loki-mode 11.17.22 → 11.17.24

package/SKILL.md

@@ -3,7 +3,7 @@ name: loki-mode
 description: An autonomous software factory that knows what it is supposed to deliver, and proves it did. Use when the user says Loki Mode or asks to build, fix or verify software autonomously.
 ---
 
-# Loki Mode v11.17.22
+# Loki Mode v11.17.24
 
 **Current entry points (Loki 10 engine):** `loki "<task>"`, `loki owner/repo#N` and `loki quick "<task>"` run the Loki 10 engine and end with a signed receipt (`loki verify`). `loki backlog owner/repo --all` runs many issues in parallel. Guide: `docs/v10/GUIDE.md`. The skill instructions below, and `loki start`, describe the previous bash loop. PRD-file starts (`loki start ./prd.md`) and the opencode provider still run on it until FC38-SWEEP ports them; the legacy-engine command and the LOKI_ENGINE switch remain removed. Prefer `loki owner/repo#N` for issues.
 
@@ -483,4 +483,4 @@ See `CHANGELOG.md` entries [7.5.7], [7.5.8], [7.5.13] for the per-fix list and r
 
 ---
 
-**v11.17.22 | [Autonomi](https://www.autonomi.dev/) flagship product | core skill**
+**v11.17.24 | [Autonomi](https://www.autonomi.dev/) flagship product | core skill**

package/VERSION

@@ -1 +1 @@
-11.17.22
+11.17.24

package/autonomy/lib/chat.sh

@@ -168,6 +168,81 @@ _chat_run_launch() {
     return 1
 }
 
+# Startup readiness: at most 3 lines, nothing when everything is ready.
+_chat_readiness() {
+    local p="${_CHAT_PROVIDER:-claude}" out="" t hint="" prov="" git_line=""
+    if ! command -v "$p" >/dev/null 2>&1; then
+        [ "$p" = "claude" ] || hint=" (or try /provider claude)"
+        prov="$p CLI not found$hint. Fix (same as loki doctor):"$'\n'"$(_loki_req_fix_line "$p")"
+    elif [ "$p" = "claude" ] && [ -z "${ANTHROPIC_API_KEY:-}" ]; then
+        t="$(command -v timeout 2>/dev/null || command -v gtimeout 2>/dev/null || true)"
+        if [ -n "$t" ]; then out="$("$t" 5 claude auth status 2>/dev/null)" || out=""; else out="$(claude auth status 2>/dev/null)" || out=""; fi
+        case "$out" in
+            *'"loggedIn"'*false*) prov="claude is logged out: claude login (or set ANTHROPIC_API_KEY)" ;;
+        esac
+    fi
+    if ! git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
+        if [ -z "$(ls -A 2>/dev/null)" ]; then
+            git_line="Empty folder: /run will set it up as a new project."
+        else
+            git_line="Not a git repo: /run needs git init in this folder first."
+        fi
+    fi
+    # Cap: provider block keeps at most 2 lines (3 total with the folder line).
+    if [ -n "$prov" ]; then
+        if [ -n "$git_line" ]; then printf '%s\n' "$prov" | head -n 2; else printf '%s\n' "$prov" | head -n 3; fi
+    fi
+    [ -z "$git_line" ] || printf '%s\n' "$git_line"
+    return 0
+}
+
+# Command names listed in _chat_help.
+_chat_command_names() {
+    _chat_help | sed -n 's/^  \(\/[a-z][a-z]*\)\([ ,].*\)\{0,1\}$/\1/p' | sort -u
+    echo /exit
+}
+
+# True when $1 and $2 differ by exactly one substitution, insertion or deletion.
+_chat_one_edit() {
+    local a="$1" b="$2" la=${#1} lb=${#2} i d=0 s l k=0
+    [ $(( la - lb )) -le 1 ] && [ $(( lb - la )) -le 1 ] || return 1
+    if [ "$la" -eq "$lb" ]; then
+        for (( i = 0; i < la; i++ )); do [ "${a:i:1}" = "${b:i:1}" ] || d=$((d + 1)); done
+        [ "$d" -eq 1 ]
+        return
+    fi
+    if [ "$la" -lt "$lb" ]; then s="$a"; l="$b"; else s="$b"; l="$a"; fi
+    while [ "$k" -lt "${#s}" ] && [ "${s:k:1}" = "${l:k:1}" ]; do k=$((k + 1)); done
+    [ "${s:k}" = "${l:k+1}" ]
+}
+
+# Suggest a command for an unknown slash command: unique prefix first, else a unique single-edit match.
+_chat_suggest() {
+    local cmd="$1" c hit="" n=0 names
+    names="$(_chat_command_names)"
+    [ "${#cmd}" -ge 3 ] || return 0
+    while IFS= read -r c; do
+        case "$c" in "$cmd"?*) hit="$c"; n=$((n + 1)) ;; esac
+    done <<EOF2
+$names
+EOF2
+    if [ "$n" -eq 1 ]; then echo "$hit"; return 0; fi
+    n=0; hit=""
+    while IFS= read -r c; do
+        if _chat_one_edit "$cmd" "$c"; then hit="$c"; n=$((n + 1)); fi
+    done <<EOF2
+$names
+EOF2
+    if [ "$n" -eq 1 ]; then echo "$hit"; fi
+    return 0
+}
+
+# Provider failed to load: show the doctor fix line instead of a bare error.
+_chat_load_fail() {
+    echo "loki chat: cannot load provider $1. Fix (same as loki doctor):" >&2
+    _loki_req_fix_line "$1" >&2
+}
+
 # Run a delegate without letting a non-zero exit end the session (autonomy/loki runs under set -e).
 _chat_do() { local _rc=0; "$@" || _rc=$?; [ "$_rc" -eq 0 ] || echo "(exit $_rc)"; return 0; }
 
@@ -256,7 +331,7 @@ _chat_send() {
         (
             # shellcheck disable=SC1091
             source "${_LOKI_SCRIPT_DIR:-.}/../providers/loader.sh" 2>/dev/null || exit 1
-            load_provider "$_CHAT_PROVIDER" >/dev/null 2>&1 || { echo "loki chat: cannot load provider $_CHAT_PROVIDER" >&2; exit 1; }
+            load_provider "$_CHAT_PROVIDER" >/dev/null 2>&1 || { _chat_load_fail "$_CHAT_PROVIDER"; exit 1; }
             provider_invoke "$prompt"
         )
         return $?
@@ -268,7 +343,7 @@ _chat_send() {
     (
         # shellcheck disable=SC1091
         source "${_LOKI_SCRIPT_DIR:-.}/../providers/loader.sh" 2>/dev/null || exit 1
-        load_provider "$_CHAT_PROVIDER" >/dev/null 2>&1 || { echo "loki chat: cannot load provider $_CHAT_PROVIDER" >&2; exit 1; }
+        load_provider "$_CHAT_PROVIDER" >/dev/null 2>&1 || { _chat_load_fail "$_CHAT_PROVIDER"; exit 1; }
         case "$_CHAT_PROVIDER" in
             codex) codex exec --sandbox read-only --skip-git-repo-check "$prompt" < /dev/null ;;
             opencode) opencode run --agent plan --model "$PROVIDER_MODEL_DEVELOPMENT" "$prompt" < /dev/null ;;
@@ -398,6 +473,7 @@ cmd_chat() {
     _CHAT_STARTED=0
     local attached=0
     echo "Loki chat (provider: $_CHAT_PROVIDER). /help for commands, /exit to quit."
+    _chat_readiness
     _chat_memory_context "$loki"
     if [ "$attach" = "1" ]; then _chat_attach_banner && attached=1; fi
     while true; do
@@ -480,7 +556,9 @@ Question: $line" || true
                     claude|codex|cline|aider|opencode) _CHAT_PROVIDER="$rest"; _CHAT_STARTED=0; echo "provider: $rest" ;;
                     *) echo "usage: /provider claude|codex|cline|aider|opencode (now: $_CHAT_PROVIDER)" ;;
                 esac ;;
-            *) echo "unknown command: $cmd (try /help)" ;;
+            *)
+                local _sg; _sg="$(_chat_suggest "$cmd")"
+                if [ -n "$_sg" ]; then echo "unknown command: $cmd (did you mean $_sg?)"; else echo "unknown command: $cmd (try /help)"; fi ;;
         esac
     done
     return 0

