loki-mode 10.5.19 → 10.5.22

package/README.md

@@ -48,6 +48,7 @@ Upgrade with `loki self-update`. Long form: [Installation Guide](docs/INSTALLATI
 ```bash
 export ANTHROPIC_API_KEY=sk-...
 loki doctor
+loki quick "fix the login bug"   # one small task on the Loki 10 engine
 ```
 
 <details>
@@ -71,9 +72,9 @@ loki-seal is a Claude Code Stop hook that runs your repo's real test suite when
 
 ## Loki 10 engine
 
-Opt-in: set LOKI_ENGINE=v10 <!-- loki10-default -->
+Default: Loki 10 engine for `loki "<task>"`, `loki owner/repo#N` and `loki quick "<task>"`. Set LOKI_ENGINE=legacy or run `loki legacy <args>` for the previous engine. <!-- loki10-default -->
 
-Loki 10 is the rewritten engine. It is not the default yet: with `LOKI_ENGINE` unset, `loki` runs the [legacy engine](#legacy-engine-reference) exactly as before. A default flip is in flight; this section describes what `main` does today (`bin/loki` routes to the v10 engine only when `LOKI_ENGINE=v10` is set). Guide, provider table and summary format: [docs/v10/GUIDE.md](docs/v10/GUIDE.md).
+Loki 10 is the rewritten engine and the default for tasks, issue mode and `quick`; `status`, `verify` and `dashboard` use it when `LOKI_ENGINE=v10` is set. Guide, provider table and summary format: [docs/v10/GUIDE.md](docs/v10/GUIDE.md).
 
 ```
 LOKI_ENGINE=v10 loki "fix the login redirect loop" --no-pr

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 v10.5.19
+# Loki Mode v10.5.22
 
 **You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
 
@@ -470,4 +470,4 @@ See `CHANGELOG.md` entries [7.5.7], [7.5.8], [7.5.13] for the per-fix list and r
 
 ---
 
-**v10.5.19 | [Autonomi](https://www.autonomi.dev/) flagship product | ~410 lines core**
+**v10.5.22 | [Autonomi](https://www.autonomi.dev/) flagship product | ~410 lines core**

package/VERSION

@@ -1 +1 @@
-10.5.19
+10.5.22

package/autonomy/loki

@@ -1606,7 +1606,9 @@ show_help() {
     echo "  loki doctor               Check your setup is ready (a few seconds)"
     echo "  loki quickstart           Guided first build from your idea (no PRD needed)"
     echo "  loki start ./prd.md       Build from a spec (PRD file, GitHub/GitLab/Jira/Azure issue, or no arg)"
-    echo "  quickstart = guided first build; quick = one small task (3 iters max)."
+    echo "  quickstart = guided first build; quick = one small task (Loki 10 engine, no PR)."
+    echo "  loki \"<task>\", loki owner/repo#N and loki quick run on the Loki 10 engine by default."
+    echo "  Previous engine: set LOKI_ENGINE=legacy or run 'loki legacy <args>'."
     echo "  Docs: https://github.com/asklokesh/loki-mode  |  Report a problem: loki crash"
     echo ""
     # CLI consolidation (Phase A): the front page presents ~17 canonical
@@ -1640,6 +1642,7 @@ show_help() {
     echo ""
     echo "Verify / trust:"
     echo "  verify [base]    Deterministic PR verification (CI-gate exit codes)"
+    echo "  keys export      Print the public receipt-signing key (JWK) for third-party verify --pubkey"
     echo "  review [opts]    Standalone code review with quality gates"
     echo "  ultracode \"task\" Run a task as a native Claude Code Dynamic Workflow (opt-in, Claude-only)"
     echo "  trust [cmd]      Visible trust trajectory; 'trust detail' for metrics"
@@ -1705,7 +1708,7 @@ show_help() {
     echo "  loki start PROJ-456           # Jira issue"
     echo "  loki start --bg ./prd.md      # Start in background"
     echo "  loki start --parallel ./prd.md   # Parallel mode (git worktrees)"
-    echo "  loki quick \"add dark mode\"  # Single-task mode (3 iters max)"
+    echo "  loki quick \"add dark mode\"  # Single-task mode (Loki 10 engine; LOKI_ENGINE=legacy for 3 iters max)"
     echo "  loki tour                     # See a real sample result (no provider, no key, no spend)"
     echo "  loki demo                     # Build a sample todo app end to end"
     echo "  loki init -t saas-starter     # Scaffold from template"
@@ -1916,7 +1919,7 @@ show_landing() {
     echo -e "  ${CYAN}loki doctor${NC}           Check your setup is ready (a few seconds)"
     echo -e "  ${CYAN}loki quickstart${NC}       Guided first build from your idea (no PRD needed)"
     echo -e "  ${CYAN}loki start ./prd.md${NC}   Build from a spec (PRD file, GitHub/GitLab/Jira/Azure issue, or no arg)"
-    echo "  quickstart = guided first build; quick = one small task (3 iters max)."
+    echo "  quickstart = guided first build; quick = one small task (Loki 10 engine, no PR)."
     echo ""
     echo -e "Need help? ${CYAN}loki help${NC} lists every command."
     echo "Tip: preview cost and scope before building: loki plan <your-prd.md>"
@@ -16408,8 +16411,10 @@ cmd_quick() {
             echo ""
             echo "Usage: loki quick \"description of what to do\""
             echo ""
-            echo "Runs Loki with a lightweight execution profile: 3 iterations max,"
-            echo "no quality council, no completion gate. Best for tiny tasks."
+            echo "Runs the Loki 10 engine on one small task (no PR is opened). Set"
+            echo "LOKI_ENGINE=legacy or run 'loki legacy quick ...' for the previous engine:"
+            echo "a lightweight profile, 3 iterations max, no quality council, no completion"
+            echo "gate. Best for tiny tasks. The options below apply to the previous engine."
             echo ""
             echo "Examples:"
             echo "  loki quick \"add dark mode to this React app\""
@@ -18647,6 +18652,11 @@ with open(manifest_path, 'w') as f:
 # usable.
 # ---------------------------------------------------------------------------
 cmd_verify() {
+    # D48: --pubkey verifies a receipt against a given public key (v10 engine, no ~/.loki needed).
