loki-mode 10.6.0 → 10.6.7

package/SKILL.md

@@ -3,7 +3,9 @@ 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 v10.6.0
+# Loki Mode v10.6.7
+
+**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 legacy engine, which still ships and is being removed (`loki start owner/repo#N` still routes to it; prefer `loki owner/repo#N`).
 
 **You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
 
@@ -11,7 +13,7 @@ description: An autonomous software factory that knows what it is supposed to de
 
 **Evidence Receipt (verify it yourself).** Every run writes a receipt to `.loki/proofs/<run_id>/` (opt out with `LOKI_PROOF=0`) that separates deterministic FACTS (git diff with base/head SHAs and a `diff_sha256`, the test command + exit code, the build command + exit code, each gate verdict) from AI ASSESSMENTS (the council verdict, labeled judgment not proof). The headline is computed only from the facts: VERIFIED (tests ran a real command and exited 0, diff non-empty, nothing skipped), VERIFIED WITH GAPS (each gap listed by name), or NOT VERIFIED (a check ran and failed). Inspect and re-check with `loki proof list|show <id>|verify <id>` (aliased `loki receipt`); `loki proof verify` re-hashes the receipt (tamper) and re-derives the diff from the recorded base SHA against the live repo (drift), exiting 0 clean / 1 tamper-or-drift / 2 could not check (64 usage, 66 unknown id; see `docs/exit-codes.md`). This is honesty-of-done, not a claim that the code is bug-free.
 
-**Provider-agnostic (stable since v5.0.0):** runs on Claude/Codex/Cline/Aider with abstract model tiers and degraded mode for non-Claude providers; no vendor lock-in. Gemini deprecated v7.5.18. See `skills/providers.md`. **Current track (v8.0.0):** the Anthropic Agent SDK route (see below), spec-mode expansion for OpenAPI/GraphQL/Postman contracts, the runtime-boot and secret-leak evidence axes, and `loki steer` / `loki why` for mid-run control. Earlier tracks: LSP grounding as a first-class agent tool (v7.7.x) and Phase 1 RARV-C closure (real provider judges, gate-failure flock, synthetic PRD e2e, status `--json`).
+**Provider-agnostic (stable since v5.0.0):** runs on Claude/Codex/Cline/Aider with abstract model tiers and degraded mode for non-Claude providers; no vendor lock-in. Gemini deprecated v7.5.18. See `skills/providers.md`. **Legacy track (v8.0.0):** the Anthropic Agent SDK route (see below), spec-mode expansion for OpenAPI/GraphQL/Postman contracts, the runtime-boot and secret-leak evidence axes, and `loki steer` / `loki why` for mid-run control. Earlier tracks: LSP grounding as a first-class agent tool (v7.7.x) and Phase 1 RARV-C closure (real provider judges, gate-failure flock, synthetic PRD e2e, status `--json`).
 
 **Runtime migration:** Bash-to-Bun migration. Read-only commands (`version`, `status`, `stats`, `doctor`, `provider show/list`, `memory list/index`) flow through Bun runtime via `bin/loki` since v7.3.0. Every other command remains on the Bash runtime (`autonomy/loki`). Rollback: `LOKI_LEGACY_BASH=1`. See `UPGRADING.md` and `docs/architecture/ADR-001-runtime-migration.md`.
 
@@ -105,13 +107,13 @@ These rules guide autonomous operation. Test results and code quality always tak
 | Integration tests, E2E, deployment | **development** | opus | sonnet | effort=high |
 | Unit tests, linting, docs, simple fixes | **fast** | sonnet | haiku | effort=low |
 
-**Parallelization rule (Claude only):** Launch up to 10 agents simultaneously for independent tasks.
+**Parallelization rule (Claude only):** Launch independent tasks in parallel.
 
 **Degraded mode (Codex/Cline/Aider):** No parallel agents or Task tool. Codex has MCP support. Runs RARV cycle sequentially. See `skills/model-selection.md`.
 
 **Git worktree parallelism:** For true parallel feature development, use `--parallel` flag with run.sh. See `skills/parallel-workflows.md`.
 
-**Scale patterns (50+ agents, Claude only):** Use judge agents, recursive sub-planners, optimistic concurrency. See `references/cursor-learnings.md`.
+**Scale patterns (Claude only):** Use judge agents, recursive sub-planners, optimistic concurrency. See `references/cursor-learnings.md`.
 
