its-magic 0.1.2-48 → 0.1.2-55

package/template/README.md

@@ -2,38 +2,78 @@
 
 [GitHub Repository](https://github.com/fl0wm0ti0n/its-magic)
 
-Happy coding! Build something awesome.
-
-Drop-in template repo that implements a structured its-magic workflow in Cursor:
-intake -> discovery -> architecture -> sprint plan -> execute -> QA -> release,
-with pause/resume, decision gates, and persistent artifacts.
+You bring the idea; its-magic is your structured **AI dev team** in Cursor — PO, Tech
+Lead, Dev, QA, Release, and Curator — that turns ideas into shipped software through
+explicit phases and handoff artifacts.
+
+State lives in repo files (`docs/product`, `handoffs`, `sprints`, `decisions`) — not
+chat-only memory. Run `/intake` with your idea, then follow intake → discovery →
+architecture → sprint plan → execute → QA → release; pause/resume and decision gates
+keep you in control when you want to steer. Implementers: see `docs/developer/README.md`
+for the DEV shard.
+
+When you want hands-off delivery, enable **`AUTO_FLOW_MODE=full_autonomy`**
+(default-off), run **`/auto` once in Cursor**, and let the native in-chat auto-chain
+drain your backlog — self-verify UAT, bounded block retry, and advance to the next OPEN
+story or bug without re-invoking each phase manually. The outer driver is **optional**
+(**fallback** for headless/CI or when native chain is unavailable). Guided and
+decision-gated modes remain the default.
 
 ## Features (what its-magic can do)
 
-- Structured phase workflow with explicit artifacts.
-- Artifact-first memory (state in files, not chat only).
-- Decision gate + escalation (`decisions/DEC-xxxx.md`).
-- Pause/resume with checkpoints (`handoffs/resume_brief.md`).
-- Automated execute/QA loop with safety caps (optional).
-- 3-layer quality chain: AI loop → local validate-and-push → CI auto-fix.
-- User-visible metadata guard for operator-facing scripts/CLI (`US-0071` / `DEC-0053`):
-  `python scripts/check-user-visible-metadata.py` (see `docs/engineering/runbook.md`).
-- CI/CD templates driven by `docs/engineering/runbook.md`.
-- Team-friendly local overrides (`scratchpad.local.md`).
-- Optional remote/docker execution and autonomous installs.
-- Built-in benchmarks (live, prompted, headless).
-- Multiplatform distribution (npm, Chocolatey, Homebrew).
+### Autonomous AI workflow
+
+- Run `/intake` through `/release` with explicit phase handoffs and fresh subagent contexts.
+- Use `/pause` and `/resume` with checkpoints when you want to steer; escalate blocking
+  choices to `decisions/DEC-xxxx.md`.
+- Enable **`AUTO_FLOW_MODE=full_autonomy`** (default-off), run **`/auto` once in Cursor**,
+  and drain backlog in-chat; outer driver is **optional** / **fallback** for headless/CI.
+- Team mode routes work across PO, Tech Lead, Dev, QA, Release, and Curator roles.
+- Backlog and bug drain advance OPEN items without re-invoking each phase manually.
+- See the catalog in **Commands and workflow** for phase commands and orchestration details.
+
+### Quality & verification gates
+
+- 3-layer quality chain: AI execute/QA loop → local `validate-and-push` → CI auto-fix.
+- Phase gates include `/plan-verify`, `/qa`, `/verify-work`, and `/uat` with fail-closed stops.
+- `/acceptance` blocks README ↔ backlog drift; user-visible metadata guard on operator scripts.
+- Browser UAT probes with structured fallback when live browser checks are unavailable.
+- Release gates enforce coverage, parity, and evidence before publish.
+- See the catalog in **Features** (`/acceptance`) and **Commands and workflow** for gate commands.
+
+### Distribution & install
+
+- Global install via npm, npx, Chocolatey, or Homebrew; apply to any repo with
+  `its-magic --target`.
+- Modes: `missing` (safe merge), `overwrite` (+ `--backup`), `upgrade` (framework only),
+  and `--clean-repo`.
+- Lifecycle QA matrix validates fresh install, upgrade, backup, and clean-repo paths.
+- Multi-target release publish with confirmation gates for npm/choco/brew.
+- See the **Feature coverage catalog** below for distribution-tagged items.
+
+### Operator control & ergonomics
+
+- Scratchpad flags and `scratchpad.local.md` tune behavior without rewriting framework files.
+- Guided intake packs structure your first `/intake` conversation.
+- Caveman voice mode and optional input compression for terse operator UX.
+- `TOKEN_PROFILE` cost profiles slim context packs without changing workflow semantics.
+- Voice input shortcuts and permissions/runtime connectivity for remote execution.
+- See the catalog in **Other useful capabilities** for scratchpad and governance flags.
 
