test-local-ci-gitleaks 6/0, test-engine10-dist 18/0. Released v9.81.0 (npm view loki-mode time: 2026-09-28T02:38:54Z). |
-| E-61 | A session that exits with an error fails its stage (implement reported done after exit "error" in 1s with 0 tokens) and its stderr tail is kept under the run dir for diagnosis | loki-ts/src/engine10/session.ts (stderr capture only), loki-ts/src/engine10/stages/implement.ts, loki-ts/src/engine10/stages/plan.ts, tests | HIGH | cd loki-ts && bun test tests/engine10/; a stub provider exiting 1 yields stage.failed with the stderr tail path | ready@2026-09-28T01:58Z | Source: incident 01:38Z (EV-8 0/5 twice). Opus reviewer. Overlaps E-68 (exit classification) and E-69; builder of E-68 covers the stage-failure part. |
-| E-62 | Eval harness v10 arm defaults to this repo's bin/loki (never the global loki, which was v9.78.0) and the manifest records its path and the agent SDK version; local-ci and the harness refuse when loki-ts/node_modules differs from bun.lock | eval/loki10/harness.py (loki_bin default, manifest), scripts/local-ci.sh (one check), eval/loki10/test-harness.sh (one leg) | HIGH | bash eval/loki10/test-harness.sh; a leg asserts the v10 arm binary is the repo bin/loki | ready@2026-09-28T01:40Z | Source: incident 01:38Z. |
+| E-61 | A session that exits with an error fails its stage (implement reported done after exit "error" in 1s with 0 tokens) and its stderr tail is kept under the run dir for diagnosis | loki-ts/src/engine10/session.ts (stderr capture only), loki-ts/src/engine10/stages/implement.ts, loki-ts/src/engine10/stages/plan.ts, tests | HIGH | cd loki-ts && bun test tests/engine10/; a stub provider exiting 1 yields stage.failed with the stderr tail path | building@2026-09-28T04:25Z | Source: incident 01:38Z (EV-8 0/5 twice). Opus reviewer. Overlaps E-68 (exit classification) and E-69; builder of E-68 covers the stage-failure part. Wave E19, after E-68 landed (ea288330). D33: states its net core line delta; core must stay under 5,000 (92 lines of headroom shared by E-67, E-66, E-61, M-14, merge order E-67, E-66, E-61); offset any excess by deleting dead core code. |
+| E-62 | Eval harness v10 arm defaults to this repo's bin/loki (never the global loki, which was v9.78.0) and the manifest records its path and the agent SDK version; local-ci and the harness refuse when loki-ts/node_modules differs from bun.lock | eval/loki10/harness.py (loki_bin default, manifest), scripts/local-ci.sh (one check), eval/loki10/test-harness.sh (one leg) | HIGH | bash eval/loki10/test-harness.sh; a leg asserts the v10 arm binary is the repo bin/loki | building@2026-09-28T04:25Z | Source: incident 01:38Z. Wave E19, after EV-13 landed (ea288330). |
 | E-63 | Pulse STALE_PROGRESS violation when the newest PROGRESS.md entry is over 35 minutes old | scripts/v10-pulse.sh, tests/test-v10-pulse.sh | MEDIUM | bash tests/test-v10-pulse.sh | approved@2026-09-28T02:50Z | Source: Loki 01:49Z (PROGRESS.md was 100 minutes stale). Built 67c6b8ac, TL APPROVE; train E17 test-v10-pulse 95/0. |
-| E-64 | Lean small path and model cascade (D31): small tasks get one sonnet implement session with the cached repo map, impacted tests, PR; no plan or Wall unless no relevant tests; opus only on a test failure, reason logged; cost per call type | loki-ts/src/engine10 (implement, fix, plan, wall, sizing, session) | HIGH | cd loki-ts && bun test tests/engine10/; then EV-8 5-task measurement | approved@2026-09-28T03:44Z | Source: D30, D31. Opus REJECT (47f0d33a): a non-escalated fix round still runs on the top model while the event says no escalation; does not merge onto main. Rework dispatched. Rework APPROVE (branch worktree-wf_4601e7b3-4d8-1: 70bae9be, db2c104f, 01ff7737): non-escalated fix rounds run on the cheap model and the event records the real model. Not merged; must be re-measured (full small arm) before it becomes the default. |
+| E-64 | Lean small path and model cascade (D31): small tasks get one sonnet implement session with the cached repo map, impacted tests, PR; no plan or Wall unless no relevant tests; opus only on a test failure, reason logged; cost per call type | loki-ts/src/engine10 (implement, fix, plan, wall, sizing, session) | HIGH | cd loki-ts && bun test tests/engine10/; then EV-8 5-task measurement | merged@2026-09-28T04:15Z | Source: D30, D31. Opus REJECT (47f0d33a): a non-escalated fix round still runs on the top model while the event says no escalation; does not merge onto main. Rework dispatched. Rework APPROVE (branch worktree-wf_4601e7b3-4d8-1: 70bae9be, db2c104f, 01ff7737): non-escalated fix rounds run on the cheap model and the event records the real model. Not merged; must be re-measured (full small arm) before it becomes the default. Merged c9c15f38 (trainE18), session.ts conflict with E-68 resolved to the 30s heartbeat; `bun test tests/engine10/` 444 pass. Still behind the gate: re-measure before default. |
 | E-65 | Session token diet: find and cut what makes one v10 session cost more than raw claude -p on the same task and model | loki-ts/src/engine10, engine10-only flag in loki-ts/src/runner if needed | HIGH | before/after token table on one task, then the EV-8 5 tasks | merged@2026-09-28T02:38Z | Source: EV-8 variant C (a sonnet session $0.155 to $0.32 vs raw opus $0.216 per whole task). Built 92e3c06c: engine sessions 6 tools, no legacy append, no MCP, settingSources project; prefix 20.4k -> 7.1k tokens; 5 tasks on claude-sonnet-5 v10 4/5 $0.1523 per completed vs raw 4/5 $0.2113. Opus CONCERN: M5 (tools spread removed) and M6 (noAppend ignored) survive 1345 tests; rework sent (query()-level assertion, rebase). Opus APPROVE on rework c9a90cce (M5, M6, M7, M8 all red; runner plus engine10 1347 pass 0 fail, also without claude on PATH). Merged 8b76fd9a with dist rebuilt. EV-8 D (opus, lean, no plan or Wall) 4/5 $0.1571 per completed p50 28s; E (sonnet, lean) 4/5 $0.1519 p50 27.5s; raw opus on the same 5 tasks 5/5 $0.2161 p50 41s (~/loki-ci-logs/ev8r-{D,E}/results.jsonl). |
