loki-mode 9.73.0 → 9.74.0

package/docs/v10/BOARD.md

@@ -151,10 +151,10 @@ set is declared to avoid overlap with those and with each other.
 | S-132 | Velocity: skip heavy Tests jobs on a version-bump-only commit whose parent Tests run succeeded (eligibility no looser than release.yml STEP 1) | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | HIGH | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | released@2026-09-27T19:42Z | Batch 4 (build then review), dispatched 18:17. Batch-4 builder was diverted by a relayed message and built nothing; re-dispatched 18:37 in batch 4b (wf_63d4c91e-86d). Review APPROVE (HIGH); cherry-picked 7b328b1f+c50efd15 into train 9, main a39c4995 pushed 19:06:25 (`git ls-remote origin refs/heads/main` = a39c4995). Tagged v9.70.0, awaiting publish-npm (`git ls-remote origin refs/tags/v9.70.0^{}` = 6c459dfa). Published: `npm view loki-mode version` = 9.71.0; npm time lists 9.70.0. |
 | S-133 | Velocity: release.yml required-ci poll 30s to 10s; fix stale publish-npm comment | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | LOW | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | released@2026-09-27T18:55Z | Batch 4 (build then review), dispatched 18:17. Review APPROVE; train 7 pushed aada49d8 (main b7a8dd50 at 18:45:14Z, ls-remote verified). In v9.68.0 (release commit 8d17be2b, pushed 18:54:35Z); released when publish-npm succeeds. |
 | S-134 | Velocity: rebuild shard-durations.tsv from a recent successful run; drift test | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | LOW | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | released@2026-09-27T19:42Z | Batch 4 (build then review), dispatched 18:17. Batch-4 builder was diverted by a relayed message and built nothing; re-dispatched 18:37 in batch 4b (wf_63d4c91e-86d). Review APPROVE; abe6a7ae into train 9 (a39c4995). Tagged v9.70.0, awaiting publish-npm (`git ls-remote origin refs/tags/v9.70.0^{}` = 6c459dfa). Published: `npm view loki-mode version` = 9.71.0; npm time lists 9.70.0. |
-| S-135 | Velocity: parallelize trust-core probe mutations (130s) | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | MEDIUM | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | building@2026-09-27T19:10Z | Batch 4 (build then review), dispatched 18:17. Blocked as scoped: probe_case mutates the shared repo in place (50 of 91 sites target autonomy/run.sh); reviewer reproduced the race. Re-scope: a private repo copy per worker plus a target override. Batch 5 build, re-scoped to a private repo copy per worker (wf_38d4e17c-211). |
+| S-135 | Velocity: parallelize trust-core probe mutations (130s) | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | MEDIUM | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | merged@2026-09-27T20:06Z | Batch 4 (build then review), dispatched 18:17. Blocked as scoped: probe_case mutates the shared repo in place (50 of 91 sites target autonomy/run.sh); reviewer reproduced the race. Re-scope: a private repo copy per worker plus a target override. Batch 5 build, re-scoped to a private repo copy per worker (wf_38d4e17c-211). 4a29e278 (MEDIUM review APPROVE); in train 12, main ec01d54b pushed 20:05:58 (`git ls-remote origin refs/heads/main` = ec01d54b). |
 | S-136 | Velocity: tests/test-select-tests.sh under 30s, same 38 cases | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | MEDIUM | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | released@2026-09-27T19:42Z | Batch 4 (build then review), dispatched 18:17. Batch-4 builder was diverted by a relayed message and built nothing; re-dispatched 18:37 in batch 4b (wf_63d4c91e-86d). 7fc63d5b REJECT (mapfile crashes under /bin/bash 3.2); rework dispatched 18:53. cafbf57c re-review APPROVE (38/38 under /bin/bash 3.2, 25.6s); lands after the release 10 bump. Note: two builders converged on the same fix. 7fc63d5b+cafbf57c onto main b61045fd pushed 19:19:39 (`/bin/bash tests/test-select-tests.sh` = 38 passed, 0 failed, 33.6s). Tagged v9.70.0, awaiting publish-npm (`git ls-remote origin refs/tags/v9.70.0^{}` = 6c459dfa). Published: `npm view loki-mode version` = 9.71.0; npm time lists 9.70.0. |
