loki-mode 7.5.9 → 7.5.11

package/README.md

@@ -1,6 +1,6 @@
 <div align="center">
 
-# Loki Mode
+# Loki Mode aka Autonomi
 
 ### Build the future, faster.
 
@@ -18,7 +18,7 @@
 
 ---
 
-> **How it works:** You provide a PRD. Loki Mode classifies complexity (`run.sh:detect_complexity()`), assembles an agent team from 41 specialized types across 8 swarms, and runs autonomous RARV cycles (Reason - Act - Reflect - Verify, see `run.sh:run_autonomous()`) with 11 quality gates (see `skills/quality-gates.md`). Code is not "done" until it passes automated verification. Output is a Git repo with source, tests, configs, and audit logs.
+> **How it works:** Drop a spec -- a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. Loki Mode classifies complexity (`run.sh:detect_complexity()`), assembles an agent team from 41 specialized types across 8 swarms, and runs autonomous RARV cycles (Reason - Act - Reflect - Verify, see `run.sh:run_autonomous()`) with 11 quality gates (see `skills/quality-gates.md`). Code is not "done" until it passes automated verification. Output is a Git repo with source, tests, configs, and audit logs.
 
 ---
 
@@ -49,7 +49,9 @@ bun install -g loki-mode
 loki doctor                                   # verify environment
 loki init my-app --template simple-todo-app
 cd my-app
-loki start prd.md                             # autonomous build starts
+loki start prd.md                             # autonomous build from a Markdown PRD
+loki start owner/repo#123                     # ...or a GitHub issue
+loki start ./openapi.yaml                     # ...or an OpenAPI/YAML spec
 ```
 
 Or skip scaffolding and go straight to a quick task:
@@ -64,7 +66,7 @@ loki quick "build a landing page with a signup form"
 |--------|---------|-------|
 | **Bun (recommended)** | `bun install -g loki-mode` | Fastest. v8 will be Bun-only. |
 | **Homebrew** | `brew tap asklokesh/tap && brew install loki-mode` | Auto-installs Bun as a dep |
-| **Docker** | `docker pull asklokesh/loki-mode:7.5.7 && docker run --rm asklokesh/loki-mode:7.5.7 start prd.md` | Bun pre-installed in image |
+| **Docker** | `docker pull asklokesh/loki-mode:7.5.11 && docker run --rm asklokesh/loki-mode:7.5.11 start prd.md` | Bun pre-installed in image |
 | **npm (compat)** | `npm install -g loki-mode` | Works without Bun (bash fallback). Migrate any time with `loki self-update --to bun`. |
 
 **Upgrading:**
@@ -124,7 +126,7 @@ The next major release sunsets the Bash runtime entirely. There is no firm calen
 | Method | Command |
 |--------|---------|
 | **Homebrew** | `brew tap asklokesh/tap && brew install loki-mode` |
-| **Docker** | `docker pull asklokesh/loki-mode:7.5.7` |
+| **Docker** | `docker pull asklokesh/loki-mode:7.5.11` |
 | **Inside Claude Code** | `claude --dangerously-skip-permissions` then type "Loki Mode" |
 | **Git clone** | `git clone https://github.com/asklokesh/loki-mode.git` |
 
@@ -132,6 +134,29 @@ See the full [Installation Guide](docs/INSTALLATION.md).
 
 </details>
 
+<details>
+<summary><strong>Supported spec formats</strong></summary>
+
+A "spec" is whatever you hand `loki start`. Loki auto-detects the format and normalises it before the RARV loop. A Markdown PRD is one form of spec; the table below lists every input the v7.5.11 CLI accepts.
+
+| Format | Example | Notes |
+|--------|---------|-------|
+| Markdown PRD | `loki start ./prd.md` | Canonical form. Headings become section anchors. |
+| JSON spec | `loki start ./spec.json` | Free-form JSON; keys surfaced to agents. |
+| YAML spec | `loki start ./openapi.yaml` | OpenAPI / AsyncAPI / plain YAML all accepted. |
+| Plain text brief | `loki start ./brief.txt` | One-paragraph briefs work; complexity auto-detects to "simple". |
+| GitHub issue URL | `loki start https://github.com/owner/repo/issues/42` | Title + body + labels become the spec. |
+| GitHub shorthand | `loki start owner/repo#42` | Same as above, shorter. |
+| Jira ticket key | `loki start PROJ-456` | Requires `JIRA_BASE_URL` + `JIRA_TOKEN` env vars. |
+| GitLab / Azure DevOps URL | `loki start https://gitlab.com/group/proj/-/issues/7` | GitLab and Azure DevOps issue URLs both supported. |
+| Bare issue number | `loki start #123` or `loki start 123` | Resolved against the current repo's `origin` remote. |
+| OpenSpec change directory | `loki start --openspec ./openspec/change-001` | Reads OpenSpec change manifest + delta files. |
+| Auto-detect (no input) | `loki start` | Picks up `./prd.md`, `./spec.{json,yaml,yml}`, or `./SPEC.md` from cwd. |
+
+All formats land in the same RARV pipeline and pass the same 11 quality gates (`skills/quality-gates.md`).
+
+</details>
+
 ---
 
 ## What You Can Build

package/SKILL.md

@@ -1,12 +1,14 @@
 ---
 name: loki-mode
-description: Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes PRD to deployed product with minimal human intervention. Requires --dangerously-skip-permissions flag.
+description: Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes a spec (PRD, GitHub issue, OpenAPI doc, etc.) to deployed product with minimal human intervention. Requires --dangerously-skip-permissions flag.
 ---
 
-# Loki Mode v7.5.9
+# Loki Mode v7.5.11
 
 **You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
 
+**Spec in, product out.** A "spec" is whatever describes the work: a Markdown PRD, a GitHub issue, an OpenAPI doc, a Jira ticket -- a PRD is one form of spec.
+
 **Multi-provider (stable since v5.0.0):** Claude/Codex/Gemini/Cline/Aider with abstract model tiers and degraded mode for non-Claude providers. See `skills/providers.md`. **Current track (v7.5.x):** Phase 1 RARV-C closure -- real provider judges, gate-failure flock, synthetic PRD e2e, status `--json`, dead code cleanup.
 
 **Runtime migration in progress:** A bash-to-Bun migration is underway on the `feat/bun-migration` branch. The first phase (shipped in v7.3.0) routes a small set of read-only commands -- `version`, `status`, `stats`, `doctor`, `provider show/list`, `memory list/index` -- through a Bun runtime via `bin/loki`. Every other command remains on the Bash runtime (`autonomy/loki`). Rollback is available with `LOKI_LEGACY_BASH=1`. See `UPGRADING.md` and `docs/architecture/ADR-001-runtime-migration.md` for the full plan.
@@ -89,11 +91,11 @@ These rules guide autonomous operation. Test results and code quality always tak
 
 ## Model Selection
 
-**Default since v5.3.0 (reaffirmed in v7.5.9):** Haiku disabled for quality. Use `--allow-haiku` or `LOKI_ALLOW_HAIKU=true` to enable.
+**Default since v5.3.0 (reaffirmed in v7.5.11):** Haiku disabled for quality. Use `--allow-haiku` or `LOKI_ALLOW_HAIKU=true` to enable.
 
 | Task Type | Tier | Claude (default) | Claude (--allow-haiku) | Codex (GPT-5.3) | Gemini |
 |-----------|------|------------------|------------------------|------------------|--------|
-| PRD analysis, architecture, system design | **planning** | opus | opus | effort=xhigh | thinking=high |
+| Spec analysis, architecture, system design | **planning** | opus | opus | effort=xhigh | thinking=high |
 | Feature implementation, complex bugs | **development** | opus | sonnet | effort=high | thinking=medium |
 | Code review (planned: 3 parallel reviewers) | **development** | opus | sonnet | effort=high | thinking=medium |
 | Integration tests, E2E, deployment | **development** | opus | sonnet | effort=high | thinking=medium |
@@ -113,7 +115,7 @@ These rules guide autonomous operation. Test results and code quality always tak
 