+    local _pk_arg
+    for _pk_arg in "$@"; do
+        [ "$_pk_arg" = "--pubkey" ] && LOKI_ENGINE=v10 exec "$_LOKI_SCRIPT_DIR/../bin/loki" verify "$@"
+    done
     # --fast: deterministic checks only, in milliseconds. Measured on this repo
     # (1,932 tracked files): 298 ms cold, 87 ms warm, 19 ms diff-scoped, against
     # an 11,040 ms shell-based baseline.
@@ -21959,6 +21969,10 @@ main() {
         verify)
             cmd_verify "$@"
             ;;
+        keys)
+            # D48: public-key export lives in the Bun v10 engine; re-enter the shim on that route.
+            LOKI_ENGINE=v10 exec "$_LOKI_SCRIPT_DIR/../bin/loki" keys "$@"
+            ;;
         spec)
             cmd_spec "$@"
             ;;

package/autonomy/run.sh

@@ -256,7 +256,10 @@ if [ -z "${LOKI_QUICK_INNER:-}" ] && [ "${LOKI_VERBOSE:-0}" != "1" ] && [ "${BAS
         if command -v python3 >/dev/null 2>&1 && python3 -c 'import os,signal' >/dev/null 2>&1; then
             _qexec=(python3 -c 'import os,signal,sys;signal.signal(signal.SIGPIPE,signal.SIG_DFL);os.execv(sys.argv[1],sys.argv[1:])' "${_qexec[@]}")
         fi
-        ( trap - INT QUIT; LOKI_QUICK_DIR="$_qd" LOKI_QUICK_OUTER_PID=$$ LOKI_QUICK_INNER=1 exec "${_qexec[@]}" >"$_qd/quick-run.log" ) &
+        # A background job gets stdin=/dev/null. Only a TTY needs it back (pause-mode
+        # keypress resume); a pipe would block the provider, which reads inherited stdin.
+        if [ -t 0 ]; then exec 3<&0; else exec 3</dev/null; fi
+        ( trap - INT QUIT; LOKI_QUICK_DIR="$_qd" LOKI_QUICK_OUTER_PID=$$ LOKI_QUICK_INNER=1 exec "${_qexec[@]}" >"$_qd/quick-run.log" <&3 3<&- ) &
         _qpid=$!
         trap 'kill -INT "$_qpid" 2>/dev/null' INT
         trap 'kill -TERM "$_qpid" 2>/dev/null' TERM HUP
@@ -265,8 +268,10 @@ if [ -z "${LOKI_QUICK_INNER:-}" ] && [ "${LOKI_VERBOSE:-0}" != "1" ] && [ "${BAS
         trap - INT TERM HUP
         _qw=$(grep -cF '[WARN]' "$_qd/quick-run.log" 2>/dev/null); _qw="${_qw:-0}"
         if [ "$_qrc" -ne 0 ] || [ ! -s "$_qd/quick-receipt.txt" ]; then
-            _qr=$(grep -E '\[(ERROR|WARN)\]|[Ss]topped|[Ff]ailed' "$_qd/quick-run.log" 2>/dev/null | tail -n 3)
-            echo "${_qr:-$(tail -n 3 "$_qd/quick-run.log" 2>/dev/null)}"
+            # Anchored to log_error/log_warn lines (optional ANSI prefix) and capped at 200
+            # chars so a long prompt line mentioning "failed" is never dumped.
+            _qr=$(grep -E $'^(\033\\[[0-9;]*m)?\\[(ERROR|WARN)\\]' "$_qd/quick-run.log" 2>/dev/null | tail -n 3 | cut -c1-200)
+            echo "${_qr:-$(tail -n 3 "$_qd/quick-run.log" 2>/dev/null | cut -c1-200)}"
         fi
         [ "$_qw" -gt 0 ] && echo "Warnings: $_qw (see $_qd/quick-run.log)"
         cat "$_qd/quick-receipt.txt" 2>/dev/null

package/autonomy/verify.sh

@@ -3071,7 +3071,7 @@ sys.exit(0 if ok else 3)" "$lib" "$pj" 2>/dev/null || rc=$?
     # Provenance: the deploy gate's own verdict (Ed25519 attestation against the local
     # key plus LOKI_RECEIPT_RETIRED_PUBKEYS; unknown kid or no key is UNCHECKED).
     # Defined in autonomy/loki, so it is absent when verify.sh runs standalone.
-    declare -f _deploy_receipt_verdict >/dev/null 2>&1 || return 0
+    declare -f _deploy_receipt_verdict >/dev/null 2>&1 || { echo "attestation: UNCHECKED (run via loki verify)"; return 0; }
     local att
     att="$(_deploy_receipt_verdict "$pj")"
     # D47: UNSIGNED is never a pass; --allow-unsigned / LOKI_VERIFY_ALLOW_UNSIGNED=1 accepts it, said aloud.

package/bin/loki

@@ -271,26 +271,73 @@ if [ "${1:-}" = "modernize" ]; then
     unset _loki_mod_a
 fi
 
-# Loki 10 engine (D29): additive; skipped entirely unless LOKI_ENGINE=v10.
-if [ "${LOKI_ENGINE:-}" = "v10" ]; then
-    _e10=0
-    case "${1:-}" in
-        status|verify|dashboard) _e10=1 ;;
-        ""|-*) _e10=0 ;;
-        # http*://*/issues/* also covers GitLab's /-/issues/ URLs.
-        */*\#[0-9]*|http*://*/issues/*|http*://*/browse/*) _e10=1 ;;
-        *" "*) _e10=1 ;;
-        # ponytail: a one-word argument stays on the legacy CLI. The telemetry
-        # allowlist is not a command registry (estimate, intent, outcomes are
-        # missing from it), so it cannot decide routing. Multi-word tasks and
-        # issue refs reach v10.
-        *) _e10=0 ;;
-    esac
-    if [ "$_e10" = "1" ]; then
-        command -v bun >/dev/null 2>&1 || { echo "Error: LOKI_ENGINE=v10 needs bun. Unset LOKI_ENGINE to use the current engine." >&2; exit 1; }
-        exec bun "$BUN_CLI" engine10 "$@"
-    fi
-fi
+# `loki legacy <args>` (D29/D48): the previous engine, exactly as LOKI_ENGINE=legacy.