 | S-137 | S-81 follow-up: shard-coverage T4 enumerates the real runner | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | LOW | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | released@2026-09-27T19:42Z | Batch 4 (build then review), dispatched 18:17. Batch-4 builder was diverted by a relayed message and built nothing; re-dispatched 18:37 in batch 4b (wf_63d4c91e-86d). Review APPROVE; 4107e16f into train 9 (a39c4995). Fix-forward 6e48decb: T4 unsharded run inherited LOKI_TEST_SHARD in CI (Tests run 36343130286 shard 7/8: "unsharded real run selected 41 of 564"); `LOKI_TEST_SHARD=6/8 bash tests/test-shard-coverage.sh` 18/1 before, 19/0 after. Tagged v9.70.0, awaiting publish-npm (`git ls-remote origin refs/tags/v9.70.0^{}` = 6c459dfa). Published: `npm view loki-mode version` = 9.71.0; npm time lists 9.70.0. |
-| S-138 | GUARDS 12: lint so test fixtures never write the real ~/.gitconfig | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | LOW | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | building@2026-09-27T19:31Z | Batch 4 (build then review), dispatched 18:17. 849b655e review REJECT; rework pending. 2f29ad49 re-review REJECT (2nd); rework in batch 5 (wf_38d4e17c-211). 7431f5dd 3rd REJECT; simplified rework (fail closed unless a named isolation helper is sourced) in batch 6 (wf_3510293b-09b). |
+| S-138 | GUARDS 12: lint so test fixtures never write the real ~/.gitconfig | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | LOW | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | merged@2026-09-27T20:06Z | Batch 4 (build then review), dispatched 18:17. 849b655e review REJECT; rework pending. 2f29ad49 re-review REJECT (2nd); rework in batch 5 (wf_38d4e17c-211). 7431f5dd 3rd REJECT; simplified rework (fail closed unless a named isolation helper is sourced) in batch 6 (wf_3510293b-09b). a95eabea (4th round, review APPROVE); in train 12, main ec01d54b pushed 20:05:58 (`git ls-remote origin refs/heads/main` = ec01d54b). |
 | S-139 | GUARDS 13 + BACKLOG 136: RELEASED_AHEAD_OF_NPM; UNKNOWN on tag/npm disagreement | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | MEDIUM | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | released@2026-09-27T19:42Z | Batch 4 (build then review), dispatched 18:17. Batch-4 builder was diverted by a relayed message and built nothing; re-dispatched 18:37 in batch 4b (wf_63d4c91e-86d). Review APPROVE; 28d18393 onto main 06bf5406 pushed 19:08:09. Tagged v9.70.0, awaiting publish-npm (`git ls-remote origin refs/tags/v9.70.0^{}` = 6c459dfa). Published: `npm view loki-mode version` = 9.71.0; npm time lists 9.70.0. |
 | S-140 | BACKLOG 103: jest "Test Suites N failed" / vitest "Test Files N failed" count as failures | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | MEDIUM | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | released@2026-09-27T19:42Z | Batch 4 (build then review), dispatched 18:17. Built 6dbfc1e6; review pending. Review APPROVE; 6dbfc1e6 onto main e952e1ae pushed 19:09:04. Tagged v9.70.0, awaiting publish-npm (`git ls-remote origin refs/tags/v9.70.0^{}` = 6c459dfa). Published: `npm view loki-mode version` = 9.71.0; npm time lists 9.70.0. |
 | S-141 | S-49 follow-up: remaining council readers (~1425, ~1564, ~4232) use -I -S | files per docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | HIGH | wall check in docs/v10/ARCHITECT-CUTS.md (18:05Z cut) | released@2026-09-27T19:42Z | Batch 4 (build then review), dispatched 18:17. Batch-4 builder was diverted by a relayed message and built nothing; re-dispatched 18:37 in batch 4b (wf_63d4c91e-86d). Review APPROVE (HIGH); 001576f3+958f6548 onto main 06bf5406 pushed 19:08:09. Tagged v9.70.0, awaiting publish-npm (`git ls-remote origin refs/tags/v9.70.0^{}` = 6c459dfa). Published: `npm view loki-mode version` = 9.71.0; npm time lists 9.70.0. |
@@ -216,7 +216,7 @@ set is declared to avoid overlap with those and with each other.
