@harness-engineering/cli 1.11.0 → 1.13.0

package/dist/agents/skills/gemini-cli/harness-execution/SKILL.md

@@ -33,20 +33,29 @@ Deviating from the plan mid-execution introduces untested assumptions, breaks ta
      path: "<project-root>",
      intent: "Execute plan tasks starting from current position",
      skill: "harness-execution",
+     session: "<session-slug-if-known>",
      include: ["state", "learnings", "handoff", "validation"]
    })
    ```
 
+   **Session resolution:** If a session directory is known (passed via autopilot dispatch or available from a previous handoff), include the `session` parameter. This scopes all state reads/writes to `.harness/sessions/<slug>/`. If no session is known, omit it — `gather_context` falls back to global files at `.harness/`.
+
    This returns `state` (current position — if null, this is a fresh start at Task 1), `learnings` (hard-won insights from previous sessions — do not ignore them), `handoff` (structured context from the previous skill), and `validation` (current project health). If any constituent fails, its field is null and the error is reported in `meta.errors`.
 
-3. **Check for known dead ends.** Review `learnings` entries tagged `[outcome:failure]`. If any match approaches in the current plan, surface warnings before proceeding.
+3. **Load session summary for cold start.** If resuming a session (session slug is known), read the session summary for quick orientation:
+   - Call `listActiveSessions()` to read the session index (~100 tokens).
+   - If the target session is known, call `loadSessionSummary()` for that session (~200 tokens).
+   - If ambiguous (multiple active sessions, no clear target), present the index to the user and ask which session to resume.
+   - The summary provides skill, phase, status, key context, and next step — enough to orient without re-reading full state + learnings + plan.
+
+4. **Check for known dead ends.** Review `learnings` entries tagged `[outcome:failure]`. If any match approaches in the current plan, surface warnings before proceeding.
 
-4. **Verify prerequisites.** For the current task:
+5. **Verify prerequisites.** For the current task:
    - Are dependency tasks marked complete in state?
    - Do the files referenced in the task exist as expected?
    - Does the test suite pass? Run `harness validate` to confirm a clean baseline.
 
-5. **If prerequisites fail,** do not proceed. Report what is missing and which task is blocked.
+6. **If prerequisites fail,** do not proceed. Report what is missing and which task is blocked.
 
 ### Graph-Enhanced Context (when available)
 
@@ -220,7 +229,7 @@ emit_interaction({
 
 Between tasks (especially between sessions):
 
-1. **Update `.harness/state.json`** with current position, progress, and `lastSession` context:
+1. **Update state (session-scoped `{sessionDir}/state.json` if session is known, otherwise `.harness/state.json`)** with current position, progress, and `lastSession` context:
 
    ```json
    {
@@ -241,7 +250,7 @@ harness scan [path]
 
 Skipping this step means subsequent graph queries (impact analysis, dependency health, test advisor) may return stale results.
 
-2. **Append tagged learnings to `.harness/learnings.md`.** Tag every entry with skill and outcome:
+2. **Append tagged learnings to the session-scoped learnings file (`{sessionDir}/learnings.md` if session is known, otherwise `.harness/learnings.md`).** Tag every entry with skill and outcome:
 
    ```markdown
    ## YYYY-MM-DD — Task N: <task name>
@@ -251,9 +260,9 @@ Skipping this step means subsequent graph queries (impact analysis, dependency h
    - [skill:harness-execution] [outcome:decision] What was decided and why
    ```
 
-3. **Record failures in `.harness/failures.md`** if any task was escalated after retry exhaustion (from Phase 2 Step 5). Include the approach attempted and why it failed, so future sessions avoid the same dead end.
+3. **Record failures in the session-scoped failures file (`{sessionDir}/failures.md` if session is known, otherwise `.harness/failures.md`)** if any task was escalated after retry exhaustion (from Phase 2 Step 5). Include the approach attempted and why it failed, so future sessions avoid the same dead end.
 
