loki-mode 11.17.37 → 11.17.39

package/docs/v10/BOARD.md

@@ -760,7 +760,7 @@ Source: ~/git/autonomi-dev/research/2026-09-30-adoption/SWARM-PROMPT-ADOPTION.md
 | A-119b | A-119 opus review (REJECT on pre-existing holes, A-119 landed as a strict improvement): weakening still ends VERIFIED via (1) a helper file a base test imports (eq=()=>{}), (2) snapshot or fixture edits (__snapshots__/*.snap, tests/fixtures/*.json), (3) tests isTestFile (testmap.ts:51) does not recognise: __tests__/*.js, mocha test/*.js, cargo tests/*.rs, including rename to .bak. Also: verdictOf returns ALREADY_SATISFIED before the weakened downgrade when implement says already_done; package.json jest testPathIgnorePatterns and vite.config.ts test.exclude skip config detection. Fix: widen the seal.ts weakTests predicate to any changed/deleted base path under test/, tests/, __tests__/, __snapshots__/, fixtures dirs plus non-test files a base test imports; check weakened before the already_done early return; add vite.config and in-block jest keys to CFG detection | loki-ts/src/engine10/stages/seal.ts, verify.ts (CFG only), tests | HIGH | each repro gives not-VERIFIED; source-only fix and new test stay VERIFIED | rejected@2026-10-01T05:12Z | |
 | A-117 | FALSE VERIFIED IN `loki verify` (A-130 r2 opus reviewer): on a run whose events.jsonl was tampered (append, edit, truncate, delete), the run now ends FAILED (A-130) but the receipt on disk still says VERIFIED with no tamper mark, because the worker sealed it before the supervisor detected the tamper; `loki verify` prints verdict: VERIFIED rc=0. Fix: record the tamper on the receipt via the registered receipt.addendum event (hash-chained) or have verify check the event log hash; verify must say TAMPERED and exit non-zero | loki-ts/src/engine10/verify_cmd.ts, supervisor.ts or seal.ts, tests | HIGH | tampered-log fixture: loki verify TAMPERED rc!=0 | released@2026-10-16T00:49Z | after A-130 (supervisor.ts); r2: opus REJECT, tail truncation erases post-seal tamper, fix = signed final log line |
 | A-118 | Exit-honest policy gap on the DEFAULT path (A-115 r2 finding): legacy `loki quick` prints `Evidence Receipt: NOT VERIFIED` yet exits rc 0 on a run whose target test was skipped; G1 exit-honest counts a skipped test as green, so it does not catch this. CTO call: should legacy quick exit non-zero on NOT VERIFIED when a relevant test was skipped/weakened, and should G1 count skipped as not-green? | autonomy/run.sh (quick exit path), scripts/first-run-gate.sh G1 | HIGH | skipped-target legacy run exits non-zero; G1 treats skipped as not green | released@2026-10-16T00:49Z | D47 decided: rc 3 on tests_integrity failed (skip added, runner config changed, test file deleted/renamed); assertion edits disclosed rc 0; G1 green needs pass 2 fail 0, 9b asserts rc 3. Files: proof-generator.py, run.sh after generate_proof_of_run, first-run-gate.sh, docs/exit-codes.md. Blocks promote of `latest`; built df404970, opus review |
-| A-112b | A-112 readability debt: subtractBase in verify.ts was folded to reach 4999 of 5000 core lines (9 lines over 200 chars, longest 347; un/progress/base-run loop each on one line). Unfold when A-150 frees budget; no behaviour change | loki-ts/src/engine10/stages/verify.ts | MEDIUM | budget test plus verify_prered unchanged | ready@2026-09-30T22:37Z | after A-150 |
+| A-112b | A-112 readability debt: subtractBase in verify.ts was folded to reach 4999 of 5000 core lines (9 lines over 200 chars, longest 347; un/progress/base-run loop each on one line). Unfold when A-150 frees budget; no behaviour change | loki-ts/src/engine10/stages/verify.ts | MEDIUM | budget test plus verify_prered unchanged | released v11.17.39 | after A-150 |
 | A-113b | A-110 opus notes on A-113: (1) under the CLI invoker (LOKI_E10_INVOKER=cli) the provider child stderr never reaches the fatal classifier (the *-impl.stderr.log is empty), so a credit/auth failure printed on plain stderr gives stop:null and burns the fix rounds; (2) machine.ts re-records the previous signature when a verify crashes, so a crashed verify counts toward a stall. Fix both in session.ts/machine.ts, with end-to-end tests through the real worker | loki-ts/src/engine10/session.ts, machine.ts, tests | HIGH | CLI stderr credit line stops fatal; crashed verify does not count as a stall repeat | released@2026-10-01T01:19Z | keep the A-110 escalated emit; the A-110 reviewer plugin probe is a good e2e template Released in v10.5.14 (merge 0377398d is an ancestor of v10.5.14). |
 | A-121 | v10 signs and verifies natively (item 3) | see plan A-121 | HIGH | first-run-gate assertion per plan card | released@2026-10-01T00:52Z | Wave per plan section 5; one writer per file. Released in v10.5.13 (merge 08b31271 is an ancestor of v10.5.13). |
 | A-122 | Delete the GPG signing layer (item 3, deletion) | see plan A-122 | HIGH | first-run-gate assertion per plan card | released@2026-10-01T00:52Z | Wave per plan section 5; one writer per file. Released in v10.5.13 (merge cb738c36 is an ancestor of v10.5.13). |
@@ -1009,10 +1009,10 @@ Source: ~/git/autonomi-dev/research/2026-09-30-adoption/SWARM-PROMPT-ADOPTION.md
 | TEN-DEPLOY-03 | Ship the provenance doc with the build and prove the live URL serves the verified SHA | autonomy/loki (_deploy_try_execute pre-exec and post-health blocks, _deploy_record live_binding field only), tests/test-deploy-receipt-gate.sh (new section), docs/WORKSPACES.md, CHANGELOG.md | HIGH | see Wall in note | ready@2026-10-17T01:40Z | SPLIT per CTO critic into (a) provenance file into deploy root per project type, (b) post-deploy live-binding probe; build as two commits or two agents. wave 3; depends: TEN-DEPLOY-01, TEN-DEPLOY-02. Goal: In _deploy_try_execute, after the gate passes and before the provider runs, write a signed .well-known/loki-provenance.json into the deploy root via `verify --sign-provenance`. The deploy root is public/ for nextjs and vite, the detected dist/ or build/ for static, and is refused with a reason for docker/python where no static root exists. Write it as an untracked build artifact so the dirty-tree gate is evaluated before it. After the deploy, probe <deployed_url>/.well-known/loki-provenance.json. Set live_binding=VERIFIED only when its head_sha equals the anchor. A mismatch gives FAILED_HEALTH exit 4 (stale or wrong build served). Update docs/WORKSPACES.md and replace 'deployed-SHA binding is not implemented' with what is now bound and what is not. Wall: RED: a stubbed vercel copies dist/ into a served dir and a python http.server serves it. On main, no provenance file exists and the record has no live_binding. GREEN: the file exists in dist/.well-known, live_binding=VERIFIED, and its head_sha equals git rev-parse HEAD. A stub that serves an older provenance gives FAILED_HEALTH exit 4. A docker project prints the refusal reason and records live_binding=unsupported, never VERIFIED. The dirty-tree gate still refuses a dirty tree before the file is written. MUTATION: compare against a constant instead of the anchor and the stale-serve case goes red. Gate: bash -n autonomy/loki && shellcheck -S warning autonomy/loki && bash tests/test-deploy-receipt-gate.sh && (cd loki-ts && bun test tests/engine10/verify_cmd.test.ts) Rules: FAILURE-CLASSES row first for any bug fix (D86); no CHANGELOG edits (Release Manager writes notes); DECISIONS numbers assigned by the Chief of Staff; reuse util/secure_scan.ts, the shared badge helper, keys_cmd export and the TS claude login probe instead of new copies; new CLI flags update autonomy/completions and the help-drift guard. |
 | TEN-DEPLOY-04 | Verified deploy badge from loki status --badge | loki-ts/src/commands/status.ts (renderLastDeploy plus --badge flag parse only), loki-ts/tests/commands/status.test.ts, CHANGELOG.md | MEDIUM | see Wall in note | released@2026-10-17T05:06Z | wave 4; depends: TEN-DEPLOY-01 (deployed_url field); live_binding from TEN-DEPLOY-03 is read if present, and its absence omits the badge. Goal: `loki status --badge` reads the newest loki.deploy/1 record (renderLastDeploy already loads it) and verifies it through the existing verify path. It prints a markdown shields badge linking to <deployed_url>/.well-known/loki-provenance.json. The message is 'deployed: verified' (brightgreen) ONLY when the record verifies and live_binding=VERIFIED. 'deployed: unverified' (red) is printed for TAMPERED or a failed health check. In all other cases the badge is omitted with a one-line reason. It never prints green from an unchecked field. The color mapping matches the share badge (autonomy/loki:38291), and no new vocabulary is added. Wall: RED: status.test.ts fixture with a signed healthy record, live_binding=VERIFIED and deployed_url. On main, --badge is unknown and no badge line is printed. GREEN: the badge line contains 'brightgreen' and deployed_url. A record with health FAILED_HEALTH gives a red badge. An unsigned record or a missing live_binding omits the badge and prints the reason. A record with no deployed_url omits the badge. MUTATION: drop the verify call and the unsigned case goes green, so the test goes red. Gate: cd loki-ts && bun test tests/commands/status.test.ts && bunx tsc --noEmit && bash tests/test-status-surface-agrees.sh Rules: FAILURE-CLASSES row first for any bug fix (D86); no CHANGELOG edits (Release Manager writes notes); DECISIONS numbers assigned by the Chief of Staff; reuse util/secure_scan.ts, the shared badge helper, keys_cmd export and the TS claude login probe instead of new copies; new CLI flags update autonomy/completions and the help-drift guard. |