 | S-154 | GUARDS 5 + TODO 8: prune-worktrees.sh treats a cherry-picked branch (git cherry, no + lines) as merged; test forbids mtime signals | scripts/prune-worktrees.sh, tests/test-prune-worktrees.sh (new) | MEDIUM | bash tests/test-prune-worktrees.sh exits 0; cherry-picked fixture listed, one-unique-commit, locked and dirty fixtures kept; dropping the git cherry branch fails the case | merged@2026-09-27T19:56Z | Removes worktrees only via git worktree remove. Captain registers the test. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on a41e625f; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
 | S-155 | Velocity: reachability scan (95s on CI, 47s local) under 10s via a per-module stem prefilter, identical verdicts | tests/lib/scan-unreachable-shipped.py | LOW | scan wall time under 10s; stdout and rc byte-identical to the pre-change capture; bash tests/test-no-unreachable-shipped.sh 4 passed 0 failed; removing one real require is still reported | merged@2026-09-27T19:56Z | Builder measures regex vs I/O first and records both numbers. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on 3f786ce0; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
 | S-156 | BACKLOG 127 remainder: auto-capture shadow_write runs with PROJECT_DIR unset, and float() splices episode importance into python source | autonomy/run.sh (shadow_write auto-capture block about 21380-21396 only), tests/test-autocapture-shadow-write-guard.sh (new) | HIGH | bash tests/test-autocapture-shadow-write-guard.sh exits 0 under /bin/bash and bash 5; no marker from a planted cwd memory package; no file from an injected importance; trust-core suite passes | merged@2026-09-27T19:56Z | Builder names who writes episode_path_file. Only run.sh row in this cut. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on 71d7a246; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
-| S-157 | BACKLOG 98/89: council member vote and _council_convergence_evidence_green read pass:true as green whatever failed_count says | autonomy/completion-council.sh (those 2 parsers only), tests/test-council-failed-count-honesty.sh (new) | HIGH | pass:true with failed_count 2 is not green at both sites; failed_count 0 stays green; trust-core and convergence-floor suites pass; reverting either site fails its case | building@2026-09-27T19:31Z | Mirrors the evidence gate rule (~2014). Only completion-council.sh row in this cut. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. |
+| S-157 | BACKLOG 98/89: council member vote and _council_convergence_evidence_green read pass:true as green whatever failed_count says | autonomy/completion-council.sh (those 2 parsers only), tests/test-council-failed-count-honesty.sh (new) | HIGH | pass:true with failed_count 2 is not green at both sites; failed_count 0 stays green; trust-core and convergence-floor suites pass; reverting either site fails its case | merged@2026-09-27T20:06Z | Mirrors the evidence gate rule (~2014). Only completion-council.sh row in this cut. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. 7a709fde (HIGH review APPROVE); in train 12, main ec01d54b pushed 20:05:58 (`git ls-remote origin refs/heads/main` = ec01d54b). |
 | S-158 | BACKLOG 118: per-run cost_partial dropped by /api/cost/timeline runs[] and /api/proofs; pages show a lower bound as a total | dashboard/server.py (runs.append in _compute_cost_timeline and the /api/proofs row only), dashboard/static/cost.html, dashboard/static/proofs.html, tests/dashboard/test_cost_partial_surfaced.py (new) | MEDIUM | pytest test_cost_partial_surfaced.py passes; fixture cost_partial true surfaces in both endpoints and renders as at least $X; dropping the key fails | merged@2026-09-27T19:56Z | Builder names the consumers checked. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on 931a93b6; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
 | S-159 | BACKLOG 114: NLSearch renders No results found when the search request failed | web-app/src/components/NLSearch.tsx, web-app/src/components/NLSearch.state.test.mjs (new) | LOW | node --test NLSearch.state.test.mjs passes incl. the negative assertion; npx tsc -b exits 0 | merged@2026-09-27T19:56Z | Captain rebuilds web-app/dist. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on ea5b4462; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
 | S-160 | BACKLOG 114: CommandPalette file-search failure reads as No results found | web-app/src/components/CommandPalette.tsx, web-app/src/components/CommandPalette.state.test.mjs (new) | LOW | node --test CommandPalette.state.test.mjs passes; npx tsc -b exits 0 | merged@2026-09-27T19:56Z | Captain rebuilds web-app/dist. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on 3f9873f3; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
@@ -228,11 +228,31 @@ set is declared to avoid overlap with those and with each other.