+# Re-runs this shim with the pin so every route below is the pre-flip route.
+case "${1:-}" in
+    legacy)
+        shift
+        [ -f "$REPO_ROOT/autonomy/lib/engine10-legacy-notice.txt" ] && cat "$REPO_ROOT/autonomy/lib/engine10-legacy-notice.txt" >&2
+        LOKI_ENGINE=legacy exec "$SCRIPT_PATH" "$@"
+        ;;
+esac
+
+# Loki 10 engine (D29, flipped to the default by D48 rows 7-9). LOKI_ENGINE unset
+# or v10 routes `loki "<task>"`, `loki owner/repo#N` and `loki quick "<task>"` to
+# engine10; LOKI_ENGINE=v10 (explicit) also routes status/verify/dashboard. Any
+# other value (legacy, v9, ...) skips this block: the previous engine, unchanged.
+_loki_engine_default="v10"
+case "${LOKI_ENGINE:-$_loki_engine_default}" in
+    v10)
+        _e10=0
+        _e10_args=("$@")
+        case "${1:-}" in
+            status|verify|dashboard|keys)
+                [ "${LOKI_ENGINE:-}" = "v10" ] && _e10=1
+                # Bare `loki verify` follows the newest run: a v10 run newer than the newest
+                # legacy proof is verified by v10, so a FAILED default run is never VERIFIED.
+                # Only a bare call or a v10 run id (e10-*) goes there; any flag (--fast, --pr, --json, unknown) stays on legacy verify.
+                if [ "$1" = "verify" ] && [ "$_e10" = "0" ] && [ -z "${LOKI_ENGINE:-}" ] && case "${2:-}" in ""|e10-*) true ;; *) false ;; esac; then
+                    _r10=""; _p10=""
+                    for _d in "${LOKI_DIR:-.loki}"/runs/e10-*/; do [ -d "$_d" ] && _r10="$_d"; done
+                    for _d in "${LOKI_DIR:-.loki}"/proofs/*/proof.json; do [ -f "$_d" ] && { [ -z "$_p10" ] || [ "$_d" -nt "$_p10" ]; } && _p10="$_d"; done
+                    if [ -n "$_r10" ] && { [ -z "$_p10" ] || [ "$_r10" -nt "$_p10" ]; }; then _e10=1; fi
+                    unset _r10 _p10 _d
+                fi
+                ;;
+            ""|-*) _e10=0 ;;
+            # quick: the lean small path, no PR (legacy quick never opened one). A flag-first
+            # call (--help, -v) stays on the legacy quick.
+            quick)
+                case "${2:-}" in
+                    ""|-*) _e10=0 ;;
+                    *) _e10=1; _e10_args=(--no-pr "${@:2}") ;;
+                esac
+                ;;
+            # http*://*/issues/* also covers GitLab's /-/issues/ URLs.
+            */*\#[0-9]*|http*://*/issues/*|http*://*/browse/*) _e10=1 ;;
+            *" "*) _e10=1 ;;
+            # ponytail: a one-word argument stays on the legacy CLI. The telemetry
+            # allowlist is not a command registry (estimate, intent, outcomes are
+            # missing from it), so it cannot decide routing. Multi-word tasks and
+            # issue refs reach v10.
+            *) _e10=0 ;;
+        esac
+        # Default (unset) mode never breaks a host: no bun, or a provider engine10 has no
+        # invoker for, falls through to the legacy engine. Explicit v10 keeps its hard error.
+        if [ "$_e10" = "1" ] && [ "${LOKI_ENGINE:-}" != "v10" ]; then
+            case "${LOKI_PROVIDER:-claude}" in claude|codex|cline|aider) ;; *) _e10=0 ;; esac
+            command -v bun >/dev/null 2>&1 || _e10=0
+            if [ "$_e10" = "0" ]; then
+                echo "loki: using the legacy engine (the Loki 10 engine needs bun and LOKI_PROVIDER of claude, codex, cline or aider)." >&2
+            fi
+        fi
+        if [ "$_e10" = "1" ]; then
+            command -v bun >/dev/null 2>&1 || { echo "Error: LOKI_ENGINE=v10 needs bun. Install bun, or set LOKI_ENGINE=legacy to use the previous engine." >&2; exit 1; }
+            exec bun "$BUN_CLI" engine10 "${_e10_args[@]}"
+        fi
+        unset _e10 _e10_args
+        ;;
+esac
 