 | TEN-DEPLOY-05 | loki deploy --env-file: push env to the provider with names-only records | autonomy/loki (cmd_deploy arg parse for --env-file, _deploy_try_execute env step, _deploy_record env_keys field only), tests/test-deploy-receipt-gate.sh (new section), autonomy/completions (loki deploy flag list only), CHANGELOG.md | HIGH | see Wall in note | released v11.17.35 | SPLIT per CTO critic into (a) env-file parser, .env.example check, masking, env_keys record, (b) four provider verbs; build as two commits or two agents. wave 4; depends: TEN-DEPLOY-03 (same function, serialized to avoid conflicts). Goal: `--env-file FILE` (with --execute only) parses KEY=VALUE with no shell eval. It refuses when a key in .env.example is missing from FILE, naming the keys. Env is applied through documented verbs only: Vercel `vercel --prod -e K=V` per key (args built as an array, never through the shell); Fly `fly secrets set --stage K=V ...` before `fly deploy`; Netlify `netlify env:import FILE`; Cloudflare `wrangler secret bulk FILE`. An unsupported provider refuses with nothing run. The record stores env_keys (names, sorted) and env_source; it NEVER stores values. Values never appear in stdout, the record or the printed 'Running:' line, where they are masked as K=***. Wall: RED: a recording vercel stub logs argv. On main, --env-file is ignored and no -e args appear. GREEN: argv has `-e API_URL=x -e TOKEN=s3cr3t`. Grepping stdout, stderr and the record for s3cr3t finds nothing; env_keys=[API_URL,TOKEN]. When .env.example lists DB_URL and the env file lacks it, the command refuses with rc 1, no stub calls and DB_URL named. A value with $(touch pwned) leaves no file named pwned. MUTATION: write values into the record and the secret-grep goes red. Gate: bash -n autonomy/loki && shellcheck -S warning autonomy/loki && bash tests/test-deploy-receipt-gate.sh && bash tests/test-completion-drift.sh (or whichever completion drift test the CHANGELOG cites) Rules: FAILURE-CLASSES row first for any bug fix (D86); no CHANGELOG edits (Release Manager writes notes); DECISIONS numbers assigned by the Chief of Staff; reuse util/secure_scan.ts, the shared badge helper, keys_cmd export and the TS claude login probe instead of new copies; new CLI flags update autonomy/completions and the help-drift guard. |
-| TEN-DEPLOY-06 | loki deploy --domain: attach a custom domain and prove TLS | autonomy/loki (cmd_deploy --domain parse and a post-health domain block in _deploy_try_execute, _deploy_record domain/tls fields only), tests/test-deploy-receipt-gate.sh (new section), CHANGELOG.md | MEDIUM | see Wall in note | ready@2026-10-17T01:40Z | wave 5; depends: TEN-DEPLOY-05 (same function, serialized). Goal: `--domain example.com` (with --execute) runs documented verbs after a healthy deploy: Vercel `vercel alias set <deployed_url> <domain>`; Fly `fly certs add <domain>`. Netlify and Cloudflare print the manual dashboard step and set domain_status=manual. Then a TLS proof runs: `openssl s_client -servername <domain> -connect <domain>:443` plus `openssl x509 -noout -enddate -checkend 604800`. It records domain, tls_status (valid/expiring/invalid/unchecked) and tls_not_after, and re-probes https://<domain>/.well-known/loki-provenance.json for the same head_sha. DNS not yet pointed gives tls_status=invalid and exit 6, with the DNS record the provider needs printed. It never claims valid without the openssl check. Wall: RED: vercel, openssl and curl are stubbed. On main, --domain is ignored. GREEN: the alias set argv is recorded, tls_status=valid and tls_not_after is set. An openssl stub that fails -checkend gives expiring. An openssl handshake failure gives invalid and exit 6. A netlify project gives domain_status=manual, no alias call, and tls still checked. No openssl on PATH gives unchecked, never valid. MUTATION: default tls_status to valid and the missing-openssl case goes red. Gate: bash -n autonomy/loki && shellcheck -S warning autonomy/loki && bash tests/test-deploy-receipt-gate.sh Rules: FAILURE-CLASSES row first for any bug fix (D86); no CHANGELOG edits (Release Manager writes notes); DECISIONS numbers assigned by the Chief of Staff; reuse util/secure_scan.ts, the shared badge helper, keys_cmd export and the TS claude login probe instead of new copies; new CLI flags update autonomy/completions and the help-drift guard. |
+| TEN-DEPLOY-06 | loki deploy --domain: attach a custom domain and prove TLS | autonomy/loki (cmd_deploy --domain parse and a post-health domain block in _deploy_try_execute, _deploy_record domain/tls fields only), tests/test-deploy-receipt-gate.sh (new section), CHANGELOG.md | MEDIUM | see Wall in note | released v11.17.38 | wave 5; depends: TEN-DEPLOY-05 (same function, serialized). Goal: `--domain example.com` (with --execute) runs documented verbs after a healthy deploy: Vercel `vercel alias set <deployed_url> <domain>`; Fly `fly certs add <domain>`. Netlify and Cloudflare print the manual dashboard step and set domain_status=manual. Then a TLS proof runs: `openssl s_client -servername <domain> -connect <domain>:443` plus `openssl x509 -noout -enddate -checkend 604800`. It records domain, tls_status (valid/expiring/invalid/unchecked) and tls_not_after, and re-probes https://<domain>/.well-known/loki-provenance.json for the same head_sha. DNS not yet pointed gives tls_status=invalid and exit 6, with the DNS record the provider needs printed. It never claims valid without the openssl check. Wall: RED: vercel, openssl and curl are stubbed. On main, --domain is ignored. GREEN: the alias set argv is recorded, tls_status=valid and tls_not_after is set. An openssl stub that fails -checkend gives expiring. An openssl handshake failure gives invalid and exit 6. A netlify project gives domain_status=manual, no alias call, and tls still checked. No openssl on PATH gives unchecked, never valid. MUTATION: default tls_status to valid and the missing-openssl case goes red. Gate: bash -n autonomy/loki && shellcheck -S warning autonomy/loki && bash tests/test-deploy-receipt-gate.sh Rules: FAILURE-CLASSES row first for any bug fix (D86); no CHANGELOG edits (Release Manager writes notes); DECISIONS numbers assigned by the Chief of Staff; reuse util/secure_scan.ts, the shared badge helper, keys_cmd export and the TS claude login probe instead of new copies; new CLI flags update autonomy/completions and the help-drift guard. |
 | TEN-DEPLOY-07 | loki github publish: receipt-stamped GitHub export from the CLI | autonomy/loki (cmd_github publish arm and its help line only), tests/test-github-publish.sh (new: no existing test owns cmd_github repo creation; test-proven-pr-check.sh covers PR checks only) plus its run-all-tests.sh registration and shard row, CHANGELOG.md | MEDIUM | see Wall in note | released@2026-10-17T03:50Z | merged efa201ffd (TL APPROVE 81346df2a) Shipped in npm 11.17.15 (latest+next) or 11.17.16 (Release run success on e3d445460). |
 | TEN-DEPLOY-08 | Web app deploy and GitHub push go through the gated CLI; no fabricated URLs | web-app/server.py (deploy_session ~5236-5336 and github_push_session ~5339-5395 only), web-app/tests/test_server.py (new cases), CHANGELOG.md | HIGH | see Wall in note | released v11.17.35 | SPLIT per CTO critic into (a) deploy_session, (b) github_push_session plus web-app url:null handling; build as two commits or two agents. wave 4; depends: TEN-DEPLOY-01 (deployed_url), TEN-DEPLOY-07 (github publish). Goal: Replace the bodies of deploy_session and github_push_session in web-app/server.py. Deploy runs `loki deploy --execute --dir <session_dir>` as an argv list with a timeout, then reads the newest <session>/.loki/deploys/*.json. It returns {url: deployed_url or null, health_status, live_binding, record_path, refused_reasons} and exits non-2xx on refusal. The platform param is kept as a hint only when it matches the CLI's detected provider; otherwise it returns 409 with the reason. GitHub push calls `loki github publish` (private default). Delete the hardcoded https://vercel.app, https://netlify.app and https://github.io fallbacks and the `git add -A` / `--public` path in the same change. Wall: RED: test_server.py with monkeypatched subprocess. On main, a deploy whose output has no URL returns url='https://vercel.app' (assert url is None fails), and no receipt gate is invoked. GREEN: the subprocess argv is [loki, deploy, --execute, --dir, <dir>]. A gate refusal returns 4xx with the reasons. A no-URL deploy returns url null. A github push argv contains `github publish` and never `add -A`. `grep -n 'https://vercel.app\/https://netlify.app\/"https://github.io"' web-app/server.py` exits 1. MUTATION: restore a fallback URL and the null-URL test goes red. Gate: python3 -m pytest web-app/tests/test_server.py -q && bash tests/moat/p7-no-fabricated-data.sh && bash tests/test-web-app-no-orphan-components.sh Rules: FAILURE-CLASSES row first for any bug fix (D86); no CHANGELOG edits (Release Manager writes notes); DECISIONS numbers assigned by the Chief of Staff; reuse util/secure_scan.ts, the shared badge helper, keys_cmd export and the TS claude login probe instead of new copies; new CLI flags update autonomy/completions and the help-drift guard. |