-| EV-11 | Medium eval tier: 15 multi-file tasks with hidden tests, tier field and --tier selection | eval/loki10/tasks/, eval/loki10/harness.py, run.sh | HIGH | python3 eval/loki10/harness.py validate; no-op baseline grades 15 not completed, 0 invalid | building@2026-09-28T03:44Z | Source: D30. Opus CONCERN: 3 of 15 medium tasks verified (ea04f1e0). Rework dispatched to finish the 15. Rework (branch worktree-wf_4601e7b3-4d8-2, head 5718225a): 4 of 15 medium tasks verified (pub-attrs-1313, pub-click-2869, pub-faker-1817, pub-jinja-1413). Opus CONCERN: 11 tasks still missing; leads in eval/loki10/tasks/INDEX.md. |
-| EV-12 | Large eval tier: 10 feature or legacy tasks with hidden tests, including augmentiq-style issues | eval/loki10/tasks/ | HIGH | validate plus no-op baseline over 10 | building@2026-09-28T03:44Z | Source: D30. Opus REJECT (fbd32234): 3 legacy tasks point at fixtures absent before merge (prepare_failed); spec items missing. Rework dispatched. Rework (branch worktree-wf_4601e7b3-4d8-3, head 0b9a2d91: 10 large tasks, repo-relative fixture sources). Opus REJECT: the repo-relative sources, .. rejection and fixture fixes are reproduced, but the large tasks are still smaller than the medium ones (task-size finding open). Next: rework with genuinely feature-sized tasks. |
+| EV-11 | Medium eval tier: 15 multi-file tasks with hidden tests, tier field and --tier selection | eval/loki10/tasks/, eval/loki10/harness.py, run.sh | HIGH | python3 eval/loki10/harness.py validate; no-op baseline grades 15 not completed, 0 invalid | building@2026-09-28T04:25Z | Source: D30. Opus CONCERN: 3 of 15 medium tasks verified (ea04f1e0). Rework dispatched to finish the 15. Rework (branch worktree-wf_4601e7b3-4d8-2, head 5718225a): 4 of 15 medium tasks verified (pub-attrs-1313, pub-click-2869, pub-faker-1817, pub-jinja-1413). Opus CONCERN: 11 tasks still missing; leads in eval/loki10/tasks/INDEX.md. Wave E18 rework: 11 missing medium tasks, branch slice-EV-11-medium-15. Opus REJECT: pub-werkzeug-3121 hidden test not verbatim as claimed; pub-werkzeug-3105 grades a feature deletion as completed. Rework wave E19. |
+| EV-12 | Large eval tier: 10 feature or legacy tasks with hidden tests, including augmentiq-style issues | eval/loki10/tasks/ | HIGH | validate plus no-op baseline over 10 | building@2026-09-28T04:25Z | Source: D30. Opus REJECT (fbd32234): 3 legacy tasks point at fixtures absent before merge (prepare_failed); spec items missing. Rework dispatched. Rework (branch worktree-wf_4601e7b3-4d8-3, head 0b9a2d91: 10 large tasks, repo-relative fixture sources). Opus REJECT: the repo-relative sources, .. rejection and fixture fixes are reproduced, but the large tasks are still smaller than the medium ones (task-size finding open). Next: rework with genuinely feature-sized tasks. Wave E18 rework: feature-sized large tasks, branch slice-EV-12-large-tasks. Opus REJECT: only lg-rbac reworked (1 of 10 feature-sized); fixture files outside the set. Rework wave E19 (fixtures now in set). |
 | M-00 | MODERNIZE.md design (CTO and Architect) and the Part 2 slice table M-01.. | docs/v10/MODERNIZE.md | HIGH | doc under 400 lines with a 20 to 30 slice plan | merged@2026-09-28T02:50Z | Source: D30 Part 2. ETA 02:45Z. Built 17e97855 (399 lines, 30 slices); merges in train E17 (b2ad73ce). |
-| M-01 | Modernize event types, log wrapper and state paths | loki-ts/src/engine10/modernize/types.ts, loki-ts/src/engine10/modernize/log.ts, loki-ts/tests/engine10/modernize/log.test.ts | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/log.test.ts | building@2026-09-28T03:44Z | Source: MODERNIZE.md (D30). Depends on none. Built on branch worktree-wf_4601e7b3-4d8-4 (777f6cdd M-01, 212a7404 M-02, 6b00c05c M-05, 3d8edb5d M-06). TL CONCERN: cluster.ts tarjanSCC recursion overflows the stack on dependency chains of about 20-50k nodes (the M-28/M-29 scale); needs an iterative SCC. |
-| M-02 | Inventory core: files, languages, build, entry points, tests | loki-ts/src/engine10/modernize/inventory.ts, loki-ts/tests/engine10/modernize/inventory.test.ts, loki-ts/tests/engine10/modernize/fixtures/inv/ | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/inventory.test.ts | building@2026-09-28T03:44Z | Source: MODERNIZE.md (D30). Depends on M-01. Built on branch worktree-wf_4601e7b3-4d8-4 (777f6cdd M-01, 212a7404 M-02, 6b00c05c M-05, 3d8edb5d M-06). TL CONCERN: cluster.ts tarjanSCC recursion overflows the stack on dependency chains of about 20-50k nodes (the M-28/M-29 scale); needs an iterative SCC. |
-| M-03 | Python import graph via tokenize (lexes py2 source) | loki-ts/src/engine10/modernize/lang/python.ts, autonomy/lib/modernize/py_imports.py, loki-ts/tests/engine10/modernize/python_graph.test.ts | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/python_graph.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-02. |
-| M-04 | Java graph via jdeps, import-scan fallback recorded | loki-ts/src/engine10/modernize/lang/java.ts, loki-ts/tests/engine10/modernize/java_graph.test.ts, loki-ts/tests/engine10/modernize/fixtures/java8/ | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/java_graph.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-02. |
-| M-05 | SCC clustering, 1,500-line unit cap, topological waves | loki-ts/src/engine10/modernize/cluster.ts, loki-ts/tests/engine10/modernize/cluster.test.ts | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/cluster.test.ts | building@2026-09-28T03:44Z | Source: MODERNIZE.md (D30). Depends on M-02. Built on branch worktree-wf_4601e7b3-4d8-4 (777f6cdd M-01, 212a7404 M-02, 6b00c05c M-05, 3d8edb5d M-06). TL CONCERN: cluster.ts tarjanSCC recursion overflows the stack on dependency chains of about 20-50k nodes (the M-28/M-29 scale); needs an iterative SCC. |
-| M-06 | Up-front estimate (cost, time, risk), --budget math, --dry-run print | loki-ts/src/engine10/modernize/estimate.ts, loki-ts/tests/engine10/modernize/estimate.test.ts | LOW | cd loki-ts && bun test tests/engine10/modernize/estimate.test.ts | building@2026-09-28T03:44Z | Source: MODERNIZE.md (D30). Depends on M-05. Built on branch worktree-wf_4601e7b3-4d8-4 (777f6cdd M-01, 212a7404 M-02, 6b00c05c M-05, 3d8edb5d M-06). TL CONCERN: cluster.ts tarjanSCC recursion overflows the stack on dependency chains of about 20-50k nodes (the M-28/M-29 scale); needs an iterative SCC. |