-4. **Write `.harness/handoff.json`** with structured context for the next skill or session:
+4. **Write the session-scoped handoff (`{sessionDir}/handoff.json` if session is known, otherwise `.harness/handoff.json`)** with structured context for the next skill or session:
 
    ```json
    {
@@ -266,11 +275,29 @@ Skipping this step means subsequent graph queries (impact analysis, dependency h
    }
    ```
 
-5. **Sync roadmap (mandatory when present).** If `docs/roadmap.md` exists, call `manage_roadmap` with action `sync` and `apply: true` to update linked feature statuses from the just-completed execution state. Do not use `force_sync: true` — the human-always-wins rule applies. If `manage_roadmap` is unavailable, fall back to direct file manipulation using `syncRoadmap()` from core. If no roadmap exists, skip silently.
+5. **Write session summary.** Write/update the session summary for cold-start context restoration:
+
+   ```json
+   writeSessionSummary(projectPath, sessionSlug, {
+     session: "<session-slug>",
+     lastActive: "<ISO timestamp>",
+     skill: "harness-execution",
+     phase: "<current phase of plan>",
+     status: "<e.g., Task 4/6 complete, paused at CHECKPOINT>",
+     spec: "<spec path if known>",
+     plan: "<plan path>",
+     keyContext: "<1-2 sentences: what was accomplished, key decisions made>",
+     nextStep: "<what to do next when resuming>"
+   })
+   ```
+
+   This overwrites any previous summary for this session. The index.md is updated automatically.
+
+6. **Sync roadmap (mandatory when present).** If `docs/roadmap.md` exists, call `manage_roadmap` with action `sync` and `apply: true` to update linked feature statuses from the just-completed execution state. Do not use `force_sync: true` — the human-always-wins rule applies. If `manage_roadmap` is unavailable, fall back to direct file manipulation using `syncRoadmap()` from core. If no roadmap exists, skip silently.
 
-6. **Learnings are append-only.** Never edit or delete previous learnings. They are a chronological record.
+7. **Learnings are append-only.** Never edit or delete previous learnings. They are a chronological record.
 
-7. **Auto-transition to verification.** When ALL tasks in the plan are complete (not when stopping mid-plan):
+8. **Auto-transition to verification.** When ALL tasks in the plan are complete (not when stopping mid-plan):
 
    Call `emit_interaction`:
 
@@ -325,8 +352,8 @@ These are non-negotiable. When any condition is met, stop immediately.
 - **`harness check-deps`** — Run when tasks add new imports or modules. Catches boundary violations early.
 - **`harness state show`** — View current execution position and progress.
 - **`harness state learn "<message>"`** — Append a learning from the command line.
-- **`.harness/state.json`** — Read at session start to resume position. Updated after every task.
-- **`.harness/learnings.md`** — Append-only knowledge capture. Read at session start for prior context.
+- **State file** — Session-scoped at `{sessionDir}/state.json` when session is known, otherwise `.harness/state.json`. Read at session start to resume position. Updated after every task.
+- **Learnings file** — Session-scoped at `{sessionDir}/learnings.md` when session is known, otherwise `.harness/learnings.md`. Append-only knowledge capture. Read at session start for prior context.
 - **Roadmap sync** — After completing plan execution, call `manage_roadmap` with action `sync` and `apply: true` to update roadmap status. Mandatory when `docs/roadmap.md` exists. Do not use `force_sync: true`. Falls back to `syncRoadmap()` from core if MCP tool is unavailable.
 - **`emit_interaction`** -- Call at plan completion to auto-transition to harness-verification. Uses auto-transition (proceeds immediately without user confirmation).
 

package/dist/agents/skills/gemini-cli/harness-planning/SKILL.md

@@ -193,22 +193,39 @@ When presenting the task breakdown, use progress markers:
    }
    ```
 
-9. **Request plan sign-off:**
+9. **Write session summary (if session is known).** If running within a session (autopilot dispatch or standalone with session context), write the session summary:
 
    ```json
-   emit_interaction({
-     path: "<project-root>",
-     type: "confirmation",
-     confirmation: {
-       text: "Approve plan at <plan-file-path>?",
-       context: "<task count> tasks, <estimated time> minutes. <one-sentence summary>",
-       impact: "Approving unlocks task-by-task execution. Plan defines exact file paths, code, and commands.",
-       risk: "low"
-     }
+   writeSessionSummary(projectPath, sessionSlug, {
+     session: "<session-slug>",
+     lastActive: "<ISO timestamp>",
+     skill: "harness-planning",
+     status: "Plan complete. <N> tasks defined.",
+     spec: "<spec path if known>",
+     plan: "<plan file path>",
+     keyContext: "<1-2 sentences: what was planned, key decisions>",
+     nextStep: "Approve plan and begin execution."
    })
    ```
 
-10. **Suggest transition to execution.** After the human approves the plan:
+   If no session slug is known (standalone invocation without session context), skip this step.
+
+10. **Request plan sign-off:**
+
+```json
+emit_interaction({
+  path: "<project-root>",
+  type: "confirmation",
+  confirmation: {
+    text: "Approve plan at <plan-file-path>?",
+    context: "<task count> tasks, <estimated time> minutes. <one-sentence summary>",
+    impact: "Approving unlocks task-by-task execution. Plan defines exact file paths, code, and commands.",
+    risk: "low"
+  }
+})
+```
+
+11. **Suggest transition to execution.** After the human approves the plan:
 