 ---
 
@@ -195,7 +197,7 @@ This protocol governs **skill module** loading -- task-scoped instruction files
 
 ## Invocation
 
-**Unified entry point (v6.84.0):** `loki start [SPEC|ISSUE-REF]` auto-detects whether the input is a PRD file, an issue URL, an issue number, or another spec format (e.g. OpenAPI). No need to pick between `loki start` and `loki run` -- the single command handles all cases.
+**Legacy entry point (v6.84.0, being removed; for Loki 10 use `loki "<task>"` or `loki owner/repo#N`):** `loki start [SPEC|ISSUE-REF]` auto-detects whether the input is a PRD file, an issue URL, an issue number, or another spec format (e.g. OpenAPI). No need to pick between `loki start` and `loki run` -- the single command handles all cases.
 
 ```bash
 # Standard mode (Claude - full features)
@@ -459,15 +461,16 @@ See `CHANGELOG.md` entries [7.5.7], [7.5.8], [7.5.13] for the per-fix list and r
 | Bun runtime (Phase 2+) | TBD | Migrate write-path commands; tracked on `feat/bun-migration` |
 | Managed Agents multiagent path | TBD | `LOKI_EXPERIMENTAL_MANAGED_*` flags -- RESEARCH PREVIEW, not on live API |
 | Benchmarks | TBD | Runner scripts and datasets exist in `benchmarks/`; no published results |
-| `loki run` removal | next major | Currently a deprecated alias for `loki start` |
+| `loki run` removal | with legacy removal | Currently a deprecated alias for `loki start` |
 
 ## Deprecated
 
 | Item | Deprecated In | Notes |
 |------|---------------|-------|
-| `loki run <issue>` | v6.84.0 | Alias for `loki start`. Will be removed in next major. |
+| `loki run <issue>` | v6.84.0 | Alias for `loki start`. Removal is part of the planned legacy removal. |
+| `loki start`, RARV skill loop | v10.6.6 | Legacy engine, planned for removal; use `loki "<task>"` / `loki owner/repo#N`. |
 | VSCode extension (`vscode-extension/`) | v7.2.0 | No longer actively maintained; dashboard web UI is the supported front-end. |
 
 ---
 
-**v10.6.0 | [Autonomi](https://www.autonomi.dev/) flagship product | ~410 lines core**
+**v10.6.7 | [Autonomi](https://www.autonomi.dev/) flagship product | core skill**

package/VERSION

@@ -1 +1 @@
-10.6.0
+10.6.7

package/autonomy/loki

@@ -1782,6 +1782,7 @@ show_help() {
     echo "  syslog telemetry template test tour trigger trust trust-metrics"
     echo "  ultracode update verify version voice watch watchdog web welcome why"
     echo "  wiki worktree (wt)"
+    echo "  control (preview, needs LOKI_CONTROL=1)"
     echo ""
     echo "Any command: loki <command> --help"
     echo ""
@@ -1871,12 +1872,39 @@ for p in range(int(sys.argv[1]), int(sys.argv[1]) + 100):
 PY
 }
 
+# Fail-closed reuse check for a dashboard found via the ~/.loki/dashboard
+# registry or a busy port: reusable only if /health reports THIS package's
+# version AND realpath, and GET / is 200 text/html. Any missing field, curl
+# error or mismatch means "not ours". Mirrors _loki_dashboard_reusable in run.sh.
+_loki_dashboard_port_is_ours() {
+    local port="$1" want want_pkg health probe
+    case "$port" in ''|*[!0-9]*) return 1 ;; esac
+    want="$(tr -d '[:space:]' <"$SKILL_DIR/VERSION" 2>/dev/null)" || return 1
+    [ -n "$want" ] || return 1
+    want_pkg="$(cd "$SKILL_DIR" 2>/dev/null && pwd -P)" || return 1
+    health="$(curl -s --max-time 2 "http://127.0.0.1:${port}/health" 2>/dev/null)" || return 1
+    case "$health" in
+        *"\"version\":\"${want}\""* | *"\"version\": \"${want}\""*) ;;
+        *) return 1 ;;
+    esac
+    case "$health" in
+        *"\"package\":\"${want_pkg}\""* | *"\"package\": \"${want_pkg}\""*) ;;
+        *) return 1 ;;
+    esac
+    probe="$(curl -s -o /dev/null -w '%{http_code} %{content_type}' --max-time 2 "http://127.0.0.1:${port}/" 2>/dev/null)" || return 1
+    case "$probe" in "200 text/html"*) return 0 ;; esac
+    return 1
+}
+
 cmd_ui() {
     local port="" pid=""
     if [ -f "$DASHBOARD_PID_FILE" ]; then
         pid=$(cat "$DASHBOARD_PID_FILE" 2>/dev/null)
         if [ -n "$pid" ] && kill -0 "$pid" 2>/dev/null; then
             port=$(cat "${DASHBOARD_PID_DIR}/port" 2>/dev/null)
+            # A registry entry whose live server is not this package's dashboard
+            # (stale, foreign worktree, other version) is never reused.
+            _loki_dashboard_port_is_ours "$port" || port=""
         fi
     fi
     if [ -z "$port" ]; then