 ```
 BOOTSTRAP ──[project initialized]──> DISCOVERY
-DISCOVERY ──[PRD analyzed, requirements clear]──> ARCHITECTURE
+DISCOVERY ──[spec analyzed, requirements clear]──> ARCHITECTURE
 ARCHITECTURE ──[design approved, specs written]──> DEEPEN_PLAN (standard/complex only)
 DEEPEN_PLAN ──[plan enhanced by 4 research agents]──> INFRASTRUCTURE
 INFRASTRUCTURE ──[cloud/DB ready]──> DEVELOPMENT
@@ -187,20 +189,21 @@ This protocol governs **skill module** loading -- task-scoped instruction files
 
 ## Invocation
 
-**Unified entry point (v6.84.0):** `loki start` auto-detects whether the input is a PRD file, an issue URL, or an issue number. No need to pick between `loki start` and `loki run` -- the single command handles all cases.
+**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.
 
 ```bash
 # Standard mode (Claude - full features)
 claude --dangerously-skip-permissions
-# Then say: "Loki Mode" or "Loki Mode with PRD at path/to/prd.md" (or .json)
+# Then say: "Loki Mode" or "Loki Mode with spec at path/to/spec" (PRD .md/.json, OpenAPI .yaml, etc.)
 
 # Unified `loki start` -- one command, auto-detected mode
-loki start                                   # no arg: analyze current dir, auto-generate PRD
-loki start ./prd.md                          # PRD mode (.md/.json/.txt/.yaml)
+loki start                                   # no arg: analyze current dir, auto-generate spec
+loki start ./prd.md                          # PRD mode (.md/.json/.txt/.yaml) -- a PRD is one form of spec
+loki start ./openapi.yaml                    # SPEC mode (OpenAPI doc treated as the spec)
+loki start owner/repo#123                    # ISSUE mode (GitHub specific repo)
 loki start https://github.com/o/r/issues/42  # ISSUE mode (GitHub URL)
 loki start 123                               # ISSUE mode (GitHub issue in current repo)
 loki start PROJ-456                          # ISSUE mode (Jira)
-loki start owner/repo#789                    # ISSUE mode (GitHub specific repo)
 loki start --prd ./prd.md                    # Explicit PRD mode (overrides detection)
 loki start --issue 123                       # Explicit issue mode (overrides detection)
 
@@ -330,6 +333,19 @@ See `references/core-workflow.md` for the full RARV-C contract.
 
 ---
 
+## Concurrency and Security Hardening (v7.5.7 - v7.5.11)
+
+Three back-to-back patches closed cross-process and security gaps. No user-facing behavior change on the default flow; verify via the cited paths.
+
+- **Cross-process file locks** on append-or-rewrite state, so parallel runs / dashboard / MCP do not corrupt shared files: gate counter (`autonomy/run.sh` gate-counter writes), task queues (`autonomy/run.sh` queue read-modify-write), checkpoint index (`autonomy/run.sh` checkpoint index updates), `events.jsonl` append (event emission paths in `events/emit.sh` and `autonomy/run.sh`), human intervention signal files (`autonomy/run.sh:check_human_intervention()` at line ~8059 / 7897 per state-machine doc).
+- **MCP path validation** -- file/path arguments to `mcp/server.py` tools are normalized and rejected if they escape the project root (path-traversal fix from v7.5.8).
+- **Dashboard auth** now required on `/api/memory/*`, `/api/learning/*`, and `/api/status` in `dashboard/server.py` (previously unauthenticated read paths).
+- **Bash quoting hardening** across `autonomy/run.sh` and `autonomy/loki` -- variable expansions inside command substitution and `[ ]` tests quoted to prevent word-splitting on paths with spaces.
+
+See `CHANGELOG.md` entries [7.5.7], [7.5.8], [7.5.11] for the per-fix list and reviewer sign-off.
+
+---
+
 ## Implemented Features
 
 | Feature | Added | Notes |
@@ -342,7 +358,7 @@ See `references/core-workflow.md` for the full RARV-C contract.
 | Notification Triggers | v5.40.0 | `GET/PUT /api/notifications/triggers` |
 | GitHub integration | v5.42.2 | Import, sync-back, PR creation, export. CLI: `loki github`, API: `/api/github/*` |
 | Legacy System Healing | v6.67.0 | `loki heal <path>` -- friction-as-semantics, characterization tests |
-| Unified `loki start` | v6.84.0 | Auto-detects PRD vs issue input |
+| Unified `loki start` | v6.84.0 | Auto-detects spec (PRD, OpenAPI, etc.) vs issue input |
 | Managed Agents (memory mirror) | v7.2.0 | Opt-in via `LOKI_MANAGED_AGENTS` -- see Managed Agents section |
 | Bun runtime (Phase 1) | v7.3.0 | Read-only commands routed through `bin/loki`; `LOKI_LEGACY_BASH=1` to revert |
 | Phase 1 RARV-C closure | v7.5.x | Findings injection, real judges, auto-learnings, handoff.md |
@@ -365,4 +381,4 @@ See `references/core-workflow.md` for the full RARV-C contract.
 
 ---
 
-**v7.5.9 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**
+**v7.5.11 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**

package/VERSION

@@ -1 +1 @@
-7.5.9
+7.5.11

package/autonomy/run.sh

@@ -477,6 +477,18 @@ parse_yaml_with_yq() {
 load_config_file
 
 # Load JSON settings from loki config set (v6.0.0)
+#
+# SECURITY NOTE (v7.5.10, L12#2 audit): The eval below is intentional and safe.
+# The Python script's output is constrained to a fixed template:
+#     [ -z "${VAR:-}" ] && export VAR=<value>
+# where:
+#   - VAR is a hardcoded env var name from the `mapping` dict (NOT user-controlled).
+#   - <value> is produced by shlex.quote(), which emits POSIX-shell-safe single-
+#     quoted strings even for adversarial input (e.g. quotes, semicolons, $()).
+#   - Non-string values from settings.json are skipped (isinstance check).
+# Therefore no user-controlled bytes can break out of the quoted value or alter
+# the surrounding shell syntax. Do NOT remove the shlex.quote() call or relax
+# the isinstance(val, str) guard without re-auditing this eval.
 _load_json_settings() {
     local settings_file="${TARGET_DIR:-.}/.loki/config/settings.json"
     [ -f "$settings_file" ] || return 0
@@ -7100,13 +7112,31 @@ rollback_to_checkpoint() {
     done
 
     # Log the rollback (use python3 for safe JSON serialization)
-    local timestamp
+    # v7.5.10: route through safe_append_event_jsonl() so parallel-worktree
+    # rollbacks cannot interleave partial JSONL lines (POSIX append is
+    # only atomic for <PIPE_BUF and not all platforms honor it).
+    local timestamp rb_event
     timestamp=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
-    _RB_CPID="$checkpoint_id" _RB_SHA="$git_sha" _RB_TS="$timestamp" \
+    rb_event=$(_RB_CPID="$checkpoint_id" _RB_SHA="$git_sha" _RB_TS="$timestamp" \
     python3 -c "
 import json,os
 print(json.dumps({'event':'rollback','checkpoint':os.environ['_RB_CPID'],'git_sha':os.environ['_RB_SHA'],'timestamp':os.environ['_RB_TS']}))
-" >> ".loki/events.jsonl" 2>/dev/null || true
+" 2>/dev/null) || rb_event=""
+    if [ -n "$rb_event" ]; then
+        # Source the emit lib once per call to get safe_append_event_jsonl.
+        # Lib-only mode skips the emit script's normal CLI execution.
+        # shellcheck disable=SC1091
+        if [ -z "${_LOKI_EMIT_LIB_LOADED:-}" ]; then
+            LOKI_EMIT_LIB_ONLY=1 . "$(dirname "${BASH_SOURCE[0]}")/../events/emit.sh" 2>/dev/null \
+                && _LOKI_EMIT_LIB_LOADED=1
+        fi
+        if declare -f safe_append_event_jsonl >/dev/null 2>&1; then
+            safe_append_event_jsonl ".loki/events.jsonl" "$rb_event" 2>/dev/null || true
+        else
+            # Last-resort fallback: bare append (preserves prior behavior).
+            printf '%s\n' "$rb_event" >> ".loki/events.jsonl" 2>/dev/null || true
+        fi
+    fi
 
     log_info "State files restored from checkpoint: ${checkpoint_id}"
 

package/dashboard/__init__.py

@@ -7,7 +7,7 @@ Modules:
     control: Session control API (start/stop/pause/resume)
 """
 
-__version__ = "7.5.9"
+__version__ = "7.5.11"
 
 # Expose the control app for easy import
 try:

package/dashboard/server.py

@@ -740,7 +740,7 @@ async def agent_card() -> dict:
 
 
 # Status endpoint - reads from .loki/ flat files (primary) + DB (fallback)
-@app.get("/api/status", response_model=StatusResponse)
+@app.get("/api/status", response_model=StatusResponse, dependencies=[Depends(auth.require_scope("read"))])
 async def get_status() -> StatusResponse:
     """Get system status from .loki/ session files."""
     loki_dir = _get_loki_dir()

package/dashboard/static/index.html

@@ -527,7 +527,7 @@
         </button>
         <button class="nav-link" data-section="prd-checklist" id="nav-prd-checklist">
           <svg viewBox="0 0 24 24"><path d="M9 11l3 3L22 4"/><path d="M21 12v7a2 2 0 01-2 2H5a2 2 0 01-2-2V5a2 2 0 012-2h11"/></svg>
-          PRD Checklist
+          Spec Checklist
         </button>
         <button class="nav-link" data-section="app-runner" id="nav-app-runner">
           <svg viewBox="0 0 24 24"><polygon points="5 3 19 12 5 21 5 3"/></svg>
@@ -618,10 +618,10 @@
         </div>
       </div>
 
-      <!-- PRD Checklist -->
+      <!-- Spec Checklist -->
       <div class="section-page" id="page-prd-checklist">
         <div class="section-page-header">
-          <h2 class="section-page-title">PRD Checklist</h2>
+          <h2 class="section-page-title">Spec Checklist</h2>
         </div>
         <loki-checklist-viewer id="checklist-viewer"></loki-checklist-viewer>
       </div>
@@ -715,7 +715,7 @@
         <div class="shortcuts-group-title">Navigation</div>
         <div class="shortcut-row"><span class="shortcut-desc">Overview</span><span class="shortcut-keys"><kbd class="shortcut-key">1</kbd></span></div>
         <div class="shortcut-row"><span class="shortcut-desc">Insights</span><span class="shortcut-keys"><kbd class="shortcut-key">2</kbd></span></div>
-        <div class="shortcut-row"><span class="shortcut-desc">PRD Checklist</span><span class="shortcut-keys"><kbd class="shortcut-key">3</kbd></span></div>
+        <div class="shortcut-row"><span class="shortcut-desc">Spec Checklist</span><span class="shortcut-keys"><kbd class="shortcut-key">3</kbd></span></div>
         <div class="shortcut-row"><span class="shortcut-desc">App Runner</span><span class="shortcut-keys"><kbd class="shortcut-key">4</kbd></span></div>
         <div class="shortcut-row"><span class="shortcut-desc">Council</span><span class="shortcut-keys"><kbd class="shortcut-key">5</kbd></span></div>
         <div class="shortcut-row"><span class="shortcut-desc">Quality</span><span class="shortcut-keys"><kbd class="shortcut-key">6</kbd></span></div>
@@ -1267,12 +1267,12 @@ var LokiDashboard=(()=>{var xt=Object.defineProperty;var Qt=Object.getOwnPropert
       </div>
     `}_renderChecklistCard(){let t=this._checklistSummary;if(!t||!t.total)return`
         <div class="overview-card">
-          <div class="card-label">PRD Progress</div>
-          <div class="card-value small-text">${this._data.status==="running"||this._data.status==="autonomous"?"Analyzing PRD...":"No checklist"}</div>
+          <div class="card-label">Spec Progress</div>
+          <div class="card-value small-text">${this._data.status==="running"||this._data.status==="autonomous"?"Analyzing spec...":"No checklist"}</div>
         </div>
       `;let e=Math.round(t.verified/t.total*100),i=t.failing>0?"var(--loki-yellow, #f59e0b)":"var(--loki-green, #22c55e)";return`
       <div class="overview-card">
-        <div class="card-label">PRD Progress</div>
+        <div class="card-label">Spec Progress</div>
         <div class="card-value small-text">${t.verified}/${t.total} (${e}%)</div>
         <div class="mini-progress" style="margin-top:4px;height:4px;background:var(--loki-bg-secondary,#e4e4e7);border-radius:2px;overflow:hidden;">
           <div style="width:${e}%;height:100%;background:${i};transition:width 0.3s;"></div>
@@ -5572,7 +5572,7 @@ var LokiDashboard=(()=>{var xt=Object.defineProperty;var Qt=Object.getOwnPropert
       <style>${this.getBaseStyles()}${this._getStyles()}</style>
       <div class="checklist-viewer">
         <div class="checklist-header">
-          <h2 class="title">PRD Checklist</h2>
+          <h2 class="title">Spec Checklist</h2>
           ${i?this._renderBadges(e.summary):""}
         </div>
         ${i?this._renderGateBanner():""}
@@ -5623,7 +5623,7 @@ var LokiDashboard=(()=>{var xt=Object.defineProperty;var Qt=Object.getOwnPropert
       `}).join(""):'<div class="item" style="color:var(--loki-text-muted)">No items</div>'}_renderEmpty(){return`
       <div class="empty-state">
         <p><strong>No checklist data yet.</strong></p>
-        <p class="hint">The PRD checklist is generated during the first iteration. Start a session with <code>loki start ./prd.md</code> -- groups and items will appear here as the session progresses and can be expanded for details.</p>
+        <p class="hint">The spec checklist is generated during the first iteration. Start a session with <code>loki start ./spec.md</code> (PRD files also accepted) -- groups and items will appear here as the session progresses and can be expanded for details.</p>
       </div>
     `}_attachEventListeners(){let t=this.shadowRoot;t&&(t.querySelectorAll(".category-header[data-category]").forEach(e=>{e.addEventListener("click",()=>this._toggleCategory(e.dataset.category))}),t.querySelectorAll("button[data-waive-id]").forEach(e=>{e.addEventListener("click",i=>{i.stopPropagation(),this._waiveItem(e.dataset.waiveId)})}),t.querySelectorAll("button[data-unwaive-id]").forEach(e=>{e.addEventListener("click",i=>{i.stopPropagation(),this._unwaiveItem(e.dataset.unwaiveId)})}))}_escapeHtml(t){return t?String(t).replace(/&/g,"&amp;").replace(/</g,"&lt;").replace(/>/g,"&gt;").replace(/"/g,"&quot;"):""}};customElements.define("loki-checklist-viewer",Y);var Nt={not_initialized:{color:"var(--loki-text-muted, #71717a)",label:"Not Started",pulse:!1},starting:{color:"var(--loki-yellow, #ca8a04)",label:"Starting...",pulse:!0},running:{color:"var(--loki-green, #16a34a)",label:"Running",pulse:!0},stale:{color:"var(--loki-yellow, #ca8a04)",label:"Stale",pulse:!1},completed:{color:"var(--loki-text-muted, #a1a1aa)",label:"Completed",pulse:!1},failed:{color:"var(--loki-red, #dc2626)",label:"Failed",pulse:!1},crashed:{color:"var(--loki-red, #dc2626)",label:"Crashed",pulse:!1},stopped:{color:"var(--loki-text-muted, #a1a1aa)",label:"Stopped",pulse:!1},unknown:{color:"var(--loki-text-muted, #71717a)",label:"Unknown",pulse:!1}},W=class extends u{static get observedAttributes(){return["api-url","theme"]}constructor(){super(),this._loading=!1,this._error=null,this._api=null,this._pollInterval=null,this._status=null,this._logs=[],this._lastDataHash=null,this._lastLogsHash=null}connectedCallback(){super.connectedCallback(),this._setupApi(),this._loadData(),this._startPolling()}disconnectedCallback(){super.disconnectedCallback(),this._stopPolling()}attributeChangedCallback(t,e,i){e!==i&&(t==="api-url"&&this._api&&(this._api.baseUrl=i,this._loadData()),t==="theme"&&this._applyTheme())}_setupApi(){let t=this.getAttribute("api-url")||window.location.origin;this._api=g({baseUrl:t})}_startPolling(){this._pollInterval=setInterval(()=>this._loadData(),3e3),this._visibilityHandler=()=>{document.hidden?this._pollInterval&&(clearInterval(this._pollInterval),this._pollInterval=null):this._pollInterval||(this._loadData(),this._pollInterval=setInterval(()=>this._loadData(),3e3))},document.addEventListener("visibilitychange",this._visibilityHandler)}_stopPolling(){this._pollInterval&&(clearInterval(this._pollInterval),this._pollInterval=null),this._visibilityHandler&&(document.removeEventListener("visibilitychange",this._visibilityHandler),this._visibilityHandler=null)}async _loadData(){try{let[t,e]=await Promise.all([this._api.getAppRunnerStatus(),this._api.getAppRunnerLogs()]),i=JSON.stringify({status:t?.status,port:t?.port,restarts:t?.restart_count,url:t?.url}),a=JSON.stringify(e?.lines?.slice(-5)||[]),s=a!