     Call `emit_interaction`:
 

package/dist/agents/skills/gemini-cli/harness-roadmap/SKILL.md

@@ -395,6 +395,38 @@ Choice?
    harness validate: passed
    ```
 
+---
+
+### Command: `--query <filter>` -- Query Features by Filter
+
+#### Phase 1: SCAN -- Load Roadmap
+
+1. Check if `docs/roadmap.md` exists.
+   - If missing: error with clear message. "No roadmap found at docs/roadmap.md. Run `--create` first to bootstrap one."
+2. Parse the roadmap (via `manage_roadmap query` or direct read).
+
+#### Phase 2: FILTER -- Apply Query
+
+1. Accept filter patterns:
+   - **Status filter:** `backlog`, `planned`, `in-progress`, `done`, `blocked` -- returns all features with that status
+   - **Milestone filter:** `milestone:<name>` -- returns all features in the named milestone (partial match)
+
+2. Display matching features with their milestone context:
+
+   ```
+   QUERY: <filter>
+
+   Results (N matches):
+     - Feature A (Current Work) .................. in-progress
+     - Feature B (Backlog) ....................... planned
+
+   Total: N matches
+   ```
+
+3. No file writes. This is a read-only operation.
+
+---
+
 ## Harness Integration
 
 - **`manage_roadmap` MCP tool** -- Primary read/write interface for roadmap operations. Supports `show`, `add`, `update`, `remove`, and `query` actions. Use this when MCP is available for structured CRUD.
@@ -422,6 +454,8 @@ Choice?
 16. `--edit` updates `last_manual_edit` timestamp (since changes are human-driven)
 17. Output matches the roadmap markdown format exactly (frontmatter, H2 milestones, H3 features, 5 fields each)
 18. `harness validate` passes after all operations
+19. `--query` filters features by status or milestone and displays results with milestone context
+20. `--query` errors gracefully when no roadmap exists, directing the user to `--create`
 
 ## Examples
 

package/dist/agents/skills/gemini-cli/harness-verification/SKILL.md

@@ -35,6 +35,26 @@ The words "should", "probably", "seems to", and "I believe" are forbidden in ver
 
 ---
 
+### Context Loading
+
+Before running verification levels, load session context if a session slug was provided (e.g., by autopilot dispatch):
+
+```json
+gather_context({
+  path: "<project-root>",
+  intent: "Verify phase deliverables",
+  skill: "harness-verification",
+  session: "<session-slug-if-provided>",
+  include: ["state", "learnings", "validation"]
+})
+```
+
+**Session resolution:** If a session slug is known (passed via autopilot dispatch or available from a previous handoff), include the `session` parameter. This scopes all state reads to `.harness/sessions/<slug>/`. If no session is known, omit it — `gather_context` falls back to global files at `.harness/`.
+
+Use the returned learnings to check for known failures and dead ends relevant to the artifacts being verified.
+
+---
+
 ### Level 1: EXISTS — The Artifact Is Present
 