 # Bun must be installed for the new path; if it isn't, fall through to bash
 # silently rather than fail. This keeps users on systems without Bun working.

package/completions/_loki

@@ -193,6 +193,7 @@ function _loki_commands {
         'spec:Living spec drift detection'
         'intent:Does the spec still say what was actually wanted'
         'verify:Deterministic PR verification'
+        'keys:Export the receipt-signing public key'
         'grill:Interrogate a spec before building'
         'trust:Visible trust trajectory'
         'trust-metrics:Trust metrics report'

package/completions/loki.bash

@@ -5,8 +5,8 @@ _loki_completion() {
     _init_completion || return
 
     # Main subcommands (must match autonomy/loki main case statement)
-    local main_commands="start backlog quick monitor demo tour welcome init stop pause resume steer status next ship dashboard web serve api sandbox notify import github issue config provider reset memory compound checkpoint council dogfood projects enterprise secrets cockpit secure own handoff doctor watchdog audit metrics syslog onboard share proof receipt outcomes explain plan report cost estimate kpis stats test ci watch telemetry agent context ctx code run export review optimize heal modernize migrate cluster worktree wt trigger failover remote deploy docker mcp magic assets analyze compliance crash open otel preview quickstart rc rollback self-update sentrux setup-skill spec state template trust trust-metrics ultracode update verify voice why wiki bench cleanup logs grill docs cp version completions help"
-    local main_commands="start backlog quick monitor demo tour welcome init stop pause resume steer status next ship dashboard web serve api sandbox notify import github issue intent config provider reset memory compound checkpoint council dogfood projects enterprise secrets cockpit secure own handoff doctor watchdog audit metrics syslog onboard share proof receipt explain plan report cost estimate kpis stats test ci watch telemetry agent context ctx code run export review optimize heal modernize migrate cluster worktree wt trigger failover remote deploy docker mcp magic assets analyze compliance crash open otel preview quickstart rc rollback self-update sentrux setup-skill spec state template trust trust-metrics ultracode update verify voice why wiki bench cleanup logs grill docs cp version completions help"
+    local main_commands="start backlog quick monitor demo tour welcome init stop pause resume steer status next ship dashboard web serve api sandbox notify import github issue config provider reset memory compound checkpoint council dogfood projects enterprise secrets cockpit secure own handoff doctor watchdog audit metrics syslog onboard share proof receipt outcomes explain plan report cost estimate kpis stats test ci watch telemetry agent context ctx code run export review optimize heal modernize migrate cluster worktree wt trigger failover remote deploy docker mcp magic assets analyze compliance crash open otel preview quickstart rc rollback self-update sentrux setup-skill spec state template trust trust-metrics ultracode update verify voice why wiki bench cleanup logs grill docs cp version completions help keys"
+    local main_commands="start backlog quick monitor demo tour welcome init stop pause resume steer status next ship dashboard web serve api sandbox notify import github issue intent config provider reset memory compound checkpoint council dogfood projects enterprise secrets cockpit secure own handoff doctor watchdog audit metrics syslog onboard share proof receipt explain plan report cost estimate kpis stats test ci watch telemetry agent context ctx code run export review optimize heal modernize migrate cluster worktree wt trigger failover remote deploy docker mcp magic assets analyze compliance crash open otel preview quickstart rc rollback self-update sentrux setup-skill spec state template trust trust-metrics ultracode update verify voice why wiki bench cleanup logs grill docs cp version completions help keys"
 
     # 1. If we are on the first argument (subcommand)
     if [[ $cword -eq 1 ]]; then

package/dashboard/__init__.py

@@ -7,7 +7,7 @@ Modules:
     control: Session control API (start/stop/pause/resume)
 """
 
-__version__ = "10.5.19"
+__version__ = "10.5.22"
 
 # Expose the control app for easy import
 try:

package/docs/INSTALLATION.md

@@ -2,7 +2,7 @@
 
 The flagship product of [Autonomi](https://www.autonomi.dev/). Loki Mode is a spec-driven autonomous builder with a built-in trust layer that takes any spec to a deployed product and verifies completion with evidence (quality gates plus a completion council), not just a "done" claim. Complete installation instructions for all platforms and use cases.
 
-**Version:** v10.5.19
+**Version:** v10.5.22
 
 ---
 

package/docs/exit-codes.md

@@ -89,9 +89,18 @@ not rank above UNCHECKED.
 | Legacy shell (`autonomy/verify.sh`) | BLOCKED (non-zero) | the receipt line passes with the same accepted line |
 
 Engine10 `loki verify [run-id]` exits: 0 verified, 1 tampered, 2 unchecked,
-3 unsigned (refused), 66 no runs. The flag never changes TAMPERED or UNCHECKED,
+3 unsigned (refused), 4 run outcome not verified (a sealed receipt of a FAILED or
+otherwise unverified run), 66 no runs. The outcome check runs before the UNSIGNED
+branch, so the flag never changes exit 4, TAMPERED or UNCHECKED,
 and verify never creates a signing key.
 
+`loki verify --pubkey FILE <receipt.json|run-id>` (v10 only) checks the signature
+against the supplied Ed25519 public key (JWK from `loki keys export`, or PEM) and
+never the local JWKS. Exits: 0 VERIFIED, 1 TAMPERED, 2 UNCHECKED (kid does not
+match the key, or the key file is unusable), 3 UNSIGNED (a receipt with no
+signature is refused even with `--allow-unsigned`, because the caller asked for a
+signature check), 4 run outcome not verified (checked before UNSIGNED).
+
 An early draft spec listed `1=BLOCKED, 2=CONCERNS`. That ordering was rejected:
 it is not used anywhere, it has no consumers, and it inverts the
 severity-rises-with-the-code rule that every other command follows.

package/docs/v10/BOARD.md

@@ -629,7 +629,7 @@ Source: ~/git/autonomi-dev/research/2026-09-30-adoption/SWARM-PROMPT-ADOPTION.md
 | E-159 | Pre-existing secret-scan gaps found by the E-157 r2 opus reviewer: (a) an evil merge, a merge commit whose OWN content adds a secret (merge -s ours --no-commit, token in the merge commit), is invisible to both the PARENT..SHA range scan and the --all scan (only `gitleaks dir` found it); (b) pinned gitleaks 8.30.0 exits 0 when its internal git log fails (invalid range), a latent fail-open. Fix: --diff-merges=first-parent (or -m) in --log-opts for both modes or a working-tree scan at the release SHA; guard `git rev-list RANGE` success or treat `[git] fatal` as failure | scripts/security-audit-gitleaks.sh, workflows, tests | HIGH | evil-merge and bad-range fixtures fail the scan | merged@2026-10-01T03:03Z | CI-health engineer after E-157 r3; r1 opus REJECT 5f33451d: stdin merge scan false-positives on real history (v10.5.13..14 rc 1), Wall checks skip in CI |