@@ -3758,9 +3786,18 @@ cmd_start() {
                 # + cockpit, honoring the card's "open dashboard" promise. The
                 # cockpit hint is printed by _loki_start_handoff for the Both path.
                 args+=("--bg")
-                local _du="http://127.0.0.1:${LOKI_DASHBOARD_PORT:-57374}"
-                # stdout must stay unredirected: loki_open_url checks the TTY.
-                loki_open_url "$_du" 2>/dev/null &
+                # Open the URL the runner PUBLISHES for the port it actually bound
+                # or reused (it walks past refused ports); never guess the default
+                # 57374, which may be a foreign or stale dashboard. stdout must
+                # stay unredirected: loki_open_url checks the TTY.
+                local _dfile="${PWD}/.loki/dashboard/url"
+                rm -f "$_dfile" 2>/dev/null
+                (
+                    for _ in $(seq 1 120); do
+                        if [ -s "$_dfile" ]; then loki_open_url "$(head -1 "$_dfile")" 2>/dev/null; exit 0; fi
+                        sleep 0.5
+                    done
+                ) &
                 ;;
             launch-bg-watch)
                 # Watch (cockpit only) detaches without opening the browser.
@@ -7481,13 +7518,15 @@ cmd_dashboard_start() {
     if [ -f "$DASHBOARD_PID_FILE" ]; then
         local existing_pid
         existing_pid=$(cat "$DASHBOARD_PID_FILE" 2>/dev/null)
-        if [ -n "$existing_pid" ] && kill -0 "$existing_pid" 2>/dev/null; then
+        if [ -n "$existing_pid" ] && kill -0 "$existing_pid" 2>/dev/null \
+            && _loki_dashboard_port_is_ours "$(cat "${DASHBOARD_PID_DIR}/port" 2>/dev/null)"; then
             echo -e "${YELLOW}Dashboard server already running (PID: $existing_pid)${NC}"
             echo ""
             cmd_dashboard_status
             exit 0
         fi
-        # Stale PID file, remove it
+        # Stale PID file, or a live server that is not this package's dashboard
+        # (never killed here, just not reused): remove the registry entry.
         rm -f "$DASHBOARD_PID_FILE"
     fi
 
@@ -21581,7 +21620,7 @@ status stop pause resume monitor watch watchdog dashboard web open preview share
 memory context ctx checkpoint state report kpis cost metrics stats logs otel \
 syslog telemetry crash config provider doctor setup-skill onboard quickstart \
 welcome update self-update rollback failover cluster enterprise remote deploy docker \
-sandbox api mcp magic compound assets export wiki docs explain why audit compliance \
+sandbox api mcp magic compound assets export wiki control docs explain why audit compliance \
 secrets analyze optimize bench ci reset cleanup notify trigger voice sentrux \
 worktree wt projects cp rc trust-metrics serve agent code self_update test help version"
     local best
@@ -22072,6 +22111,9 @@ main() {
         wiki)
             cmd_wiki "$@"
             ;;
+        control)
+            cmd_control "$@"
+            ;;
         magic)
             cmd_magic "$@"
             ;;
@@ -33803,6 +33845,35 @@ cmd_outcomes() {
     LOKI_DIR="${LOKI_DIR:-.loki}" python3 "$lib" "$@"
 }
 
+# loki control -- D56 control plane (preview). The live route is the Bun CLI
+# (loki-ts/src/commands/control.ts); this is the LOKI_LEGACY_BASH / no-shim
+# fallback. It keeps the gate and help in bash and hands the work to Bun.
+cmd_control() {
+    local sub="${1:-}"
+    case "$sub" in
+        ""|-h|--help|help)
+            echo "Usage: loki control <command> [options]   (preview, requires LOKI_CONTROL=1)"
+            echo ""
+            echo "Commands:"
+            echo "  serve [--port N] [--db PATH]   Run the control plane + UI on 127.0.0.1"
+            echo "  backfill [DIR]                 Ship DIR/.loki/runs to the control plane"
+            echo "  status                         Show whether the control plane is reachable"
+            return 0
+            ;;
+    esac
+    if [ "${LOKI_CONTROL:-}" != "1" ]; then
+        echo "loki control is in preview. Enable it with: export LOKI_CONTROL=1"
+        return 0
+    fi
+    local cli="$SKILL_DIR/loki-ts/dist/loki.js"
+    if ! command -v bun >/dev/null 2>&1; then
+        echo "loki control requires bun (https://bun.sh)" >&2
+        return 1
+    fi
+    [ -f "$cli" ] || cli="$SKILL_DIR/loki-ts/src/cli.ts"
+    exec bun "$cli" control "$@"