 | S-166 | BACKLOG 114: checkpoint viewer ignores a rejected allSettled fetch and clears the error | dashboard-ui/components/loki-checkpoint-viewer.js (load block only), dashboard-ui/tests/loki-checkpoint-viewer-fetch-error.node.test.mjs (new) | LOW | node --test the new file passes incl. the negative assertion | merged@2026-09-27T19:56Z | Captain rebuilds dashboard/static/index.html. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on 4035d21d; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
 | S-167 | BACKLOG 114: council transcripts render a failed hook-events read as zero events | dashboard-ui/components/loki-council-transcripts.js (hook events load only), dashboard-ui/tests/loki-council-transcripts-fetch-error.node.test.mjs (new) | LOW | node --test the new file passes | merged@2026-09-27T19:56Z | Captain rebuilds dashboard/static/index.html. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on 3fea74e8; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
 | S-168 | BACKLOG 114: task board hides a server load error whenever local tasks exist | dashboard-ui/components/loki-task-board.js (catch and error render only), dashboard-ui/tests/loki-task-board-fetch-error.node.test.mjs (new) | LOW | node --test the new file passes; loki-task-board-modal-guard test still passes | merged@2026-09-27T19:56Z | Captain rebuilds dashboard/static/index.html. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on aa2a64a4; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
-| S-169 | BACKLOG 114: log stream swallows API failures with an empty catch | dashboard-ui/components/loki-log-stream.js (API poll catch and empty render only), dashboard-ui/tests/loki-log-stream-fetch-error.node.test.mjs (new) | LOW | node --test the new file passes; loki-poll-registry test still passes | building@2026-09-27T19:57Z | Captain rebuilds dashboard/static/index.html. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. a990a9ce review REJECT; rework dispatched 19:57Z. |
+| S-169 | BACKLOG 114: log stream swallows API failures with an empty catch | dashboard-ui/components/loki-log-stream.js (API poll catch and empty render only), dashboard-ui/tests/loki-log-stream-fetch-error.node.test.mjs (new) | LOW | node --test the new file passes; loki-poll-registry test still passes | merged@2026-09-27T20:06Z | Captain rebuilds dashboard/static/index.html. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. a990a9ce review REJECT; rework dispatched 19:57Z. 707283f3 (re-review APPROVE, runner lists 598 = main + 1); in train 12, main ec01d54b pushed 20:05:58 (`git ls-remote origin refs/heads/main` = ec01d54b). |
 | S-170 | BACKLOG 114: API keys panel renders No API keys configured under its own load-error banner | dashboard-ui/components/loki-api-keys.js (table branch only), dashboard-ui/tests/loki-api-keys-fetch-error.node.test.mjs (new) | LOW | node --test the new file passes; error render lacks the empty-state sentence | merged@2026-09-27T19:56Z | Captain rebuilds dashboard/static/index.html. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on ab837a75; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
-| S-171 | BACKLOG 124: lint for response fields interpolated into innerHTML without the escape helper | tests/test-no-unescaped-innerhtml.sh (new), tests/lib/scan-unescaped-innerhtml.py (new) | MEDIUM | passes on main with a reasoned in-file allowlist; planted fixture exits 1; empty-reason entry fails; at least 20 files scanned | building@2026-09-27T19:31Z | Any real XSS found is reported only; repairs go to separate slices. Captain registers. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. |