package/autonomy/lib/help-core.sh

@@ -19,7 +19,7 @@ help_core_screen() {
     echo "  quick \"<task>\"   One small task, no PR"
     echo ""
     echo "Check:"
-    echo "  status [--json]  What is running and where it stands"
+    echo "  status [--json|--badge]  What is running and where it stands"
     echo "  verify [--json]  Deterministic verification (CI-gate exit codes)"
     echo "  receipt          Inspect the proof-of-run receipt (alias of: proof)"
     echo "  diff / undo      See what a run changed; undo <run> to plan or apply a rollback"

package/autonomy/loki

@@ -1838,7 +1838,7 @@ show_help_all() {
     echo "  quickstart [idea]  Guided first build: setup, idea, template, plan, go"
     echo ""
     echo "Session:"
-    echo "  status [--json]  Show current status (--json for machine-readable)"
+    echo "  status [--json|--badge]  Show current status (--json machine-readable, --badge deploy badge)"
     echo "  next             Run the right next step for you (resume / ship / why)"
     echo "  stop             Stop execution immediately"
     echo "  pause            Pause after current session"
@@ -6553,10 +6553,11 @@ cmd_status() {
     while [[ $# -gt 0 ]]; do
         case "$1" in
             --json) cmd_status_json; return $? ;;
-            --help|-h) echo "Usage: loki status [--json]"; return 0 ;;
+            --badge) echo "loki status --badge requires the Bun CLI (loki-ts); not available on the bash fallback" >&2; return 1 ;;
+            --help|-h) echo "Usage: loki status [--json|--badge]"; return 0 ;;
             *)
                 echo -e "${RED}Unknown flag: $1${NC}"
-                echo "Usage: loki status [--json]"
+                echo "Usage: loki status [--json|--badge]"
                 return 1
                 ;;
         esac

package/autonomy/telemetry.sh

@@ -201,7 +201,7 @@ _loki_known_blocker() {
         # single most common post-install failure unactionable in the data --
         # and it is the worst-placed one, since without this the user only learns
         # of it after confirming the spend.
-        no_provider|not_logged_in|node|python3|jq|git|curl|disk|skill_symlink)
+        no_provider|not_logged_in|not_a_repo|git_identity|node|python3|jq|git|curl|disk|skill_symlink)
             printf '%s' "$1" ;;
         *)
             printf 'other' ;;
@@ -368,3 +368,15 @@ loki_emit_build_verified() {
     loki_telemetry "build_verified" "${_args[@]}"
     return 0
 }
+
+# loki_emit_build_verified_enum <headline> <route>: build_verified for the
+# default engine10 route, which has no proof.json reader. Enum args only:
+# anything but headline=VERIFIED and route=engine10 sends nothing. Same strict
+# analytics gate as loki_emit_build_verified.
+loki_emit_build_verified_enum() {
+    _loki_analytics_enabled || return 0
+    [ "${1:-}" = "VERIFIED" ] || return 0
+    [ "${2:-}" = "engine10" ] || return 0
+    loki_telemetry "build_verified" "headline=VERIFIED" "route=engine10"
+    return 0
+}

package/completions/_loki

@@ -66,6 +66,7 @@ function _loki {
                 status)
                     _arguments \
                         '--json[Output machine-readable JSON]' \
+                        '--badge[Print verified deploy badge]' \
                         '--help[Show help]'
                     ;;
                 doctor)

package/completions/loki.bash

@@ -130,7 +130,7 @@ _loki_completion() {
 
         status)
             if [[ "$cur" == -* ]]; then
-                COMPREPLY=( $(compgen -W "--json --help" -- "$cur") )
+                COMPREPLY=( $(compgen -W "--json --badge --help" -- "$cur") )
                 return 0
             fi
             ;;

package/dashboard/__init__.py

@@ -7,6 +7,6 @@ Modules:
     control: Session control helpers (status, atomic writes, origin check)
 """
 
-__version__ = "11.17.22"
+__version__ = "11.17.24"
 
 __all__ = ["__version__"]

package/docs/CLI-REFERENCE.md

@@ -1,6 +1,6 @@
 # CLI reference
 
-Generated from `loki-ts/src/cli/registry.ts` by `scripts/generate-stale-zero.sh` for v11.17.22. Do not edit by hand.
+Generated from `loki-ts/src/cli/registry.ts` by `scripts/generate-stale-zero.sh` for v11.17.24. Do not edit by hand.
 Hidden and legacy-only commands are omitted; see `docs/v10/CLI-MODERN.md` for the full inventory.
 
 | Command | Description |

package/docs/INSTALLATION.md

@@ -2,7 +2,7 @@
 
 Loki Mode, by [Autonomi](https://www.autonomi.dev/), turns a spec or an issue into a verified pull request with a receipt you can check. This page covers installing it, a first run, and the options around it.
 
-**Version:** v11.17.22
+**Version:** v11.17.24
 
 **Engine note:** `loki start` is the primary command. `loki start`, `loki "<task>"`, `loki owner/repo#N` and `loki quick` all run the Loki 10 engine, whatever the flag order or input form (PRD file, issue ref, task or one-word brief). The previous loop runs only on `--engine legacy`, `LOKI_ENGINE=legacy`, or for one call when a flag Loki 10 cannot honor is present. See the [user guide](v10/GUIDE.md) and the [5-minute quickstart](QUICKSTART.md).
 

