@terreno/mcp 0.30.0 → 56.0.0-beta.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@terreno/mcp",
-  "version": "0.30.0",
+  "version": "56.0.0-beta.0",
   "description": "MCP server for Terreno - provides documentation, tools, and prompts for building full-stack apps",
   "type": "module",
   "main": "dist/index.js",
@@ -27,7 +27,7 @@
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.27.0",
     "@sentry/bun": "^10.39.0",
-    "@terreno/api": "0.30.0",
+    "@terreno/api": "56.0.0-beta.0",
     "minisearch": "^7.2.0",
     "mongoose": "8.23.0"
   },
@@ -35,7 +35,7 @@
     "@biomejs/biome": "^2.3.6",
     "@types/bun": "^1.3.8",
     "@types/node": "^25.3.0",
-    "typescript": "~5.9.2"
+    "typescript": "~6.0.3"
   },
   "files": [
     "dist",

package/src/docs/templates/bootstrap/frontend/app/_layout.template.tsx

@@ -1,5 +1,5 @@
 import FontAwesome from "@expo/vector-icons/FontAwesome";
-import {DarkTheme, DefaultTheme, ThemeProvider} from "@react-navigation/native";
+import {DarkTheme, DefaultTheme, ThemeProvider} from "expo-router/react-navigation";
 import {useFonts} from "expo-font";
 import {Stack} from "expo-router";
 import * as SplashScreen from "expo-splash-screen";

package/src/docs/versioned/0.30.0/explanation/explicit-any-policy.md

@@ -0,0 +1,88 @@
+# Explicit `any` policy
+
+Terreno discourages `any` in TypeScript. Biome blocks **new** unsuppressed explicit `any` at lint time; this document describes how we inventory existing usages and track remediation.
+
+## Why
+
+- **Type safety**: `any` disables checking and hides bugs at compile time.
+- **Refactor confidence**: precise types make API and UI changes safer.
+- **Consistency**: one convention for when `any` is acceptable and how it is documented.
+
+Prefer `unknown` (and narrow) or a precise type. Use `as unknown as T` over `as any as T` when a cast is unavoidable.
+
+## Allowed uses
+
+Explicit `any` is acceptable only at **framework or library boundaries** where types are not expressible in TypeScript today, for example:
+
+- Mongoose `Schema<any, …>` accepting arbitrary consumer schemas (`api/src/plugins.ts`)
+- RTK Query `Api<any, any, any, any>` in generic middleware (`rtk/src/offlineMiddleware.ts`)
+- Dynamic RTK hook lookup where endpoint names are not statically known (`admin-frontend`)
+- Test mocks with type-erased doubles (`*.test.ts`, `*.isolated.tsx`)
+
+Every allowed use must be **lint-clean** and **documented** (see below).
+
+## Remediation status
+
+The audit script (`bun run check:explicit-any`) classifies each explicit `any`:
+
+| Status | Meaning |
+|--------|---------|
+| `violation` | No `biome-ignore` — fails Biome lint |
+| `suppressed-only` | Has `biome-ignore` but missing `// noExplicitAny:` rationale |
+| `fully-documented` | Has both `biome-ignore` and `// noExplicitAny:` |
+| `file-blanket` | File-level `biome-ignore-all` without file-level `noExplicitAny:` |
+| `out-of-scope` | In Biome-excluded source (e.g. `api/src/populate.ts`) |
+
+## How to document an `any`
+
+When `any` cannot be removed, add **both** comments on the line above (or a file header for tests):
+
+```typescript
+// noExplicitAny: RTK Query generates hook names dynamically; not statically expressible
+// biome-ignore lint/suspicious/noExplicitAny: dynamic hook lookup on RTK Query enhanced API
+const hook = (api as any)[`useGet${name}Query`];
+```
+
+For test files with many mocks, a file-level header is fine:
+
+```typescript
+// noExplicitAny: test mocks use type-erased RTK Query API doubles
+// biome-ignore-all lint/suspicious/noExplicitAny: test mock typing
+```
+
+## Commands
+
+```bash
+bun run check:explicit-any                         # summary report
+bun run check:explicit-any:json                    # JSON inventory
+bun run check:explicit-any:baseline                # fail if counts regress vs baseline
+bun run check:explicit-any -- --undocumented       # only suppressed-but-undocumented
+bun run check:explicit-any -- --list --undocumented  # file:line list for remediation
+bun run check:explicit-any -- --production-only --undocumented --list
+bun run check:explicit-any -- --package=api        # filter to one package
+bun run check:explicit-any -- --include-excluded   # include Biome-excluded files
+bun run check:explicit-any -- --write-baseline     # refresh scripts/check-explicit-any/baseline.json
+bun run check:explicit-any:remediate               # auto-add missing noExplicitAny: comments
+```
+
+## Enforcement
+
+| Layer | What it does |
+|-------|----------------|
+| **Biome `noExplicitAny: error`** | Blocks new unsuppressed `any` in every linted package |
+| **`bun run check:explicit-any:baseline`** | CI ratchet — total, undocumented, and violation counts must not increase |
+| **`bun run lint`** | Per-package lint including `noExplicitAny` |
+
+Baseline file: `scripts/check-explicit-any/baseline.json`. After intentional reductions (removing or properly documenting `any`), refresh with `--write-baseline` and commit the updated baseline.
+
+## Remediation workflow
+
+1. Run `bun run check:explicit-any -- --list --undocumented --production-only` for a work queue.
+2. For each hit, either **replace** `any` with a proper type or **document** with `noExplicitAny:` + `biome-ignore`.
+3. Prefer line-level suppressions over file-level `biome-ignore-all` in production code.
+4. Run `bun run check:explicit-any:baseline` before opening a PR.
+5. If counts decreased, run `--write-baseline` and commit the new baseline.
+
+## Exclusions
+
+The audit skips generated and template files (`openApiSdk.ts`, `*.template.ts`). Biome-excluded paths (see `!!` patterns in `biome.jsonc`) are omitted unless `--include-excluded` is passed.