+| S-171 | BACKLOG 124: lint for response fields interpolated into innerHTML without the escape helper | tests/test-no-unescaped-innerhtml.sh (new), tests/lib/scan-unescaped-innerhtml.py (new) | MEDIUM | passes on main with a reasoned in-file allowlist; planted fixture exits 1; empty-reason entry fails; at least 20 files scanned | merged@2026-09-27T20:06Z | Any real XSS found is reported only; repairs go to separate slices. Captain registers. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. db501eba (review APPROVE); in train 12, main ec01d54b pushed 20:05:58 (`git ls-remote origin refs/heads/main` = ec01d54b). |
 | S-172 | BACKLOG 132: shadow-write mutant check is green on bash 5.3 and red on /bin/bash 3.2 | tests/test-council-shadow-write-project-dir.sh | LOW | bash tests/test-council-shadow-write-project-dir.sh exits 0; mutant leg red under both /bin/bash and PATH bash, both versions printed | merged@2026-09-27T19:56Z | Test-only. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on e2114d09; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
 | S-173 | BACKLOG 135: P2.council-readers-not-shadowed does not drive council_managed_should_stop (cwd-shadow class only) | tests/moat/p2-honest-verdict.sh (that case only) | HIGH | p2-honest-verdict.sh prints CASE P2.council-readers-not-shadowed PASS; removing the sys.path filter in a scratch copy prints FAIL | merged@2026-09-27T19:56Z | No .pth leg: that reader is still python3 -E, so a .pth leg would redden a proven case; follows alternate A2. Source: 19:10Z cut. Batch 6 (wf_3510293b-09b), build then review. Review APPROVE on 6bc4b5cf; in train 11, main 2a024770 pushed 19:56:04 (`git ls-remote origin refs/heads/main` = 2a024770). |
+| S-174 | Guard: run_test with a missing or empty argument stops run-all-tests.sh with no summary and skips later suites | tests/run-all-tests.sh (run_test guard and missing-script return only), tests/test-run-all-missing-arg.sh (new) | MEDIUM | bash tests/test-run-all-missing-arg.sh exits 0 with Failed: 1 per leg (one-arg, empty-arg, missing-script) and the later stub's PASSED line printed; guard removed in a scratch copy exits 1; bash tests/test-run-all-dispatch.sh and LOKI_TEST_LIST=1 bash tests/test-shard-coverage.sh exit 0 | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-175 | BACKLOG 62: a whitelist-rejected LOKI_MONOREPO_TEST_CMD records pass true and touches unit-tests.pass | autonomy/run.sh (enforce_test_coverage monorepo-custom-rejected branch only), tests/test-monorepo-rejected-cmd-inconclusive.sh (new) | HIGH | bash tests/test-monorepo-rejected-cmd-inconclusive.sh exits 0: pass is "inconclusive", status not_run, no unit-tests.pass; reverting the branch exits 1; bash tests/test-trust-core-tests-detect.sh exits 0 | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-176 | BACKLOG 98: proof headline reads a stale test-results.json (_collect_tests has no .test-results.iter check) | autonomy/lib/proof-generator.py (_collect_tests only), tests/test_proof_tests_freshness.py (new) | HIGH | python3 -m pytest -q tests/test_proof_tests_freshness.py passes: ITERATION_COUNT=5 with marker 4 gives facts.tests.status not_run and a headline unlike the fresh case; marker 5 keeps the prior status; removing the check fails the stale case | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-177 | BACKLOG 98: Bun npm-test fallback reads an exit-0 run that prints failures as passed | loki-ts/src/runner/quality_gates.ts (runTestCoverage npm fallback only), loki-ts/tests/runner/npm_fallback_summary_failures.test.ts (new) | HIGH | cd loki-ts && bun test tests/runner/npm_fallback_summary_failures.test.ts exits 0: jest Tests 1 failed, vitest Test Files 1 failed and pytest 1 passed 1 error all return passed false; Tests 3 passed returns passed true; removing the parse fails the first three | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-178 | BACKLOG 112: /api/cost reads tracker tokens without a USD total as a