 <!-- readme-feature-coverage-catalog -->
 
 ### Feature coverage catalog (US-0091)
 
+- `/acceptance` — README ↔ backlog/acceptance feature coverage backfill + blocking drift gate (`US-0091`).
+- `README.md` — Visionary intro + tiered feature hierarchy (autonomous AI dev team positioning, root/template parity) (`US-0094`).
+- `/auto` — Native in-chat auto-chain + full-autonomy mode (`US-0095`, `US-0092`).
 - `/bin` — POSIX npm installer + Linux remote test targets (WSL / SSH / Docker) (`US-0084`).
 - `/choco` — Configurable Multi-Target Release Publish with Confirmation Gate (`US-0054`).
 - `/devops` — First-Class Bug Issue Workflow (Open/Closed) (`US-0079`).
 - `/engineering` — Agent-Driven Codebase Map Bootstrap (`US-0082`).
 - `/engineering` — Remote Runtime Connectivity Contract for QA/Release/Publish (`US-0064`).
 - `/install` — Template/install payload omits intake gate scripts (`BUG-0001`).
+- `/installed` — its-magic ships its OWN packaging CI into generated repos, breaking CI in every created project (`BUG-0009`).
 - `/intake` — Optional Caveman-style input compression (safe file scope) (`US-0090`).
 - `/lint` — CI/CD Workflows (`US-0007`).
 - `/or` — Cursor Caveman mode (scratchpad-configurable terse responses) (`US-0089`).
@@ -969,6 +1009,12 @@ Troubleshooting quick guide:
   - Fix JSON syntax and retry.
 - Secret-like inline value detected:
   - Replace literal secret with an env-var reference field.
+- **CI still runs its-magic packaging jobs?** Your project received a pre-fix workflow.
+  Run **`its-magic --target <repo> --mode upgrade`** (or **`--mode clean`** then reinstall)
+  to refresh `.github/workflows/ci.yml` from the corrected template. After upgrade, GitHub
+  Actions should show only **`checks`** and **`auto-fix`** jobs — not `npm-test`,
+  `brew-test`, or `choco-test`. Fix applies to new installs/upgrades; stale repos heal on
+  next upgrade (**US-0018**).
 
 Team/local (recommended in `.cursor/scratchpad.local.md`):
 
@@ -1134,6 +1180,7 @@ workflow stops and points you to `scripts/validate-and-push` for local fixing.
 - `/acceptance` — Mandatory Intake Question Packs for First and Small Intakes (`US-0068`).
 - `/ask` — /ask Command: Context-Aware Questions Without Workflow (`US-0020`).
 - `/ask` — Context Compaction and Tiered Token-Cost Optimization Mode (`US-0053`).
+- `/auto` — Architecture triad archiver ignores `## US-xxxx` headings, blocking `/auto` with `STATE_ARCHIVE_BOUNDARY_AMBIGUOUS` (`BUG-0010`).
 - `/auto` — Configurable Auto Phase Selection Policy (`US-0070`).
 - `/auto` — Continuous `/auto` Backlog-Drain Mode with Fine-Tune Switches (`US-0044`).
 - `/auto` — Fresh Subagent Context Per Phase and /auto Orchestration (`US-0023`).
@@ -1178,6 +1225,7 @@ workflow stops and points you to `scripts/validate-and-push` for local fixing.
 - `/repetitive` — Delegable Intake Clarification Without Hard Blocks (`US-0083`).
 - `/research` — Knowledge Curation & Early Research (`US-0029`).
 - `/risk` — Intelligent Intake Decomposition and Risk-Aware PO Questioning (`US-0051`).
+- `/scratchpad` — Caveman mode missing voice compression rules (US-0089 incomplete delivery) (`BUG-0011`).
 - `/scratchpad` — Executable Scratchpad-Driven Sync and Auto-Push Wiring (`US-0076`).
 - `/scratchpad` — Scratchpad Delivery Simplification (Example-Only Install Policy) (`US-0073`).
 - `/scratchpad` — Upgrade Scratchpad Example–First Refresh (Fix Example Drift vs Materialized Baseline) (`US-0075`).
@@ -1185,6 +1233,7 @@ workflow stops and points you to `scripts/validate-and-push` for local fixing.
 - `/sprint-plan` — Explicit `/sprint-plan --bulk` Mode (`US-0046`).
 - `/sprint-plan` — Sprint Sizing Rules and Configurable Sprint Planning (`US-0022`).
 - `/story` — Optional Feature User Guide Generation (`US-0032`).
+- `/uat` — Cursor browser-integrated UAT self-test (browser_smoke + automatable manual UI) (`US-0093`).
 - `/uat` — UAT Artifact Lifecycle and Ownership (`US-0027`).
 - `SKILL` scratchpad flag — Skill and Templates (`US-0004`).
 - `US-0001` scratchpad flag — Core Workflow Commands (`US-0001`).