+}
+
 cmd_wiki() {
     local subcmd="${1:-}"
     shift 2>/dev/null || true

package/autonomy/run.sh

@@ -19183,6 +19183,14 @@ _loki_dashboard_reusable() {
     return 1
 }
 
+# Publish the URL of the port actually bound or reused, so the launcher (bg
+# banner, browser opener) never guesses the default 57374 after start_dashboard
+# walked past a refused port.
+_loki_publish_dashboard_url() {
+    mkdir -p .loki/dashboard 2>/dev/null || return 0
+    printf '%s\n' "$1" > .loki/dashboard/url.tmp 2>/dev/null && mv -f .loki/dashboard/url.tmp .loki/dashboard/url 2>/dev/null || true
+}
+
 start_dashboard() {
     loki_background_services_enabled || return 0
     log_header "Starting Loki Dashboard"
@@ -19262,6 +19270,7 @@ start_dashboard() {
     if [ "${DASHBOARD_REUSED:-0}" = "1" ]; then
         export LOKI_DASHBOARD_PORT="$DASHBOARD_PORT"
         log_info "Dashboard already live on port $DASHBOARD_PORT; reusing it."
+        _loki_publish_dashboard_url "http://127.0.0.1:${DASHBOARD_PORT}/"
         return 0
     fi
 
@@ -19419,6 +19428,7 @@ start_dashboard() {
         DASHBOARD_LAST_ALIVE=$(date +%s)
         log_info "Dashboard started (PID: $DASHBOARD_PID)"
         log_info "Dashboard: ${CYAN}${url_scheme}://127.0.0.1:$DASHBOARD_PORT/${NC}"
+        _loki_publish_dashboard_url "${url_scheme}://127.0.0.1:${DASHBOARD_PORT}/"
 
         # Auto-open the dashboard in the browser, but ONLY for an interactive
         # foreground session. loki_open_url (lib/browser-open.sh) refuses on
@@ -28816,6 +28826,8 @@ main() {
         fi
         # Initialize .loki directory first
         mkdir -p .loki/logs
+        # A url left by an earlier run must never be mistaken for this child's.
+        rm -f .loki/dashboard/url
 
         local log_file=".loki/logs/background-$(date +%Y%m%d-%H%M%S).log"
         local pid_file
@@ -28869,6 +28881,19 @@ main() {
         echo "$bg_pid" > "$pid_file"
         register_pid "$bg_pid" "background-session" "log=$log_file"
 
+        # The child picks the dashboard port (it walks past refused ports), so
+        # print the URL it publishes, never the requested default.
+        local _bg_dash_line="disabled (LOKI_DASHBOARD=false)"
+        if [ "$ENABLE_DASHBOARD" = "true" ] && loki_background_services_enabled; then
+            _bg_dash_line="starting (run: loki dashboard url, or see $log_file)"
+            local _bg_i
+            for _bg_i in $(seq 1 60); do
+                if [ -s .loki/dashboard/url ]; then _bg_dash_line="$(head -1 .loki/dashboard/url)"; break; fi
+                kill -0 "$bg_pid" 2>/dev/null || break
+                sleep 0.5
+            done
+        fi
+
         echo ""
         echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
         echo -e "${GREEN}  Loki Mode Running in Background${NC}"
@@ -28878,7 +28903,7 @@ main() {
         echo -e "  ${CYAN}Path:${NC}       $project_path"
         echo -e "  ${CYAN}PID:${NC}        $bg_pid"
         echo -e "  ${CYAN}Log:${NC}        $log_file"
-        echo -e "  ${CYAN}Dashboard:${NC}  http://127.0.0.1:${DASHBOARD_PORT}/"
+        echo -e "  ${CYAN}Dashboard:${NC}  ${_bg_dash_line}"
         echo ""
         echo -e "${YELLOW}Control Commands:${NC}"
         echo -e "  ${DIM}Pause:${NC}      touch .loki/PAUSE"

package/autonomy/telemetry.sh

@@ -168,7 +168,7 @@ _loki_known_command() {
     case "${1:-}" in
         --help|--version|-h|-v|agent|analyze|api|assets\
         |audit|bench|checkpoint|ci|cleanup|cluster|cockpit|code\
-        |completions|compliance|compound|config|context|cost|council|cp\
+        |completions|compliance|compound|config|context|control|cost|council|cp\
         |crash|ctx|dashboard|demo|deploy|docker|docs|doctor\
         |dogfood|enterprise|explain|export|failover|github|grill|handoff\
         |heal|help|import|init|internal|issue|kpis|logs\

package/bin/loki

@@ -350,6 +350,14 @@ case "${LOKI_ENGINE:-$_loki_engine_default}" in
                     *) _e10=1; _e10_args=(--no-pr "${@:2}") ;;
                 esac
                 ;;
+            # D58: `loki start <issue ref|issue URL|"multi-word task">` takes the same v10 path as
+            # `loki <ref>`; any other start call (PRD file, flags first, one word) stays legacy.
+            start)
+                case "${2:-}" in