-| TEN-DEPLOY-09 | One-click from loki start and loki chat: pass the new deploy flags through | autonomy/loki (cmd_start _ps_ deploy parse block ~2625-2690 only), loki-ts/src/commands/start.ts (help string ~148-151 only), autonomy/lib/chat.sh (help line 53, system prompt line 6, _chat_deploy echo only), tests/test-help-start-flags.sh, docs/DEPLOYMENT.md, CHANGELOG.md | LOW | see Wall in note | building@2026-10-17T05:48Z | SPLIT per CTO critic into (a) start passthrough, (b) chat and docs text; build as two commits or two agents. wave 5; depends: TEN-DEPLOY-05, TEN-DEPLOY-06, TEN-DEPLOY-07. Goal: `loki start --deploy` passes --destination, --canary, --env-file, --domain and --github through to cmd_deploy. --github runs `loki github publish` after a successful deploy. Flag validation uses the existing _ps_ pattern (a value must not start with '-'). Bun-route start.ts help text lists them, and the PATH-slice divert keeps routing --deploy to bash. chat.sh `/deploy` help and _LOKI_CHAT_SYSTEM_PROMPT mention --domain, --env-file and `loki verify --url`, and the confirm prompt prints the full argv. docs/DEPLOYMENT.md gets one end-to-end 'brief to verified URL' section. Wall: RED: test-help-start-flags.sh asserts `loki start --help` lists --domain and --env-file, and a stubbed cmd_deploy recorder receives `--domain x.com --env-file .env` from `loki start --deploy --domain x.com --env-file .env`. It fails on main. GREEN: both pass. `--domain --env-file` (flag-shaped value) exits 2. A non-zero start exit still never deploys. MUTATION: drop the --domain forward and the recorder assertion goes red. Gate: bash -n autonomy/loki autonomy/lib/chat.sh && bash tests/test-help-start-flags.sh && (cd loki-ts && bun test tests/commands/start.test.ts && bunx tsc --noEmit) && bash tests/test-help-drift.sh Rules: FAILURE-CLASSES row first for any bug fix (D86); no CHANGELOG edits (Release Manager writes notes); DECISIONS numbers assigned by the Chief of Staff; reuse util/secure_scan.ts, the shared badge helper, keys_cmd export and the TS claude login probe instead of new copies; new CLI flags update autonomy/completions and the help-drift guard. |
+| TEN-DEPLOY-09 | One-click from loki start and loki chat: pass the new deploy flags through | autonomy/loki (cmd_start _ps_ deploy parse block ~2625-2690 only), loki-ts/src/commands/start.ts (help string ~148-151 only), autonomy/lib/chat.sh (help line 53, system prompt line 6, _chat_deploy echo only), tests/test-help-start-flags.sh, docs/DEPLOYMENT.md, CHANGELOG.md, completions/loki.bash, completions/_loki | LOW | see Wall in note | released v11.17.39 | SPLIT per CTO critic into (a) start passthrough, (b) chat and docs text; build as two commits or two agents. wave 5; depends: TEN-DEPLOY-05, TEN-DEPLOY-06, TEN-DEPLOY-07. Goal: `loki start --deploy` passes --destination, --canary, --env-file, --domain and --github through to cmd_deploy. --github runs `loki github publish` after a successful deploy. Flag validation uses the existing _ps_ pattern (a value must not start with '-'). Bun-route start.ts help text lists them, and the PATH-slice divert keeps routing --deploy to bash. chat.sh `/deploy` help and _LOKI_CHAT_SYSTEM_PROMPT mention --domain, --env-file and `loki verify --url`, and the confirm prompt prints the full argv. docs/DEPLOYMENT.md gets one end-to-end 'brief to verified URL' section. Wall: RED: test-help-start-flags.sh asserts `loki start --help` lists --domain and --env-file, and a stubbed cmd_deploy recorder receives `--domain x.com --env-file .env` from `loki start --deploy --domain x.com --env-file .env`. It fails on main. GREEN: both pass. `--domain --env-file` (flag-shaped value) exits 2. A non-zero start exit still never deploys. MUTATION: drop the --domain forward and the recorder assertion goes red. Gate: bash -n autonomy/loki autonomy/lib/chat.sh && bash tests/test-help-start-flags.sh && (cd loki-ts && bun test tests/commands/start.test.ts && bunx tsc --noEmit) && for t in tests/test-help-*.sh; do bash "$t" || exit 1; done Rules: FAILURE-CLASSES row first for any bug fix (D86); no CHANGELOG edits (Release Manager writes notes); DECISIONS numbers assigned by the Chief of Staff; reuse util/secure_scan.ts, the shared badge helper, keys_cmd export and the TS claude login probe instead of new copies; new CLI flags update completions/loki.bash and completions/_loki and every tests/test-help-*.sh guard (row fixed by CoS 2026-10-17: there is no autonomy/completions dir and no tests/test-help-drift.sh). |
 | TEN-ADOPTION-01 | Tour shows a receipt you can actually verify offline | autonomy/loki (cmd_demo offline branch only, ~15927-15965); skills/fixtures/demo-receipt/ (add receipt.json, the event log the log_seal check reads, pubkey.jwk; update README.md); tests/cli/test-tour-verify.sh (new: no test owns tour today, and test-proof-command.sh covers the legacy proof store) | MEDIUM | see Wall in note | released v11.17.33 | wave 3; depends: none (the fixture must come from a real sealed run; see not_codeable). Goal: `loki tour` (and `loki demo --offline`) runs the real Bun verifier against a bundled engine10 receipt.json, its event log and a public JWK, and prints VERIFIED. It then flips one byte in a copy under a run-owned temp dir and prints TAMPERED. It stays offline, needs no key and spends nothing. When Bun is absent it prints the exact verify command instead of claiming a result. The display-only disclaimer at autonomy/loki:15953-15957 goes away (the replaced text is deleted). Wall: Red first: the new test asserts the tour stdout contains VERIFIED from the verifier, and TAMPERED for the byte-flipped copy, with rc 0. On main it fails because the stdout says 'for display only'. Mutations: (a) point the tour at a receipt with one changed field: the test must see TAMPERED, not VERIFIED; (b) remove pubkey.jwk: the tour must say UNCHECKED or the verify-command fallback, never VERIFIED; (c) hide bun from PATH: output has the command and no verdict. Gate: bash tests/cli/test-tour-verify.sh && bash tests/test-help-discoverability.sh && bash scripts/local-ci.sh. Register the new test in tests/run-all-tests.sh and its shard. Rules: FAILURE-CLASSES row first for any bug fix (D86); no CHANGELOG edits (Release Manager writes notes); DECISIONS numbers assigned by the Chief of Staff; reuse util/secure_scan.ts, the shared badge helper, keys_cmd export and the TS claude login probe instead of new copies; new CLI flags update autonomy/completions and the help-drift guard. |
 | TEN-ADOPTION-02 | Portable receipt bundle builder | loki-ts/src/util/receipt_bundle.ts (new: no existing module packages a receipt for third-party verify, and engine10/verify_cmd.ts is core at its line budget); loki-ts/tests/util/receipt_bundle.test.ts (new, beside the existing util tests) | HIGH | see Wall in note | released@2026-10-17T03:50Z | TL APPROVE bb4957e90, merged for v11.17.14 Shipped in npm 11.17.15 (latest+next) or 11.17.16 (Release run success on e3d445460). |
 | TEN-ADOPTION-03 | proof bundle/badge/share work for loki start (engine10) runs | loki-ts/src/commands/proof.ts; loki-ts/tests/commands/proof_badge.test.ts; loki-ts/tests/commands/proof.test.ts | HIGH | see Wall in note | released@2026-10-17T04:08Z | v11.17.17; TL APPROVE 260474376, merged as clean cherry-pick 029bdd1a6 |
@@ -1127,26 +1127,59 @@ Source: ~/git/autonomi-dev/research/2026-09-30-adoption/SWARM-PROMPT-ADOPTION.md
 | TEN-DEPLOY-04-F1 | register --badge in dispatcher route, help, registry and completions | loki-ts/src/commands/run_status.ts, registry.ts, cli.ts, autonomy/loki, help-core.sh, completions | LOW | help-changelog drift and completions coverage pass; removing the route line turns the status test red | released@2026-10-17T05:34Z v11.17.24 | TL APPROVE 50579a177 |
 | TEN-COST-11-F1 | enhancement: direct test for the machine.ts wall-stage distrust call (TEN-COST-11 review follow-up) | loki-ts/tests/engine10/machine.test.ts | LOW | wall base run green while implement changed files must yield already_satisfied false and base_run unproven; red mutation: delete the distrustGreenBase call at machine.ts:221 turns the test red; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/machine.test.ts | released v11.17.37 | goal: pin the fail-closed branch (machine.ts:221) that has no direct test; test only, no src change |
 | TEN-COST-28 | feature: per-stage share of spend printed in the cost summary (plan, wall, implement, fix, xreview) with the top stage named | loki-ts/src/engine10/cost.ts, loki-ts/tests/engine10/cost.test.ts | MEDIUM | red: summary shows only a total; green: stage shares sum to 100 percent, unmetered stages say unmetered not 0; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/cost.test.ts | released v11.17.37 | goal: make the 2x cost proof attributable; grep cost.ts for an existing by-stage field first |
-| TEN-COST-29 | enhancement: flag a cache-cold stage (cache read under 30 percent of input) with one line in the cost breakdown | loki-ts/src/util/cost_breakdown.ts, loki-ts/tests/engine10/cost_unmetered.test.ts | LOW | red: a stage with 5 percent cache reads prints no hint; green: one 'cache cold: <stage>' line, none when all stages are warm or unmetered; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/cost_unmetered.test.ts | ready@2026-10-17T07:00Z | goal: surface the biggest cost lever (prefix cache hit) per run |