package/template/docs/engineering/auto-orchestration-reference.md

@@ -796,25 +796,121 @@ script or manual re-invocation with `start-from` / refreshed `resume_brief`) is
 | `RELEASE_PUBLISH_MODE=auto` | Explicit opt-in | **No change — hard default-off** | Always on publish |
 | Security deny (`.env`, intake mutation) | Hard deny | **No change — hard** | Always |
 
-**Drain-advance-without-pause**: outer driver schedules next OPEN story/bug immediately;
-paired **`resume_brief`** + **`state.md`** refresh per **DEC-0069** at every boundary.
+**Drain-advance-without-pause**: with **`full_autonomy`** in IDE, native in-chat chain
+schedules next OPEN story/bug **immediately** **without operator re-`/auto`**; outer
+driver is **optional** / **fallback** for headless/CI. Paired **`resume_brief`** +
+**`state.md`** refresh per **DEC-0069** at every boundary.
 
-### Block-retry ledger + cap interaction (US-0092)
+### Native in-chat auto-chain (US-0095 / DEC-0080)
+
+**IDE primary path** when **`AUTO_FLOW_MODE=full_autonomy`** + Cursor IDE + Task tool:
+orchestrator runs a **foreground sequential** spawn loop in the **same /auto orchestrator
+session** (**Native in-chat auto-chain**). Continuation loop: preflight → spawn → await →
+verify → caps → branch. **`NATIVE_CHAIN_UNAVAILABLE`** when Task tool denied or spawn
+depth limit hit — hard stop for native path; suggest outer driver as **optional** fallback.
+
+**Activation gate**: `full_autonomy` + IDE context + Task tool → set **`native_chain_active=true`**
+in `state.md` boundary.
+
+**Spawn-only invariants** (**BUG-0006**): orchestrator schedules phase-role subagents only;
+each phase completes via fresh spawn + artifacts; no in-band phase work.
+
+**Forbidden turn-boundary semantics**: **`stop_reason=completed (segment exhausted)`** is
+**invalid** when next phase, drain target, or relaxable retry is schedulable.
+
+### IDE drain-advance-without-pause algorithm (US-0095)
+
+**Trigger** (all required): `stop_phase=refresh-context`; `stop_reason=completed`; drain
+enabled (**`AUTO_BACKLOG_DRAIN=1`** or bug-queue per **US-0087** mutex); budget remaining.
+
+| Step | Action |
+|------|--------|
+| **1** | **READ** latest phase-boundary block in `docs/engineering/state.md` (`stop_phase`, `stop_reason`, `story_id`, `sprint_id`, `orchestrator_run_id`, `backlog_drain_stories_remaining_budget`, `bug_queue_remaining`) |
+| **2** | **ASSERT** **DEC-0069** pairing — completed phase refreshed **`resume_brief`** + **`state.md`**; stale → **`RESUME_BRIEF_STALE`** (fail-closed, no advance) |
+| **3** | **SELECT** next work item — story: decrement budget, select OPEN story per `AUTO_STORY_SELECTION`; bug: ascending **`BUG-####`** per **US-0087** |
+| **4** | **RELOAD** scratchpad; **MATERIALIZE** `resolved_phase_plan` (**US-0070**); intersect with segment entry phase |
+| **5** | **PREPEND** `handoffs/resume_brief.md` — `story_id`/`bug_id`, `intended_resume_phase`, unchanged `orchestrator_run_id`, drain counters |
+| **6** | **APPEND** `state.md` materialization breadcrumb for new segment |
+| **7** | **IMMEDIATELY** spawn first phase subagent — **without operator re-`/auto`**, **no** mandatory outer-driver instruction |
+
+**DEC-0069 pairing mandate**: every phase boundary and drain advance **must** refresh
+**`resume_brief`** + **`state.md`** before scheduling in-chat continuation.
+
+### Native-chain stop matrix (US-0095)
+
+Native chain **does not weaken** **DEC-0078** hard gates:
+
+| Condition | Native chain behavior |
+|-----------|----------------------|