package/src/docs/versioned/0.30.0/implementationPlans/PLAN_INDEX.md

@@ -0,0 +1,75 @@
+# Implementation plan index
+
+Tracks active and completed implementation plans (IP) for Terreno. File paths are relative to `docs/implementationPlans/`.
+
+## Programs
+
+Umbrella plans that coordinate several IPs.
+
+| Program | Status | Created | IPs |
+|---------|--------|---------|-----|
+| [Open source launch](oss-launch-program.md) | Draft — decisions recorded; Vercel spike open | 2026-07-27 | 15 |
+
+## Active
+
+| Plan | Status | Created | Tasks |
+|------|--------|---------|-------|
+| [Admin UI v2 — Django-parity admin](admin-ui-v2-django-parity.md) | Approved | 2026-06-15 | [tasks](../tasks/admin-ui-v2-django-parity.md) |
+| [RBAC Permissions](rbac-permissions.md) | Draft (API design) | 2026-07-08 | TBD |
+| [SyncDB Local-First Data Layer](syncdb-local-first.md) | In progress ([PR #869](https://github.com/flourishhealth/terreno/pull/869)) | 2026-07-13 | [tasks](../tasks/syncdb-local-first.md) |
+| [MCP Boost parity](mcp-boost-parity.md) | In progress ([PR #802](https://github.com/flourishhealth/terreno/pull/802)) | 2026-06-21 | TBD |
+
+## Open source launch IPs
+
+All part of the [launch program](oss-launch-program.md). The **RTK flag** column marks dependence on the `@terreno/rtk` → `@terreno/syncdb` migration in PR #869: `None` is safe to implement now, `Partial` has some blocked tasks, `Blocked` cannot start until #869 merges.
+
+### Wave 0 — unblocked
+
+| Plan | Status | RTK flag | Tasks |
+|------|--------|----------|-------|
+| [OSS governance baseline](oss-governance-baseline.md) | Draft | None | [tasks](../tasks/oss-governance-baseline.md) |
+| [Public roadmap on GitHub](public-roadmap-github.md) | Draft | None | [tasks](../tasks/public-roadmap-github.md) |
+| [Deploy to GCP (generalized)](deploy-to-gcp.md) | Draft | None | [tasks](../tasks/deploy-to-gcp.md) |
+| [Agentic SDLC plugin (`/terreno-*`)](agentic-sdlc-plugin.md) | Draft | Partial | [tasks](../tasks/agentic-sdlc-plugin.md) |
+
+### Wave 1 — gated on PR #869
+
+| Plan | Status | RTK flag | Tasks |
+|------|--------|----------|-------|
+| [RTK deprecation and syncdb migration docs](rtk-to-syncdb-migration-docs.md) | Draft | **Blocked** (gating IP) | [tasks](../tasks/rtk-to-syncdb-migration-docs.md) |
+| [Positioning — Django/Rails for TypeScript](positioning-django-rails-universal.md) | Draft | Partial | [tasks](../tasks/positioning-django-rails-universal.md) |
+| [Reference documentation coverage](docs-reference-coverage.md) | Draft | Blocked | [tasks](../tasks/docs-reference-coverage.md) |
+| [AI-first tutorials](docs-tutorials-ai-first.md) | Draft | Blocked | [tasks](../tasks/docs-tutorials-ai-first.md) |