==this._lastLogsHash;if(i===this._lastDataHash&&!s)return;this._lastDataHash=i,this._lastLogsHash=a,this._status=t,this._logs=e?.lines||[],this._error=null,this.render(),this._scrollLogsToBottom()}catch(t){this._error||(this._error=`Failed to load app status: ${t.message}`,this.render())}}_scrollLogsToBottom(){let t=this.shadowRoot;if(!t)return;let e=t.querySelector(".log-area");e&&(e.scrollTop=e.scrollHeight)}async _handleRestart(){try{await this._api.restartApp(),this._loadData()}catch(t){this._error=`Restart failed: ${t.message}`,this.render()}}async _handleStop(){try{await this._api.stopApp(),this._loadData()}catch(t){this._error=`Stop failed: ${t.message}`,this.render()}}_formatUptime(t){if(!t)return"--";let e=new Date(t),a=Math.floor((new Date-e)/1e3);if(a<60)return`${a}s`;if(a<3600)return`${Math.floor(a/60)}m ${a%60}s`;let s=Math.floor(a/3600),r=Math.floor(a%3600/60);return`${s}h ${r}m`}_isValidUrl(t){if(!t)return!1;try{let e=new URL(t);return e.protocol==="http:"||e.protocol==="https:"}catch{return!1}}_getStyles(){return`
       .app-status {

package/docs/COMPARISON.md

@@ -37,7 +37,7 @@
 |---------|--------------|-----------|-----------|------------|----------|-----------------|--------------|--------------|
 | **Code Review** | 3 blind reviewers + devil's advocate | Basic | Basic | BugBot PR | Property-based | Artifacts | Doc/Review | Basic |
 | **Anti-Sycophancy** | Yes (CONSENSAGENT) | No | No | No | No | No | No | No |
-| **Quality Gates** | 9 gates + PBT | Basic | Sandbox | Tests | Spec validation | Artifact checks | Tests | Permissions |
+| **Quality Gates** | 11 gates + PBT | Basic | Sandbox | Tests | Spec validation | Artifact checks | Tests | Permissions |
 | **Constitutional AI** | Yes (principles) | No | Refusal training | No | No | No | No | No |
 
 ---
@@ -47,7 +47,7 @@
 | Feature | **Loki Mode** | **Devin** | **Codex** | **Cursor** | **Kiro** | **Antigravity** | **Amazon Q** | **OpenCode** |
 |---------|--------------|-----------|-----------|------------|----------|-----------------|--------------|--------------|
 | **Spec-First** | OpenAPI-first | Natural lang | Natural lang | Natural lang | requirements.md, design.md, tasks.md | Natural lang | Natural lang | AGENTS.md |
-| **PRD Support** | Native parsing | Ticket-based | Issue-based | No | Native specs | No | Issue-based | No |
+| **Spec Support (PRD / issue / YAML)** | Native parsing across all three | Ticket-based | Issue-based | No | Native specs | No | Issue-based | No |
 | **Design Docs** | Auto-generates | No | No | No | Yes (design.md) | Artifacts | Yes | No |
 
 ---
@@ -207,7 +207,7 @@
 | **Skills** | Progressive disclosure | 6 slash commands | N/A | 129 skills | N/A | 35 skills | Memory focus |
 | **Multi-Provider** | Yes (Claude/Codex/Gemini) | 3 CLIs (separate) | No | No | No | No | No |
 | **Memory System** | 3-tier (episodic/semantic/procedural) | None | N/A | N/A | Hybrid | N/A | SQLite+FTS5 |
-| **Quality Gates** | 9 gates + Completion Council | User verify only | Two-Stage Review | N/A | Consensus | Tiered | N/A |
+| **Quality Gates** | 11 gates + Completion Council | User verify only | Two-Stage Review | N/A | Consensus | Tiered | N/A |
 | **Context Mgmt** | Standard | Fresh per task (core innovation) | Fresh per task | N/A | N/A | N/A | Progressive |
 | **Autonomy** | High (minimal human) | Semi (checkpoints) | Human-guided | Human-guided | Orchestrated | Human-guided | N/A |
 
@@ -232,7 +232,7 @@ These are patterns from competing projects that are **practically and scientific
 |----------|---------|-------------------------|
 | **Multi-Provider Support** | Only skill supporting Claude, Codex, and Gemini with graceful degradation | All 8 competitors are Claude-only |
 | **RARV Cycle** | Reason-Act-Reflect-Verify is more rigorous than Plan-Execute | Most use simple Plan-Execute |
-| **9-Gate Quality System** | Static analysis + 3 reviewers + devil's advocate + anti-sycophancy + severity blocking + coverage + debate | Superpowers has 2-stage, others have less |
+| **11-Gate Quality System** | Static analysis + 3 reviewers + devil's advocate + anti-sycophancy + severity blocking + coverage + debate + backward-compat (healing) + Phase 1 closure | Superpowers has 2-stage, others have less |
 | **Constitutional AI Integration** | Principles-based self-critique from Anthropic research | None have this |
 | **Anti-Sycophancy (CONSENSAGENT)** | Blind review + devil's advocate prevents groupthink | None have this |
 | **Provider Abstraction Layer** | Clean degradation from full-featured to sequential-only | Claude-only projects can't degrade |
@@ -342,7 +342,7 @@ Tiered agent architecture with explicit escalation:
 
 | Agent | Killer Feature |
 |-------|---------------|
-| **Loki Mode** | Minimal-human-intervention full SDLC, 41 agents in 8 swarms, Constitutional AI, anti-sycophancy, cross-project learning, code transformation, property-based testing |
+| **Loki Mode** | Minimal-human-intervention full SDLC from any spec (PRD, GitHub issue, or YAML), 41 agents in 8 swarms, Constitutional AI, anti-sycophancy, cross-project learning, code transformation, property-based testing |
 | **Devin** | Full software engineer persona, Slack integration, 67% PR merge rate |
 | **OpenAI Codex** | Skills marketplace, $skill-creator, GPT-5.2-Codex, secure sandbox |
 | **Cursor** | 8 parallel agents, BugBot, Memories, $10B valuation, Composer model (250 tok/s) |
@@ -359,7 +359,7 @@ Tiered agent architecture with explicit escalation:
 |-----------|-------------------|
 | **Autonomy** | Designed for high autonomy with minimal human intervention |
 | **Multi-Agent** | 41 specialized agents in 8 swarms vs 1-8 in competitors |
-| **Quality** | 9 gates + blind review + devil's advocate + property-based testing |
+| **Quality** | 11 gates + blind review + devil's advocate + property-based testing |
 | **Research** | 10+ academic papers integrated vs proprietary/undisclosed |
 | **Anti-Sycophancy** | Only agent with CONSENSAGENT-based blind review |
 | **Memory** | 3-tier memory (episodic/semantic/procedural) + review learning + cross-project |

package/docs/INSTALLATION.md

@@ -2,7 +2,7 @@
 
 The flagship product of [Autonomi](https://www.autonomi.dev/). Complete installation instructions for all platforms and use cases.
 
-**Version:** v7.5.9
+**Version:** v7.5.11
 
 ---
 
@@ -128,15 +128,25 @@ package, while `loki-mode-sdk` is the thin client.
 
 ## Quick Start
 
+Drop a spec -- any artifact that describes what you want built -- and Loki
+Mode takes it from spec to deployed app. Specs can be a markdown PRD, a
+GitHub issue URL, or a YAML feature description.
+
 ```bash
-# CLI mode (works with any provider)
-loki start ./prd.md
-loki start ./prd.md --provider codex
-loki start ./prd.md --provider gemini
+# CLI mode (works with any provider) -- spec as markdown PRD
+loki start ./spec.md
+loki start ./spec.md --provider codex
+loki start ./spec.md --provider gemini
+
+# Spec as a GitHub issue
+loki start --github-issue https://github.com/owner/repo/issues/42
+
+# Spec as a YAML feature description
+loki start ./feature.yaml
 