 | E-160 | D46 runner contention (peer steer 02:11Z): a green train SHA fast-forwarded to main re-runs Tests (8 shards), Bun Parity, Security Audit and First-run gate on the identical SHA, doubling runner load and queueing the next train. Proposal: on push to main, a first job checks for a successful run of the same workflow at the same SHA from a train/** push and, if found, exits success recording the reused run id (D28: same SHA = same tree); any SHA not train-tested runs in full. CTO call FIRST: OPERATING-MODEL says "Tier B full verification on every main commit (never cancelled on main)"; confirm reuse does not weaken Release required-ci, branch-conditional steps (train vs main), or the Security Audit range (base tag config). Sequence after E-157 r4 (same files) | .github/workflows/test.yml, bun-parity.yml, security-audit.yml, tests/test_release_required_ci.py | HIGH | main push of a train-green SHA records reuse and finishes in under 1 min; an untested SHA runs in full; a train-red SHA is not reused | ready@2026-10-01T02:10Z | CTO decision first; after E-157 |
 | E-161 | INCIDENT 02:46Z: an opus reviewer ran `git checkout --detach <tag>` x7 plus a `.gitleaksignore` overwrite in the SHARED main checkout (reflog 02:46:04Z to 02:46:38Z). Cause: its run-owned clone dir was deleted, the next `cd` into a new clone failed, and the shell cwd fell back to the main checkout; every later command ran there. Restored by the Chief of Staff (`git checkout main`, fafe50dd, clean). Guard: v10-guard.sh (PreToolUse) blocks `git checkout`/`git switch`/`git reset`/`git worktree remove` and writes to tracked files when cwd resolves to the main checkout and the caller is an agent (not the leader session); agent prompts use `cd DIR` followed by an exit-on-failure check. Test: a hook test with cwd=main checkout blocks a detached checkout and allows it in a worktree | scripts/v10-guard.sh, tests | HIGH | detached checkout in main checkout blocked; same in a worktree allowed | ready@2026-10-01T02:47Z | GUARDS.md entry |
-| E-162 | Founder "faster" (03:05Z): slice CI runs only Tier A plus diff-selected suites (the existing Tier A selection), Bun Parity and the structural guards; the full 8-shard Tests stays on train/** and main, and the train stays the release verdict. Frees runners and targets about 2 min slice CI | .github/workflows/test.yml (slice-* job matrix only), tests | HIGH | slice-* push runs no 8-shard matrix; train/** and main still run all 8 shards; a slice touching a suite runs that suite | ready@2026-10-01T03:01Z | after E-157 r4 (same file) |
+| E-162 | Founder "faster" (03:05Z): slice CI runs only Tier A plus diff-selected suites (the existing Tier A selection), Bun Parity and the structural guards; the full 8-shard Tests stays on train/** and main, and the train stays the release verdict. Frees runners and targets about 2 min slice CI | .github/workflows/test.yml (slice-* job matrix only), tests | HIGH | slice-* push runs no 8-shard matrix; train/** and main still run all 8 shards; a slice touching a suite runs that suite | merged@2026-10-01T05:22Z | after E-157 r4 (same file) |
 | E-165 | tests/test-mirofish-integration.sh line 413 runs `autonomy/loki start --no-mirofish` in the repo root: a live autonomous build that ran about 45 min, switched a worktree branch to loki/session-* and committed a docs change (found by DOC-02). Guard: the test must run against a run-owned fixture repo with a stub provider and LOKI_NO_BROWSER=1, never the repo root; add a structural guard that no test launches start/run against REPO_ROOT | tests/test-mirofish-integration.sh, a structural guard | HIGH | the test never runs loki start in the repo root; guard catches a planted case | ready@2026-10-01T04:07Z | P0 guard (D26) |
 | E-166 | Jira auto-sync never starts: src/integrations/sync-subscriber.js builds JiraApiClient without the required email and apiToken, so LOKI_JIRA_URL plus LOKI_JIRA_TOKEN do nothing (DOC-02 added a known-issue note to the setup docs). Fix the wiring or remove the advertised auto-sync | src/integrations/sync-subscriber.js, tests | MEDIUM | with env set, the subscriber constructs a working client (mocked API) | ready@2026-10-01T04:07Z | none |
 | D49-auto | Auto-promote to latest on Post-Release Smoke success (founder D49) | .github/workflows/promote.yml, tests/test_release_next_tag.py | HIGH | smoke-success from Release promotes; manual smoke never promotes; not-lower guard | merged@2026-10-01T03:03Z | opus APPROVE 5510b8c8. Follow-ups (D49-auto-b): not-lower guard fails OPEN on an npm error (make it fail closed); loki-mode-sdk latest has no not-lower guard; a newer queued promote can replace a pending one in a release burst |
@@ -642,20 +642,20 @@ Source: ~/git/autonomi-dev/research/2026-09-30-adoption/SWARM-PROMPT-ADOPTION.md
 | A-115 | TIER 0 (steer 22:50Z). FALSE VERIFIED ON MAIN (A-112 opus reviewer, c10 on 275b4fc0): a conftest.py that skips the target test (and the unrelated red one) seals VERIFIED rc=0, "2 passed, 2 skipped", nothing disclosed. Seal accuracy: a relevant check with more skipped tests than base, or a diff touching conftest.py / pytest.ini / pyproject [tool.pytest] / jest or node test config, must not count as a pass or as progress; list it in NOT PROVEN | loki-ts/src/engine10/stages/verify.ts, failures.ts, tests | HIGH | c10 and e9 fixtures seal FAILED or NOT VERIFIED | released@2026-10-01T00:52Z | core at the 5000 cap: needs an offset (A-150) Released in v10.5.13 (merge bdb332e3 is an ancestor of v10.5.13). |
 | A-115b | A-115 opus notes: (1) an honest fix that also appends a new test to a relevant test file, in a repo with an unrelated red test, ends STALLED/FAILED instead of PARTIAL: the edited file is excluded from progress so the unrelated red is never subtracted; allow progress when the file's pre-existing target ids went red to green; (2) the node base-count fallback sums every `pass N`/`fail N` line, so a base test printing them inflates the count (safe-direction false PARTIAL); take the last pass and last fail lines | loki-ts/src/engine10/stages/verify.ts, verify_weak.test.ts | HIGH | both fixtures | released@2026-10-01T01:53Z | Released in v10.5.15 (merge 945f58ec is an ancestor of v10.5.15). |
 | A-119 | P0 FALSE VERIFIED ON MAIN (A-115b opus reviewer, reproduced on bba2e5ec): rename the target test file and weaken its expectation (sum.test.js => sum.spec.test.js with 6 changed to 5), add a comment to sum.js: rc=0 Outcome VERIFIED, receipt shows node:sum.spec.test.js pass, sum.js still buggy. verify only sees relevant test files that still exist on head; seal writes `weakened test: sum.test.js` (seal.ts:205) but that line never downgrades the verdict. Fix: seal's `weakened test:` downgrades to PARTIAL like verify's not_proven | loki-ts/src/engine10/stages/seal.ts, tests | HIGH | rename-and-weaken fixture: not VERIFIED, rc!=0 | released@2026-10-01T01:53Z | Tier 0 Released in v10.5.15 (merge c41a2b83 is an ancestor of v10.5.15). |