 For every artifact that was supposed to be created or modified:
@@ -201,6 +221,22 @@ Write `.harness/handoff.json`:
 }
 ```
 
+**Write session summary (if session is known).** If running within a session context, update the session summary:
+
+```json
+writeSessionSummary(projectPath, sessionSlug, {
+  session: "<session-slug>",
+  lastActive: "<ISO timestamp>",
+  skill: "harness-verification",
+  status: "Verification <PASS|FAIL|INCOMPLETE>. <N> artifacts checked, <N> gaps.",
+  spec: "<spec path if known>",
+  keyContext: "<1-2 sentences: verification outcome, any gaps found>",
+  nextStep: "<e.g., Proceed to code review / Resolve gaps>"
+})
+```
+
+If no session slug is known, skip this step.
+
 **If verdict is PASS (all levels passed, no gaps):**
 
 Call `emit_interaction`:
@@ -339,6 +375,12 @@ Task: "Create UserService with create, read, update, delete operations."
 - **When verification reveals the spec itself is incomplete:** Do not fill in the gaps yourself. Escalate to the human: "Verification found that the spec does not define behavior for [scenario]. How should this be handled?"
 - **When you cannot run harness checks:** If `harness validate` or `harness check-deps` cannot be run (missing configuration, broken tooling), this is a blocking issue. Do not skip verification — fix the tooling or escalate.
 
+## Harness Integration
+
+- **`gather_context`** — Used in Context Loading phase (before Level 1) to load session-scoped state, learnings, and validation in a single call. The `session` parameter scopes reads to the session directory when provided by autopilot dispatch.
+- **`harness validate`** — Run during Level 3 (WIRED) to verify artifact integration.
+- **`harness check-deps`** — Run during Level 3 (WIRED) to verify dependency boundaries.
+
 After verification completes, append a tagged learning:
 
 - **YYYY-MM-DD [skill:harness-verification] [outcome:pass/fail]:** Verified [feature]. [Brief note on what was found or confirmed.]

package/dist/{agents-md-ZFV6RR5J.js → agents-md-P2RHSUV7.js}

@@ -1,7 +1,7 @@
 import {
   generateAgentsMd
 } from "./chunk-NKDM3FMH.js";
-import "./chunk-2YSQOUHO.js";
+import "./chunk-KELT6K6M.js";
 import "./chunk-MHBMTPW7.js";
 export {
   generateAgentsMd

package/dist/{architecture-EXNUMH5R.js → architecture-ESOOE26S.js}

@@ -1,11 +1,11 @@
 import {
   checkDependenciesDefinition,
   handleCheckDependencies
-} from "./chunk-TI4TGEX6.js";
+} from "./chunk-WPPDRIJL.js";
 import "./chunk-K6XAPGML.js";
 import "./chunk-IDZNPTYD.js";
 import "./chunk-W6Y7ZW3Y.js";
-import "./chunk-2YSQOUHO.js";
+import "./chunk-KELT6K6M.js";
 import "./chunk-MHBMTPW7.js";
 export {
   checkDependenciesDefinition,

package/dist/bin/harness-mcp.js

@@ -1,24 +1,24 @@
 #!/usr/bin/env node
 import {
   startServer
-} from "../chunk-I6JZYEGT.js";
-import "../chunk-Z75JC6I2.js";
-import "../chunk-GSIVNYVJ.js";
-import "../chunk-PA2XHK75.js";
-import "../chunk-X3MN5UQJ.js";
-import "../chunk-WUJTCNOU.js";
+} from "../chunk-7KQSUZVG.js";
+import "../chunk-MACVXDZK.js";
+import "../chunk-2VU4MFM3.js";
+import "../chunk-7PZWR4LI.js";
+import "../chunk-5VY23YK3.js";
+import "../chunk-LD3DKUK5.js";
 import "../chunk-ZOAWBDWU.js";
-import "../chunk-WJZDO6OY.js";
+import "../chunk-PSNN4LWX.js";
 import "../chunk-2YPZKGAG.js";
-import "../chunk-TI4TGEX6.js";
+import "../chunk-WPPDRIJL.js";
 import "../chunk-K6XAPGML.js";
-import "../chunk-NC6PXVWT.js";
+import "../chunk-MI5XJQDY.js";
 import "../chunk-IDZNPTYD.js";
 import "../chunk-W6Y7ZW3Y.js";
 import "../chunk-HD4IBGLA.js";
 import "../chunk-3WGJMBKH.js";
 import "../chunk-VRFZWGMS.js";
-import "../chunk-2YSQOUHO.js";
+import "../chunk-KELT6K6M.js";
 import "../chunk-MHBMTPW7.js";
 
 // src/bin/harness-mcp.ts

package/dist/bin/harness.js

@@ -1,12 +1,12 @@
 #!/usr/bin/env node
 import {
   createProgram
-} from "../chunk-ZWC3MN5E.js";
+} from "../chunk-RZSUJBZZ.js";
 import "../chunk-VUCPTQ6G.js";
 import {
   findConfigFile,
   loadConfig