+                    */*\#[0-9]*|http*://*/issues/*|http*://*/browse/*|*" "*) _e10=1; _e10_args=("${@:2}") ;;
+                    *) _e10=0 ;;
+                esac
+                ;;
             # http*://*/issues/* also covers GitLab's /-/issues/ URLs.
             */*\#[0-9]*|http*://*/issues/*|http*://*/browse/*) _e10=1 ;;
             *" "*) _e10=1 ;;
@@ -559,7 +567,7 @@ fi
 # Two-token routes (provider show/list, memory list/index) match on the first
 # token only; the Bun dispatcher handles subcommand routing internally.
 case "${1:-}" in
-    version|--version|-v|status|stats|doctor|provider|memory|rollback|internal|kpis|trust|proof|receipt|wiki|crash)
+    version|--version|-v|status|stats|doctor|provider|memory|rollback|internal|kpis|trust|proof|receipt|wiki|crash|control)
         # v7.5.2: rollback added (wires loki-ts/src/commands/rollback.ts).
         # v7.5.3: internal added for autonomy/run.sh phase1-hooks calls.
         # v7.5.28: kpis added (Phase K MVP: read-only KPI snapshot).

package/completions/_loki

@@ -206,6 +206,7 @@ function _loki_commands {
         'crash:Crash report management'
         'otel:OpenTelemetry management'
         'wiki:Wiki commands'
+        'control:Control plane (preview, LOKI_CONTROL=1)'
         'backlog:Run every matching open issue, N in parallel'
         'explain:Explain Loki concepts'
         'optimize:Optimization commands'

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 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"
+    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 control 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 control 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__ = "10.6.0"
+__version__ = "10.6.7"
 
 # Expose the control app for easy import
 try:

package/docs/AUDIT-CHAIN-THREAT-MODEL.md

@@ -32,7 +32,7 @@ The history was replaced wholesale and `verifyChain()` reported `valid: true`.
 `dashboard/audit.py` is a separate implementation with the same property:
 genesis is the constant `"0" * 64` (`:58`, `:115`), and `_compute_chain_hash`
 (`:194-200`) is an unkeyed `sha256(prev_hash + entry_json)`. Its own docstring
-at `:197` calls the result tamper-evident. Forged with the writer's exact recipe
+at `:197` overstates what the chain proves. Forged with the writer's exact recipe
 (`json.dumps(entry, sort_keys=True, default=str)`, field `_integrity_hash`,
 `:369-371`), `verify_log_integrity` reports:
 

package/docs/DEMOS.md

@@ -1,24 +1,12 @@
 # Loki Mode -- Interactive Content Index
 
-Complete listing of all interactive HTML experiences in the Loki Mode repository. 13 files total across three categories.
+Complete listing of all interactive HTML experiences in the Loki Mode repository. 8 files total across three categories.
 
-## Walkthroughs (6 HTML files)
+## Overview (1 HTML file)
 
-Located in `docs/walkthrough/`.
-
-| File | Title | Description |
-|------|-------|-------------|
-| `index.html` | Build Your First App | Step-by-step tutorial from PRD to deployment |
-| `architecture.html` | System Architecture | Interactive SVG diagram of the full system |
-| `comparison.html` | Feature Comparison | Loki Mode vs competitor feature matrix |
-| `gallery.html` | Project Gallery | Example projects across categories |
-| `video-placeholder.html` | Build Process Animation | CSS-animated build walkthrough |
-| `hub.html` | Walkthrough Hub | Links to all walkthroughs with categories and estimated durations |
-
-An earlier version of this page also listed `build-demo.html`, `ide-demo.html`,
-`enterprise-demo.html`, `provider-race-demo.html`, `memory-demo.html`, and
-`dashboard-demo.html`. None of those files exist in the repository; they have
-been removed from the list rather than left as broken references.
+`docs/overview.html`: Loki Mode 10 explained in five views (Users, Engineers,
+Architects, Executives, Pitch), with Mermaid flow diagrams. It replaces the six
+legacy-era pages that used to live in `docs/walkthrough/`.
 
 ## Demo Apps (6 HTML files)
 
@@ -43,28 +31,25 @@ Located in `examples/`. Each was generated by Loki Mode from a single prompt.
 
 | Category | Count |
 |----------|-------|
-| Walkthroughs | 6 |
+| Overview | 1 |
 | Demo Apps | 6 |
 | Product Website | 1 |
-| **Total** | **13** |
+| **Total** | **8** |
 
 ## Viewing Locally
 
 All files are self-contained HTML. Open directly in any browser:
 