-| TEN-COST-30 | fix: an unknown cost.profile value in loki.yaml or --cost (for example 'leen') warns once and names the valid profiles instead of silently using default | loki-ts/src/util/cost_profile.ts, loki-ts/tests/util/cost_profile.test.ts | MEDIUM | red: 'leen' resolves to default with no message; green: one stderr warning naming lean and default, valid values unchanged and quiet mode keeps stdout clean; cd loki-ts && bunx tsc --noEmit && bun test tests/util/cost_profile.test.ts | ready@2026-10-17T07:00Z | goal: a typo must not forfeit the cost win silently; follows TEN-COST-27 |
+| TEN-COST-29 | enhancement: flag a cache-cold stage (cache read under 30 percent of input) with one line in the cost breakdown | loki-ts/src/util/cost_breakdown.ts, loki-ts/tests/engine10/cost_unmetered.test.ts | LOW | red: a stage with 5 percent cache reads prints no hint; green: one 'cache cold: <stage>' line, none when all stages are warm or unmetered; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/cost_unmetered.test.ts | released v11.17.38 | goal: surface the biggest cost lever (prefix cache hit) per run |
+| TEN-COST-30 | fix: an unknown cost.profile value in loki.yaml or --cost (for example 'leen') warns once and names the valid profiles instead of silently using default | loki-ts/src/util/cost_profile.ts, loki-ts/tests/util/cost_profile.test.ts | MEDIUM | red: 'leen' resolves to default with no message; green: one stderr warning naming lean and default, valid values unchanged and quiet mode keeps stdout clean; cd loki-ts && bunx tsc --noEmit && bun test tests/util/cost_profile.test.ts | released v11.17.38 | goal: a typo must not forfeit the cost win silently; follows TEN-COST-27 |
 | TEN-SPEED-03 | feature: run summary Time line names the slowest stage and its share of wall time | loki-ts/src/util/run_summary.ts, loki-ts/tests/util/run_summary.test.ts | LOW | red: Time line has total only; green: 'slowest: <stage> NN%' appended, omitted when stage durations are missing; cd loki-ts && bunx tsc --noEmit && bun test tests/util/run_summary.test.ts | released v11.17.37 | goal: speed work needs a visible per-run bottleneck |
-| TEN-SPEED-04 | enhancement: repo map and test map reused across fix rounds when the git tree hash is unchanged | loki-ts/src/engine10/cache.ts, loki-ts/tests/engine10/cache.test.ts | MEDIUM | red: second fix round rebuilds the map with identical tree; green: cache hit counted, miss when tree hash differs; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/cache.test.ts | ready@2026-10-17T07:00Z | goal: cut seconds per fix round; read cache.ts key first and skip if the tree hash is already in the key |
-| TEN-SPEED-05 | fix: back-to-back loki start runs reuse a successful claude login probe for 10 minutes instead of re-spawning the CLI every time | loki-ts/src/engine10/preflight.ts, loki-ts/tests/engine10/preflight.test.ts | MEDIUM | red: two starts inside 10 min spawn the probe twice; green: second reuses the result, a failed probe is never cached, TTL expiry re-probes; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/preflight.test.ts | ready@2026-10-17T07:00Z | goal: shave start latency without hiding a logged-out state |
+| TEN-SPEED-04 | enhancement: repo map and test map reused across fix rounds when the git tree hash is unchanged | loki-ts/src/engine10/cache.ts, loki-ts/tests/engine10/cache.test.ts | MEDIUM | red: second fix round rebuilds the map with identical tree; green: cache hit counted, miss when tree hash differs; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/cache.test.ts | released v11.17.38 | goal: cut seconds per fix round; read cache.ts key first and skip if the tree hash is already in the key |
+| TEN-SPEED-05 | fix: back-to-back loki start runs reuse a successful claude login probe for 10 minutes instead of re-spawning the CLI every time | loki-ts/src/engine10/preflight.ts, loki-ts/tests/engine10/preflight.test.ts | MEDIUM | red: two starts inside 10 min spawn the probe twice; green: second reuses the result, a failed probe is never cached, TTL expiry re-probes; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/preflight.test.ts | released v11.17.38 | goal: shave start latency without hiding a logged-out state |
 | TEN-QUALITY-13 | feature: cross-review (xreview) prompt carries the intent card Acceptance lines and the verdict names any line left unmet | loki-ts/src/engine10/stages/xreview.ts, loki-ts/tests/engine10/xreview.test.ts | MEDIUM | red: reviewer prompt omits acceptance lines; green: prompt includes them, verdict lists unmet lines, absent card keeps today's prompt byte-identical; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/xreview.test.ts | released v11.17.37 | goal: review checks what the user asked, not only the diff |
-| TEN-QUALITY-14 | enhancement: Wall authoring prompt requires one negative-case assertion (rejects bad input or fails before the fix) per acceptance line | loki-ts/src/engine10/stages/wall.ts, loki-ts/tests/engine10/wall.test.ts | MEDIUM | red: prompt has no negative-case rule; green: rule present, prompt size growth under 400 chars, existing wall tests green; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/wall.test.ts | ready@2026-10-17T07:00Z | goal: stronger Wall checks reject wrong implementations; wall.ts line budget applies (shrink-or-flat) |
-| TEN-QUALITY-15 | fix: fix rounds stop retrying the same model when the failing test set is identical two rounds in a row and escalate once | loki-ts/src/engine10/stages/fix.ts, loki-ts/tests/engine10/fix.test.ts | MEDIUM | red: identical failure signature loops on the same model to the round cap; green: escalates once then stops with a stalled reason; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/fix.test.ts | ready@2026-10-17T07:00Z | goal: stop wasted fix spend; grep stallClimb in unit_model.ts and reuse it, do not duplicate |
+| TEN-QUALITY-14 | enhancement: Wall authoring prompt requires one negative-case assertion (rejects bad input or fails before the fix) per acceptance line | loki-ts/src/engine10/stages/wall.ts, loki-ts/tests/engine10/wall.test.ts | MEDIUM | red: prompt has no negative-case rule; green: rule present, prompt size growth under 400 chars, existing wall tests green; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/wall.test.ts | released v11.17.38 | goal: stronger Wall checks reject wrong implementations; wall.ts line budget applies (shrink-or-flat) |
+| TEN-QUALITY-15 | fix: fix rounds stop retrying the same model when the failing test set is identical two rounds in a row and escalate once | loki-ts/src/engine10/stages/fix.ts, loki-ts/tests/engine10/fix.test.ts | MEDIUM | red: identical failure signature loops on the same model to the round cap; green: escalates once then stops with a stalled reason; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/fix.test.ts | released v11.17.38 | goal: stop wasted fix spend; grep stallClimb in unit_model.ts and reuse it, do not duplicate |
 | TEN-GATES-14 | feature: loki verify --explain lists each gate with exogenous or agent-influenced and the evidence it read | loki-ts/src/engine10/verify_cmd.ts, loki-ts/tests/engine10/verify_cmd.test.ts | HIGH | red: --explain is an unknown flag; green: one line per gate, exit code unchanged, --json carries the same fields; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/verify_cmd.test.ts | released v11.17.37 | goal: make the moat legible to buyers; read-only output, no verdict change |
 | TEN-GATES-15 | enhancement: Seal receipt records the seeded-defect corpus version and catch rate used for the ablation gate | loki-ts/src/engine10/stages/seal.ts, loki-ts/tests/engine10/seal_verify_roundtrip.test.ts | HIGH | red: receipt lacks corpus id; green: corpus version and rate in the signed payload and loki verify rejects a tampered value; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/seal_verify_roundtrip.test.ts | ready@2026-10-17T07:00Z | goal: tie the load-bearing claim to evidence; builds on TEN-GATES-12/13 (released) |
-| TEN-GATES-16 | fix: loki verify reports DRIFT, not OK, when HEAD moved after the seal and the changed paths overlap the sealed diff | loki-ts/src/util/seal_drift.ts, loki-ts/tests/engine10/log_seal.test.ts | HIGH | red: sealed run then an amend on a sealed path still verifies OK; green: DRIFT with the path named, unrelated commits keep OK; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/log_seal.test.ts | ready@2026-10-17T07:00Z | goal: a seal must not vouch for code it did not see; read seal_drift.ts first and extend it |
+| TEN-GATES-16 | fix: loki verify reports DRIFT, not OK, when HEAD moved after the seal and the changed paths overlap the sealed diff | loki-ts/src/util/seal_drift.ts, loki-ts/tests/engine10/log_seal.test.ts | HIGH | red: sealed run then an amend on a sealed path still verifies OK; green: DRIFT with the path named, unrelated commits keep OK; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/log_seal.test.ts | released v11.17.38 | goal: a seal must not vouch for code it did not see; read seal_drift.ts first and extend it |
 | TEN-UX-13 | feature: loki undo --dry-run prints the diffstat it would revert and changes nothing | loki-ts/src/commands/undo.ts, loki-ts/tests/commands/undo.test.ts | LOW | red: --dry-run unknown or applies the revert; green: diffstat printed, tree and HEAD unchanged, exit 0; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/undo.test.ts | released v11.17.37 | goal: safe undo; new test file because no existing test owns undo.ts (rollback.test.ts covers rollback.ts only) |