+| Next intersected phase, no hard stop | **Continue in-chat** — schedule spawn |
+| **`decision_gate`**, isolation/strict-proof, security deny | **Hard stop** — unchanged |
+| **`BACKLOG_MAX_STORIES_REACHED`**, **`loop_max`**, unrecoverable **`error`**, **`pause_request`** | **Hard stop** — unchanged |
+| Relaxable transient stops (**DEC-0078**) | Bounded ledger retry → `phase_respawn` / `native_chain_continue` |
+| Segment complete + drain enabled | **Drain-advance** — immediate in-chat continuation |
+| Task spawn denied | **`NATIVE_CHAIN_UNAVAILABLE`** — hard for native path |
+
+### `AUTO_QUIET` under native chain (US-0095)
+
+| Event | `AUTO_QUIET=0` | `AUTO_QUIET=1` |
+|-------|----------------|----------------|
+| Routine phase PASS | May notify | **Suppress** |
+| Native chain continuing to next phase | Compact breadcrumb OK | **Suppress** |
+| Drain advance to next story/bug | Segment handoff notify OK | **Suppress** routine prose; **no** outer-driver instruction |
+| `decision_gate`, errors, caps, **`NATIVE_CHAIN_UNAVAILABLE`** | **Always** | **Always** |
+| `BACKLOG_MAX_STORIES_REACHED`, `BLOCK_RETRY_CAP_EXHAUSTED` | **Always** | **Always** |
+
+**Forbidden grep patterns** (IDE-primary `full_autonomy` sections): mandatory `run the outer driver`;
+`re-run /auto` between drain segments; `segment exhausted` as terminal when continuation pending;
+unqualified `python scripts/auto_outer_driver.py`.
+
+### Block-retry ledger + unified cap interaction (US-0092 / US-0095)
 
 Append-only **`handoffs/auto_block_retry/<orchestrator_run_id>.jsonl`** — names-only;
-no secrets. Cap interaction:
+no secrets. IDE native chain and outer driver **share one accounting model**:
 
 | Cap | Scope |
 |-----|-------|
-| `AUTO_LOOP_MAX_CYCLES` | Outer-driver `/auto` invocations (incl. drain advances) |
-| `AUTO_IMPLEMENTATION_LOOP` | Inner `execute`↔`qa`↔`verify-work` when `1` |
+| `AUTO_LOOP_MAX_CYCLES` | Each phase spawn + each drain advance = **1** `outer_cycle_index` increment |
+| `AUTO_IMPLEMENTATION_LOOP` | Inner `execute`↔`qa`↔`verify-work` → `implementation_loop_index` |
 | `AUTO_BLOCK_RETRY_MAX` | Per `(story_id, stop_reason)` recoverable retries |
-| `AUTO_BACKLOG_MAX_STORIES` | Drain breadth — outer driver exit **4** |
+| `AUTO_BACKLOG_MAX_STORIES` | `backlog_drain_stories_remaining_budget` decremented at segment advance |
+
+**`remediation_action` values**: `phase_respawn`, `native_chain_continue`, `drain_advance`
+(alongside existing `outer_reinvoke`).
+
+**State breadcrumb fields** (each `full_autonomy` phase boundary):
+
+| Field | Semantics |
+|-------|-----------|
+| **`native_chain_active`** | `true` when IDE native chain is driving continuation |
+| **`outer_cycle_index`** | Continuation cycles this run (int ≥ 0) |
+| **`implementation_loop_index`** | Inner remediation cycles for current story segment (int ≥ 0) |
+
+Cap exhaustion → exit **6** `BLOCK_RETRY_CAP_EXHAUSTED`. **Ordering**: check
+**`AUTO_LOOP_MAX_CYCLES`** first; then **`AUTO_IMPLEMENTATION_LOOP`** +
+**`AUTO_BLOCK_RETRY_MAX`** before recoverable retry; unrecoverable classes bypass ledger.
+
+**Security deny-list** (unchanged from **DEC-0078**): no auto-read **`.env`**, no intake
+evidence mutation, no publish without **`RELEASE_PUBLISH_MODE=auto`**.
+
+### Browser UAT self-test (US-0093)
+
+Two-tier browser UAT: **`scripts/uat_probe_lib.py`** classifies and completes subprocess probes;
+phase subagents (**`/verify-work`**, **`/qa`**, **`/execute`**) own Cursor browser MCP when
+**`UAT_BROWSER_PROBE_MODE=cursor`** (default). Lib **never** invokes browser MCP (**BUG-0006**).
 