+| M-01 | Modernize event types, log wrapper and state paths | loki-ts/src/engine10/modernize/types.ts, loki-ts/src/engine10/modernize/log.ts, loki-ts/tests/engine10/modernize/log.test.ts | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/log.test.ts | merged@2026-09-28T04:25Z | Source: MODERNIZE.md (D30). Depends on none. Built on branch worktree-wf_4601e7b3-4d8-4 (777f6cdd M-01, 212a7404 M-02, 6b00c05c M-05, 3d8edb5d M-06). TL CONCERN: cluster.ts tarjanSCC recursion overflows the stack on dependency chains of about 20-50k nodes (the M-28/M-29 scale); needs an iterative SCC. Wave E18 (wf_5063e58d-7a5) carries it with the M-05 iterative SCC rework, branch slice-M-05-iterative-scc. Merged f4d98c0b with M-05. |
+| M-02 | Inventory core: files, languages, build, entry points, tests | loki-ts/src/engine10/modernize/inventory.ts, loki-ts/tests/engine10/modernize/inventory.test.ts, loki-ts/tests/engine10/modernize/fixtures/inv/ | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/inventory.test.ts | merged@2026-09-28T04:25Z | Source: MODERNIZE.md (D30). Depends on M-01. Built on branch worktree-wf_4601e7b3-4d8-4 (777f6cdd M-01, 212a7404 M-02, 6b00c05c M-05, 3d8edb5d M-06). TL CONCERN: cluster.ts tarjanSCC recursion overflows the stack on dependency chains of about 20-50k nodes (the M-28/M-29 scale); needs an iterative SCC. Wave E18 with M-05, branch slice-M-05-iterative-scc. Merged f4d98c0b with M-05. |
+| M-03 | Python import graph via tokenize (lexes py2 source) | loki-ts/src/engine10/modernize/lang/python.ts, autonomy/lib/modernize/py_imports.py, loki-ts/tests/engine10/modernize/python_graph.test.ts | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/python_graph.test.ts | building@2026-09-28T04:25Z | Source: MODERNIZE.md (D30). Depends on M-02. Wave E18, based on the M-02 branch, branch slice-M-03-python-graph. TL REJECT: bare relative from-imports (from . import X) mis-parsed in py_imports.py. Rework wave E19. |
+| M-04 | Java graph via jdeps, import-scan fallback recorded | loki-ts/src/engine10/modernize/lang/java.ts, loki-ts/tests/engine10/modernize/java_graph.test.ts, loki-ts/tests/engine10/modernize/fixtures/java8/ | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/java_graph.test.ts | building@2026-09-28T04:25Z | Source: MODERNIZE.md (D30). Depends on M-02. Wave E18, based on the M-02 branch, branch slice-M-04-java-graph. TL REJECT: wildcard and static imports silently dropped in the import-scan fallback. Rework wave E19. |
+| M-05 | SCC clustering, 1,500-line unit cap, topological waves | loki-ts/src/engine10/modernize/cluster.ts, loki-ts/tests/engine10/modernize/cluster.test.ts | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/cluster.test.ts | merged@2026-09-28T04:25Z | Source: MODERNIZE.md (D30). Depends on M-02. Built on branch worktree-wf_4601e7b3-4d8-4 (777f6cdd M-01, 212a7404 M-02, 6b00c05c M-05, 3d8edb5d M-06). TL CONCERN: cluster.ts tarjanSCC recursion overflows the stack on dependency chains of about 20-50k nodes (the M-28/M-29 scale); needs an iterative SCC. Wave E18 rework: iterative Tarjan, branch slice-M-05-iterative-scc. TL APPROVE (sonnet): iterative Tarjan 372ebe11, red on recursive (RangeError), 2000/2000 fuzz identical; merged f4d98c0b, `bun test tests/engine10/modernize/` 28 pass 0 fail. |
+| M-06 | Up-front estimate (cost, time, risk), --budget math, --dry-run print | loki-ts/src/engine10/modernize/estimate.ts, loki-ts/tests/engine10/modernize/estimate.test.ts | LOW | cd loki-ts && bun test tests/engine10/modernize/estimate.test.ts | merged@2026-09-28T04:25Z | Source: MODERNIZE.md (D30). Depends on M-05. Built on branch worktree-wf_4601e7b3-4d8-4 (777f6cdd M-01, 212a7404 M-02, 6b00c05c M-05, 3d8edb5d M-06). TL CONCERN: cluster.ts tarjanSCC recursion overflows the stack on dependency chains of about 20-50k nodes (the M-28/M-29 scale); needs an iterative SCC. Wave E18 with M-05, branch slice-M-05-iterative-scc. Merged f4d98c0b with M-05. |
 | M-07 | modernize CLI and flag parsing; TABLE route in engine10 cli | loki-ts/src/engine10/modernize/cli.ts, loki-ts/src/engine10/cli.ts (TABLE and USAGE line only), loki-ts/tests/engine10/modernize/cli.test.ts | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/cli.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-06, E-31 merged or parked. |
 | M-08 | bin/loki modernize arm to engine10 regardless of default | bin/loki (modernize arm only), tests/test-modernize-dispatch.sh | MEDIUM | bash tests/test-modernize-dispatch.sh | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-07. |
-| M-09 | py2/3 capture tracer with type-tagged JSON and branch coverage | autonomy/lib/modernize/py_capture.py, tests/test-modernize-py-capture.sh, tests/fixtures/modernize/py2/ | HIGH | bash tests/test-modernize-py-capture.sh | building@2026-09-28T03:44Z | Source: MODERNIZE.md (D30). Depends on M-01. Built a4fbf034 (branch worktree-wf_4601e7b3-4d8-5). Opus REJECT (reproduced): unsupported types (sets, Decimal, datetime, bytearray, custom classes) record as equal with no not_proven entry, so the oracle could certify unproven equivalence. Next: rework. |
+| M-09 | py2/3 capture tracer with type-tagged JSON and branch coverage | autonomy/lib/modernize/py_capture.py, tests/test-modernize-py-capture.sh, tests/fixtures/modernize/py2/ | HIGH | bash tests/test-modernize-py-capture.sh | building@2026-09-28T04:25Z | Source: MODERNIZE.md (D30). Depends on M-01. Built a4fbf034 (branch worktree-wf_4601e7b3-4d8-5). Opus REJECT (reproduced): unsupported types (sets, Decimal, datetime, bytearray, custom classes) record as equal with no not_proven entry, so the oracle could certify unproven equivalence. Next: rework. Wave E18 rework: unsupported types yield not_proven, branch slice-M-09-not-proven-types. Opus REJECT of 3594eee5: subclasses of supported types (namedtuple, IntEnum, OrderedDict) tag as the base type with no not_proven. Rework wave E19. |