 ```bash
-# Open the demo hub (links to everything)
-open docs/walkthrough/hub.html
-
-# Open a specific walkthrough
-open docs/walkthrough/architecture.html
+# Open the overview
+open docs/overview.html
 
 # Open a demo app
 open examples/demo-saas-dashboard.html
 
 # Or serve the entire repo with a local server
 python3 -m http.server 8080
-# Then visit http://localhost:8080/docs/walkthrough/hub.html
+# Then visit http://localhost:8080/docs/overview.html
 ```
 
 ## Design
@@ -75,4 +60,4 @@ All interactive content shares these characteristics:
 - **No build step** -- Open in any browser, works offline (except Google Fonts)
 - **Dark theme** -- Consistent dark design with purple accent (#553DE9)
 - **Responsive** -- Adapts to mobile, tablet, and desktop viewports
-- **No external dependencies** -- No npm packages, no CDN libraries, no frameworks
+- **No build step dependencies** -- No npm packages; `docs/overview.html` loads Mermaid from a CDN to draw its diagrams

package/docs/EVALUATING.md

@@ -191,9 +191,8 @@ both of us if you find it here.
 
 - **No published enterprise case studies.** We have adoption signal (fork ratio
   well above the norm for a tool this size) but no named enterprise references.
-- **No independent third-party benchmark placement.** The SWE-bench Verified
-  leaderboard is months stale and every entry on it is self-reported, ours would
-  be too.
+- **No independent third-party benchmark placement.** Public leaderboards are
+  self-reported, and ours would be too.
 - **Only the CLI surface is audited, not whole products.** Section 6 measures
   every named competitor that ships a local CLI (opencode, aider, codex, Claude
   Code, cursor-agent) and none exposes output verification. That is a real

package/docs/INSTALLATION.md

@@ -2,7 +2,9 @@
 
 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:** v10.6.0
+**Version:** v10.6.7
+
+**Engine note:** `loki "<task>"`, `loki owner/repo#N` and `loki quick` run the Loki 10 engine. `loki start` still routes to the legacy engine, which is being removed (planned work resumes 2026-10-07); prefer `loki owner/repo#N`. See [docs/v10/GUIDE.md](v10/GUIDE.md).
 
 ---
 
@@ -149,10 +151,9 @@ Install Loki Mode without the bundled bun binary. This reduces the package size
 - OpenTelemetry instrumentation packages
 
 **What happens:**
-- The legacy bash engine runs when loki is invoked
-- Each `loki` command that would use the Loki 10 engine prints this as the first line on stderr: "loki: the Loki 10 engine cannot run on this machine: no working bun (none on PATH, and the bundled bun for darwin-aarch64 is missing). Running the legacy engine instead. To fix: install bun from https://bun.sh, or reinstall loki-mode without --omit=optional."
+- Loki 10 requires Bun. Each `loki` command prints an error on stderr if Bun is not found: "loki: the Loki 10 engine cannot run on this machine: no working bun (none on PATH, and the bundled bun for darwin-aarch64 is missing). To fix: install bun from https://bun.sh, or reinstall loki-mode without --omit=optional."
 
-**To restore Loki 10 engine access:**
+**To restore Loki access:**
 - Install bun: `curl -fsSL https://bun.sh/install | bash` or `brew install oven-sh/bun/bun`
 - Or reinstall loki-mode without the flag: `npm install -g loki-mode`
 
@@ -164,7 +165,7 @@ Install Loki Mode without the bundled bun binary. This reduces the package size
 brew tap asklokesh/tap && brew install loki-mode
 ```
 