-Cap exhaustion → exit **6** `BLOCK_RETRY_CAP_EXHAUSTED`. Ordering: outer driver checks
-`AUTO_LOOP_MAX_CYCLES` first; orchestrator checks `AUTO_IMPLEMENTATION_LOOP` +
-`AUTO_BLOCK_RETRY_MAX` before scheduling remediation.
+| Key | Role |
+|-----|------|
+| `UAT_BROWSER_PROBE_MODE` | `cursor` \| `http_fallback` \| `playwright_fallback` |
+| `UAT_BROWSER_FALLBACK_CHAIN` | HTTP → Playwright after **`UAT_BROWSER_UNAVAILABLE`** |
+| `UAT_PROCESS_HEALTH_POLL_SECONDS` / `UAT_PROCESS_HEALTH_POLL_INTERVAL_SECONDS` | `process_health` readiness |
+| `DEV_SERVER_PORT` / `DEV_SERVER_COMMAND` | Dev-server inference overrides |
 
+CI: set **`UAT_BROWSER_PROBE_MODE=http_fallback`**. Evidence:
+**`sprints/Sxxxx/evidence/browser/`** + **`browser_evidence_refs`** in **`uat.json`**.
+Validate: **`python scripts/uat_probe_lib.py --merge-result <fragment.json>`**.
+Manual override: **`@browser`** in Agent panel. Orthogonal to **`PERMISSION_MODE`** and browser
+approval modes.
 ### `AUTO_QUIET` vs `TOKEN_PROFILE` (US-0088 / AC-2)
 
 | Key | Values | Role |
@@ -879,15 +975,19 @@ conditions the script is a no-op and the fail-closed reason codes from
    - `resolution_source` (`argument|resume_brief|state_fallback`)
    - `resolution_status` (`resolved|fail-fast`)
    - `timestamp`
-5. **(reference Step 5 — continuous multi-phase spawn)** Spawn a fresh subagent
-   for each remaining phase in **the intersected resolved schedule order** (not
-   the full canonical list when phases are omitted), starting at
+5. **(reference Step 5 — continuous multi-phase spawn)** **IDE primary path
+   (US-0095)**: when **`AUTO_FLOW_MODE=full_autonomy`** + Cursor IDE + Task tool,
+   orchestrator runs **Native in-chat auto-chain** — **foreground sequential**
+   spawn loop in the **same /auto orchestrator session** until stop matrix fires
+   (see **Native in-chat auto-chain (US-0095)** above). Otherwise spawn a fresh
+   subagent for each remaining phase in **the intersected resolved schedule order**
+   (not the full canonical list when phases are omitted), starting at
    `resolved_start_phase`, and **advance through all subsequent phases** until a
    **deterministic stop condition** fires (see **Deterministic stop matrix
    (US-0088)** above). The orchestrator does **not** stop after a single phase
    spawn unless the stop matrix requires it; outer-driver equivalence applies
-   when a single invocation cannot schedule multiple subagent turns (see
-   **Outer-driver equivalence (AC-1, Option B)** above):
+   when native chain is unavailable or a single invocation cannot schedule
+   multiple subagent turns (see **Outer-driver equivalence (AC-1, Option B)** above):
    default full path:
    intake -> discovery -> research -> architecture -> sprint plan ->
    plan verify -> execute -> QA -> verify work -> release -> refresh context.

package/template/docs/engineering/runbook.md

@@ -1366,13 +1366,46 @@ success chatter. Non-suppressible notifications:
 `AUTO_QUIET` is **orthogonal** to `TOKEN_PROFILE` (**DEC-0035** / **US-0080**):
 `TOKEN_PROFILE` controls context breadth and token cost, not notification policy.
 