-| TEN-UX-14 | enhancement: loki queue list shows age and status columns and a count footer | loki-ts/src/commands/queue.ts, loki-ts/tests/commands/queue.test.ts | LOW | red: list prints ids only; green: id, age, status columns and 'N queued' footer, empty queue prints a next step; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/queue.test.ts | ready@2026-10-17T07:00Z | goal: queue is inspectable at a glance |
-| TEN-UX-15 | fix: shell completions list flags added after the completion table was written (--probe, --badge, --cost) from the registry | loki-ts/src/commands/completion.ts, loki-ts/tests/commands/cli_help_routes.test.ts | LOW | red: completion output lacks a registered flag; green: every flag in registry.ts appears for its command; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/cli_help_routes.test.ts | ready@2026-10-17T07:00Z | goal: no hand-maintained drift; derive from registry |
-| TEN-ADOPTION-11 | feature: loki trust prints a copyable README badge snippet for the last sealed run | loki-ts/src/commands/trust.ts, loki-ts/tests/commands/trust.test.ts | MEDIUM | red: no snippet; green: markdown snippet pointing at the verified badge, absent when no sealed run (prints the next step); cd loki-ts && bunx tsc --noEmit && bun test tests/commands/trust.test.ts | ready@2026-10-17T07:00Z | goal: every sealed repo advertises Loki; reuse the TEN-DEPLOY-04 badge output |
-| TEN-ADOPTION-12 | enhancement: after an upgrade the next loki start prints a one-line what-is-new once | loki-ts/src/util/update_check.ts, loki-ts/tests/util/update_check.test.ts | LOW | red: no notice after version change; green: one line once per version, none in quiet or CI mode; cd loki-ts && bunx tsc --noEmit && bun test tests/util/update_check.test.ts | ready@2026-10-17T07:00Z | goal: retention; no network call added |
+| TEN-UX-14 | enhancement: loki queue list shows age and status columns and a count footer | loki-ts/src/commands/queue.ts, loki-ts/tests/commands/queue.test.ts | LOW | red: list prints ids only; green: id, age, status columns and 'N queued' footer, empty queue prints a next step; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/queue.test.ts | released v11.17.38 | goal: queue is inspectable at a glance |
+| TEN-UX-15 | fix: shell completions list flags added after the completion table was written (--probe, --badge, --cost) from the registry | loki-ts/src/commands/completion.ts, loki-ts/tests/commands/cli_help_routes.test.ts | LOW | red: completion output lacks a registered flag; green: every flag in registry.ts appears for its command; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/cli_help_routes.test.ts | released v11.17.38 | goal: no hand-maintained drift; derive from registry |
+| TEN-ADOPTION-11 | feature: loki trust prints a copyable README badge snippet for the last sealed run | loki-ts/src/commands/trust.ts, loki-ts/tests/commands/trust.test.ts | MEDIUM | red: no snippet; green: markdown snippet pointing at the verified badge, absent when no sealed run (prints the next step); cd loki-ts && bunx tsc --noEmit && bun test tests/commands/trust.test.ts | released v11.17.38 | goal: every sealed repo advertises Loki; reuse the TEN-DEPLOY-04 badge output |
+| TEN-ADOPTION-12 | enhancement: after an upgrade the next loki start prints a one-line what-is-new once | loki-ts/src/util/update_check.ts, loki-ts/tests/util/update_check.test.ts | LOW | red: no notice after version change; green: one line once per version, none in quiet or CI mode; cd loki-ts && bunx tsc --noEmit && bun test tests/util/update_check.test.ts | released v11.17.38 | goal: retention; no network call added |
 | TEN-DEPLOY-11 | feature: loki rollback prints the provider rollback command (names only, no secrets) for the last deploy record | loki-ts/src/commands/rollback.ts, loki-ts/tests/commands/rollback.test.ts | MEDIUM | red: rollback ignores deploy records; green: prints provider command from the record, nothing when no record, no env values; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/rollback.test.ts | released v11.17.37 | goal: complete the deploy loop; read-only, never executes the provider command |
-| TEN-DEPLOY-12 | fix: loki status --probe retries once after 5 seconds before reporting a regression, so a cold start is not a false alarm | loki-ts/src/commands/status.ts, loki-ts/tests/commands/status.test.ts | MEDIUM | red: first 503 then 200 exits non-zero; green: retry passes exit 0, two failures exit non-zero, retry visible in output; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/status.test.ts | ready@2026-10-17T07:00Z | goal: stop false regressions; depends on TEN-DEPLOY-10 (released v11.17.33) |
+| TEN-DEPLOY-12 | fix: loki status --probe retries once after 5 seconds before reporting a regression, so a cold start is not a false alarm | loki-ts/src/commands/status.ts, loki-ts/tests/commands/status.test.ts | MEDIUM | red: first 503 then 200 exits non-zero; green: retry passes exit 0, two failures exit non-zero, retry visible in output; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/status.test.ts | released v11.17.38 | goal: stop false regressions; depends on TEN-DEPLOY-10 (released v11.17.33) |
 | TEN-STABILITY-11 | enhancement: run_pid detects a reused PID by comparing process start time and treats it as dead | loki-ts/src/util/run_pid.ts, loki-ts/tests/engine10/run_pid.test.ts | MEDIUM | red: unrelated live process with the recorded PID blocks a new run; green: start-time mismatch treated as stale; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/run_pid.test.ts | released v11.17.37 | goal: no phantom lock after reboot; never kill by name or pattern |
-| TEN-STABILITY-12 | fix: a truncated outbox entry left by a crash is quarantined and skipped, not fatal to the next start | loki-ts/src/util/outbox.ts, loki-ts/tests/util/outbox.test.ts | MEDIUM | red: half-written JSON entry throws on drain; green: entry moved to a quarantine name, the rest drain, one warning printed; cd loki-ts && bunx tsc --noEmit && bun test tests/util/outbox.test.ts | ready@2026-10-17T07:00Z | goal: crash-safe delivery |
-| TEN-SECURITY-01 | feature: the pre-PR secure scan also matches provider keys (sk-ant, AIza, xox[bp]-, ghp_) in added lines and blocks with the file and line | loki-ts/src/util/secure_scan.ts, loki-ts/tests/util/secure_scan.test.ts | HIGH | red: fixture with a runtime-built sk-ant key passes the scan; green: blocked naming file:line without echoing the secret, clean diff passes; cd loki-ts && bunx tsc --noEmit && bun test tests/util/secure_scan.test.ts | ready@2026-10-17T07:00Z | goal: no leaked key in a Loki PR; fixtures build keys at runtime (gitleaks rule); grep first, extend patterns only |
-| TEN-SECURITY-02 | fix: redact() strips URL userinfo (https://user:pass@host) and Authorization headers from logged and receipted output | loki-ts/src/util/redact.ts, loki-ts/tests/util/redact.test.ts | HIGH | red: https://u:p@host survives redact; green: userinfo replaced, plain URLs and existing redactions unchanged; cd loki-ts && bunx tsc --noEmit && bun test tests/util/redact.test.ts | ready@2026-10-17T07:00Z | goal: close a credential-in-log path; new test file because no existing test owns redact.ts |
-| TEN-GATES-17 | fix: a pre-existing test file the run edited must not count as agent-independent proof for loki verify --require-exogenous (reviewer finding on the n-key fix: status M edits keep provenance exogenous) | loki-ts/src/util/check_result.ts, loki-ts/tests/engine10/seal.test.ts | HIGH | red: a sealed run whose only passing check is a test file the run modified (status M, assertions weakened or replaced) passes --require-exogenous with rc 0; green: that check is advisory and --require-exogenous exits 4 while an untouched exogenous test still counts; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/seal.test.ts tests/engine10/verify_cmd.test.ts tests/engine10/budget.test.ts | ready@2026-10-17T06:55Z | Source: HIGH review of c958f563c. Grep checkProvenance and the A-119 edit rule first; decide whether to reuse the weakened-test detector instead of a blanket M rule, so legit test fixes stay exogenous. Record the call in DECISIONS.md if it changes D104. |
+| TEN-STABILITY-12 | fix: a truncated outbox entry left by a crash is quarantined and skipped, not fatal to the next start | loki-ts/src/util/outbox.ts, loki-ts/tests/util/outbox.test.ts | MEDIUM | red: half-written JSON entry throws on drain; green: entry moved to a quarantine name, the rest drain, one warning printed; cd loki-ts && bunx tsc --noEmit && bun test tests/util/outbox.test.ts | released v11.17.38 | goal: crash-safe delivery |
+| TEN-SECURITY-01 | feature: the pre-PR secure scan also matches provider keys (sk-ant, AIza, xox[bp]-, ghp_) in added lines and blocks with the file and line | loki-ts/src/util/secure_scan.ts, loki-ts/tests/util/secure_scan.test.ts | HIGH | red: fixture with a runtime-built sk-ant key passes the scan; green: blocked naming file:line without echoing the secret, clean diff passes; cd loki-ts && bunx tsc --noEmit && bun test tests/util/secure_scan.test.ts | released v11.17.38 | goal: no leaked key in a Loki PR; fixtures build keys at runtime (gitleaks rule); grep first, extend patterns only |
+| TEN-SECURITY-02 | fix: redact() strips URL userinfo (https://user:pass@host) and Authorization headers from logged and receipted output | loki-ts/src/util/redact.ts, loki-ts/tests/util/redact.test.ts | HIGH | red: https://u:p@host survives redact; green: userinfo replaced, plain URLs and existing redactions unchanged; cd loki-ts && bunx tsc --noEmit && bun test tests/util/redact.test.ts | released v11.17.38 | goal: close a credential-in-log path; new test file because no existing test owns redact.ts |