package/docs/v10/BOARD.md

@@ -1040,19 +1040,19 @@ Source: ~/git/autonomi-dev/research/2026-09-30-adoption/SWARM-PROMPT-ADOPTION.md
 | TEN-QUALITY-09 | Offline localization-recall eval on the pinned SWE-bench subset | benchmarks/swebench/loader.py, benchmarks/bench/tests/ (extend the existing loader test file there; grep for its current name before adding) | LOW | see Wall in note | released@2026-10-17T03:50Z | TL APPROVE db3196348. wave 1; depends: none. Goal: benchmarks/swebench/loader.py gains gold_files(patch), which parses the paths in the gold patch's diff headers, and a `localization` subcommand. For each pinned instance with a checkout at $LOKI_SWEBENCH_REPOS/<repo>@<base_commit>, it runs `bun -e` importing buildRepoMap and selectRelevantFiles from loki-ts/src. It writes recall@8 and recall@20 JSON with per-instance hits. An instance without a checkout is listed as skipped with its reason, never scored 0. Offline only, with no network. This gives TEN-QUALITY-04/05 a before/after number versus E-98d's 4/7, and gives TEN-QUALITY-08's paid A/B a pre-registered harness to run through the existing claude_code and loki adapters. Wall: Red first: gold_files on a recorded 2-file patch returns both paths and ignores /dev/null. The localization command on a temp git repo fixture plus a stub instance gives recall@8 = 1.0 when the gold file is named in the problem statement. A missing checkout appears as skipped with recall None, never 0. Mutation: count skipped as 0 and the skip test goes red. Gate: cd /Users/lokesh/git/lokimode-anthropic && python3 -I -m pytest benchmarks/bench/tests -q && bash scripts/local-ci.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. Shipped in npm 11.17.15 (latest+next) or 11.17.16 (Release run success on e3d445460). |
 | TEN-UX-01 | Empty-folder first run: loki start "<brief>" sets up a repo and checks Claude login before any spend | loki-ts/src/util/first_run_repo.ts (new; justification: no existing module owns setting up an empty folder as a repo, and core has about 36 lines left so the logic cannot live in preflight.ts); loki-ts/src/engine10/preflight.ts (call the helper and the login check, net +3 lines max); loki-ts/src/commands/doctor.ts (export claudeAuthStatusLoggedIn only, and let it take an argv/env so preflight reuses it; no second parser); loki-ts/tests/engine10/preflight.test.ts; docs/v10/FAILURE-CLASSES.md (row first) | MEDIUM | see Wall in note | released@2026-10-17T05:06Z | SPLIT per CTO critic into (a) empty folder becomes a repo, (b) Claude login check in preflight plus doctor export; build as two commits or two agents. wave 2; depends: none. Goal: In an empty folder with no git repo, `loki start "<brief>"` runs git init -q, sets the default branch to main and makes an empty initial commit, then continues. It prints one line: `initialized a new git repository in <dir> (LOKI_AUTO_GIT_INIT=0 to refuse)`. A folder that is not empty and has no repo is never initialised automatically: it stays fatal, and the message gives the exact commands (git init && git add . && git commit -m init). A missing git identity stays fatal with the exact git config command; the identity is never set automatically. When the provider is claude and no ANTHROPIC_API_KEY or CLAUDE_CODE_OAUTH_TOKEN is set, preflight runs `claude auth status` (5s timeout, using the run env's PATH and LOKI_CLAUDE_CLI). A clear loggedIn:false is fatal and names the fix `claude login (or set ANTHROPIC_API_KEY)`. An unknown or empty answer is a warning only, never fatal, so a stub CLI still works. Wall: Red first: preflight.test.ts gains cases that fail on main today: (a) empty temp folder, no repo: checkPreflight returns fatal null, the folder now has .git and HEAD resolves; (b) folder holding one file, no repo: fatal contains `git init && git add . && git commit -m init`, and no .git is created; (c) LOKI_AUTO_GIT_INIT=0 on an empty folder: still fatal, no .git; (d) a fake claude on PATH printing {"loggedIn":false} gives a fatal containing `claude login`; (e) fake printing {} or exiting 1 gives fatal null plus one warning; (f) ANTHROPIC_API_KEY set: the fake claude is never called (it writes a marker file; assert the file is absent). Mutations: (1) drop the emptiness check, so case (b) must go red; (2) treat the unknown login answer as fatal, so case (e) must go red; (3) delete the export in doctor.ts, so the build/typecheck must go red. Gate: cd loki-ts && bun test tests/engine10/preflight.test.ts tests/engine10/budget.test.ts tests/commands/doctor.test.ts && bun test && bunx tsc --noEmit; then bash scripts/local-ci.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-UX-02 | Failure-specific Next line: every failed start names the exact fix | loki-ts/src/util/run_summary.ts (nextOf only); loki-ts/src/engine10/supervisor.ts (line 393 argument only; rebase after Q18-07 if it lands first); loki-ts/tests/util/run_summary.test.ts | LOW | see Wall in note | released@2026-10-17T02:57Z | merge 63cdd70ec, dist bd6348d77; TL APPROVE f450cf65f (94 pass, 2 mutations red); post-merge tsc 0 errors, 130 pass. wave 1; depends: none (rebase onto Q18-07 if supervisor.ts:313 moved). Goal: nextOf takes the run's reason and outcome and returns one concrete command per failure class: provider authentication failed -> `claude login` (or that provider's fix line from setup-requirements.json via requirementFix); provider credit exhausted -> `loki start ... --provider <other>` or check billing; '<check> failed: ...' -> `loki chat --attach` (ask why) plus `loki undo` when files changed; spec conflict (BLOCKED) -> `loki answer --text "..."`; STALLED -> `loki chat --attach`; engine ended before sealing a receipt -> `loki doctor`. The existing verified, done-unverified and budget branches stay byte-identical. The supervisor call site passes res.reason on the same line, with zero net core lines. Wall: Red first: run_summary.test.ts adds one table row per reason string that output.ts:74 reasonOf really produces (copy the literals, do not paraphrase), each asserting the exact Next command. These fail today because nextOf returns loki doctor/loki undo. A pin asserts the old outputs for verified, done-unverified, stopped and failed-without-reason, so default output does not drift. A source-scan test asserts every literal reason produced at output.ts:74 has a nextOf mapping (catches new reasons with no mapping). Mutation: make nextOf ignore the reason argument, so every new row must go red; remove the supervisor argument, so a contract test in tests/features/contract.test.ts that runs the summary with fatal:auth must go red. Gate: cd loki-ts && bun test tests/util/run_summary.test.ts tests/features/contract.test.ts tests/engine10/budget.test.ts && bun test && bunx tsc --noEmit 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. v11.17.13 npm next 11.17.13 |