 # Interactive mode (inside your coding agent)
 claude --dangerously-skip-permissions
-# Then say: "Loki Mode with PRD at ./my-prd.md"
+# Then say: "Loki Mode with spec at ./my-spec.md"
 ```
 
 ---
@@ -198,11 +208,11 @@ Run Loki Mode in an isolated Docker container for enhanced security.
 ### Usage
 
 ```bash
-# Run in sandbox mode
-./autonomy/sandbox.sh ./my-prd.md
+# Run in sandbox mode (spec can be PRD, issue link, or YAML)
+./autonomy/sandbox.sh ./my-spec.md
 
 # With provider selection
-./autonomy/sandbox.sh --provider codex ./my-prd.md
+./autonomy/sandbox.sh --provider codex ./my-spec.md
 ```
 
 ### Security Controls
@@ -213,10 +223,10 @@ By default, prompt injection is **disabled** for enterprise safety:
 
 ```bash
 # Default: prompt injection disabled
-./autonomy/run.sh ./my-prd.md
+./autonomy/run.sh ./my-spec.md
 
 # Opt-in to enable prompt injection
-LOKI_PROMPT_INJECTION_ENABLED=true ./autonomy/run.sh ./my-prd.md
+LOKI_PROMPT_INJECTION_ENABLED=true ./autonomy/run.sh ./my-spec.md
 ```
 
 #### Human Input Security
@@ -228,7 +238,7 @@ The `HUMAN_INPUT.md` file has security controls:
 
 ### When to Use Sandbox Mode
 
-- Running untrusted PRD files
+- Running untrusted spec files (PRD, issue export, YAML)
 - Enterprise environments with strict security requirements
 - Automated CI/CD pipelines
 - Multi-tenant deployments
@@ -272,13 +282,13 @@ Use the `--provider` flag when invoking Loki Mode:
 
 ```bash
 # Use Claude (default)
-loki start ./my-prd.md --provider claude
+loki start ./my-spec.md --provider claude
 
 # Use OpenAI Codex
-loki start ./my-prd.md --provider codex
+loki start ./my-spec.md --provider codex
 
 # Use Google Gemini
-loki start ./my-prd.md --provider gemini
+loki start ./my-spec.md --provider gemini
 ```
 
 #### Docker
@@ -289,12 +299,12 @@ Pass the provider as an environment variable:
 # Use Codex with Docker
 docker run -e LOKI_PROVIDER=codex \
   -v $(pwd):/workspace -w /workspace \
-  asklokesh/loki-mode:latest start ./my-prd.md
+  asklokesh/loki-mode:latest start ./my-spec.md
 
 # Use Gemini with Docker
 docker run -e LOKI_PROVIDER=gemini \
   -v $(pwd):/workspace -w /workspace \
-  asklokesh/loki-mode:latest start ./my-prd.md
+  asklokesh/loki-mode:latest start ./my-spec.md
 ```
 