-| 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 | building@2026-10-01T02:18Z | |
+| 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 | merged@2026-10-01T02:50Z | 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 | building@2026-10-01T02:15Z | 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-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 | merged@2026-10-01T05:12Z | 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-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). |
-| A-121b | A-121 opus note: a receipt downgrade exits 0. Anyone can edit the body, recompute receipt_sha256 and null the jwt to get UNSIGNED rc 0 on `loki verify`, and the legacy deploy gate refuses UNSIGNED but the v10 verify does not. Decide the signed-by-default policy: once a local key exists, UNSIGNED on a receipt from this machine exits non-zero (or the receipt records its kid outside the hashed body) | loki-ts/src/engine10/verify_cmd.ts, stages/seal.ts, tests | HIGH | downgrade fixture exits non-zero | building@2026-10-01T02:33Z | D47 decided: UNSIGNED exits 3 on both engines (verify_cmd.ts EXIT_BY_VERDICT, autonomy/verify.sh _verify_receipt_digest), --allow-unsigned / LOKI_VERIFY_ALLOW_UNSIGNED=1 accepts with explicit line; update tests/test-engine10-live-pr.sh 115-122; verify never creates a key |
+| A-121b | A-121 opus note: a receipt downgrade exits 0. Anyone can edit the body, recompute receipt_sha256 and null the jwt to get UNSIGNED rc 0 on `loki verify`, and the legacy deploy gate refuses UNSIGNED but the v10 verify does not. Decide the signed-by-default policy: once a local key exists, UNSIGNED on a receipt from this machine exits non-zero (or the receipt records its kid outside the hashed body) | loki-ts/src/engine10/verify_cmd.ts, stages/seal.ts, tests | HIGH | downgrade fixture exits non-zero | released@2026-10-01T03:00Z | D47 decided: UNSIGNED exits 3 on both engines (verify_cmd.ts EXIT_BY_VERDICT, autonomy/verify.sh _verify_receipt_digest), --allow-unsigned / LOKI_VERIFY_ALLOW_UNSIGNED=1 accepts with explicit line; update tests/test-engine10-live-pr.sh 115-122; verify never creates a key |
 | A-121c | A-121b opus finding B: legacy `loki verify` passes a WELL-FORMED token with an unknown kid at rc 0 (`attestation: UNCHECKED`, `VERDICT: VERIFIED`) with or without the local key; engine10 gives rc 2. A forger can always mint such a token, so on legacy a downgrade-to-foreign-kid is a pass. D47 kept legacy UNCHECKED unchanged because it also covers honest cross-machine verification. CTO call: make legacy UNCHECKED non-zero (parity with engine10 rc 2), now that D48 row 2 adds `loki verify --pubkey` as the honest cross-machine path? Also: a missing .loki/state/last-proof-id.txt makes legacy verify skip the receipt check entirely and pass (pre-existing, A-134) | autonomy/loki (_deploy_receipt_verdict, verify), tests | HIGH | unknown-kid forged token exits non-zero on legacy; honest cross-machine path documented | ready@2026-10-01T02:33Z | CTO decision first; after A-121b |
 | A-110 | One named outcome, fixed exit ladder, --json (items 1 and 5) | see plan A-110 | 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 47ac1ccc is an ancestor of v10.5.13). |
 | A-112 | Baseline subtract: judge only the delta (item 5) | see plan A-112 | 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 69f1a910 is an ancestor of v10.5.13). |
 | A-123 | Doctor: only the selected provider blocks, one Ready line (item 3) | see plan A-123 | MEDIUM | 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 275b4fc0 is an ancestor of v10.5.13). |
 | A-134 | Legacy: receipt after the final commit, chatter behind --verbose (item 2) | see plan A-134 | MEDIUM | 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 7d3edf96 is an ancestor of v10.5.13). |
-| A-134b | A-134 opus notes: (1) standalone autonomy/verify.sh prints no attestation line (only `loki verify` has _deploy_receipt_verdict); print `attestation: UNCHECKED (run via loki verify)` instead of silence; (2) the quiet failure tail grep `[Ff]ailed` matched the RALPH system-prompt line and printed ~1.5k chars; anchor to `^\[(ERROR|WARN)\]` or cap line length; (3) the quiet inner run starts as a background job so its stdin is /dev/null even from a TTY: pause-mode keypress resume changes for quiet runs; (4) `loki quick --verbose` is also the A-122 cmd_quick flag, done | autonomy/verify.sh, autonomy/run.sh | MEDIUM | each note has a test | building@2026-10-01T02:24Z | |
+| A-134b | A-134 opus notes: (1) standalone autonomy/verify.sh prints no attestation line (only `loki verify` has _deploy_receipt_verdict); print `attestation: UNCHECKED (run via loki verify)` instead of silence; (2) the quiet failure tail grep `[Ff]ailed` matched the RALPH system-prompt line and printed ~1.5k chars; anchor to `^\[(ERROR|WARN)\]` or cap line length; (3) the quiet inner run starts as a background job so its stdin is /dev/null even from a TTY: pause-mode keypress resume changes for quiet runs; (4) `loki quick --verbose` is also the A-122 cmd_quick flag, done | autonomy/verify.sh, autonomy/run.sh | MEDIUM | each note has a test | merged@2026-10-01T05:22Z | |
 | A-134c | A-134b r1 review finding: provider call sites in autonomy/run.sh (mainline claude -p at about 25455/25460, provider_invoke_argv about 1050/1053) do not redirect stdin, so under LOKI_VERBOSE=1 (and any non-quiet path) a parent stdin pipe that never closes blocks `claude -p` reading stdin (pre-existing). Fix: `< /dev/null` at provider invocations that pass the prompt as an argument | autonomy/run.sh (provider call sites only), providers/*.sh, tests | MEDIUM | never-closing stdin pipe: verbose `loki quick` completes under timeout 60 | ready@2026-10-01T01:37Z | |
 | A-130 | v10 quiet by default (item 2) | see plan A-130 | MEDIUM | first-run-gate assertion per plan card | released@2026-10-01T01:19Z | Wave per plan section 5; one writer per file. Released in v10.5.14 (merge a518bfea is an ancestor of v10.5.14). |
 | A-130b | A-130 Reason line prints first_error from a failing check verbatim (capped at 200 chars, control chars stripped) but unredacted: a `ghp_` token in a test failure line reaches the terminal. No TS redactor is reachable from engine10 core (only autonomy/lib/proof_redact.py). Port the token patterns to a small TS helper outside core or redact first_error where it is captured in verify | loki-ts/src (util), verify.ts or output.ts, tests | MEDIUM | ghp_/sk- token in first_error prints redacted | released@2026-10-01T02:27Z | ; sonnet APPROVE be50510f (redaction before cap, parity with proof_redact.py) Released in v10.5.16 (merge f214a0fa is an ancestor of v10.5.16). |

package/docs/v10/GUIDE.md

@@ -1,10 +1,20 @@
 # Loki 10 engine guide
 
-Opt-in: set LOKI_ENGINE=v10 <!-- loki10-default -->
-
-Loki 10 is the rewritten engine (docs/v10/ENGINE.md). It is not the default
-yet. Every command below only runs when LOKI_ENGINE=v10 is set; leave it
-unset and `loki` keeps using the current (legacy) engine exactly as before.