-| TEN-UX-03 | Funnel on the default engine10 route: first_run_blocked at preflight and build_verified at seal | loki-ts/src/util/funnel.ts (new; justification: telemetry.sh is the owner and this file is the only TS bridge to it, replacing the private copy in doctor.ts); loki-ts/src/commands/doctor.ts (emitFirstRunBlocked becomes a call to the helper; remove the spawn code); loki-ts/src/engine10/cli.ts (one call after main, at most +2 lines); autonomy/telemetry.sh (_loki_known_blocker keys and a loki_emit_build_verified_enum function); tests/test-first-run-funnel-coverage.sh | MEDIUM | see Wall in note | ready@2026-10-17T01:40Z | wave 3; depends: TEN-UX-01 (shares doctor.ts; also needs the not_a_repo fatal text to exist). Goal: Move the detached, opt-out-respecting telemetry.sh spawn from doctor.ts:1047-1069 into one TS helper (emitFunnel(kind, key)), and delete the copy in doctor.ts in the same change. Call it from engine10/cli.ts after the supervisor returns: preflight exit 2 sends first_run_blocked with a bounded key; a VERIFIED or ALREADY_SATISFIED exit sends build_verified carrying only headline=VERIFIED and route=engine10. No other field is sent. Add keys not_a_repo and git_identity to _loki_known_blocker (telemetry.sh:204), and add an allowlisted build_verified variant that takes enum args instead of a proof.json path. All existing opt-outs still apply because everything goes through _loki_analytics_enabled. Wall: Red first: test-first-run-funnel-coverage.sh gains (a) a wiring assertion that engine10/cli.ts reaches emitFunnel on a preflight exit 2 and on a VERIFIED exit, and (b) a run with a stub telemetry.sh in a throwaway HOME, analytics forced on, with no network: loki_telemetry is replaced by a recorder function. Assert that one first_run_blocked blocker=not_a_repo line is recorded for a start in a non-empty folder with no repo, and that a second identical run records nothing (once-per-install marker). Assert DO_NOT_TRACK=1 and LOKI_TELEMETRY_DISABLED=1 each record zero lines. Assert the recorded payload contains no path, home dir or brief text (grep the recorder file for the temp folder path and the brief: must be absent). Mutations: emit a raw blocker string instead of the enum, so the no-path assertion must go red; drop the marker write, so the second-run assertion must go red; leave doctor's old spawn copy in place, so a grep guard counting `telemetry.sh` spawns in loki-ts/src (exactly 1) must go red. Gate: bash tests/test-first-run-funnel-coverage.sh && bash tests/test-first-run-blocked-signal.sh && cd loki-ts && bun test tests/engine10/budget.test.ts tests/commands/doctor.test.ts && bun test; then bash scripts/local-ci.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-UX-03 | Funnel on the default engine10 route: first_run_blocked at preflight and build_verified at seal | loki-ts/src/util/funnel.ts (new; justification: telemetry.sh is the owner and this file is the only TS bridge to it, replacing the private copy in doctor.ts); loki-ts/src/commands/doctor.ts (emitFirstRunBlocked becomes a call to the helper; remove the spawn code); loki-ts/src/engine10/cli.ts (one call after main, at most +2 lines); autonomy/telemetry.sh (_loki_known_blocker keys and a loki_emit_build_verified_enum function); tests/test-first-run-funnel-coverage.sh | MEDIUM | see Wall in note | released@2026-10-17T05:34Z v11.17.24 | wave 3; depends: TEN-UX-01 (shares doctor.ts; also needs the not_a_repo fatal text to exist). Goal: Move the detached, opt-out-respecting telemetry.sh spawn from doctor.ts:1047-1069 into one TS helper (emitFunnel(kind, key)), and delete the copy in doctor.ts in the same change. Call it from engine10/cli.ts after the supervisor returns: preflight exit 2 sends first_run_blocked with a bounded key; a VERIFIED or ALREADY_SATISFIED exit sends build_verified carrying only headline=VERIFIED and route=engine10. No other field is sent. Add keys not_a_repo and git_identity to _loki_known_blocker (telemetry.sh:204), and add an allowlisted build_verified variant that takes enum args instead of a proof.json path. All existing opt-outs still apply because everything goes through _loki_analytics_enabled. Wall: Red first: test-first-run-funnel-coverage.sh gains (a) a wiring assertion that engine10/cli.ts reaches emitFunnel on a preflight exit 2 and on a VERIFIED exit, and (b) a run with a stub telemetry.sh in a throwaway HOME, analytics forced on, with no network: loki_telemetry is replaced by a recorder function. Assert that one first_run_blocked blocker=not_a_repo line is recorded for a start in a non-empty folder with no repo, and that a second identical run records nothing (once-per-install marker). Assert DO_NOT_TRACK=1 and LOKI_TELEMETRY_DISABLED=1 each record zero lines. Assert the recorded payload contains no path, home dir or brief text (grep the recorder file for the temp folder path and the brief: must be absent). Mutations: emit a raw blocker string instead of the enum, so the no-path assertion must go red; drop the marker write, so the second-run assertion must go red; leave doctor's old spawn copy in place, so a grep guard counting `telemetry.sh` spawns in loki-ts/src (exactly 1) must go red. Gate: bash tests/test-first-run-funnel-coverage.sh && bash tests/test-first-run-blocked-signal.sh && cd loki-ts && bun test tests/engine10/budget.test.ts tests/commands/doctor.test.ts && bun test; then bash scripts/local-ci.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-UX-04 | loki doctor --fix: consent-gated installs and Claude login, plus its first tests | loki-ts/src/commands/doctor_fix.ts; loki-ts/src/commands/doctor.ts (pass --yes through to runDoctorFix only; rebase after TEN-UX-01/03 if they touch the same hunk); loki-ts/tests/commands/doctor.test.ts (extend; no doctor_fix test exists today) | MEDIUM | see Wall in note | ready@2026-10-17T01:40Z | wave 4; depends: TEN-UX-03 (doctor.ts edit order only). Goal: On a TTY, `loki doctor --fix` offers each missing default-provider install as a y/N question before running it: `npm install -g @anthropic-ai/claude-code`, then `claude login` when evaluateClaudeLogin returns fail. `--fix --yes` runs the same steps without asking, for scripted onboarding. Without a TTY and without --yes, it prints the commands only, exactly as today. System package managers and sudo are never run. Every step that runs reports `fixed:` or `failed: <first stderr line>`, and the command exits non-zero when a required step still fails. Command execution is behind an injectable runner, so tests never install anything. Wall: Red first: doctor.test.ts gains applyDoctorFixes/runDoctorFix cases with an injected has() and runner: (a) claude missing, tty=false, no --yes: the runner is never called and the npm command is printed; (b) claude missing, --yes: the runner gets exactly [npm, install, -g, @anthropic-ai/claude-code]; (c) runner fails: output has `failed:` and the exit code is non-zero; (d) jq missing with --yes: the runner is never called for jq (system package, print only); (e) claude present and logged out with --yes: the runner gets [claude, login]. These fail today because doctor_fix has no runner, no --yes and no exit code. Mutations: drop the tty/--yes gate, so (a) must go red; let system packages through the runner, so (d) must go red. Gate: cd loki-ts && bun test tests/commands/doctor.test.ts tests/commands/doctor_router.test.ts && bun test && bunx tsc --noEmit; bash tests/test-doctor-ux.sh; bash tests/test-doctor-single-impl.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-UX-05 | loki chat startup readiness check and slash-command suggestions | autonomy/lib/chat.sh; tests/test-doctor-ux.sh (already owns the chat assertions, P12-16) | LOW | see Wall in note | building@2026-10-17T04:43Z | wave 3; depends: none (the folder message text refers to TEN-UX-01 behaviour; write it to whichever behaviour is on main). Goal: When cmd_chat starts (after the TTY check), print at most 3 readiness lines, once, using existing helpers only. (1) The provider CLI for _CHAT_PROVIDER is missing (any provider, not only claude): print `_loki_req_fix_line <provider>` and a hint to try `/provider claude`. (2) claude is logged out: print `claude login (or set ANTHROPIC_API_KEY)`. (3) The folder is not a git repo: say that `/run` will set up an empty folder (TEN-UX-01) or needs `git init` for a non-empty one. When everything is ready, print nothing extra, so a working setup sees no new text. An unknown slash command prints `unknown command: /stat (did you mean /status?)` by unique-prefix or single-edit match against the _chat_help list. The hint for a missing non-Claude provider replaces the bare 'cannot load provider X' at chat.sh:259/:271 with the fix line. Wall: Red first: test-doctor-ux.sh adds cases that drive cmd_chat through `script`/a pty helper already used there (or calls the new _chat_readiness function directly). With PATH holding no codex and LOKI_PROVIDER=codex, the output contains the codex fix string from setup-requirements.json. With a fake claude printing {"loggedIn":false}, the output contains `claude login`. In a non-git temp folder, the output mentions git. With every check passing (fake claude logged in, inside a repo), the readiness output is empty. `/stat` suggests `/status`; `/zzzz` prints no suggestion. Mutations: print readiness lines unconditionally, so the all-ready empty assertion must go red; hardcode the claude fix for every provider, so the codex fix assertion must go red. bash -n and shellcheck on chat.sh. Gate: bash tests/test-doctor-ux.sh && bash tests/test-loki-steer.sh && bash tests/test-first-run-bash32.sh && shellcheck autonomy/lib/chat.sh; then bash scripts/local-ci.