 ### Degraded Mode
@@ -445,7 +455,7 @@ description: Multi-Agent Autonomous Startup System
 
 1. Start a new conversation
 2. Type: `Loki Mode`
-3. Claude should recognize the skill and ask for a PRD
+3. Claude should recognize the skill and ask for a spec (PRD, GitHub issue link, or YAML)
 
 ### For API Console
 
@@ -475,7 +485,7 @@ loki-mode/
 ├── autonomy/             # Autonomous runner (CLI only)
 │   ├── run.sh
 │   └── README.md
-├── templates/            # 22 PRD templates for project scaffolding
+├── templates/            # 22 spec templates (PRD-style) for project scaffolding
 │   ├── simple-todo-app.md
 │   ├── api-only.md
 │   ├── static-landing-page.md
@@ -628,7 +638,7 @@ The completion scripts support:
 * **Smart Context**
 
   * `loki start --provider <TAB>` shows only installed providers (`claude`, `codex`, `gemini`).
-  * `loki start <TAB>` defaults to file completion for PRD templates.
+  * `loki start <TAB>` defaults to file completion for spec files (PRD templates, YAML).
 
 * **Nested Commands**
   Handles specific subcommands for `council`, `memory`, `config`, `audit`, `metrics`, `watchdog`, and `secrets`.
@@ -797,9 +807,9 @@ After installation:
    cd my-app
    ```
 
-3. **Start Building:** Launch autonomous development
+3. **Start Building:** Launch autonomous development from any spec (PRD, GitHub issue, or YAML)
    ```bash
-   loki start prd.md
+   loki start spec.md
    ```
 
 4. **Read Documentation:** Check out [README.md](../README.md) for usage guides

package/docs/cursor-comparison.md

@@ -11,10 +11,10 @@
 |-----------|--------|-----------|--------|
 | **Proven Scale** | 1M+ LoC, large agent count | Benchmarks only | Cursor |
 | **Research Foundation** | Empirical iteration | 25+ academic citations | Loki Mode |
-| **Quality Assurance** | Workers self-manage | 9-gate system + anti-sycophancy | Loki Mode |
+| **Quality Assurance** | Workers self-manage | 11-gate system + anti-sycophancy | Loki Mode |
 | **Anti-Sycophancy** | Not mentioned | CONSENSAGENT blind review | Loki Mode |
 | **Velocity-Quality Balance** | Not mentioned | arXiv-backed metrics | Loki Mode |
-| **Full SDLC Coverage** | Code generation focus | PRD to production + growth | Loki Mode |
+| **Full SDLC Coverage** | Code generation focus | Spec (PRD/issue/YAML) to production + growth | Loki Mode |
 | **Memory Systems** | Not detailed | Episodic/semantic/procedural | Loki Mode |
 | **Scale Patterns** | Battle-tested | Now incorporated (v3.3.0) | Tie |
 
@@ -66,7 +66,7 @@ velocity_quality_balance:
 
 ---
 
-### 3. 9-Gate Quality System
+### 3. 11-Gate Quality System
 
 **Loki Mode's Gates:**
 1. Input Guardrails - Validate scope, detect injection (OpenAI SDK pattern)
@@ -174,7 +174,7 @@ Cursor learned through failure:
 ### 3. Simplicity Principle
 > "A surprising amount of the system's behavior comes down to how we prompt the agents. The harness and models matter, but the prompts matter more."
 
-**Loki Mode:** More complex infrastructure (9 gates, 41 agent types, memory systems). May be over-engineered for some use cases.
+**Loki Mode:** More elaborate infrastructure (11 gates, 41 agent types, memory systems). May be over-engineered for some use cases.
 
 ---
 
@@ -192,10 +192,10 @@ We incorporated Cursor's proven patterns:
 ## Conclusion
 
 **Loki Mode is scientifically better in:**
-- Quality assurance (research-backed 9-gate system)
+- Quality assurance (research-backed 11-gate system)
 - Anti-sycophancy (CONSENSAGENT blind review)
 - Velocity-quality balance (arXiv metrics)
-- Full SDLC coverage (PRD to growth)
+- Full SDLC coverage (spec to growth -- PRD, GitHub issue, or YAML)
 - Memory architecture (episodic/semantic/procedural)
 
 **Cursor is operationally better in:**

package/events/emit.sh

@@ -11,6 +11,82 @@
 #
 # Environment:
 #   LOKI_DIR - Path to .loki directory (default: .loki)
+#
+# Sourcing:
+#   This script can also be sourced (LOKI_EMIT_LIB_ONLY=1) to expose the
+#   safe_append_event_jsonl() helper without performing an emit.
+
+# safe_append_event_jsonl <events_jsonl_path> <line>
+#
+# Cross-process serialized append to .loki/events.jsonl. POSIX append is
+# atomic only for writes <PIPE_BUF (typically 4KB) and not all filesystems
+# honor it; under parallel-worktree contention bare `>>` can interleave
+# partial JSONL lines. This helper serializes appends across processes.
+#
+# Strategy (v7.5.10):
+#   - Prefer flock(1) when available (Linux, util-linux). Uses an
+#     exclusive lock on a sentinel FD bound to <events>.lock so the lock
+#     is released automatically when the subshell exits.
+#   - Fall back to a mkdir() mutex on macOS / BSDs where flock is not
+#     installed by default. mkdir is atomic on POSIX -- exactly one
+#     concurrent caller wins the create. We retry with backoff up to
+#     ~5s, and treat a stale lockdir (>30s old) as abandonable.
+#   - The newline is appended by the helper -- callers pass the JSON
+#     payload only.
+safe_append_event_jsonl() {
+    local events_path="$1"
+    local line="$2"
+    local lock_target="${events_path}.lock"
+    local events_dir
+    events_dir="$(dirname "$events_path")"
+    mkdir -p "$events_dir" 2>/dev/null || true
+
+    if command -v flock >/dev/null 2>&1; then
+        # flock path: bind FD 9 to the sentinel file (created if absent),
+        # take an exclusive lock, append, release on subshell exit.
+        (
+            flock -x 9
+            printf '%s\n' "$line" >> "$events_path"
+        ) 9>"$lock_target"
+        return $?
+    fi
+
+    # Fallback: mkdir-based mutex. mkdir is atomic on POSIX.
+    local lock_dir="${events_path}.lockdir"
+    local attempts=0
+    local max_attempts=500   # ~5s at 10ms sleep
+    while ! mkdir "$lock_dir" 2>/dev/null; do
+        attempts=$((attempts + 1))
+        if [ "$attempts" -ge "$max_attempts" ]; then
+            # Stale lock: if the dir is older than 30s, force-remove it.
+            local age
+            age=$(( $(date +%s) - $(stat -f%m "$lock_dir" 2>/dev/null \
+                                    || stat -c%Y "$lock_dir" 2>/dev/null \
+                                    || echo 0) ))
+            if [ "$age" -gt 30 ]; then
+                rmdir "$lock_dir" 2>/dev/null || rm -rf "$lock_dir" 2>/dev/null || true
+                attempts=0
+                continue
+            fi
+            # Give up -- best-effort write so observability never blocks.
+            printf '%s\n' "$line" >> "$events_path" 2>/dev/null || true
+            return 1
+        fi
+        # Sleep ~10ms (perl avoids `sleep 0.01` portability issues).
+        perl -e 'select(undef,undef,undef,0.01)' 2>/dev/null || sleep 1
+    done
+    # Critical section.
+    printf '%s\n' "$line" >> "$events_path"
+    local rc=$?
+    rmdir "$lock_dir" 2>/dev/null || true
+    return $rc
+}
+
+# Library-only mode: source this file to get safe_append_event_jsonl
+# without executing the emit logic below.
+if [ "${LOKI_EMIT_LIB_ONLY:-0}" = "1" ]; then
+    return 0 2>/dev/null || exit 0
+fi
 
 set -euo pipefail
 

package/loki-ts/dist/loki.js

@@ -423,7 +423,7 @@ Subcommands:
 