-### Full-autonomy outer driver (US-0092)
+Under **`full_autonomy`** IDE native chain (**US-0095**), drain advance suppresses
+routine prose when **`AUTO_QUIET=1`** but **must not** emit mandatory outer-driver
+wait instructions between segments.
 
-Opt-in **`AUTO_FLOW_MODE=full_autonomy`** (exact literal, default-off) enables the
-shipped stdlib outer driver. Spawn-only preserved — the driver loops hook
-invocations; it never performs phase-role work.
+### Native in-chat auto-chain (US-0095)
 
-#### Enable and run (once per portfolio segment)
+**Primary IDE recipe** for hands-off delivery when **`AUTO_FLOW_MODE=full_autonomy`**
+(default-off): run **`/auto` once in Cursor** — orchestrator self-chains in-chat
+across phases and drain segments via **foreground sequential** Task loop in the
+**same /auto orchestrator session**.
+
+#### Enable and run (IDE primary)
+
+1. Set in merged scratchpad:
+   - `AUTO_FLOW_MODE=full_autonomy`
+   - Optional: `AUTO_BACKLOG_DRAIN=1`, caps (`AUTO_LOOP_MAX_CYCLES`, `AUTO_BACKLOG_MAX_STORIES`, `AUTO_BLOCK_RETRY_MAX`)
+2. Run **`/auto`** once in Cursor Agent panel (no `--invoke-cmd`).
+3. Orchestrator continues in-chat until hard stop, drain budget exhausted, or
+   **`NATIVE_CHAIN_UNAVAILABLE`** (optional fallback: outer driver below).
+
+Normative detail: **`.cursor/commands/auto.md`** § **Native in-chat auto-chain (US-0095)**
+and **`docs/engineering/auto-orchestration-reference.md`** § **Native in-chat auto-chain**.
+
+#### Primary / fallback boundary
+
+| Context | Native in-chat chain | Outer driver | Messaging |
+|---------|---------------------|--------------|-----------|
+| **Cursor IDE + `full_autonomy`** | **Primary** | **Optional fallback** | No mandatory outer-driver drain recipe |
+| **Headless / CI** | Unavailable | **Recommended** | Runbook: headless primary |
+| **`--invoke-cmd`** | N/A | **Required** bridge | Document in runbook |
+| **`NATIVE_CHAIN_UNAVAILABLE`** | Stops | Suggested (**optional** tone) | Non-suppressible |
+
+### Full-autonomy outer driver (US-0092) — fallback
+
+Opt-in **`AUTO_FLOW_MODE=full_autonomy`** (exact literal, default-off) also enables
+the shipped stdlib outer driver as **optional** / **fallback** for headless/CI or
+when native in-chat chain is unavailable. Spawn-only preserved — the driver loops hook
+invocations; it never performs phase-role work. **Not required** for IDE drain.
+
+#### Enable and run (headless/CI fallback)
 
 1. Set in merged scratchpad (`.cursor/scratchpad.md` + optional local overrides):
    - `AUTO_FLOW_MODE=full_autonomy`
@@ -1406,6 +1439,39 @@ without side effects. `--invoke-cmd` overrides the default normative `/auto …`
 
 UAT self-verify: **`scripts/uat_probe_lib.py`** shared by **`/verify-work`** and **`/qa`**.
 