-Installs the `loki` CLI. For the Loki 10 default engine the formula in `asklokesh/tap` needs bun; if bun is not installed, run `brew install oven-sh/bun/bun`. Without bun, each Loki 10 command prints the "no working bun" line and runs the legacy engine (see Slim install above).
+Installs the `loki` CLI. Loki 10 requires Bun; if bun is not installed, run `brew install oven-sh/bun/bun`. Without bun, each command exits 1 with an error message.
 
 To also install the skill for interactive use with all providers:
 

package/docs/TOOLS.md

@@ -607,7 +607,7 @@ Model cost advisor -- /tmp/ws
   Projected saving:    UNKNOWN
   Records found: 0  measured: 0  priced: 0
 
-  Cited external benchmark (SWE-bench verified) -- NOT a measurement of your workload:
+  Cited external benchmark -- NOT a measurement of your workload:
     MiniMax M2.5 (open weights)    score 75.8   cost $36.64
     Claude Opus 4.6                score 75.6   cost $275.76
     the harness itself was worth about 3.4 points on an identical model

package/docs/air-gapped.md

@@ -13,7 +13,7 @@ Verified from vendor documentation, 2026-07-31:
 | Cursor | No. Cloud service; embeddings are uploaded (obfuscated and encrypted). |
 | Claude Code | Partly. Runs against Bedrock / Vertex / Foundry in your own cloud, so data residency is yours -- but a model endpoint is still required. |
 | Lovable, Replit, Emergent | No. Browser products on their infrastructure. |
-| opencode | Structurally yes (MIT, self-hostable) -- but no SOC2, SSO, audit logs, or support. |
+| opencode | Structurally yes (MIT, self-hostable) -- but no SSO, audit logs, or support. |
 
 Devin's is the strongest enterprise packaging in the category and it still
 cannot run disconnected. That is a structural property of a hosted control

package/docs/dashboard-guide.md

@@ -26,6 +26,8 @@ The dashboard automatically syncs with Loki Mode when it's running, polling `das
 
 **Ports:** The dashboard and API run on unified port **57374** (FastAPI serves both). See [INSTALLATION.md](INSTALLATION.md#ports) for details.
 
+**Bound port:** if 57374 is held by something that is not this install's dashboard (another project, an older version, a foreign process), Loki walks to the next free port and never reuses or opens the foreign one. `loki start` and `loki dashboard` open and print the URL of the port actually bound; `loki start` publishes it to `.loki/dashboard/url`. A running dashboard is reused only when its `/health` reports the same version and install path.
+
 ---
 
 ## UI Components

package/docs/dev/project-structure.md

@@ -72,7 +72,7 @@ autonomy/                   # Runtime and autonomous execution
   context-tracker.py        # Context window usage tracking
   notification-checker.py   # Notification trigger evaluation
 templates/                  # 21 PRD templates (saas, cli, discord-bot, etc.)
-benchmarks/                 # SWE-bench and HumanEval benchmarks
+benchmarks/                 # benchmark harnesses
 ```
 
 ## Codebase Knowledge Graph (Quick Reference)

package/docs/dev/release-checklist.md

@@ -157,6 +157,5 @@ gh release view vX.Y.Z
 ## Testing
 