-} from "../chunk-2NCIKJES.js";
+} from "../chunk-3KOLLWWE.js";
 import "../chunk-GNGELAXY.js";
 import "../chunk-Q6AB7W5Z.js";
 import "../chunk-TRAPF4IX.js";
@@ -18,18 +18,18 @@ import "../chunk-QPEH2QPG.js";
 import "../chunk-JSTQ3AWB.js";
 import "../chunk-KET4QQZB.js";
 import "../chunk-NKDM3FMH.js";
-import "../chunk-I6JZYEGT.js";
-import "../chunk-Z75JC6I2.js";
-import "../chunk-GSIVNYVJ.js";
-import "../chunk-PA2XHK75.js";
-import "../chunk-X3MN5UQJ.js";
-import "../chunk-WUJTCNOU.js";
+import "../chunk-7KQSUZVG.js";
+import "../chunk-MACVXDZK.js";
+import "../chunk-2VU4MFM3.js";
+import "../chunk-7PZWR4LI.js";
+import "../chunk-5VY23YK3.js";
+import "../chunk-LD3DKUK5.js";
 import "../chunk-ZOAWBDWU.js";
-import "../chunk-WJZDO6OY.js";
+import "../chunk-PSNN4LWX.js";
 import "../chunk-2YPZKGAG.js";
-import "../chunk-TI4TGEX6.js";
+import "../chunk-WPPDRIJL.js";
 import "../chunk-K6XAPGML.js";
-import "../chunk-NC6PXVWT.js";
+import "../chunk-MI5XJQDY.js";
 import "../chunk-IDZNPTYD.js";
 import "../chunk-W6Y7ZW3Y.js";
 import "../chunk-HD4IBGLA.js";
@@ -48,7 +48,7 @@ import {
   readCheckState,
   shouldRunCheck,
   spawnBackgroundCheck
-} from "../chunk-2YSQOUHO.js";
+} from "../chunk-KELT6K6M.js";
 import "../chunk-MHBMTPW7.js";
 
 // src/bin/update-check-hooks.ts

package/dist/{check-phase-gate-VZFOY2PO.js → check-phase-gate-S2MZKLFQ.js}

@@ -1,10 +1,10 @@
 import {
   createCheckPhaseGateCommand,
   runCheckPhaseGate
-} from "./chunk-2NCIKJES.js";
+} from "./chunk-3KOLLWWE.js";
 import "./chunk-EBJQ6N4M.js";
 import "./chunk-3WGJMBKH.js";
-import "./chunk-2YSQOUHO.js";
+import "./chunk-KELT6K6M.js";
 import "./chunk-MHBMTPW7.js";
 export {
   createCheckPhaseGateCommand,

package/dist/{chunk-GSIVNYVJ.js → chunk-2VU4MFM3.js}

@@ -27,7 +27,7 @@ var checkPerformanceDefinition = {
 };
 async function handleCheckPerformance(input) {
   try {
-    const { EntropyAnalyzer } = await import("./dist-JVZ2MKBC.js");
+    const { EntropyAnalyzer } = await import("./dist-WF4C7A4A.js");
     const typeFilter = input.type ?? "all";
     const projectPath = sanitizePath(input.path);
     const analyzer = new EntropyAnalyzer({
@@ -80,7 +80,7 @@ var getPerfBaselinesDefinition = {
 };
 async function handleGetPerfBaselines(input) {
   try {
-    const { BaselineManager } = await import("./dist-JVZ2MKBC.js");
+    const { BaselineManager } = await import("./dist-WF4C7A4A.js");
     const manager = new BaselineManager(sanitizePath(input.path));
     const baselines = manager.load();
     return resultToMcpResponse(
@@ -128,7 +128,7 @@ var updatePerfBaselinesDefinition = {
 };
 async function handleUpdatePerfBaselines(input) {
   try {
-    const { BaselineManager } = await import("./dist-JVZ2MKBC.js");
+    const { BaselineManager } = await import("./dist-WF4C7A4A.js");
     const manager = new BaselineManager(sanitizePath(input.path));
     manager.save(input.results, input.commitHash);
     const updated = manager.load();
@@ -158,7 +158,7 @@ var getCriticalPathsDefinition = {
 };
 async function handleGetCriticalPaths(input) {
   try {
-    const { CriticalPathResolver } = await import("./dist-JVZ2MKBC.js");
+    const { CriticalPathResolver } = await import("./dist-WF4C7A4A.js");
     const resolver = new CriticalPathResolver(sanitizePath(input.path));
     const result = await resolver.resolve();
     return resultToMcpResponse(Ok(result));

package/dist/{chunk-2NCIKJES.js → chunk-3KOLLWWE.js}

@@ -7,7 +7,7 @@ import {
 } from "./chunk-3WGJMBKH.js";
 import {
   ArchConfigSchema
-} from "./chunk-2YSQOUHO.js";
+} from "./chunk-KELT6K6M.js";
 import {
   Err,
   Ok

package/dist/{chunk-X3MN5UQJ.js → chunk-5VY23YK3.js}

@@ -26,7 +26,7 @@ var runSecurityScanDefinition = {
 };
 async function handleRunSecurityScan(input) {
   try {
-    const core = await import("./dist-JVZ2MKBC.js");
+    const core = await import("./dist-WF4C7A4A.js");
     const projectRoot = sanitizePath(input.path);
     let configData = {};
     try {