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-UX-05 | loki chat startup readiness check and slash-command suggestions | autonomy/lib/chat.sh; tests/test-doctor-ux.sh (already owns the chat assertions, P12-16) | LOW | see Wall in note | released@2026-10-17T05:25Z v11.17.23 | wave 3; depends: none (the folder message text refers to TEN-UX-01 behaviour; write it to whichever behaviour is on main). Goal: When cmd_chat starts (after the TTY check), print at most 3 readiness lines, once, using existing helpers only. (1) The provider CLI for _CHAT_PROVIDER is missing (any provider, not only claude): print `_loki_req_fix_line <provider>` and a hint to try `/provider claude`. (2) claude is logged out: print `claude login (or set ANTHROPIC_API_KEY)`. (3) The folder is not a git repo: say that `/run` will set up an empty folder (TEN-UX-01) or needs `git init` for a non-empty one. When everything is ready, print nothing extra, so a working setup sees no new text. An unknown slash command prints `unknown command: /stat (did you mean /status?)` by unique-prefix or single-edit match against the _chat_help list. The hint for a missing non-Claude provider replaces the bare 'cannot load provider X' at chat.sh:259/:271 with the fix line. Wall: Red first: test-doctor-ux.sh adds cases that drive cmd_chat through `script`/a pty helper already used there (or calls the new _chat_readiness function directly). With PATH holding no codex and LOKI_PROVIDER=codex, the output contains the codex fix string from setup-requirements.json. With a fake claude printing {"loggedIn":false}, the output contains `claude login`. In a non-git temp folder, the output mentions git. With every check passing (fake claude logged in, inside a repo), the readiness output is empty. `/stat` suggests `/status`; `/zzzz` prints no suggestion. Mutations: print readiness lines unconditionally, so the all-ready empty assertion must go red; hardcode the claude fix for every provider, so the codex fix assertion must go red. bash -n and shellcheck on chat.sh. Gate: bash tests/test-doctor-ux.sh && bash tests/test-loki-steer.sh && bash tests/test-first-run-bash32.sh && shellcheck autonomy/lib/chat.sh; then bash scripts/local-ci.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-UX-06 | Dashboard page: empty state, auto-select of the live run, stage progress strip, readable timeline, theme and narrow-screen layout | loki-ts/src/util/dashboard_page.ts; loki-ts/tests/engine10/dashboard_entry.test.ts (extend; it already serves the real page from a fixture events.jsonl) | LOW | see Wall in note | released@2026-10-17T03:50Z | merged 0a45be416 (TL APPROVE d933581dc; follow-up: test that a later click survives the next poll) Shipped in npm 11.17.15 (latest+next) or 11.17.16 (Release run success on e3d445460). |
 | TEN-UX-07 | Dashboard server panels: Reason, Next step and current stage elapsed | loki-ts/src/runner/engine10_dashboard.ts (formatPanels and summarizeRun only); loki-ts/tests/engine10/dashboard.test.ts | LOW | see Wall in note | released@2026-10-17T04:08Z | v11.17.17; TL APPROVE batch J workflow w9sw9xytw |
-| TEN-UX-08 | First-run gate: empty-folder loki start scenario and the install-to-first-success time budget | scripts/first-run-gate.sh; tests/test-first-run-gate.sh; docs/v10/METRICS.md (row 14 text only, written by --real runs, not by the engineer) | MEDIUM | see Wall in note | ready@2026-10-17T01:40Z | wave 4; depends: TEN-UX-01 (empty-folder start must work), TEN-UX-02 (Next wording). Goal: Add `--entry start-empty` to scripts/first-run-gate.sh. It installs (with --installed) or uses the tree, creates an empty folder under the run-owned temp directory, sets git identity through GIT_* env vars only, and runs `loki doctor` then `loki start "<brief>"` with the existing stub claude. It asserts: the folder was set up as a repo, Outcome is VERIFIED, a receipt is sealed, Next is present, and install+doctor+start wall time on the stub is <= 120s, recorded as `install_to_first_success_s`. The stub run measures harness overhead only. With --real, it appends the measured time-to-first-sealed-result row to docs/v10/METRICS.md, replacing the 'not measured' row at METRICS.md:14 with a dated measurement and its command. In stub mode it never writes METRICS. Wall: Red first: test-first-run-gate.sh adds fake-loki modes for the new entry: (a) a fake that leaves the folder without a repo: FAIL repo-init; (b) a fake that sleeps past an injected budget FRG_BUDGET_S=1: FAIL first-success-budget; (c) a fake with no Next line: FAIL next-line; (d) a well-behaved fake: all PASS and the report has `install_to_first_success_s=<int>`. The new entry does not exist today, so these fail. Mutations: drop the budget comparison, so (b) must go red; parse the time field as a string compare, so a budget of 9 vs a measured 10 must go red. Tests use loki_run_tmp_create/cleanup only, never /tmp globs. Gate: bash tests/test-first-run-gate.sh && bash scripts/first-run-gate.sh --stub --entry start-empty; then bash scripts/local-ci.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-UX-08 | First-run gate: empty-folder loki start scenario and the install-to-first-success time budget | scripts/first-run-gate.sh; tests/test-first-run-gate.sh; docs/v10/METRICS.md (row 14 text only, written by --real runs, not by the engineer) | MEDIUM | see Wall in note | building@2026-10-17T05:30Z r2 after TEN-UX-01-F1 | wave 4; depends: TEN-UX-01 (empty-folder start must work), TEN-UX-02 (Next wording). Goal: Add `--entry start-empty` to scripts/first-run-gate.sh. It installs (with --installed) or uses the tree, creates an empty folder under the run-owned temp directory, sets git identity through GIT_* env vars only, and runs `loki doctor` then `loki start "<brief>"` with the existing stub claude. It asserts: the folder was set up as a repo, Outcome is VERIFIED, a receipt is sealed, Next is present, and install+doctor+start wall time on the stub is <= 120s, recorded as `install_to_first_success_s`. The stub run measures harness overhead only. With --real, it appends the measured time-to-first-sealed-result row to docs/v10/METRICS.md, replacing the 'not measured' row at METRICS.md:14 with a dated measurement and its command. In stub mode it never writes METRICS. Wall: Red first: test-first-run-gate.sh adds fake-loki modes for the new entry: (a) a fake that leaves the folder without a repo: FAIL repo-init; (b) a fake that sleeps past an injected budget FRG_BUDGET_S=1: FAIL first-success-budget; (c) a fake with no Next line: FAIL next-line; (d) a well-behaved fake: all PASS and the report has `install_to_first_success_s=<int>`. The new entry does not exist today, so these fail. Mutations: drop the budget comparison, so (b) must go red; parse the time field as a string compare, so a budget of 9 vs a measured 10 must go red. Tests use loki_run_tmp_create/cleanup only, never /tmp globs. Gate: bash tests/test-first-run-gate.sh && bash scripts/first-run-gate.sh --stub --entry start-empty; then bash scripts/local-ci.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-GATES-01 | FC row plus pure check-provenance classifier in check_result.ts | loki-ts/src/util/check_result.ts, loki-ts/tests/engine10/check_result.test.ts, docs/v10/FAILURE-CLASSES.md | HIGH | see Wall in note | released@2026-10-17T03:50Z | merged 0970d5887 (HIGH r2 APPROVE 10be1a1bd; FAILURE-CLASSES append conflict kept both sections) Shipped in npm 11.17.15 (latest+next) or 11.17.16 (Release run success on e3d445460). |