 | M-10 | Coverage-guided input search (read-only session, plateau stop) | loki-ts/src/engine10/modernize/oracle/search.ts, loki-ts/tests/engine10/modernize/search.test.ts | HIGH | cd loki-ts && bun test tests/engine10/modernize/search.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-09. |
 | M-11 | Java capture: JUnit under JDK 8 with JaCoCo plus Randoop | autonomy/lib/modernize/java_capture.sh, loki-ts/src/engine10/modernize/oracle/java.ts, loki-ts/tests/engine10/modernize/java_capture.test.ts | HIGH | cd loki-ts && bun test tests/engine10/modernize/java_capture.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-04. |
 | M-12 | Oracle seal, held-out split, 80% floor, up-front NOT PROVEN | loki-ts/src/engine10/modernize/oracle/seal.ts, loki-ts/tests/engine10/modernize/oracle_seal.test.ts | HIGH | cd loki-ts && bun test tests/engine10/modernize/oracle_seal.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-09. |
 | M-13 | Equivalence checker with sealed normalizers and contract output | loki-ts/src/engine10/modernize/equiv.ts, loki-ts/tests/engine10/modernize/equiv.test.ts, loki-ts/tests/engine10/modernize/fixtures/equiv/ | HIGH | cd loki-ts && bun test tests/engine10/modernize/equiv.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-12. |
-| M-14 | Wall pre-sealed mode: oracle plus conformance, green base is an error | loki-ts/src/engine10/stages/wall.ts (pre-sealed branch only), loki-ts/tests/engine10/modernize/wall_presealed.test.ts | HIGH | cd loki-ts && bun test tests/engine10/modernize/wall_presealed.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-12, E-54. |
+| M-14 | Wall pre-sealed mode: oracle plus conformance, green base is an error | loki-ts/src/engine10/stages/wall.ts (pre-sealed branch only), loki-ts/tests/engine10/modernize/wall_presealed.test.ts | HIGH | cd loki-ts && bun test tests/engine10/modernize/wall_presealed.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-12, E-54. D33: states its net core line delta; core must stay under 5,000 (92 lines of headroom shared by E-67, E-66, E-61, M-14, merge order E-67, E-66, E-61); offset any excess by deleting dead core code. |
 | M-15 | Unit runner: card to v10 run with oracle Wall and equiv check | loki-ts/src/engine10/modernize/unit.ts, loki-ts/tests/engine10/modernize/unit.test.ts | HIGH | cd loki-ts && bun test tests/engine10/modernize/unit.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-13, M-14. |
 | M-16 | Deterministic codemods first (futurize, OpenRewrite) or skipped | loki-ts/src/engine10/modernize/codemod.ts, loki-ts/tests/engine10/modernize/codemod.test.ts | MEDIUM | cd loki-ts && bun test tests/engine10/modernize/codemod.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-02. |
 | M-17 | Scheduler: N workers, worktrees, cascade, best-of-2, budget stop | loki-ts/src/engine10/modernize/scheduler.ts, loki-ts/tests/engine10/modernize/scheduler.test.ts | HIGH | cd loki-ts && bun test tests/engine10/modernize/scheduler.test.ts | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-15. |
@@ -382,12 +382,18 @@ set is declared to avoid overlap with those and with each other.
 | M-28 | 200K scale run (Mercurial 4.x, measured first, fallback Calibre) | eval/modernize/scale.py, eval/modernize/SCALE.md | HIGH | python3 eval/modernize/scale.py --target hg --dry-run-first | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-27. |
 | M-29 | 1M scale run (Hadoop 2.x Java 8 to 21, measured first) | eval/modernize/scale_1m.py, eval/modernize/SCALE-1M.md | HIGH | python3 eval/modernize/scale_1m.py --dry-run-first | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-28, M-11. |
 | M-30 | User docs for loki modernize, no dashes, commands match USAGE | docs/v10/GUIDE-MODERNIZE.md, tests/test-modernize-docs.sh | LOW | bash tests/test-modernize-docs.sh | ready@2026-09-28T02:45Z | Source: MODERNIZE.md (D30). Depends on M-07. |
-| E-66 | "Already implemented" outcome: evidence search in code, tests, docs, CHANGELOG; no change needed verdict, receipt, issue comment, no PR | loki-ts/src/engine10 (intake or plan, implement marker path, seal, pr) | HIGH | fixture with the feature ends no change needed, no implement session; fixture without proceeds | building@2026-09-28T03:20Z | Source: D32 (augmentiq #52). Opus REJECT (reproduced): no test that ALREADY_SATISFIED opens no PR; evidence search matched 652 hits for an unrelated task on this repo; confirmation need not cite files. Rework dispatched. Rework 1c7e1b09 (branch worktree-wf_b707f4ab-24f-1): all 3 blockers fixed (no-PR test F5, 0 hits for both review sentences on this repo, citation must name an existing code or test hit; evidence in receipt). Opus CONCERN: the real-repo test uses listRepoFiles capped at 2000 of 4784 files, so removing STOP_WORDS still passes; the existsSync branch of the citation check is untested. Next: small fix (full file list in that test, one existsSync test). |
-| EV-13 | Eval expected_outcome no_change_needed; aiq-52 set to it | eval/loki10/harness.py, eval/loki10/tasks/aiq-52-searchbar, test-harness.sh | HIGH | bash eval/loki10/test-harness.sh | approved@2026-09-28T03:20Z | Source: D32. Opus CONCERN: a correct v10 no-change run on aiq-52 is graded as a source change. Rework dispatched. Rework APPROVE (branch worktree-wf_b707f4ab-24f-5: 19224201, e0264724): v10 Wall side effect excluded from the diff check. Not merged yet. |
-| E-67 | No pause state: unfinishable runs end as a draft PR or an issue comment with the reason within the cap; stdin never read | loki-ts/src/engine10 (machine, supervisor, worker, escalate, session) | HIGH | a stub provider that asks for input ends within the cap with a draft-PR or comment argv | building@2026-09-28T03:20Z | Source: D32. Opus REJECT (reproduced): a hung worker ended FAILED with no draft PR and no comment, after the cap. Rework dispatched. Rework ba679f4e (branch worktree-wf_b707f4ab-24f-2). Opus REJECT: at the default cap the supervisor backstop fires before the worker cap can seal; concern: the diff check misses untracked files and uncommitted work never reaches a PR. Next: rework. |