measured $0 and labels the model sonnet | dashboard/server.py (get_cost context-tracker fallback only), tests/dashboard/test_cost_tracker_fallback_unmeasured.py (new) | MEDIUM | python3 -m pytest -q tests/dashboard/test_cost_tracker_fallback_unmeasured.py passes (tokens without total_cost_usd give cost null; recorded 0.0 stays 0.0; no provider gives model unknown); reverting fails case 1; bash tests/moat/p7-no-fabricated-data.sh prints CASE P7.unmeasured-cost-never-zero PASS | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-179 | BACKLOG 106: loki cost puts 0.0 in place of unknown spend | autonomy/loki (cmd_cost only), tests/test-loki-cost-unmeasured.sh (new) | MEDIUM | bash tests/test-loki-cost-unmeasured.sh exits 0: cap 10 with no measured records gives --json used null and percent null; measured 2.50 gives 2.5 and 25.0; reverting fails the first leg | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-180 | BACKLOG 144: P7 helper-return arm misses class-method helpers | tests/moat/p7-no-fabricated-data.sh (helper-return arm only) | HIGH | bash tests/moat/p7-no-fabricated-data.sh prints PASS for every P7 case and flags the in-script class-method fixture; removing the method-head pattern lets the fixture through; tests/moat/cases.txt unchanged | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-181 | GUARDS 11: v10-guard blocks a glob rm whose parent is a shared root (/tmp, TMPDIR, scratchpad) | scripts/v10-guard.sh (Rule 4 region only), tests/test-v10-guard.sh, docs/v10/GUARDS.md (section 11 only) | MEDIUM | bash tests/test-v10-guard.sh exits 0 with rm -f /tmp/*.log and rm -f scratchpad/* blocked and rm -f /tmp/run-1/*.log allowed; dropping the new rule fails the blocked cases | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-182 | docs/exit-codes.md omits the pending loki verify codes (verify --fast exits 0 on INCONCLUSIVE until v10.0.0) | docs/exit-codes.md (loki verify section only) | LOW | bash tests/test-exit-codes-documented.sh exits 0; grep -n P2.fast-verify-inconclusive-not-zero docs/exit-codes.md prints one line; the four measured codes appear in the report with their commands | ready@2026-09-27T19:57Z | Source: 19:57Z cut. |
+| S-183 | BACKLOG 114: migration dashboard renders a failed load as No migration data available | dashboard-ui/components/loki-migration-dashboard.js (error render branch only), dashboard-ui/tests/loki-migration-dashboard-fetch-error.node.test.mjs (new) | LOW | node --test dashboard-ui/tests/loki-migration-dashboard-fetch-error.node.test.mjs passes: a rejected fetch renders Could not load and lacks the empty-state sentence; an empty list still renders No migrations found | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-184 | BACKLOG 114: managed memory panel ignores a 200 events payload carrying error | dashboard-ui/components/loki-managed-memory-panel.js (events load only), dashboard-ui/tests/loki-managed-memory-events-error.node.test.mjs (new) | LOW | node --test dashboard-ui/tests/loki-managed-memory-events-error.node.test.mjs passes: the error payload renders the error line and not the empty sentence; events [] with no error still renders the empty sentence | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-185 | BACKLOG 114: DeployConnections rows read Not connected under their own load error | web-app/src/components/DeployConnections.tsx (row status render only), web-app/src/components/DeployConnections.state.test.mjs (new) | LOW | node --test web-app/src/components/DeployConnections.state.test.mjs passes: no row reads Not connected after a failed fetch; a real connected false still does; cd web-app && npx tsc -b exits 0 | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-186 | BACKLOG 116: issue list comment count never shows (gh sends comments as an