 | TEN-GATES-02 | Seal: receipt checks carry provenance; VERIFIED requires agent-independent proof | loki-ts/src/engine10/stages/seal.ts, loki-ts/src/engine10/types.ts, loki-ts/tests/engine10/seal.test.ts, docs/v10/DECISIONS.md | HIGH | see Wall in note | ready@2026-10-17T01:40Z | wave 3; depends: TEN-GATES-01, Q18-05b (seal.ts in flight). Goal: In seal.ts replace hasExecutedProof at seal.ts:190 with hasExogenousProof (wallGreenOnBase still counts); when only agent_authored/llm_judge checks passed, verdict caps at PARTIAL and not_proven gains 'only agent-authored tests executed (no agent-independent proof)'. Each receipt check gains additive optional provenance (types.ts ReceiptCheck provenance?: ...; omitted key keeps older receipts byte-stable for verification). renderReceiptMd splits '### Agent-independent checks' and '### Agent-authored / advisory checks'. Opt-out LOKI_EXOGENOUS_PROOF=0 (record the default-on decision in DECISIONS.md under the D99 grant). Net-zero line change in engine10 core (fold into existing lines or move helpers to util). Wall: Red first in seal.test.ts: fake verify outputs with one passing check on a test file ADDED in the diff and no Wall -> expect PARTIAL plus the not_proven line (today VERIFIED); same check on a pre-existing file -> VERIFIED; receipt.json checks carry provenance; receipt.md has both sections. Mutation: revert to hasExecutedProof -> red. LOKI_EXOGENOUS_PROOF=0 restores old verdict. Gate: cd loki-ts && bun test tests/engine10/seal.test.ts tests/engine10/seal_verify_roundtrip.test.ts tests/engine10/budget.test.ts && bun test && bunx tsc --noEmit 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-GATES-03 | loki verify reports agent-independent evidence and adds --require-exogenous | loki-ts/src/engine10/verify_cmd.ts, loki-ts/tests/engine10/verify_cmd.test.ts | HIGH | see Wall in note | released@2026-10-17T04:08Z | v11.17.17; TL APPROVE batch J workflow w9sw9xytw |
-| TEN-GATES-04 | TS-callable app boot and HTTP health probe over app-runner.sh | loki-ts/src/util/app_probe.ts (new), loki-ts/tests/util/app_probe.test.ts (new) | MEDIUM | see Wall in note | building@2026-10-17T04:38Z | SPLIT per CTO critic into (a) app boot and health, (b) functional-verify run and artifact write; build as two commits or two agents. wave 2; depends: none. Goal: New loki-ts/src/util/app_probe.ts (justification: no TS module owns app boot; app-runner.sh is bash-only and deep.ts:121-122 names this missing surface). appProbe(repoDir, lokiDir, {specText?, timeoutMs}) sources autonomy/app-runner.sh in a bash child (token-free env via plainTestEnv), runs app_runner_init, app_runner_start, app_runner_health_check, reads .loki/app-runner/health.json, then (when specText given) runs autonomy/lib/functional-verify.py against the URL and writes .loki/quality/functional-results.json in the shape proof-generator.py:841-870 reads. ALWAYS calls app_runner_stop in finally (stops only the PID app-runner recorded). Returns ReceiptCheck-shaped results: 'app boot' and 'http probe' with result pass/fail/not_run and reason; missing runtime or no app detected = not_run, never fail. Wall: Red first: fixture repo with a static index.html (app-runner static-site path, as tests/test-app-runner-static-site.sh) -> app boot pass + health.json ok; fixture whose start command exits 1 -> fail; empty repo -> not_run. Assert no process left on the recorded PID after return. Mutation: drop the stop call -> leftover-PID assertion red. Gate: cd loki-ts && bun test tests/util/app_probe.test.ts && bun test && bunx tsc --noEmit; register the new test file per the structural guards (select-tests.sh --guards-only rows, shard registration) 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-GATES-04 | TS-callable app boot and HTTP health probe over app-runner.sh | loki-ts/src/util/app_probe.ts (new), loki-ts/tests/util/app_probe.test.ts (new) | MEDIUM | see Wall in note | released@2026-10-17T05:25Z v11.17.23 | SPLIT per CTO critic into (a) app boot and health, (b) functional-verify run and artifact write; build as two commits or two agents. wave 2; depends: none. Goal: New loki-ts/src/util/app_probe.ts (justification: no TS module owns app boot; app-runner.sh is bash-only and deep.ts:121-122 names this missing surface). appProbe(repoDir, lokiDir, {specText?, timeoutMs}) sources autonomy/app-runner.sh in a bash child (token-free env via plainTestEnv), runs app_runner_init, app_runner_start, app_runner_health_check, reads .loki/app-runner/health.json, then (when specText given) runs autonomy/lib/functional-verify.py against the URL and writes .loki/quality/functional-results.json in the shape proof-generator.py:841-870 reads. ALWAYS calls app_runner_stop in finally (stops only the PID app-runner recorded). Returns ReceiptCheck-shaped results: 'app boot' and 'http probe' with result pass/fail/not_run and reason; missing runtime or no app detected = not_run, never fail. Wall: Red first: fixture repo with a static index.html (app-runner static-site path, as tests/test-app-runner-static-site.sh) -> app boot pass + health.json ok; fixture whose start command exits 1 -> fail; empty repo -> not_run. Assert no process left on the recorded PID after return. Mutation: drop the stop call -> leftover-PID assertion red. Gate: cd loki-ts && bun test tests/util/app_probe.test.ts && bun test && bunx tsc --noEmit; register the new test file per the structural guards (select-tests.sh --guards-only rows, shard registration) 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-GATES-05 | Spec-derived API auth probe in functional-verify.py | autonomy/lib/functional-verify.py, tests/test_functional_verify.py | HIGH | see Wall in note | parked@2026-10-17T03:30Z | HIGH r1 BLOCK; re-sliced as TEN-GATES-05b |
-| TEN-GATES-06 | Deep verify: real app boot and secure-scan rules on engine10 | loki-ts/src/engine10/stages/deep.ts, loki-ts/tests/engine10/deep.test.ts | HIGH | see Wall in note | ready@2026-10-17T01:40Z | wave 3; depends: TEN-GATES-04, Q18-04 (deep.ts in flight). Goal: Replace runAppBoot's hard-coded not_run (deep.ts:105-130) with a call to util/app_probe.ts, pushing its 'app boot' and 'http probe' checks; extend the existing 'security scan' check to also run autonomy/lib/secure-scan.py over changed files (HIGH active finding = fail, scanner absent = not_run). DEEP_NOT_PROVEN entries clear only for checks that actually ran. Net-zero lines in engine10 core (app boot body shrinks to the call). Wall: Red first in deep.test.ts: injected appProbe fake returning pass -> 'app boot' check result pass (today always not_run); a changed file with a committed PEM private key -> security scan fail with secure-scan rule id; secure-scan missing -> not_run. Mutation: ignore secure-scan exit -> red. Gate: cd loki-ts && bun test tests/engine10/deep.test.ts tests/engine10/deep_wiring.test.ts tests/engine10/budget.test.ts && bun test && bunx tsc --noEmit 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-GATES-07 | loki start route: collect app health and functional facts before the proof | loki-ts/src/runner/proof.ts, loki-ts/tests/runner/proof.test.ts | MEDIUM | see Wall in note | ready@2026-10-17T01:40Z | wave 3; depends: TEN-GATES-04. Goal: In runner/proof.ts, before spawning proof-generator.py, call util/app_probe.ts with the run's PRD text (LOKI_PROOF_APP_PROBE=0 opts out) so .loki/app-runner/health.json and .loki/quality/functional-results.json exist on the primary route; the proof's healthcheck and functional facts stop being permanently not_run. Still never throws; probe failure leaves the facts absent (not_run), never fabricated. Wall: Red first in proof.test.ts: inject a fake probe that writes both artifacts -> generator facts.healthcheck/functional ran=true; probe throwing -> generator still invoked, facts not_run. Mutation: skip probe -> red. Gate: cd loki-ts && bun test tests/runner/proof.test.ts tests/runner/proof_run_id_pointer.test.ts && bun test && bunx tsc --noEmit 