+Default: Loki 10 engine for `loki "<task>"`, `loki owner/repo#N` and `loki quick "<task>"`. Set LOKI_ENGINE=legacy or run `loki legacy <args>` for the previous engine. <!-- loki10-default -->
+
+Loki 10 is the rewritten engine (docs/v10/ENGINE.md). Since the D48 flip it
+is the default for three entry points: `loki "<task>"`, `loki owner/repo#N`
+(issue mode) and `loki quick "<task>"`. Each prints one start line,
+`Loki 10 engine (set LOKI_ENGINE=legacy or run 'loki legacy' for the previous
+engine)`, then the summary below. Everything else (`loki start`, `loki
+status`, `loki dashboard` and the rest) is unchanged unless you set
+LOKI_ENGINE=v10 explicitly, which also routes status, verify and dashboard
+to the v10 commands. Bare `loki verify` (no LOKI_ENGINE) follows the newest
+run: when the newest entry in .loki/runs/ is a v10 run newer than the newest
+legacy proof it runs the v10 verify, otherwise the legacy verify. If bun is
+missing or LOKI_PROVIDER is unsupported, the default mode falls back to the
+legacy engine and prints one stderr line saying why. The previous engine stays one step away:
+`loki legacy <args>` and LOKI_ENGINE=legacy.
 
 Some pieces named in this guide are still being built. Each one below says
 so plainly instead of describing a finished feature.
@@ -12,19 +22,34 @@ so plainly instead of describing a finished feature.
 ## Quickstart
 
 Put the task first, as a quoted multi-word string, so bin/loki's router
-sends it to the v10 engine instead of the legacy one. A one-word argument
-that is not an issue ref, or any first argument starting with `-`, stays
-on the legacy engine.
+sends it to the v10 engine. A one-word argument that is not an issue ref,
+or any first argument starting with `-`, stays on the legacy engine.
+
+```
+loki "fix the login redirect loop" --no-pr
+```
+
+`loki quick "<task>"` is the small-task entry. It runs the same engine
+without opening a pull request (the legacy quick never opened one), and the
+engine's own sizing picks the lean path for a small task: Plan and Wall are
+skipped and implement starts on sonnet, escalating to the top model only
+on a real test failure (E-64; `LOKI_E10_CASCADE=0` turns the cascade off).
+`loki quick --help` and a flag-first `loki quick -v "<task>"` stay on the
+legacy quick.
 
 ```
-LOKI_ENGINE=v10 loki "fix the login redirect loop" --no-pr
+loki quick "fix the login redirect loop"
 ```
 
+If bun is not installed, or LOKI_PROVIDER names a provider the v10 engine
+has no invoker for (anything but claude, codex, cline, aider), these entry
+points fall back to the legacy engine instead of failing.
+
 Issue refs work the same way:
 
 ```
-LOKI_ENGINE=v10 loki owner/repo#123
-LOKI_ENGINE=v10 loki https://github.com/owner/repo/issues/123
+loki owner/repo#123
+loki https://github.com/owner/repo/issues/123
 ```
 
 bin/loki routes GitHub, GitLab (`.../-/issues/N`) and Jira
@@ -58,9 +83,13 @@ verify, seal) and then, in the supervisor, the pr stage, ending in the
 Slack is not part of the v10 engine surface (no command, no notification
 hook) and is in progress, tracked with the other wave 3 items.
 
-## The 5-line summary
+## The summary
 
-A finished run prints five lines, one label each:
+A finished run prints the start line, then one label per line (Outcome,
+PR, Receipt, NOT PROVEN, Cost, Time; a Reason line is added for any
+outcome other than VERIFIED or ALREADY_SATISFIED). The quiet default stays
+within 8 lines. The block below is the older 5-line form; the labels are the
+same:
 
 ```
 PR:         https://github.com/owner/repo/pull/1
@@ -81,7 +110,13 @@ Time:       4m12s (intake 11s, plan 20s, implement 3m10s, verify 31s)
   separate `; flaky ...` clause on the same line.
 - **Cost**: the provider-reported dollar figure and token count. When the
   provider does not report cost, this line reads `not measured` instead of
-  `$0.00`; a missing cost is never rendered as free.
+  `$0.00`; a missing cost is never rendered as free. The one exception is the
+  CLI invoker (LOKI_E10_INVOKER=cli, which the first-run gate's stub uses): it
+  has no dollar figure to report, so the run records 0 with the source marker
+  `cli-invoker-unmetered` in the cost event, the receipt (`cost.source`) and
+  the efficiency record, shows `$0.00 (...; CLI invoker records no cost)`, and
+  adds `cost unmetered (CLI invoker; recorded as 0)` to NOT PROVEN. The cost
+  fields are never null on such a run.
 - **Time**: total wall time, then each stage's own duration in parentheses.
 
 This formatter (`loki-ts/src/engine10/output.ts`, `formatSummary`) is
@@ -138,15 +173,12 @@ provider names (`claude`, `codex`, `cline`, `aider`); it is not supported.