-| E-68 | Per-call deadline at the stage limit, progress every 30s, every exit code classified (125, 143 included), never "cause not classified" | loki-ts/src/engine10/session.ts, failures.ts | HIGH | per-code tests plus a grep test | approved@2026-09-28T03:20Z | Source: D32. Opus REJECT (reproduced): a real limit kill reports "exit 143 (SIGTERM)" because the session child traps SIGTERM; the stub test missed it. Rework dispatched. Rework APPROVE (branch worktree-wf_b707f4ab-24f-3: 4dd05bf9, 922bd923): a limit kill is classified from the engine, not the child exit code. Not merged yet. |
-| E-69 | Cost shows "not measured" (or partial), never $0 when unmeasured | output.ts, pr_body.ts, seal.ts, status.ts, dashboard/page.ts, cost.ts | MEDIUM | output and receipt tests for measured, partial, unmeasured | approved@2026-09-28T03:20Z | Source: D32 (EV-8 printed $0.00 with 0 tokens). TL CONCERN: genuine-zero test never exercises it; partialCost bypasses the tamper guard; dashboard lacks the partial detail. Rework dispatched. Rework APPROVE (branch worktree-wf_b707f4ab-24f-4: b9825c4c, f42a2aee, 5c66dc55). Not merged yet. |
+| E-66 | "Already implemented" outcome: evidence search in code, tests, docs, CHANGELOG; no change needed verdict, receipt, issue comment, no PR | loki-ts/src/engine10 (intake or plan, implement marker path, seal, pr) | HIGH | fixture with the feature ends no change needed, no implement session; fixture without proceeds | building@2026-09-28T04:25Z | Source: D32 (augmentiq #52). Opus REJECT (reproduced): no test that ALREADY_SATISFIED opens no PR; evidence search matched 652 hits for an unrelated task on this repo; confirmation need not cite files. Rework dispatched. Rework 1c7e1b09 (branch worktree-wf_b707f4ab-24f-1): all 3 blockers fixed (no-PR test F5, 0 hits for both review sentences on this repo, citation must name an existing code or test hit; evidence in receipt). Opus CONCERN: the real-repo test uses listRepoFiles capped at 2000 of 4784 files, so removing STOP_WORDS still passes; the existsSync branch of the citation check is untested. Next: small fix (full file list in that test, one existsSync test). Wave E18 small fix (uncapped file list, existsSync test), branch slice-E-66-test-fixes. Opus APPROVE of 0a64ea98 (uncapped list, existsSync test). Merge onto main conflicts in seal.ts, supervisor.ts, types.ts, rule_of_two.test.ts after E-68/E-69; rebase dispatched (wave E19). D33: states its net core line delta; core must stay under 5,000 (92 lines of headroom shared by E-67, E-66, E-61, M-14, merge order E-67, E-66, E-61); offset any excess by deleting dead core code. |
+| EV-13 | Eval expected_outcome no_change_needed; aiq-52 set to it | eval/loki10/harness.py, eval/loki10/tasks/aiq-52-searchbar, test-harness.sh | HIGH | bash eval/loki10/test-harness.sh | merged@2026-09-28T04:15Z | Source: D32. Opus CONCERN: a correct v10 no-change run on aiq-52 is graded as a source change. Rework dispatched. Rework APPROVE (branch worktree-wf_b707f4ab-24f-5: 19224201, e0264724): v10 Wall side effect excluded from the diff check. Not merged yet. Merged c9c15f38 (trainE18); `bash eval/loki10/test-harness.sh` 103 passed 0 failed. |
+| E-67 | No pause state: unfinishable runs end as a draft PR or an issue comment with the reason within the cap; stdin never read | loki-ts/src/engine10 (machine, supervisor, worker, escalate, session) | HIGH | a stub provider that asks for input ends within the cap with a draft-PR or comment argv | ready@2026-09-28T04:35Z | Source: D32. Opus REJECT (reproduced): a hung worker ended FAILED with no draft PR and no comment, after the cap. Rework dispatched. Rework ba679f4e (branch worktree-wf_b707f4ab-24f-2). Opus REJECT: at the default cap the supervisor backstop fires before the worker cap can seal; concern: the diff check misses untracked files and uncommitted work never reaches a PR. Next: rework. Held, no builder since 03:20Z (row was stale, not running). Dispatch after E-61 (session.ts) and the E-66 rebase (supervisor.ts) merge, from rework ba679f4e plus the Opus findings above. D33: states its net core line delta; core must stay under 5,000 (92 lines of headroom shared by E-67, E-66, E-61, M-14, merge order E-67, E-66, E-61); offset any excess by deleting dead core code. |
+| E-68 | Per-call deadline at the stage limit, progress every 30s, every exit code classified (125, 143 included), never "cause not classified" | loki-ts/src/engine10/session.ts, failures.ts | HIGH | per-code tests plus a grep test | merged@2026-09-28T04:15Z | Source: D32. Opus REJECT (reproduced): a real limit kill reports "exit 143 (SIGTERM)" because the session child traps SIGTERM; the stub test missed it. Rework dispatched. Rework APPROVE (branch worktree-wf_b707f4ab-24f-3: 4dd05bf9, 922bd923): a limit kill is classified from the engine, not the child exit code. Not merged yet. Merged c9c15f38 (trainE18); engine10 `bun test tests/engine10/` 444 pass 0 fail. |
+| E-69 | Cost shows "not measured" (or partial), never $0 when unmeasured | output.ts, pr_body.ts, seal.ts, status.ts, dashboard/page.ts, cost.ts | MEDIUM | output and receipt tests for measured, partial, unmeasured | merged@2026-09-28T04:15Z | Source: D32 (EV-8 printed $0.00 with 0 tokens). TL CONCERN: genuine-zero test never exercises it; partialCost bypasses the tamper guard; dashboard lacks the partial detail. Rework dispatched. Rework APPROVE (branch worktree-wf_b707f4ab-24f-4: b9825c4c, f42a2aee, 5c66dc55). Not merged yet. Merged c9c15f38 (trainE18); engine10 `bun test tests/engine10/` 444 pass 0 fail. |
 | E-70 | Dashboard shows its and the CLI's version, warns on mismatch; loki dashboard replaces an older Loki dashboard on its port, leaves a non-Loki listener alone | loki-ts/src/engine10/dashboard/ | MEDIUM | version, mismatch, replace and refuse tests | approved@2026-09-28T02:40Z | Source: D32. Built 1397a1f8, TL APPROVE. Merges in the next train. |