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-GATES-06 | Deep verify: real app boot and secure-scan rules on engine10 | loki-ts/src/engine10/stages/deep.ts, loki-ts/tests/engine10/deep.test.ts | HIGH | see Wall in note | building@2026-10-17T05:20Z | wave 3; depends: TEN-GATES-04, Q18-04 (deep.ts in flight). Goal: Replace runAppBoot's hard-coded not_run (deep.ts:105-130) with a call to util/app_probe.ts, pushing its 'app boot' and 'http probe' checks; extend the existing 'security scan' check to also run autonomy/lib/secure-scan.py over changed files (HIGH active finding = fail, scanner absent = not_run). DEEP_NOT_PROVEN entries clear only for checks that actually ran. Net-zero lines in engine10 core (app boot body shrinks to the call). Wall: Red first in deep.test.ts: injected appProbe fake returning pass -> 'app boot' check result pass (today always not_run); a changed file with a committed PEM private key -> security scan fail with secure-scan rule id; secure-scan missing -> not_run. Mutation: ignore secure-scan exit -> red. Gate: cd loki-ts && bun test tests/engine10/deep.test.ts tests/engine10/deep_wiring.test.ts tests/engine10/budget.test.ts && bun test && bunx tsc --noEmit 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-GATES-07 | loki start route: collect app health and functional facts before the proof | loki-ts/src/runner/proof.ts, loki-ts/tests/runner/proof.test.ts | MEDIUM | see Wall in note | building@2026-10-17T05:20Z | wave 3; depends: TEN-GATES-04. Goal: In runner/proof.ts, before spawning proof-generator.py, call util/app_probe.ts with the run's PRD text (LOKI_PROOF_APP_PROBE=0 opts out) so .loki/app-runner/health.json and .loki/quality/functional-results.json exist on the primary route; the proof's healthcheck and functional facts stop being permanently not_run. Still never throws; probe failure leaves the facts absent (not_run), never fabricated. Wall: Red first in proof.test.ts: inject a fake probe that writes both artifacts -> generator facts.healthcheck/functional ran=true; probe throwing -> generator still invoked, facts not_run. Mutation: skip probe -> red. Gate: cd loki-ts && bun test tests/runner/proof.test.ts tests/runner/proof_run_id_pointer.test.ts && bun test && bunx tsc --noEmit 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-GATES-08 | loki start route: secure-scan as an exogenous security_scan gate | loki-ts/src/runner/quality_gates.ts, loki-ts/tests/runner/quality_gates.test.ts | MEDIUM | see Wall in note | released@2026-10-17T04:08Z | v11.17.17; TL APPROVE batch J workflow w9sw9xytw |
 | TEN-GATES-09 | loki start route: write build-results.json (wire the dead pythonBuildCheck) | loki-ts/src/util/python_build_check.ts, loki-ts/src/runner/autonomous.ts, loki-ts/tests/util/python_build_check.test.ts | MEDIUM | see Wall in note | released@2026-10-17T03:50Z | merged f24496198 (TL APPROVE 09a2ae73f) Shipped in npm 11.17.15 (latest+next) or 11.17.16 (Release run success on e3d445460). |
 | TEN-GATES-10 | Proof headline: VERIFIED needs one agent-independent fact beside the agent's suite | autonomy/lib/proof-generator.py, tests/test_proof_generator.py, docs/v10/DECISIONS.md | HIGH | see Wall in note | ready@2026-10-17T01:40Z | wave 4; depends: COST-WALL-f (proof-generator.py in flight), TEN-GATES-07, TEN-GATES-08, TEN-GATES-09 (facts must exist before tightening, or every primary-route run downgrades). Goal: In proof-generator.py the tests_verified branch (:2045-2055) returns VERIFIED only when at least one exogenous fact also passed: build verified, healthcheck ok, functional passed, security clean that actually ran, or an exogenous quality gate passed; otherwise VERIFIED WITH GAPS with degraded item 'no agent-independent evidence (only the agent's own test suite passed)'. Gap record is additive; LOKI_PROOF_REQUIRE_EXOGENOUS=0 opt-out; decision recorded in DECISIONS.md under D99. Wall: Red first in test_proof_generator.py: facts with tests verified + nonempty diff and nothing else -> 'VERIFIED WITH GAPS' plus the degraded item (today VERIFIED); add build verified -> VERIFIED; only an advisory code_review pass -> still WITH GAPS. Mutation: count advisory gates as corroboration -> red. Gate: python3 -m pytest -q tests/test_proof_generator.py tests/test_proof_degraded_disabled_gates.py tests/test_proof_verify.py; bash tests/test-proven-pr-receipt.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. |
@@ -1095,3 +1095,10 @@ Source: ~/git/autonomi-dev/research/2026-09-30-adoption/SWARM-PROMPT-ADOPTION.md
 | TEN-GATES-03-F1 | verify --require-exogenous fails closed with --allow-unsigned and ignores zero-test checks | loki-ts/src/engine10/verify_cmd.ts; loki-ts/tests/engine10/verify_cmd.test.ts | HIGH | an UNSIGNED agent-only receipt with --require-exogenous --allow-unsigned exits 4; an exogenous pass with n=0 does not count toward k | building@2026-10-17T04:15Z | from GATES-03 HIGH review non-blocking findings 1 and 2; batch O |
 | TEN-ADOPTION-03-F1 | proof share scan catches tokens (ghp_, AKIA, sk-ant) and proof registry lists badge, md, bundle | autonomy/lib/secure-scan.py or loki-ts/src/util/secure_scan.ts; loki-ts/src/commands/proof.ts; loki-ts/src/cli/registry.ts; tests | MEDIUM | a bundle with a ghp_ token in events.jsonl shows a finding in the share preview; registry proof subcommands include badge, md, bundle | building@2026-10-17T04:15Z | from ADOPTION-03 TL review notes 1 and 2; batch O |
 | TEN-QUALITY-03-F1 | lint baseline abort test proves the in-flight rerun is killed | loki-ts/tests/engine10/verify_lint.test.ts | LOW | removing signal from AbortSignal.any in verify.ts turns the test red | building@2026-10-17T04:15Z | from QUALITY-03 TL review non-blocking finding 1; batch O |
+| TEN-P9-FIX | P0: first-run login probe spawns the provider CLI with the withheld env | loki-ts/src/commands/doctor.ts, loki-ts/tests/engine10/preflight.test.ts, docs/v10/FAILURE-CLASSES.md | HIGH | bash tests/moat/p9-rule-of-two.sh all CASE PASS; reverting doctor.ts turns preflight.test.ts red | released@2026-10-17T05:34Z v11.17.24 | culprit 08a8ae052 (TEN-UX-01); opus HIGH APPROVE cc74ce7cc |
+| TEN-SEC-GITLEAKS-01 | fixture builds the fake AWS key at runtime; pre-push gitleaks scans merges first-parent like CI | .githooks/pre-push, tests/test-security-audit-config.sh, tests/test-pre-push-gitleaks.sh, loki-ts/tests/engine10/check_result.test.ts | HIGH | G1 red when the flag is dropped from the call line; evil-merge case refused rc=1 | released@2026-10-17T05:34Z v11.17.24 | opus HIGH r2 APPROVE d39b7b8af |
+| TEN-UX-01-F1 | supervisor calls initEmptyRepo before refusing a non-repo folder | loki-ts/src/engine10/supervisor.ts, an existing supervisor/cli test file | MEDIUM | first-run-gate --stub --entry start-empty repo-init line passes; removing the call goes red | building@2026-10-17T05:30Z | FC-TEN-UX-01 recurrence; found by TEN-UX-08 TL review; workflow wplxouy32 |
+| TEN-P9-FIX-F1 | doctor login probe reuses withholdGithubTokens instead of a hand-built copy | loki-ts/src/commands/doctor.ts, loki-ts/src/runner/github_token.ts (export only if needed), loki-ts/tests/engine10/preflight.test.ts | HIGH | p9 probe all PASS; a new channel added to withholdGithubTokens is withheld from the probe too | ready@2026-10-17T05:35Z | P9-FIX HIGH review non-blocking 1; extend-never-duplicate |
+| TEN-SEC-GITLEAKS-01-F1 | local-ci gitleaks step uses --diff-merges=first-parent and joins the G1 comparison set; G1 reads the mode at any indentation | scripts/local-ci.sh, tests/test-security-audit-config.sh | LOW | dropping the flag from local-ci.sh turns G1 red; indented reassignment turns G1 red | ready@2026-10-17T05:35Z | SEC-GITLEAKS-01 HIGH r2 non-blocking |
+| TEN-UX-03-F1 | build_verified payload asserted to carry only headline and route | tests/test-first-run-funnel-coverage.sh | LOW | adding an extra arg to loki_emit_build_verified_enum turns the test red | ready@2026-10-17T05:35Z | UX-03 TL review non-blocking 1 |
+| 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 |