+| TEN-GATES-17 | fix: a pre-existing test file the run edited must not count as agent-independent proof for loki verify --require-exogenous (reviewer finding on the n-key fix: status M edits keep provenance exogenous) | loki-ts/src/util/check_result.ts, loki-ts/tests/engine10/seal.test.ts | HIGH | red: a sealed run whose only passing check is a test file the run modified (status M, assertions weakened or replaced) passes --require-exogenous with rc 0; green: that check is advisory and --require-exogenous exits 4 while an untouched exogenous test still counts; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/seal.test.ts tests/engine10/verify_cmd.test.ts tests/engine10/budget.test.ts | released v11.17.38 | Source: HIGH review of c958f563c. Grep checkProvenance and the A-119 edit rule first; decide whether to reuse the weakened-test detector instead of a blanket M rule, so legit test fixes stay exogenous. Record the call in DECISIONS.md if it changes D104. |
+| TEN-STABILITY-13 | P0 fix-forward: engine10 core is 5006 lines against the 5000 cap (budget.test.ts red on main since at least v11.17.35); bring core to 4950 or below without behavior change | loki-ts/src/engine10 (non-modernize) files only, plus the util or e10ext module that already owns any moved helper | MEDIUM | red: cd loki-ts && bun test tests/engine10/budget.test.ts fails with core is 5006 lines; green: same command passes with core at or below 4950, bun test tests/engine10 and bunx tsc --noEmit pass | released v11.17.38 | Move pure helpers out of the largest core files into the module that owns their concern (extend, never duplicate); delete dead code first; never squeeze lines by joining statements. Source: combined-tree run after v11.17.36. |
+| TEN-SECURITY-03 | fix: the bash secret scanners miss Anthropic keys (sk-ant-...) and the bash run_secure_scan applies the token rule only to browser-served files | autonomy/lib/secret-scan.sh, autonomy/verify.sh (secret pattern near 1177 and run_secure_scan only), the existing test that owns secret-scan.sh | HIGH | red: a runtime-built sk-ant key in a committed non-browser file passes both bash scanners; green: both report it by file and line without echoing the key, clean fixture passes; bash -n on both files plus the owning test | released v11.17.38 | Source: TEN-SECURITY-01 HIGH review (non-blocking item 5). Reuse one pattern list across both scripts if one already exists; fixtures build keys at runtime (gitleaks rule). |
+| TEN-STABILITY-14 | P0 fix-forward: four loki-ts/tests/util structural guards are red on main (model_output_regex_guard: wall.ts count mismatched after TEN-STABILITY-13 moved classifiers to util/check_result.ts; full_env_spawn_guard: doctor.ts mismatched and util/funnel.ts unlisted; registration_list_guard: stale commands/status.ts entry; start_flag_parity_guard: --cost undeclared) | the four allowlist or table files those guards load, plus the src file only when the honest fix is in code (for example funnel.ts spawning with the full env) | MEDIUM | red: cd loki-ts && bun test tests/util/model_output_regex_guard.test.ts tests/util/full_env_spawn_guard.test.ts tests/util/registration_list_guard.test.ts tests/util/start_flag_parity_guard.test.ts has 4 fails; green: 0 fails and bun test tests/util tests/engine10 has 0 fails | released v11.17.39 | Each allowlist entry needs a true reason; a full-env spawn in funnel.ts is fixed in code (allowlisted env) unless it is a documented passthrough. Three were red at ac43fb498 (v11.17.37). Source: combined-tree run before v11.17.38. |
+| TEN-COST-31 | feature: loki report kpis --since <Nd or YYYY-MM-DD> limits the iteration totals to a window and the human output names the window | loki-ts/src/commands/kpis.ts, loki-ts/src/metrics/kpis.ts, loki-ts/tests/commands/kpis.test.ts | MEDIUM | red: `loki report kpis --since 7d` exits 1 with unknown arg; green: iterations older than the window are excluded from cost and token totals, output says "since <date>", bad value exits 1; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/kpis.test.ts | ready@2026-10-17T08:05Z | Gap: grep -n -e '--since' loki-ts/src/commands/kpis.ts returned 0 hits; the flag loop at kpis.ts:66-80 accepts only --json and help. Engineer confirms the iteration file mtime or timestamp field in metrics/kpis.ts before filtering. |
+| TEN-COST-32 | enhancement: a BUDGET_STOP run's next line names the exact recovery (loki start --max-cost <higher> or the resume command) instead of the generic loki status | loki-ts/src/util/run_summary.ts, loki-ts/tests/util/run_summary.test.ts | LOW | red: nextOf for a BUDGET_STOP run returns "loki status"; green: next line contains "--max-cost" and the run id; cd loki-ts && bunx tsc --noEmit && bun test tests/util/run_summary.test.ts | ready@2026-10-17T08:05Z | Gap: run_summary.ts:62-67 returns "loki status" for every stopped result; grep -n 'max-cost' loki-ts/src/util/run_summary.ts returned 0 hits. Keep the change in util/ (engine10/output.ts is at the line cap): key on the outcome the summary input already carries. |
+| TEN-COST-33 | feature: loki queue run --max-total-cost <usd> stops the queue before the next item once cumulative spend reaches the cap and says so in the digest | loki-ts/src/commands/queue.ts, loki-ts/tests/commands/queue.test.ts, loki-ts/src/cli/registry.ts | MEDIUM | red: queue run has no total cap, a 3-item queue runs all 3 with injected spend 2 each and cap 3; green: stops after item 2, remaining items stay queued, digest line names the cap; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/queue.test.ts tests/cli/registry_guard.test.ts | ready@2026-10-17T08:05Z | Gap: grep -nE 'max-cost or total or spend' loki-ts/src/commands/queue.ts shows only the governor forecast (queue.ts:213-235); no cumulative cap. Serialize on queue.ts after TEN-STABILITY-15 and TEN-UX-16. |
+| TEN-COST-34 | enhancement: the run summary Spend line adds "of which $X on retries" when retry sessions cost money | loki-ts/src/util/run_summary.ts, loki-ts/tests/util/run_summary.test.ts | LOW | red: a summary input with retry_usd 0.40 prints no retry figure; green: Spend line ends with "($0.40 on retries)", nothing printed when retry_usd is 0 or null; cd loki-ts && bunx tsc --noEmit && bun test tests/util/run_summary.test.ts | ready@2026-10-17T08:05Z | Gap: costBreakdown computes retry_usd and retry_sessions (util/cost_breakdown.ts:17-43) and engine10/cost.ts:168 attaches it, but grep -rn retry_usd loki-ts/src outside cost_breakdown.ts returned 0 hits, so no reader. If the breakdown does not reach the summary input, thread it through spendText in run_summary.ts:166 only. |
+| TEN-SPEED-06 | enhancement: loki doctor runs its independent CLI version and network probes concurrently (Promise.all) so the report takes the slowest probe, not the sum | loki-ts/src/commands/doctor.ts, loki-ts/tests/commands/doctor.test.ts | MEDIUM | red: a test with three injected probes of 200ms each takes at least 600ms; green: under 350ms and the output order is unchanged; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/doctor.test.ts | ready@2026-10-17T08:05Z | Gap: grep -c 'spawnSync or execSync' loki-ts/src/commands/doctor.ts is 11 against 4 Promise.all uses. Output ordering must stay byte-identical (doctor_router and doctor_count tests). Do not touch claudeLoginProbeCached (TEN-SPEED-05). |
+| TEN-SPEED-07 | feature: fix-round verification runs the previously failing test files first (pytest --ff style, bun/vitest file order) and stops at first failure when the runner supports it | loki-ts/src/util/check_result.ts, loki-ts/src/e10ext/select.ts, loki-ts/tests/e10ext/select.test.ts | MEDIUM | red: fix-round test command is identical to the round-1 command; green: command lists last-round failing files first for bun test, pytest and jest, unchanged for unknown runners; cd loki-ts && bunx tsc --noEmit && bun test tests/e10ext/select.test.ts tests/util | ready@2026-10-17T08:05Z | Gap: grep -rnE 'failed.?first or lastFailed or --ff or --bail' loki-ts/src returned 0 hits. Engineer finds the verify command builder; if the only wiring point is inside engine10 core, land the pure helper in e10ext/ and wire with a net-zero line change. |
+| TEN-SPEED-08 | fix: back-to-back loki start runs reuse a successful gh auth status probe for 10 minutes like the Claude login probe | loki-ts/src/commands/doctor.ts, loki-ts/src/engine10/preflight.ts, loki-ts/tests/engine10/preflight.test.ts | MEDIUM | red: two checkPreflight calls with --pr spawn gh auth status twice; green: second call within 10 minutes spawns once, a failed probe is never cached; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10/preflight.test.ts tests/engine10 | ready@2026-10-17T08:05Z | Gap: engine10/preflight.ts:36-38 spawns gh --version and gh auth status on every PR run; TEN-SPEED-05 cached only claudeLoginProbeCached (preflight.ts:30). Put ghAuthProbeCached beside claudeLoginProbeCached in doctor.ts; preflight.ts may change by net zero lines (4949 of 5000 core cap). |