 This command is invoked by autonomy/run.sh between iterations. Users
 should not run it directly -- run \`loki start\` instead.
-`,T5;var $6=w(()=>{m();T1();T5=c1});m();import{readFileSync as U6}from"fs";import{resolve as q6,dirname as H6}from"path";import{fileURLToPath as G6}from"url";var o=null;function r1(){if(o!==null)return o;let $="7.5.9";if(typeof $==="string"&&$.length>0)return o=$,o;try{let Q=H6(G6(import.meta.url)),z=E1(Q);o=U6(q6(z,"VERSION"),"utf-8").trim()}catch{o="unknown"}return o}function s1(){return process.stdout.write(`Loki Mode v${r1()}
+`,T5;var $6=w(()=>{m();T1();T5=c1});m();import{readFileSync as U6}from"fs";import{resolve as q6,dirname as H6}from"path";import{fileURLToPath as G6}from"url";var o=null;function r1(){if(o!==null)return o;let $="7.5.11";if(typeof $==="string"&&$.length>0)return o=$,o;try{let Q=H6(G6(import.meta.url)),z=E1(Q);o=U6(q6(z,"VERSION"),"utf-8").trim()}catch{o="unknown"}return o}function s1(){return process.stdout.write(`Loki Mode v${r1()}
 `),0}p();n();m();import{readFileSync as A6,existsSync as T6}from"fs";import{resolve as O6}from"path";var j6=["claude","codex","gemini","cline","aider"];function i1(){let $=O6(P(),"state","provider");if(!T6($))return"";try{return A6($,"utf-8").trim()}catch{return""}}function _6($,Q){return $||Q||process.env.LOKI_PROVIDER||"claude"}function I6($){let Q=i1(),z=_6($,Q);switch(process.stdout.write(`${D}Current Provider${W}
 `),process.stdout.write(`
 `),process.stdout.write(`${A}Provider:${W} ${z}
@@ -506,4 +506,4 @@ Set LOKI_LEGACY_BASH=1 to force the bash CLI for every command.
 `),2}default:return process.stderr.write(`Unknown command: ${Q}
 `),process.stderr.write(z6),2}}process.on("SIGINT",()=>process.exit(130));process.on("SIGTERM",()=>process.exit(143));var _5=await j5(Bun.argv.slice(2));process.exit(_5);
 
-//# debugId=CACEACF76B85BD5C64756E2164756E21
+//# debugId=8438E5E6200ECBFA64756E2164756E21

package/loki-ts/package.json

@@ -5,7 +5,8 @@
   "private": true,
   "type": "module",
   "engines": {
-    "bun": ">=1.3.0"
+    "bun": ">=1.3.0",
+    "node": ">=20.0.0"
   },
   "scripts": {
     "version": "bun src/cli.ts version",

package/mcp/__init__.py

@@ -57,4 +57,4 @@ try:
 except ImportError:
     __all__ = ['mcp']
 
-__version__ = '7.5.9'
+__version__ = '7.5.11'

package/memory/retrieval.py

@@ -295,6 +295,42 @@ class MemoryRetrieval:
         """Get the current namespace."""
         return self._namespace
 
+    # Track which legacy entries we've already warned about to avoid log spam.
+    _LEGACY_WARN_LIMIT = 5
+    _legacy_warned_count: int = 0
+
+    def _belongs_to_namespace(self, result: Dict[str, Any]) -> bool:
+        """
+        Check if a memory result belongs to the current namespace.
+
+        Cross-namespace leak defense (v7.5.10). Storage layer should isolate
+        files by directory, but this filter provides defense-in-depth and
+        handles cases where vector indices span namespaces.
+
+        Behavior:
+        - If self._namespace is None, accept all (backward compat for unscoped retrieval).
+        - If result has "_namespace" matching, accept.
+        - If result lacks "_namespace" (legacy entry written before stamping),
+          log a deprecation warning (rate-limited) and ACCEPT for backward compat.
+        - Otherwise, reject.
+        """
+        if self._namespace is None:
+            return True
+        result_ns = result.get("_namespace")
+        if result_ns is None:
+            # Legacy entry without namespace stamp; accept for backward compat
+            # but warn so operators can re-save to add stamps.
+            if MemoryRetrieval._legacy_warned_count < MemoryRetrieval._LEGACY_WARN_LIMIT:
+                logger.warning(
+                    "Memory entry id=%s lacks '_namespace' stamp (legacy "
+                    "entry). Including in results for backward compatibility. "
+                    "Re-save this entry to enable namespace isolation.",
+                    result.get("id", "<unknown>"),
+                )
+                MemoryRetrieval._legacy_warned_count += 1
+            return True
+        return result_ns == self._namespace
+
     def with_namespace(self, namespace: str) -> "MemoryRetrieval":
         """
         Create a new MemoryRetrieval instance with a different namespace.
@@ -761,7 +797,10 @@ class MemoryRetrieval:
             item["id"] = item_id
             item["_score"] = float(score)
             item["_source"] = collection
-            items.append(item)
+            # Cross-namespace leak defense (v7.5.10): vector indices may be
+            # shared across namespaces, so filter here too.
+            if self._belongs_to_namespace(item):
+                items.append(item)
 
         return items
 
@@ -810,7 +849,8 @@ class MemoryRetrieval:
                     )
                     if data:
                         data["_source"] = "episodic"
-                        results.append(data)
+                        if self._belongs_to_namespace(data):
+                            results.append(data)
 
         # Filter semantic patterns by last_used
         patterns_data = self.storage.read_json("semantic/patterns.json") or {}
@@ -831,7 +871,8 @@ class MemoryRetrieval:
 
                     if since <= last_used_dt <= until:
                         pattern["_source"] = "semantic"
-                        results.append(pattern)
+                        if self._belongs_to_namespace(pattern):
+                            results.append(pattern)
                 except (ValueError, TypeError):
                     continue
 