+| E-71 | Pulse UNEVIDENCED_CLAIM treats M-NN rows like S/E/EV rows (only status and notes cells can claim), so an M row's spec cell never flags | scripts/v10-pulse.sh (the row-id regex in check_unevidenced_claims only), tests/test-v10-pulse.sh | LOW | bash tests/test-v10-pulse.sh; a case with an M row whose Wall cell says "green" is not flagged, and its notes cell still is | merged@2026-09-28T04:35Z | Source: pulse flagged M-14 (8f4dc965) for its title "green base is an error", a spec, not a claim. TL APPROVE (sonnet): red without the fix (95 passed 1 failed), `bash tests/test-v10-pulse.sh` 96 passed 0 failed on main. |
+| E-72 | release.sh --bump-only leaves a dist bundle unchanged when only its debugId differs (no churn in cockpit.js on a version bump) | scripts/release.sh (dist step only), tests/test-release-bump-only.sh | LOW | bash tests/test-release-bump-only.sh | merged@2026-09-28T04:35Z | Source: v10.0.1 bump rewrote cockpit.js and .map with only a new debugId; the Release Manager reverted them by hand. TL APPROVE (sonnet): red on pre-fix release.sh (3 passed 3 failed), `bash tests/test-release-bump-only.sh` 6 passed 0 failed on main; registered in run-all-tests. |
+| E-73 | Guard (D26): no test writes a hardcoded "far-future" latest version that the current VERSION can overtake; derive it from VERSION instead | tests/test-no-stale-future-version.sh, docs/v10/GUARDS.md (one entry) | LOW | bash tests/test-no-stale-future-version.sh; red on a fixture test that writes latest 9.99.0 against VERSION 10.0.1 | merged@2026-09-28T04:35Z | Source: incident 898fa081, v10.0.0 blocked from npm by latest=9.99.0 in tests/test-start-update-hint.sh (fixed 306b6b0c). TL APPROVE (sonnet); `bash tests/test-no-stale-future-version.sh` RESULT: PASS on main; registered in run-all-tests. |
+| E-74 | release.sh run_bump_only actually calls the debugId restore helper (end-to-end test of the call site, not only the helper) | tests/test-release-bump-only.sh (one leg) | LOW | bash tests/test-release-bump-only.sh; deleting the call site in run_bump_only turns the new leg red | ready@2026-09-28T04:35Z | Source: E-72 TL non-blocking note on 1b06bc61: removing the call site does not turn the E-72 test red. |
+| E-75 | Pulse main-CI check never reads UNKNOWN for a completed Tests run: fall back to `gh run list --commit <sha> --workflow Tests` when the cached check fails, and report RED with the run id | scripts/v10-pulse.sh (main CI check only), tests/test-v10-pulse.sh | MEDIUM | bash tests/test-v10-pulse.sh; a stubbed gh whose check call fails but whose run list says failure yields CI_RED, not UNKNOWN | ready@2026-09-28T04:45Z | Source: main red at 5404b0c6, e26bf52b, 983dda58 (Tests run 36377688703) while the pulse printed Main CI UNKNOWN each turn. |
+| E-76 | Split the engine10 budget test per D33: core under 5,000, modernize/ under 4,000, core never imports modernize | loki-ts/tests/engine10/budget.test.ts | LOW | cd loki-ts && bun test tests/engine10/budget.test.ts; core limit 4900 turns test 1 red | merged@2026-09-28T04:42Z | Source: D33 (CTO). Main red since 5404b0c6 on the combined 5,288 count. TL APPROVE (sonnet) on 797705bc: `bun test tests/engine10/budget.test.ts` 3 pass exit 0, core 4907, modernize 381, core limit 4900 goes red; merged 84fbf9b4, full `bun test tests/engine10/` 474 pass 0 fail. |
 | E-58 | Issue-ref runs: supervisor creates runDir before the fetch child writes issue.json; makes E-47 green | loki-ts/src/engine10/supervisor.ts (one line before fetchIssueToFile), E-47 test files from 544348a7 | MEDIUM | cd loki-ts && bun test tests/engine10/issue_ref_e2e.test.ts (3 pass) | released@2026-09-28T02:38Z | Source: E-47 finding (TL reproduced). Merged 646a6cd7 (train E13): engine10 388 pass 0 fail, tsc exit 0, test-engine10-dist 18/0, test-engine10-docs 26 passed, test-harness 82/0. APPROVE (6384fff9); issue_ref_e2e 3 pass. Released v9.81.0 (npm view loki-mode time: 2026-09-28T02:38:54Z). |
 | E-59 | Receipt model and summary tokens match the provider: cost.ts takes model from the result-cost file; events.ts fold sums cache read and creation tokens; makes E-50 green | loki-ts/src/engine10/cost.ts, loki-ts/src/engine10/events.ts, E-50 test files from 716618d4 | HIGH | cd loki-ts && bun test tests/engine10/model_report.test.ts tests/engine10/output.test.ts | released@2026-09-28T02:38Z | Source: E-50 finding. Reconcile with E-44 (output.ts already folds cache tokens at render). Opus reviewer (cost numbers feed the gate). Opus CONCERN: writeResultCost writes no model, so real records still use the caller model; summary tokens at supervisor.ts still exclude cache. Rework dispatched. Merged 3ab2a8fa (train E14, rebased on main): engine10 404 pass 0 fail (402 pass 0 fail with claude removed from PATH), tsc exit 0, test-harness 86/0, test-local-ci-gitleaks 6/0, test-engine10-dist 18/0. Released v9.81.0 (npm view loki-mode time: 2026-09-28T02:38:54Z). |
 | EV-8 | v10 cost check on 5 tasks before the full arm (CEO 23:31Z): v10 arm, same model, after E-42 and E-45 merge | eval/loki10 results (gitignored) plus docs/v10/METRICS.md block | HIGH | eval/loki10/run.sh --arm v10 --tasks <5 ids> reports completed, time to PR and provider cost per task | released@2026-09-28T02:38Z | Target cost per completed task at or below $0.2363 (raw claude -p full arm). Depends on E-42, E-45, E-38 (--tasks). Incident 01:38Z: first run 0/5 on both variants measured the wrong code. The harness default arm binary is the global loki (loki --version: v9.78.0), and the main checkout node_modules still had agent SDK 0.3.267 (package.json pins 0.3.283), whose bundled Claude Code 2.1.267 rejects claude-opus-5-5, so every session exited "error" in about 1s with 0 tokens. Fixed in 7c3dea3d: bun install (node_modules 0.3.283), repro with the harness arm_env and arm_auth now completes on claude-opus-5-5 ($0.11, 13s); dist rebuilt. Rerun started with LOKI_EVAL_LOKI_BIN=<repo>/bin/loki. Guards E-61, E-62. Rerun measured (not a code slice): A 4/5 $0.5954, B 5/5 $0.3976, C (all sonnet, no plan, no Wall) 4/5 $0.294, raw 5/5 $0.2161 (~/loki-ci-logs/ev8r-{A,B,C}/results.jsonl). Gate not met on cost; D31 and E-64, E-65 follow. Released v9.81.0 (npm view loki-mode time: 2026-09-28T02:38:54Z). |

package/docs/v10/DECISIONS.md

@@ -256,3 +256,12 @@ One entry per decision: context, choice, why, how to reverse. Newest last.