array) | web-app/src/components/GitHubIssuesPanel.tsx (list comment badge only), web-app/src/types/api.ts (GitHubIssue.comments only), web-app/src/components/GitHubIssuesPanel.comments.test.mjs (new) | LOW | node --test web-app/src/components/GitHubIssuesPanel.comments.test.mjs passes: array of 2 renders 2, number 3 renders 3; cd web-app && npx tsc -b exits 0 | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-187 | BACKLOG 118: CostEstimator prices the whole iteration cap as the estimate | web-app/src/components/ProjectWorkspace.tsx (CostEstimator props only), web-app/src/components/CostEstimator.tsx (export only if needed), web-app/src/components/CostEstimator.estimate.test.mjs (new) | LOW | node --test web-app/src/components/CostEstimator.estimate.test.mjs passes; grep -n 'estimatedIterations={buildStatus.maxIterations' web-app/src/components/ProjectWorkspace.tsx exits 1; cd web-app && npx tsc -b exits 0 | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-188 | BACKLOG 123: overview proof card wording has no test of its own | dashboard-ui/tests/loki-overview-proof-card.node.test.mjs (new) | LOW | node --test dashboard-ui/tests/loki-overview-proof-card.node.test.mjs passes: no proof reads Not evaluated, a headline carries the recorded-copy prefix, gaps null reads uncertainty not measured; deleting the prefix in a scratch copy fails it | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-189 | BACKLOG 114: learning dashboard renders failed metrics and trends reads as no data | dashboard-ui/components/loki-learning-dashboard.js (metrics and trends load plus their two empty branches only), dashboard-ui/tests/loki-learning-dashboard-fetch-error.node.test.mjs (new) | LOW | node --test dashboard-ui/tests/loki-learning-dashboard-fetch-error.node.test.mjs passes: rejected metrics and trends render Could not load; an empty trends response still renders No trend data available | building@2026-09-27T20:12Z | Source: 19:57Z cut. Batch 7 (wf_a3ea2c8c-560), build then review. |
+| S-190 | BACKLOG 112: R3 design doc describes project_total_usd as a plain sum | docs/R3-COST-OBSERVABILITY-DESIGN.md | LOW | grep -n 'sum of per-run proof costs' docs/R3-COST-OBSERVABILITY-DESIGN.md exits 1; grep -n project_total_partial docs/R3-COST-OBSERVABILITY-DESIGN.md prints at least one line | ready@2026-09-27T19:57Z | Source: 19:57Z cut. |
+| S-191 | Velocity: test-review-assurance-tail.sh (116s) under 60s by running independent cases concurrently, budgets unchanged | tests/test-review-assurance-tail.sh | MEDIUM | time LOKI_TEST_SHARD=0/8 bash tests/test-review-assurance-tail.sh exits 0 with real under 60s and the same pass-count line as the pre-change capture; both timings reported | ready@2026-09-27T19:57Z | Source: 19:57Z cut. |
+| S-192 | BACKLOG 112: no test drives the web-app WebSocket status push payload for unmeasured cost | web-app/tests/test_status_push_unmeasured.py (new), web-app/server.py (lift the nested status reader only if needed) | MEDIUM | python3 -m pytest -q web-app/tests/test_status_push_unmeasured.py passes: no tokens gives cost null and max_iterations null, priced tokens give a number; forcing 0.0 in a scratch copy fails case 1 | ready@2026-09-27T19:57Z | Source: 19:57Z cut. |
+| S-193 | Velocity: v10-ops worktree-budget prints how many worktrees a batch may open before dispatch | scripts/v10-ops.sh (new worktree-budget subcommand), tests/test-v10-ops.sh | LOW | bash tests/test-v10-ops.sh exits 0; scripts/v10-ops.sh worktree-budget 15 prints 15 minus the .claude/worktrees entries in git worktree list --porcelain, and at or over the cap prints 0 and exits 1 | ready@2026-09-27T19:57Z | Source: 19:57Z cut. |
 
 Every slice above: implement with red-then-green tests, run diff-scoped tests
 plus `bash tests/moat/run.sh` in your own worktree, never touch `main`,