+| TEN-QUALITY-16 | feature: before the commit stage the run formats only its own changed files with the repo's own formatter when the repo already configures one (ruff format, prettier, gofmt, cargo fmt) | loki-ts/src/e10ext/commit_filter.ts, loki-ts/src/runner/repo_profile.ts, loki-ts/tests/e10ext/commit_filter_guard.test.ts | MEDIUM | red: a run that leaves an unformatted py file commits it unformatted; green: changed files are formatted, unchanged files untouched, no formatter config means no-op; cd loki-ts && bunx tsc --noEmit && bun test tests/e10ext tests/runner/harness_intelligence.test.ts | ready@2026-10-17T08:05Z | Gap: grep -rnE 'ruff format or prettier --write or eslint --fix or gofmt -w or cargo fmt' loki-ts/src returned 0 hits. Detect config only (pyproject [tool.ruff], .prettierrc, rustfmt.toml); never install a formatter. Reviewer PRs stay small because no unrelated reformat. |
+| TEN-QUALITY-17 | enhancement: a failing test that passes on one immediate rerun is classified flaky (not fail) so fix rounds are not spent on it | loki-ts/src/util/check_result.ts, loki-ts/tests/util/check_result.test.ts | MEDIUM | red: a check that fails then passes on rerun is classified fail; green: classified flaky with the rerun evidence, a deterministic fail stays fail; cd loki-ts && bunx tsc --noEmit && bun test tests/util | ready@2026-10-17T08:05Z | Gap: grep -nE 'rerun or re-run or retryOnce' loki-ts/src/util/check_result.ts returned 0 hits; the flaky label exists only for Playwright output (check_result.ts:162) and the summary renderer (run_summary.ts:192). A flaky result must never count as agent-independent proof. If no check_result.test.ts exists, add cases to the nearest test that imports it. |
+| TEN-QUALITY-18 | feature: a TypeScript repo with tsconfig.json and a typescript dependency but no typecheck script gets a tsc --noEmit typecheck command in the repo profile | loki-ts/src/runner/repo_profile.ts, loki-ts/tests/runner/harness_intelligence.test.ts | LOW | red: profile for such a repo has no typecheck command; green: entry "typecheck: <runner> tsc --noEmit" sourced from tsconfig.json, a script named typecheck still wins; cd loki-ts && bunx tsc --noEmit && bun test tests/runner/harness_intelligence.test.ts | ready@2026-10-17T08:05Z | Gap: repo_profile.ts:296 picks typecheck only from package scripts named typecheck, type-check or tsc, while Python gets a config-based mypy fallback at repo_profile.ts:311; grep -n tsconfig loki-ts/src/runner/repo_profile.ts returned 0 hits. |
+| TEN-GATES-18 | feature: Seal risk summary flags a dependency manifest change (package.json deps, pyproject deps, go.mod) with no matching lockfile change | loki-ts/src/util/check_result.ts, loki-ts/tests/util/check_result.test.ts | HIGH | red: diff touching package.json dependencies only produces no finding; green: advisory finding "manifest changed without lockfile", clean when both change or only scripts change; cd loki-ts && bunx tsc --noEmit && bun test tests/util tests/engine10 | ready@2026-10-17T08:05Z | Gap: check_result.ts:272 classifies lockfile paths and :312 flags deleted tests, but nothing pairs a manifest with its lockfile (grep -nE 'manifest.*lock' returned only the classifier). Advisory only, never turns a VERIFIED into a fail; needs FAILURE-CLASSES row. |
+| TEN-GATES-19 | feature: the signed receipt records the toolchain that ran the checks (bun, node, python3, git versions) so a verifier can see what produced the proof | loki-ts/src/util/composite_seal.ts, loki-ts/src/util/receipt_signer.ts, loki-ts/tests/engine10/seal_group.test.ts | HIGH | red: receipt payload has no toolchain field; green: receipt carries toolchain {bun,node,python3,git}, absent tools recorded as null, old receipts still verify; cd loki-ts && bunx tsc --noEmit && bun test tests/engine10 tests/util/receipt_bundle.test.ts | ready@2026-10-17T08:05Z | Gap: grep -rnE 'node_version or toolchain or bun_version or python_version' loki-ts/src/util loki-ts/src/engine10 returned 0 hits. Schema is additive and optional so verify of pre-existing receipts is unchanged; moat file set, two unanimous reviewers. |
+| TEN-GATES-20 | enhancement: secure-scan.py reports files_scanned and the Seal treats a scan of zero files as not_run instead of a clean pass | autonomy/lib/secure-scan.py, loki-ts/src/util/secure_scan.ts, loki-ts/tests/util/secure_scan.test.ts | HIGH | red: scanning an empty directory returns ok with total 0 and no file count; green: result carries summary.files_scanned, zero files yields not_run in the wrapper; cd loki-ts && bunx tsc --noEmit && bun test tests/util/secure_scan.test.ts && bash tests/test-secure-scan.sh | ready@2026-10-17T08:05Z | Gap: scan() at autonomy/lib/secure-scan.py:600-630 returns only rules_version, findings, summary.total and by_severity; grep -n 'files_scanned or scanned' loki-ts/src/util/secure_scan.ts returned 0 hits. Serialize with TEN-SECURITY-06/07 (same python file). |
+| TEN-UX-16 | feature: loki queue remove <issue...> and loki queue clear take items out of the queue | loki-ts/src/commands/queue.ts, loki-ts/src/cli/registry.ts, loki-ts/tests/commands/queue.test.ts | LOW | red: `loki queue remove 12` prints the usage error; green: remove drops the normalized ref and reports "N removed, M left", clear empties the file, missing ref exits 0 with "not queued"; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/queue.test.ts tests/cli/registry_guard.test.ts | ready@2026-10-17T08:05Z | Gap: runQueue dispatches only add, list, run (queue.ts:384-390) and registry.ts:174 declares the same three subcommands; grep -nE 'queue.*(remove or rm or clear)' loki-ts/src returned 0 hits. Serialize after TEN-STABILITY-15. |
+| TEN-UX-17 | feature: loki undo --list prints the recent runs that can be undone (run id, verdict, files changed, age) | loki-ts/src/commands/undo.ts, loki-ts/tests/commands/undo.test.ts | LOW | red: `loki undo --list` prints the usage text and exits 2; green: lists newest first from the runs dir, exits 0, empty state says "no runs to undo"; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/undo.test.ts | ready@2026-10-17T08:05Z | Gap: undo.ts:156 USAGE lists only --plan and --dry-run forms and :180 requires a run id; grep -rnE '"--list"' loki-ts/src/commands returned 0 hits. New test file only if grep -rl runUndo loki-ts/tests finds none. Read-only: no git writes. |
+| TEN-UX-18 | enhancement: loki doctor --quiet prints only failed and warned checks plus the summary footer | loki-ts/src/commands/doctor.ts, loki-ts/tests/commands/doctor.test.ts | LOW | red: doctor --quiet is rejected or prints every pass row; green: only non-pass rows and the footer, exit code unchanged, --json unaffected; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/doctor.test.ts | ready@2026-10-17T08:05Z | Gap: grep -nE 'quiet or -q\b' loki-ts/src/commands/doctor.ts returned 0 hits; the footer tally is at doctor.ts:1026. Update the usage text at doctor.ts:1052 and the start_flag_parity or help-drift guards if they list doctor flags. |
+| TEN-UX-19 | enhancement: loki start --help ends with three copyable examples (brief, PRD file, issue ref) | loki-ts/src/commands/start.ts, loki-ts/tests/commands/start.test.ts | LOW | red: start help text has no Examples section; green: help lists loki start "<brief>", loki start ./prd.md, loki start owner/repo#123 and the quick-start docs agree; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/start.test.ts tests/commands/cli_help_routes.test.ts | ready@2026-10-17T08:05Z | Gap: grep -nE 'Examples?:' loki-ts/src/commands/start.ts returned 0 hits. Check the bash help route (autonomy/help-core.sh) is not the one users reach; if it is, change the one that owns the text and keep the other byte-equal per the help-drift guard. |
+| TEN-ADOPTION-13 | feature: loki proof share --dry-run runs the secret scan and prints what would be published without publishing | loki-ts/src/commands/proof.ts, loki-ts/tests/commands/proof.test.ts | MEDIUM | red: `proof share <id> --dry-run` is treated as an unknown arg or publishes; green: prints the file list and scan verdict, publishes nothing, exit 0 clean and 1 when the scan blocks; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/proof.test.ts | ready@2026-10-17T08:05Z | Gap: grep -n 'dry' loki-ts/src/commands/proof.ts returned 0 hits; share dispatch is at proof.ts:890 and its token scan came from TEN-ADOPTION-03-F1. |
+| TEN-ADOPTION-14 | enhancement: loki proof list --json prints the proof index as machine-readable JSON | loki-ts/src/commands/proof.ts, loki-ts/tests/commands/proof.test.ts | LOW | red: `proof list --json` prints the text table; green: JSON array of {id, verdict, created} sorted newest first, text output unchanged; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/proof.test.ts | ready@2026-10-17T08:05Z | Gap: only show handles --json (proof.ts:47 and :149 args.includes("--json") inside show); the list arm at proof.ts:873 ignores it. Serialize after TEN-ADOPTION-13 (same file). |
+| TEN-ADOPTION-15 | enhancement: loki self-update --check also reports the installed version, the latest published version and whether an update is available | autonomy/loki, tests/test-self-update.sh | MEDIUM | red: --check prints only the detected package manager; green: also prints "installed X, latest Y, update available yes/no", offline prints "latest unknown" and exits 0; bash tests/test-self-update.sh | ready@2026-10-17T08:05Z | Gap: autonomy/loki:14665 and :14694 document --check as "Print detection result" only. Reuse the registry lookup already in loki-ts/src/util/update_check.ts:97 instead of a second fetch. If tests/test-self-update.sh does not exist, extend the test that owns cmd_self_update (grep -l self-update tests/*.sh). |