+### Browser UAT self-test (US-0093)
+
+Enable Cursor browser-integrated UAT probes for web acceptance steps (**DEC-0079**).
+
+#### Scratchpad keys
+
+| Key | Values | Default | Notes |
+|-----|--------|---------|-------|
+| `UAT_BROWSER_PROBE_MODE` | `cursor` \| `http_fallback` \| `playwright_fallback` | `cursor` | Primary probe path |
+| `UAT_BROWSER_FALLBACK_CHAIN` | `0` \| `1` | `1` | HTTP → Playwright after MCP unavailable |
+| `UAT_PROCESS_HEALTH_POLL_SECONDS` | int | `60` | Readiness poll cap |
+| `UAT_PROCESS_HEALTH_POLL_INTERVAL_SECONDS` | int | `2` | Poll interval |
+| `DEV_SERVER_PORT` | int | unset | Port override |
+| `DEV_SERVER_COMMAND` | command | unset | Startup override |
+
+Orthogonal to **`PERMISSION_MODE`** and Cursor browser approval modes. Health URLs from
+**`docs/engineering/runtime-connectivity.md`** first.
+
+#### CI recipe
+
+Set **`UAT_BROWSER_PROBE_MODE=http_fallback`** in CI — never false PASS without agent evidence.
+
+#### Evidence layout
+
+Binary artifacts under **`sprints/Sxxxx/evidence/browser/`** (gitignored OK). JSON carries path
+refs only. Validate agent write-back:
+`python scripts/uat_probe_lib.py --merge-result sprints/Sxxxx/evidence/browser/fragment.json`.
+
+#### Manual override
+
+Use **`@browser`** in Agent panel or invoke browser tools manually when MCP sequence needs operator
+approval for production-like targets.
+
 ### Caveman mode (US-0089)
 
 Optional response-side terse / imperative assistant voice. **Default off.**

package/template/scripts/check_intake_template_parity.py

@@ -7,6 +7,8 @@ Scoped modes (DEC-0073 §10 / US-0090):
   --scope=readme-feature-coverage DEC-0074 README feature-coverage pair table.
   --scope=downstream-ci-guard   DEC-0075 downstream CI guard script pair table.
   --scope=us-0092               DEC-0078 full-autonomy outer driver + probe surfaces.
+  --scope=us-0093               DEC-0079 browser UAT probe surfaces.
+  --scope=us-0095               DEC-0080 native in-chat auto-chain surfaces.
   --scope=all              union of all tables.
 """
 
@@ -78,6 +80,40 @@ US0092_PAIRS: tuple[tuple[str, str], ...] = (
     ("docs/engineering/runbook.md", "template/docs/engineering/runbook.md"),
 )
 
+US0093_PAIRS: tuple[tuple[str, str], ...] = (
+    ("scripts/uat_probe_lib.py", "template/scripts/uat_probe_lib.py"),
+    (".cursor/commands/verify-work.md", "template/.cursor/commands/verify-work.md"),
+    (".cursor/commands/qa.md", "template/.cursor/commands/qa.md"),
+    (".cursor/commands/execute.md", "template/.cursor/commands/execute.md"),
+    (
+        ".cursor/scratchpad.local.example.md",
+        "template/.cursor/scratchpad.local.example.md",
+    ),
+    ("docs/engineering/runbook.md", "template/docs/engineering/runbook.md"),
+    (
+        "docs/engineering/auto-orchestration-reference.md",
+        "template/docs/engineering/auto-orchestration-reference.md",
+    ),
+    (
+        "docs/engineering/context/installer-owned-paths.manifest",
+        "template/docs/engineering/context/installer-owned-paths.manifest",
+    ),
+)
+
+US0095_PAIRS: tuple[tuple[str, str], ...] = (
+    (".cursor/commands/auto.md", "template/.cursor/commands/auto.md"),
+    (
+        "docs/engineering/auto-orchestration-reference.md",
+        "template/docs/engineering/auto-orchestration-reference.md",
+    ),
+    ("docs/engineering/runbook.md", "template/docs/engineering/runbook.md"),
+    ("README.md", "template/README.md"),
+    (
+        "scripts/check_intake_template_parity.py",
+        "template/scripts/check_intake_template_parity.py",
+    ),
+)
+
 DOWNSTREAM_CI_GUARD_PAIRS: tuple[tuple[str, str], ...] = (
     (
         "scripts/check_downstream_ci_guard.py",
@@ -95,12 +131,16 @@ SCOPES: dict[str, tuple[tuple[str, str], ...]] = {
     "readme-feature-coverage": README_FEATURE_COVERAGE_PAIRS,
     "downstream-ci-guard": DOWNSTREAM_CI_GUARD_PAIRS,
     "us-0092": US0092_PAIRS,
+    "us-0093": US0093_PAIRS,
+    "us-0095": US0095_PAIRS,
     "all": (
         INTAKE_TEMPLATE_PAIRS
         + CAVEMAN_COMPRESS_PAIRS
         + README_FEATURE_COVERAGE_PAIRS
         + DOWNSTREAM_CI_GUARD_PAIRS
         + US0092_PAIRS
+        + US0093_PAIRS
+        + US0095_PAIRS
     ),
 }