 
 - Built into the v10 engine, no legacy fixes: "already implemented" is a first-class outcome with evidence, receipt and issue comment, no PR (E-66; aiq-52 expected outcome in the eval, EV-13); no pause state, anything unfinishable ends as a draft PR or an issue comment with the reason within the 15-minute cap (E-67); per-call deadline, progress every 30s, every exit code classified including 125 and 143 (E-68); cost shows "not measured", never $0 when unmeasured (E-69); the dashboard shows its version and the CLI's, warns on mismatch, and replaces an older dashboard on its port (E-70).
 - Legacy stays as it is until v10 becomes the default; then legacy is deleted.
+
+## D33. 2026-09-28: engine10 line budgets split, core cap held at 5,000
+
+- The E-02 budget test went red at 5,288 (Tests run 36377688703) because modernize/ (M-01, M-02, M-05, M-06) was counted inside the D29 "under 5K lines" core.
+- Core engine (engine10 minus modernize/) stays under 5,000 lines, counted as today (raw lines, blanks and comments included). Not raised, not recounted as SLOC: that would add about 920 lines by redefinition, and the cap is the auditability part of the moat.
+- Pending core slices (E-67, E-66, E-61, M-14) share the 92-line headroom (core 4,907 at 983dda58). Each card states its net core delta; anything over is offset by deleting dead or duplicated core code in the same slice. Deleting comments on Seal, Wall, verify or Rule of Two logic is not an offset.
+- modernize/ gets its own cap of 4,000 lines in the same test: 25 planned modules (MODERNIZE.md section 13) at about 150 lines each plus 15% slack. M-24's view moves to mod/dashboard.ts. M-14 stays under 20 lines in wall.ts and calls into mod/oracle/.
+- Core never imports modernize/ (the cli.ts TABLE string is exempt), so the split cannot hide core code.
+- Hitting either cap means re-slice or delete, never raise. Ruled by the CTO (opus) on the Chief of Staff's request; implemented by E-76.

package/docs/v10/GUARDS.md

@@ -531,3 +531,41 @@ previously mismarked two merged guards (S-16, S-74) as PENDING.
   AKIA-shaped token fails the step, and a commit adding the identical
   characters via source-level concatenation (never contiguous in the
   committed bytes) passes it.
+
+## 16. A "far-future" `latest` version literal in a test went stale (E-73)
+
+- **Incident:** `tests/test-start-update-hint.sh` hardcoded `latest=9.99.0`
+  (two occurrences, lines 130 and 163 as of `306b6b0c`'s parent) as a value
+  meant to always read as "far in the future" so the update-available hint
+  would reliably fire. The v10.0.0 major release made `9.99.0` older than
+  the real `VERSION`, so the hint stopped firing and Tests shards 5/8 (this
+  test) and 1/8 (trust-core baseline, rc 67) went red on commit `898fa081`.
+- **Root cause with evidence:** commit `306b6b0c` (`fix(tests): stale-install
+  hint test used 9.99.0 as "far-future", older than 10.0.0`) states it
+  directly: "The 10.0.0 bump made latest=9.99.0 older than VERSION, so the
+  hint stayed silent." A literal future-version constant was compared only
+  against the `VERSION` at the time it was written, with nothing keeping it
+  ahead of later major bumps. The fix bumped the literal to `999.0.0`, but
+  nothing stopped a second copy of the same mistake from being added
+  elsewhere in tests/.
+- **The guard:** `tests/test-no-stale-future-version.sh` scans `tests/`
+  (`.sh`, `.py`, `.ts`) for literal `latest` version assignments
+  (`"latest":"X.Y.Z"`, `latest=X.Y.Z`, `latest: 'X.Y.Z'`) and fails, printing
+  `file:line`, whenever a found version's major component is not strictly
+  greater than the current `VERSION` major plus 10 -- so a planted
+  "far-future" literal must stay comfortably ahead of the next several major
+  releases, not just the one at the time it was written. Each `latest`
+  occurrence is scored on its own matched version text, so a sibling version
+  number elsewhere on the same line (a `"current"` or `"version"` key, say)
+  can never mask or fake a violation.
+- **The test that proves it fires:** `tests/test-no-stale-future-version.sh`
+  is itself the test: it runs its own scanner against the real `tests/` tree
+  (must be clean on main) and against a synthetic fixture directory planting
+  `latest="9.99.0"` alongside a `latest="999.0.0"` fixture and two
+  mixed-line fixtures pairing a stale/fresh `latest` with a fresher/staler
+  sibling number on the same line, asserting file:line for every case that
+  must be caught and silence for every case that must not. Replaying the
+  scanner against the actual pre-`306b6b0c` tree (`VERSION=10.0.0` plus the
+  old `test-start-update-hint.sh`) reproduces the incident directly: exit 1,
+  reporting both `9.99.0` lines by file:line. Run:
+  `bash tests/test-no-stale-future-version.sh`.