 
 ## After the flip
 
-Once v10 becomes the default (docs/v10/DECISIONS.md, D29), `loki`, `loki
-status`, `loki verify` and `loki dashboard` with no `LOKI_ENGINE` set will
-mean the v10 commands described above. The previous engine stays
-reachable through `LOKI_ENGINE=legacy` (bin/loki sends every value other
-than `v10` to it), unchanged. Nothing is removed at the flip. A separate
-legacy alias command is planned (docs/v10/ENGINE.md, E-31) but is not on
-main.
-
-That flip has not happened on main as of this guide. The opt-in line near
-the top of this file and of README.md's section is the one place that
-records which state we are in; it changes in the same commit as the flip
-itself.
+D48 made v10 the default for `loki "<task>"`, `loki owner/repo#N` and
+`loki quick "<task>"`. The previous engine stays fully reachable and
+unchanged: `loki legacy <args>` (prints a short deprecation notice to
+stderr, then runs exactly the pre-flip route for `<args>`) and
+`LOKI_ENGINE=legacy` (the same, without the notice, for scripts). Any
+LOKI_ENGINE value other than v10 or unset also keeps the legacy engine.
+Nothing is removed at the flip. The one place that records which state we
+are in is the marked line near the top of this file and of README.md's
+Loki 10 section; it changed in the same commit as the flip.

package/docs/v10/PROGRESS.md

@@ -1740,3 +1740,23 @@ The swarm is stopped: .loki/V10-STOP exists, the loop has no wake-ups, and the c
 - Fix forward (main already contains it): slice-P0-codeql (constant allowlists for the provider binary and secret file names) in progress; then train with it, then re-cut the release.
 - train/31 731a335d is green on Tests/Parity/Coverage but its Security Audit fails on the same alert; it will not release until the fix lands.
 - D48-flip rejected by opus (bare loki verify still legacy after a default v10 run: FAILED run reads VERIFIED); r2 in progress.
+
+## 2026-10-01T05:22Z v10.5.19 cut (CodeQL fix forward), train/33 pushed
+- train/32 aad61f9a green: Tests, Bun Parity, Coverage (baseline), Security Audit all completed success (watcher bs3ybh02p). main fast-forwarded to aad61f9a.
+- v10.5.19 release commit 47050d65 pushed by SHA (parent == origin/main; --check-clean rc=0). It carries the unpublished 10.5.18 content plus the CodeQL 604-607 fix, A-118 r5 and DOC-01. Release run and auto-promote watcher: bqimqxkgo.
+- Merged on local main: D48-flip r3 (opus APPROVE: FAILED receipt exits 4 with or without --allow-unsigned; dispatch 56/0; gate --stub 0 failed), A-134b r4 (sonnet APPROVE; registration rc=0, shard rc=0, own test 6/0), E-162 (opus APPROVE as CTO call).
+- train/33 63db8710 pushed. Guards: registration rc=0, shard-coverage rc=0 (E2e Features row 19 -> 20 to keep the five heaviest suites in distinct shards), v10-ops rc=0, run-shellcheck rc=0, docs-cli-drift rc=0, release-dist-guard rc=0, budget.test 24 pass.
+- REJECTED, fix rounds building: E-163 (live /usage timeout has no process-group kill), D48-r2 (unsigned receipt exits 0 under --pubkey; merge conflicts with the exit-4 change).
+
+## 2026-10-01T05:34Z v10.5.19 published and auto-promoted; train/33 red, flip dropped
+- v10.5.19: Release run 47050d65 completed success; npm view loki-mode@10.5.19 gitHead 47050d6533d7 matches; dist-tags latest=10.5.19 next=10.5.19 (D49 auto-promote). Unblocks the CodeQL P0 (10.5.18 never published).
+- train/33 63db8710 RED: Tests shard 7/8, suite "first-run gate assertion logic (A-02)" (tests/test-first-run-gate.sh): "FAIL clean: gate exit 1". Reproduced locally on 63db8710, not on aad61f9a. Cause: D48-flip r3 added gate checks (engine-start-line, cost-non-null, output-lines 8, bare verify rc 4) that the test's clean fixture does not emit.
+- D46 drop: reverted c2c43fd10 on main (5d25b205; reverted paths identical to aad61f9a; local test-first-run-gate rc=0, 0 FAIL). train/34 5d25b205 pushed with E-163 r3 (haiku fix; env parse probes abc/-5/nan/inf/0 -> 20, 46/0), A-134b r4, E-162.
+- D48-flip r4 (fixture fix) building; D48-r2b (pubkey, null-jwt exits 3 under --pubkey) built, in opus re-review; it needs the flip re-landed first.
+
+## 2026-10-01T06:07Z v10.5.20 promoted; v10.5.21 (D48 engine flip) released; train/39
+- v10.5.20 240f3285: Release success; npm gitHead 240f3285f42b matches; dist-tags latest=10.5.20 next=10.5.20 (auto-promote, watcher bybzbhat6). Contents A-134b, E-162, E-163.
+- train/35 RED (Tests shard 1/8: "1 command(s) absent from 'loki help': keys"). D46 drop of D48-r2b (76e3d25c, revert clean vs flip-r4 merge). Fix r2c 2e7c68a3 (one help line), re-landed as 3eade3d4; train/37 green on Tests, Bun Parity, Coverage, Security Audit.
+- train/36 76e3d25c green (all four); main fast-forwarded; v10.5.21 189f347e pushed (--check-clean rc=0, parent == origin/main). CHANGELOG corrected: the flip's Unreleased notes said "loki verify unchanged"; r3 routes bare verify to v10 when the newest run is a v10 run (bin/loki:296-305), exit 4 for a non-VERIFIED outcome. Watcher bpighrue2.
+- Tier A red on every train since train/33: E-162 ran tests/test-shard-coverage.sh before the Python deps install; two pytest-gated suites (run-all-tests.sh:782-787) were not registered, 666 of 668. Fix 55d559ea moves the step after pip install (train/38).
+- train/39 c34511e5 = flip + keys (D48 rows 2, 7-9) + Tier A fix + 10.5.21 merge; local help, registration, shard-coverage, docs-drift, v10-ops all rc=0.