+| TEN-DEPLOY-13 | fix: loki status --probe reports a regression when the health URL redirects to a different host (login page, provider not-found page) even though the final status is 200 | loki-ts/src/commands/status.ts, loki-ts/tests/commands/status.test.ts | MEDIUM | red: probe of a URL that redirects to another host returning 200 prints "Deploy health OK"; green: prints a failure naming the final host and exits 1, same-host redirects (http to https, trailing slash) still pass; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/status.test.ts | ready@2026-10-17T08:05Z | Gap: status.ts:865 fetches with redirect follow and accepts 200-399 without comparing res.url to the recorded health_url host, so a redirect to a shared provider page reads healthy. |
+| TEN-DEPLOY-14 | feature: loki status --probe --json prints the probe result as one JSON object (url, ok, status, attempts, reason) | loki-ts/src/commands/status.ts, loki-ts/tests/commands/status.test.ts | LOW | red: --probe --json prints text lines; green: single JSON object, exit codes unchanged (0 healthy or nothing to probe, 1 regression); cd loki-ts && bunx tsc --noEmit && bun test tests/commands/status.test.ts | ready@2026-10-17T08:05Z | Gap: status.ts:1023-1031 parses --probe and the usage text allows --json only without --probe; probe output at status.ts:850-880 is text only. Serialize after TEN-DEPLOY-13 (same region). |
+| TEN-DEPLOY-15 | enhancement: loki doctor disk check measures the current repo directory and the temp directory volumes, not only the home directory | loki-ts/src/commands/doctor.ts, loki-ts/tests/commands/doctor.test.ts | LOW | red: checkDisk reads statfs of homedir only; green: result reports the minimum free GB across home, cwd and tmpdir and names which volume is low; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/doctor.test.ts | ready@2026-10-17T08:05Z | Gap: checkDisk at doctor.ts:353-365 calls statfsSync(homedir()) only; builds and worktrees write under cwd and tmpdir, which can be a separate full volume. Keep the DiskCheck JSON shape backwards compatible (add a field, do not rename). Serialize after TEN-SPEED-06 and TEN-UX-18 (same file). |
+| TEN-STABILITY-15 | fix: queue add on a corrupt queue file quarantines it and warns instead of silently overwriting every queued item | loki-ts/src/commands/queue.ts, loki-ts/tests/commands/queue.test.ts | MEDIUM | red: a truncated queue.json followed by queue add leaves a file holding only the new item; green: the bad file is renamed to queue.json.corrupt-<ts>, a warning is printed once, the new item is added to a fresh file; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/queue.test.ts | ready@2026-10-17T08:05Z | Gap: readQueue returns [] on any JSON error (queue.ts:79-86) and queueAdd then writeQueue overwrites (queue.ts:108-124). Same class as TEN-STABILITY-12 (outbox quarantine at util/outbox.ts:28-33); reuse that pattern and add the row to FAILURE-CLASSES.md. |
+| TEN-STABILITY-16 | enhancement: loki start sweeps stale temp files left by a killed atomic write (name.tmp.<deadpid>.<n>) older than 1 hour in the .loki state dirs | loki-ts/src/util/atomic.ts, loki-ts/tests/util/atomic.test.ts | MEDIUM | red: a leftover state.json.tmp.99999.1 with a dead pid stays forever; green: swept when pid is dead and mtime older than 1h, a live pid or fresh file is untouched, only exact tmp names matched; cd loki-ts && bunx tsc --noEmit && bun test tests/util | ready@2026-10-17T08:05Z | Gap: grep -rnE '\.tmp\.' loki-ts/src shows temp names created at util/atomic.ts:89 and run_control.ts:13 with no sweeper anywhere. Never glob outside .loki; reuse processStartTime or kill -0 from util/run_pid.ts for the liveness test; wire from a util/ entry point, not engine10 core. |
+| TEN-STABILITY-17 | feature: loki doctor lists orphan runs (a run dir whose owner process died before run.completed) with the resume or undo command for each | loki-ts/src/commands/doctor.ts, loki-ts/tests/commands/doctor.test.ts | MEDIUM | red: doctor ignores a run dir with a dead pid and no run.completed event; green: a warn row names the run id and "loki resume" or "loki undo", live and completed runs produce no row; cd loki-ts && bunx tsc --noEmit && bun test tests/commands/doctor.test.ts | ready@2026-10-17T08:05Z | Gap: runOwnerAlive (util/run_pid.ts:59) is consumed only by util/run_outputs.ts:156; grep -n runOwnerAlive loki-ts/src/commands/doctor.ts returned 0 hits. Warn level only, never fails doctor. Serialize after TEN-DEPLOY-15 (same file). |
+| TEN-SECURITY-04 | fix: redactSecrets also strips GitLab (glpat-), npm (npm_), Hugging Face (hf_), Stripe (sk_live_, rk_live_) tokens and PEM private key blocks | loki-ts/src/util/redact.ts, loki-ts/tests/util/redact.test.ts | HIGH | red: each of the five token shapes and a -----BEGIN PRIVATE KEY----- block survive redactSecrets; green: all replaced with [REDACTED:...] markers, existing rules and ordering unchanged; cd loki-ts && bunx tsc --noEmit && bun test tests/util/redact.test.ts | ready@2026-10-17T08:05Z | Gap: redact.ts RULES (lines 3-14) cover Anthropic, GitHub, Slack, AWS, JWT, Google, OpenAI, Bearer, URL userinfo; grep -rnE 'glpat or npm_ or hf_ or BEGIN [A-Z ]*PRIVATE or sk_live' loki-ts/src/util/redact.ts returned 0 hits (export_sarif.ts:18 and contrib/ai_bom.ts:83 know the shapes but are not the redactor). Specific rules before generic, keep ReDoS-safe quantifiers. |
+| TEN-SECURITY-05 | enhancement: redactSecrets strips secret query parameters (token, access_token, api_key, apikey, password, secret, sig) from URLs in logged and receipted output | loki-ts/src/util/redact.ts, loki-ts/tests/util/redact.test.ts | HIGH | red: https://h/x?access_token=abc123 survives; green: value replaced, parameter name and other params kept, non-secret params untouched; cd loki-ts && bunx tsc --noEmit && bun test tests/util/redact.test.ts | ready@2026-10-17T08:05Z | Gap: TEN-SECURITY-02 covers URL userinfo and Authorization only (redact.ts:12-13); grep -nE 'access_token or api_key or \?' loki-ts/src/util/redact.ts returned 0 query-string rules. Serialize after TEN-SECURITY-04 (same two files). |
+| TEN-SECURITY-06 | feature: secure-scan rule 6 flags disabled TLS verification in committed code (verify=False, rejectUnauthorized: false, InsecureSkipVerify: true, NODE_TLS_REJECT_UNAUTHORIZED=0) | autonomy/lib/secure-scan.py, tests/test-secure-scan.sh | HIGH | red: a fixture with requests.get(url, verify=False) scans clean; green: finding rule tls-verify-disabled with file and line, test and fixture paths and comments excluded like rule 4; bash tests/test-secure-scan.sh | ready@2026-10-17T08:05Z | Gap: secure-scan.py has rules 1-5 only (rule comments at lines 93, 105, 193, 238, 345); grep -nE 'verify=False or rejectUnauthorized or InsecureSkipVerify or NODE_TLS' autonomy/lib/secure-scan.py returned 0 hits. Bump RULES_VERSION (line 49). Serialize after TEN-GATES-20 and before TEN-SECURITY-07. |
+| TEN-SECURITY-07 | feature: secure-scan rule 7 flags shell injection shapes (subprocess with shell=True and an f-string or format argument, os.system with concatenation, child_process.exec with a template literal) | autonomy/lib/secure-scan.py, tests/test-secure-scan.sh | HIGH | red: subprocess.run(f"rm {x}", shell=True) scans clean; green: finding rule shell-injection with file and line, constant-string commands and test paths not flagged; bash tests/test-secure-scan.sh | ready@2026-10-17T08:05Z | Gap: grep -nE 'shell=True or os\.system or child_process' autonomy/lib/secure-scan.py returned 0 hits. Precision first (the file's stated design: literal forms only), measure false positives on this repo's own tests before shipping. Serialize after TEN-SECURITY-06. |

package/docs/v10/PROGRESS.md

@@ -2491,3 +2491,9 @@ v11.17.21 published (Release success on 462fbc40a; npm latest 11.17.21, next 11.
 
 ## 2026-10-17T07:20Z (CoS) v11.17.37
 - Wave AD released: TEN-COST-11-F1, TEN-COST-28, TEN-SPEED-03, TEN-QUALITY-13, TEN-GATES-14 (HIGH), TEN-UX-13, TEN-DEPLOY-11 (7 APPROVE, merged clean, merged-ad.txt). TEN-STABILITY-11 already shipped (run_pid.ts verifyRunPid). TEN-SECURITY-01 BLOCK 13bec58ff after fix round. Combined tree: bun test tests/engine10 had 1 fail, the core size budget (core is 5006 lines, cap 5000), pre-existing at 18900e64d and b81a1012a; P0 fix-forward dispatched.
+
+## 2026-10-17T08:00Z (CoS) v11.17.38
+- Wave AE released: 17 APPROVE merged clean (merged-ae.txt), including P0 TEN-STABILITY-13 (core 4949 lines) and HIGH TEN-SECURITY-01/02/03, TEN-GATES-16/17. TEN-COST-30 and TEN-QUALITY-15 already shipped. TEN-DEPLOY-03 BLOCK eca0e17e0 and TEN-GATES-15 BLOCK 6f7591b8c re-dispatched. Combined tree: bun test tests/engine10 tests/util had 4 structural guard fails (3 pre-existing at ac43fb498: full_env_spawn, registration_list, start_flag_parity; 1 new: model_output_regex wall.ts count); P0 TEN-STABILITY-14 opened.
+
+## 2026-10-17T09:06Z (CoS) v11.17.39
+- Wave AF: TEN-STABILITY-14 (APPROVE f0a131549) and TEN-DEPLOY-09 (APPROVE 87fa1bbfb) merged; cd loki-ts && bun test tests/util: 382 pass, 0 fail on the merged tree. A-112b already shipped (bfd6b98d8). Q17-05b BLOCK 812d13e0c and Q18-03e BLOCK 0c0c7ef0c after a fix round; TEN-DEPLOY-03 and TEN-GATES-15 fix rounds never ran (CoS script bug: the review pointer did not start with BLOCK), re-dispatched.