 ```bash
-./benchmarks/run-benchmarks.sh humaneval --execute --loki
-./benchmarks/run-benchmarks.sh swebench --execute --loki
+npm test
 ```

package/docs/enterprise/architecture.md

@@ -202,7 +202,7 @@ Key methods:
 - `AuditLog.verifyChain()` -- Verify hash chain integrity, returns `{ valid, entries, brokenAt, error }`
 - `AuditLog.readEntries(filter)` -- Query entries with `who`, `what`, `since`, `until` filters
 
-The public API at `src/audit/index.js` adds compliance reporting (`generateReport('soc2'|'iso27001'|'gdpr')`) and data residency checks (`checkProvider(provider, region)`).
+The public API at `src/audit/index.js` adds audit report summaries and data residency checks (`checkProvider(provider, region)`).
 
 **Python Audit (Dashboard-Level):** `dashboard/audit.py`
 

package/docs/siem-integration.md

@@ -474,8 +474,8 @@ enterprise:
 ## Compliance Reporting
 
 **Loki does not generate framework-specific compliance reports.** An earlier
-version of this page showed `loki enterprise audit export --format soc2|hipaa|pci`
-and `loki compliance report --framework <name>`. Neither exists:
+version of this page showed framework-specific export and report commands.
+They do not exist:
 `loki enterprise audit` has only `summary` and `tail`, and `loki compliance`
 has only `snapshot`.
 

package/docs/v10/CONTROL-PLANE.md

@@ -73,7 +73,7 @@ Rules for every card: file sets do not overlap; only CP-02 touches supervisor.ts
 |---|---|---|---|---|
 | CP-00 | Corpus: events.jsonl and receipts written by the real supervisor under the engine10 e2e fake sessions (VERIFIED, PARTIAL, FAILED, BLOCKED, cap.hit, tampered, unpriced cost, resumed). `packages/control-plane/test/fixtures/runs/` + `EXPECTED.json` | EXPECTED.json counts equal a direct `fold()` over each file | LOW | none |
 | CP-01 | **Parallel A.** Service + DB: `src/server/{app,ingest,runs}.ts`, `src/db/{schema,migrate}.ts`, `drizzle/`, `package.json` | ingest corpus twice: run count, verdict counts, cost_usd (null where expected), duplicate=all on 2nd pass; changed line gives 409 | MEDIUM | CP-00 |
-| CP-02 | **Parallel B.** Shipper + backfill: `src/shipper/{ship,backfill}.ts`, hook `loki-ts/src/engine10/ship_hook.ts`, one line each in supervisor.ts and registry.ts | backfill corpus into a CP-01 stub server; kill mid-batch, rerun: every event exactly once; redacted token never appears in the posted body; ship.json advances | MEDIUM | CP-00 |
+| CP-02 | **Parallel B.** Shipper + backfill: `src/shipper/{ship,backfill}.ts`, hook `loki-ts/src/e10ext/ship_hook.ts`, one line each in supervisor.ts and registry.ts | backfill corpus into a CP-01 stub server; kill mid-batch, rerun: every event exactly once; redacted token never appears in the posted body; ship.json advances | MEDIUM | CP-00 |
 | CP-03 | **Parallel C.** UI: `ui/` (Vite, React, Tailwind), Runs list with filters, run detail timeline, receipt and NOT PROVEN panel; empty states | build, render against section 4 JSON captured from the corpus: row count, verdict badges and NOT PROVEN items match EXPECTED.json; empty DB shows "no runs ingested" | MEDIUM | CP-00 |
 | CP-04 | Wire: service serves `ui/dist`; `loki control [serve,backfill,status]` in autonomy/loki + loki-ts cli; bundle into the npm package (`files[]`) | `npm pack` tarball contains server and UI; `loki control serve` + backfill corpus: /v1/runs count = corpus | MEDIUM | 01,02,03 |
 | CP-05 | Local lifecycle: `src/local/lifecycle.ts` (instance.json, reuse rule, restart, replay) | stale-version instance not reused; dead pid restarted and replayed; never touches unrecorded pid | MEDIUM | CP-04 |