package/docs/v10/FAILURE-CLASSES.md

@@ -1011,3 +1011,11 @@ L0 review rule (ENGINE-LAWS.md L0): a fix that adds an `if` or a regex about the
 - Siblings: preflight.ts git identity check (stays fatal, names the git config command, never set automatically); doctor.ts login probe (same `claude auth status` parse, now shared); non-empty folder without a repo (stays fatal, now names `git init && git add . && git commit -m init`).
 - Mechanism: util/first_run_repo.ts initialises only a truly empty folder (LOKI_AUTO_GIT_INIT=0 refuses); preflight reuses doctor claudeAuthStatusLoggedIn: loggedIn false is fatal, an unknown answer is a warning only.
 - Fixture: tests/engine10/preflight.test.ts "first run (TEN-UX-01)" cases (empty folder, one-file folder, LOKI_AUTO_GIT_INIT=0, fake claude loggedIn false / unknown / API key set).
+- Recurrence (2026-10-17, TEN-UX-01-F1): the mechanism was wired only into preflight.ts, but supervisor.ts exits 2 on `git rev-parse --show-toplevel` before preflight runs, so `bash scripts/first-run-gate.sh --stub --entry start-empty` still printed "engine10: not inside a git repository" (TEN-UX-08 TL review). Fix: the supervisor repo lookup calls the same initEmptyRepo and prints its notice or its named-fix fatal; fixture is that first-run gate entry plus a supervisor-level test that runs the real start path in an empty folder, not preflight in isolation.
+
+## FC-TEN-P9-FIX The first-run login probe spawned the provider CLI holding the GitHub token (P9-PREFLIGHT-LEAK)
+- User-visible vs raw: moat P9.injection-cannot-reach-token went red on v11.17.22 (canary GH_TOKEN/GITHUB_TOKEN, hosts.yml, credential.helper and SSH_AUTH_SOCK reached the provider stub in every scenario); the raw cause was preflight running `claude auth status` from the supervisor with its full env.
+- Law broken: every spawn of a provider CLI gets the withheld env (moat P9); the supervisor env is never handed to an agent binary, probe or not.
+- Siblings: doctor.ts provider probe at the json route (already tokenFreeEnv); modernize/oracle/search.ts `--version` probe (already tokenFreeEnv); engine10 session spawns (worker env, assertWorkerEnv).
+- Mechanism: doctor.ts claudeAuthStatusLoggedIn, the one shared login probe, spawns with tokenFreeEnv plus GIT_SSH_COMMAND=false unless LOKI_ALLOW_AGENT_GITHUB_TOKEN=1.
+- Fixture: tests/engine10/preflight.test.ts "the login probe spawns the provider CLI without the GitHub token or SSH agent"; tests/moat/p9-rule-of-two.sh against a dist rebuilt from the tree.

package/docs/v10/PROGRESS.md

@@ -2438,3 +2438,13 @@ v11.17.20 published (Release run success on e2b6b77d2; npm latest 11.17.20, next
 ## 2026-10-17T05:06Z (CoS) v11.17.22
 
 v11.17.21 published (Release success on 462fbc40a; npm latest 11.17.21, next 11.17.21). Security Audit red on 462fbc40a: 4 leaks, reproduced locally only with --diff-merges=first-parent (slice-branch merges fd027051c, bc0e97c63 re-add the QUALITY-01 fixture key); fingerprints added, rescan rc=0. Pre-push scans without first-parent merge diffs, so it passed; TEN-SEC-GITLEAKS-01 (HIGH) dispatched to make the fixture key runtime-built and align pre-push with CI. Ships batch P approvals: DEPLOY-04 (TL APPROVE 4ed77ee5b), QUALITY-05 (TL APPROVE 69f284f71), UX-01 (TL APPROVE 08a8ae052), STABILITY-07 (TL APPROVE 0261d735a); tsc on merged main clean. Round 2 dispatched: DEPLOY-02 (HIGH BLOCK, --max-age ignored on --url), GATES-04 (TL BLOCK, app leak on boot timeout), UX-05 (TL BLOCK, 4 readiness lines), COST-11 (HIGH BLOCK, haiku already-satisfied false green and stage limit cuts the sonnet retry).
+
+## 2026-10-17T05:25Z (CoS) v11.17.23
+- v11.17.22 published: npm latest=11.17.22 next=11.17.22 (npm view dist-tags). Its Release gate job failed on P9 injection-cannot-reach-token (reproduced locally: bash tests/moat/p9-rule-of-two.sh prints CASE P9.injection-cannot-reach-token FAIL on 2a4dad0c1); P0 fix-forward TEN-P9-FIX dispatched with opus HIGH review (workflow wpvgygoia). Security Audit on 67c21ba72: success.
+- v11.17.23 ships TEN-GATES-04 (TL APPROVE 6ce706340) and TEN-UX-05 (TL APPROVE bbba42387).
+- TEN-SEC-GITLEAKS-01 r1 HIGH BLOCK c2db05d04 (G1 greps the echo line, not the gitleaks call); r2 dispatched. Round 3 for DEPLOY-02 and COST-11 plus GATES-06 and GATES-07 building (workflow wg0hl8nge).
+
+## 2026-10-17T05:34Z (CoS) v11.17.24
+- v11.17.23 published: npm latest=11.17.23 next=11.17.23 (npm view dist-tags). Release gate stayed red on P9 for v11.17.22 and v11.17.23, so tags, GitHub release, docker, homebrew and SDK jobs were skipped for both (git tag -l shows v11.17.21 as newest).
+- v11.17.24 ships TEN-P9-FIX (opus HIGH APPROVE cc74ce7cc; culprit 08a8ae052 from TEN-UX-01, preflight spawned claude auth status with the unwithheld env; reviewer: base probe FAIL, fix probe 5 CASE PASS, revert mutation red), TEN-SEC-GITLEAKS-01 (opus HIGH r2 APPROVE d39b7b8af; 54 passed config suite, evil-merge case refused), TEN-UX-03 (TL APPROVE 5a4ffa9a9) and TEN-DEPLOY-04-F1 (TL APPROVE 50579a177).
+- TEN-UX-08 r1 TL BLOCK 7b061f7c8 found TEN-UX-01 not wired end to end (supervisor exits before preflight); FC-TEN-UX-01 recurrence recorded; TEN-UX-01-F1 then TEN-UX-08 r2 building (workflow wplxouy32). Follow-ups queued ready: TEN-P9-FIX-F1, TEN-SEC-GITLEAKS-01-F1, TEN-UX-03-F1.