package/docs/v10/PROGRESS.md

@@ -1,6 +1,20 @@
 # Progress
 
-## 2026-09-28T03:44Z: RELEASE BLOCKED -- read first on resume
+## 2026-09-28T04:45Z: drift audit (turn 432, 6-hour window) and main red again
+- Releases in 6h: 6 (v9.79.0, v9.80.0, v9.80.1, v9.81.0, v10.0.0 tag only, v10.0.1), 151 commits on main. CONTROL "1 per 90 min" met; the 30/day pace is not (about 24/day).
+- Red main windows in 6h, from `gh run list --workflow Tests --branch main`: 898fa081 to d8774dd5 (about 1h, version-literal test, fixed 306b6b0c, guard E-73) and 5404b0c6 to 983dda58 (now). Cause of the second: M-05 merged after only `bun test tests/engine10/modernize/`; the full `tests/engine10/` includes the E-02 size budget, which went 5,288 against 5,000. The Chief of Staff's own merge, not a builder's.
+- Also red at 983dda58: shard-durations rows missing for the E-72/E-73 suites registered by the Chief of Staff (fixed 83cc5734, drift detector 6 passed 0 failed).
+- The pulse printed Main CI UNKNOWN for all three red pushes; slice E-75 makes it read the Tests run list.
+- Correction: the 04:25Z BOARD note "merged f4d98c0b, 28 pass 0 fail" covered only the modernize tests, not the engine10 suite.
+- Rule from now: every merge touching loki-ts/src runs the full `cd loki-ts && bun test tests/engine10/` before push; D33 (CTO) splits the budget, E-76 implements it.
+
+## 2026-09-28T04:30Z: v10.0.1 SHIPPED -- read first on resume
+- v10.0.1 republishes v10.0.0 (tag v10.0.0 at 898fa081 never reached npm). Root cause: tests/test-start-update-hint.sh used latest=9.99.0 as "far-future", older than 10.0.0; fixed 306b6b0c (control: old test on the new tree fails "a stale install prints NO warning on start"; new test 10 passed 0 failed; trust-core 95 passed 0 failed). Tests green on 306b6b0c (run 36375975977).
+- Release run 36376357720 all jobs success; `npm view loki-mode dist-tags` latest 10.0.1, gitHead 76ec1c24 = tag v10.0.1^{}; GitHub release v10.0.1 published 04:14:03Z; `loki --version` from a fresh prefix prints "Loki Mode v10.0.1" (rc=0).
+- Train E18 on main (ea288330): E-68, E-69, EV-13, E-64 merged; M-01/02/05/06 merged f4d98c0b. Wave E18 rejects (M-03, M-04, M-09, EV-11, EV-12) and E-66 rebase, E-61, E-62 building in wave E19 (wf_bd919989-941); E-71..E-73 in wave E18b (wf_f55ed4cc-ca6). E-67 held (overlaps E-61 session.ts and E-66 supervisor.ts). EV-9 held until E-64 is re-measured.
+- Wave E18 spend ESTIMATE: 1,468,032 subagent tokens (14 agents, workflow usage block).
+
+## 2026-09-28T03:44Z: RELEASE BLOCKED (resolved by v10.0.1, see above)
 - v10.0.0 did NOT publish. The release commit 898fa081 (tag v10.0.0 pushed) failed Tests shards 1/8 and 5/8, so the Release workflow failed; `npm view loki-mode version` is still 9.81.0. Failing suites (gh run view 36372016155 --log-failed): "loki start surfaces a stale install" (line: "FAIL: a stale install prints NO warning on start") and "trust-core tests detect their regressions".
 - Next step: fix those 2 shards on main (likely the 10.0.0 major bump changes the version comparison the stale-install check uses; confirm from the test before editing), wait for Tests green on the fix SHA, then re-release v10.0.0 (the tag v10.0.0 already points at 898fa081: delete nothing; cut the re-release per docs/dev/release-checklist.md, bumping to 10.0.1 if the tag cannot be reused). Default stays legacy; v10 opt-in; gate numbers are in CHANGELOG v10.0.0 and docs/v10/METRICS.md.
 - Session hand-off: no workflows started after 03:11Z. Merge-ready (approved, not merged): E-68, E-69, EV-13 (branches worktree-wf_b707f4ab-24f-3/-4/-5), E-64 (worktree-wf_4601e7b3-4d8-1), E-70 already merged, E-31 held for the gate. Needs rework: E-66 (small test fixes), E-67 (backstop inside the cap), M-09, M-01/02/05/06 (iterative SCC), EV-11 (11 medium tasks missing), EV-12 (REJECT: large tasks smaller than medium). Both workflows (p0-rework, d30-rework-and-m1) finished; nothing running.
@@ -1278,7 +1292,7 @@ sample.
 - On main (`git ls-remote origin refs/heads/main` = addda547): E-42 real entry end to end (run.ts glue deleted), E-44 output fixes, agent SDK 0.3.283 (9db2a4ed), E-51 eval PR path regression, and train E12 (23b20e6f): E-33 gate report, EV-6 publish script, E-38 legacy arm pin, E-39 interrupt/resume, E-40 live PR smoke. Train checks: engine10 349 pass 0 fail, tsc exit 0, test-harness 79/0, test-gate-report 34/0.
 - SDK route: claude-opus-5-5 now runs through the SDK (probe: `success OK`); 0.3.267 rejected it. The same probe cost $0.33 for a one-word reply, so fixed per-call overhead, not task work, drives v10 cost.
 - Legacy arm (EV-5): 3 results so far (2 hidden pass), each at the 900s cap; runner alive at parallel 3, ETA about 02:15Z. Incident: 6 then 2 legacy watchdog loops escaped the harness timeout group (ppid 1, 30 min); stopped by PID; guard slice EV-10.
-- In flight (wave E13, 12 builders): E-45 cost path rework, E-36 preflight (plus E-37), E-32 rebase, E-34 docs refresh, E-52..E-56, E-58 (makes E-47 green), E-59 (makes E-50 green), EV-10.
+- In flight (wave E13, 12 builders): E-45 cost path rework, E-36 preflight (plus E-37), E-32 rebase, E-34 docs refresh, E-52..E-56, E-58 (unblocks E-47), E-59 (unblocks E-50), EV-10.
 - ETA: E-45 merge about 00:45Z, EV-8 5-task cost check right after, EV-9 full v10 arm about 01:00Z to 01:45Z, gate decision 03:00Z.
 - Top blocker: cost per completed task (raw $0.2363); E-45 plus the per-call overhead finding decide it.