@@ -1428,7 +1469,8 @@ class MemoryRetrieval:
                     data_copy = dict(data)
                     data_copy["_score"] = score
                     data_copy["_source"] = "episodic"
-                    results.append(data_copy)
+                    if self._belongs_to_namespace(data_copy):
+                        results.append(data_copy)
 
         return results
 
@@ -1457,7 +1499,8 @@ class MemoryRetrieval:
                 pattern_copy = dict(pattern)
                 pattern_copy["_score"] = score
                 pattern_copy["_source"] = "semantic"
-                results.append(pattern_copy)
+                if self._belongs_to_namespace(pattern_copy):
+                    results.append(pattern_copy)
 
         return results
 
@@ -1486,7 +1529,8 @@ class MemoryRetrieval:
                 data_copy = dict(data)
                 data_copy["_score"] = score
                 data_copy["_source"] = "skills"
-                results.append(data_copy)
+                if self._belongs_to_namespace(data_copy):
+                    results.append(data_copy)
 
         return results
 
@@ -1511,7 +1555,8 @@ class MemoryRetrieval:
                 anti_copy = dict(anti)
                 anti_copy["_score"] = score
                 anti_copy["_source"] = "anti_patterns"
-                results.append(anti_copy)
+                if self._belongs_to_namespace(anti_copy):
+                    results.append(anti_copy)
 
         return results
 

package/memory/storage.py

@@ -391,6 +391,11 @@ class MemoryStorage:
         episode_id = episode_data.get("id") or self._generate_id("episode")
         episode_data["id"] = episode_id
 
+        # Stamp namespace so retrieval can verify isolation (cross-namespace
+        # leak defense, v7.5.10). Defaults to DEFAULT_NAMESPACE for unscoped
+        # storage instances.
+        episode_data["_namespace"] = self._namespace or DEFAULT_NAMESPACE
+
         # Determine storage path based on date
         timestamp = episode_data.get("timestamp", datetime.now(timezone.utc).isoformat())
         if isinstance(timestamp, str):
@@ -557,6 +562,8 @@ class MemoryStorage:
             "created_at",
             datetime.now(timezone.utc).isoformat()
         )
+        # Stamp namespace for cross-namespace leak defense (v7.5.10).
+        pattern_data["_namespace"] = self._namespace or DEFAULT_NAMESPACE
 
         patterns_path = self.base_path / "semantic" / "patterns.json"
 
@@ -750,6 +757,8 @@ class MemoryStorage:
             "created_at",
             datetime.now(timezone.utc).isoformat()
         )
+        # Stamp namespace for cross-namespace leak defense (v7.5.10).
+        skill_data["_namespace"] = self._namespace or DEFAULT_NAMESPACE
 
         # Use skill name for filename if available, otherwise use ID
         skill_name = skill_data.get("name", skill_id)

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "loki-mode",
-  "version": "7.5.9",
-  "description": "Loki Mode by Autonomi - Multi-agent autonomous startup system for Claude Code, Codex CLI, and Gemini CLI",
+  "version": "7.5.11",
+  "description": "Loki Mode by Autonomi. Multi-agent autonomous SDLC framework. Spec to deployed app: PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers (Claude Code, OpenAI Codex, Google Gemini, Cline, Aider). 11 quality gates.",
   "keywords": [
     "agent",
     "agent-orchestration",
@@ -102,7 +102,7 @@
   ],
   "scripts": {
     "prepack": "find . -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null; find . -name '*.pyc' -delete 2>/dev/null; if command -v bun >/dev/null 2>&1; then (cd loki-ts && bun install --production && bun run build) || echo 'WARN: loki-ts build failed, using existing dist if present'; else echo 'WARN: bun not on PATH, skipping loki-ts build (using committed dist if present)'; fi; true",
-    "prepublishOnly": "cd dashboard-ui && npm ci && npm run build:all",
+    "prepublishOnly": "cd dashboard-ui && npm ci && npm run build:all && test -f ../dashboard/static/index.html",
     "test": "bash -n autonomy/run.sh && bash -n autonomy/loki && bash -n autonomy/completion-council.sh && bash -n autonomy/app-runner.sh && bash -n autonomy/prd-checklist.sh && bash -n autonomy/playwright-verify.sh && node --test tests/protocols/*.test.js && node --test tests/protocols/a2a/*.test.js && node --test tests/observability/*.test.js && node --test tests/policies/*.test.js && node --test tests/audit/*.test.js && node --test tests/integrations/*.test.js && node --test tests/integrations/jira/*.test.js && node --test tests/integrations/github/*.test.js && node --test tests/integrations/slack/*.test.js && bash tests/managed_memory/test_flag_matrix.sh && bash tests/managed_memory/test_sdk_isolation.sh && bash tests/managed_memory/test_kill_switch.sh && python3 -m unittest tests.managed_memory.test_shadow_write_mock tests.managed_memory.test_retrieve_mock && echo 'All checks passed'",
     "test:visual": "node --experimental-vm-modules node_modules/jest/bin/jest.js dashboard-ui/tests/visual-regression.test.js",
     "test:parity": "node --experimental-vm-modules dashboard-ui/scripts/check-parity.js",
@@ -111,7 +111,7 @@
     "test:integration": "bash tests/integration/run_integration_suite.sh"
   },
   "engines": {
-    "node": ">=18.0.0"
+    "node": ">=20.0.0"
   },
   "os": [
     "darwin",
@@ -124,7 +124,7 @@
     "@opentelemetry/exporter-trace-otlp-http": "^0.57.0"
   },
   "overrides": {
-    "protobufjs": ">=7.5.9"
+    "protobufjs": ">=7.5.6"
   },
   "devDependencies": {
     "@types/node": "^25.2.0",

package/skills/healing.md

@@ -505,3 +505,15 @@ loki heal --report
 # Strict mode: block any behavioral change without approval
 LOKI_HEAL_STRICT=true loki heal ./legacy-app
 ```
+
+## Checkpoint metadata hardening (v7.5.8)
+
+As defense-in-depth for the healing checkpoint store, the checkpoint
+writer now rejects ASCII control characters (U+0000-U+001F except TAB,
+LF, CR, plus U+007F) anywhere in checkpoint metadata keys or values
+before persisting `.loki/healing/checkpoints/<phase>.json`. This blocks
+log-injection and JSON-poisoning vectors where adapter output, friction
+notes, or institutional-knowledge excerpts could smuggle terminal
+escapes or NUL bytes into the resume path. Rejected writes raise a
+typed error and never partially overwrite the prior checkpoint, so
+`loki heal --resume` always restarts from a clean, validated state.

package/skills/quality-gates.md

@@ -160,6 +160,16 @@ are silently dropped at load time. The override council uses a stub
 judge in v7.5.x that approves any of those six trusted proofTypes;
 real provider-backed judges land in Phase 2 of Part B.
 
+**Cross-process gate counter (v7.5.5+)**: the per-iteration gate counter
+at `.loki/state/gate-counter-<iter>.json` is now incremented under a
+cross-process file lock via `withFileLockSync` in
+`loki-ts/src/util/atomic.ts`. Concurrent gate runs (parallel worktrees,
+overlapping `runQualityGates` invocations) no longer race the
+read-modify-write, so override-council quotas and per-finding counters
+remain consistent across processes. The lock file lives at
+`.loki/state/gate-counter-<iter>.json.lock` and is released even on
+crash via the primitive's `finally` cleanup.
+
 ---
 
 ## Guardrails Execution Modes

package/web-app/requirements.txt

@@ -25,3 +25,6 @@ passlib[bcrypt]>=1.7.4
 # Encryption (optional) -- Fernet encryption for user secrets.
 # Needed only for the /api/secrets endpoints in cloud mode.
 cryptography>=41.0.0
+
+# YAML parsing -- used by server.py for config loading
+pyyaml>=6.0