+| [Deployment foundation](deployment-foundation.md) | Draft | Partial | [tasks](../tasks/deployment-foundation.md) |
+| [Deploy to Vercel](deploy-to-vercel.md) | Draft | Partial | [tasks](../tasks/deploy-to-vercel.md) |
+| [Upgrade guides and skill](upgrade-guides-and-skill.md) | Draft | Blocked | [tasks](../tasks/upgrade-guides-and-skill.md) |
+| [The AI development loop (Boost)](ai-dev-loop-boost.md) | Draft | Partial | [tasks](../tasks/ai-dev-loop-boost.md) |
+| [Dogfooding run and launch blog post](build-terreno-app-validation.md) | Draft | Blocked | [tasks](../tasks/build-terreno-app-validation.md) |
+| [Examples, demo, and test coverage](examples-demo-coverage.md) | Draft | Partial | [tasks](../tasks/examples-demo-coverage.md) |
+
+### Wave 2 — independent
+
+| Plan | Status | RTK flag | Tasks |
+|------|--------|----------|-------|
+| [Web SSR and admin SPA](web-ssr-and-admin-spa.md) | Draft | Partial | [tasks](../tasks/web-ssr-and-admin-spa.md) |
+
+## Completed
+
+| Plan | Status | Created | Tasks |
+|------|--------|---------|-------|
+| [APIError redesign — standards-first extension of Error](apierror-standard-error-redesign.md) | Complete | 2026-07-28 | n/a |
+
+## Deferred / Closed
+
+*(Plans parked or superseded.)*
+
+## Backlog
+
+*(Links to ideas not yet promoted to a full IP.)*
+
+| Idea | Notes |
+|------|-------|
+| [Langfuse integration](terreno-langfuse-integration.md) | AI observability plugin |
+| [modelRouter MCP tools](model-router-mcp.md) | MCP surface for consumer app APIs |
+| [Offline mode](offline-mode.md) | Superseded in large part by [syncdb](syncdb-local-first.md) — confirm and close |
+| [modelRouter actions](model-router-actions.md) | — |

package/src/docs/versioned/0.30.0/implementationPlans/agentic-sdlc-plugin.md

@@ -0,0 +1,177 @@
+# Implementation Plan: Publish and Document the Agentic SDLC Plugin
+
+**Status:** Draft — key decisions recorded (2026-07-29)
+**Priority:** High
+**Effort:** Big batch
+**Owner:** unassigned
+**Created:** 2026-07-27
+**Program:** [OSS launch](oss-launch-program.md)
+**Depends on:** [`positioning-django-rails-universal`](positioning-django-rails-universal.md) (shared copy blocks), [`oss-governance-baseline`](oss-governance-baseline.md) (license coverage for `plugins/`)
+**RTK deprecation flag:** **Partial** — the pipeline's frontend-verification gates name `rtk/` in their path lists and must be updated to name `syncdb/` after PR #869.
+
+## Goal
+
+Terreno ships a five-stage agentic SDLC pipeline as an installable Cursor plugin, and **nobody outside the team knows it exists.** `.cursor-plugin/marketplace.json` declares a team marketplace; `plugins/terreno-planning/` contains five skills that take work from a raw request all the way to a mergeable PR. There is no `plugins/README.md`, no page in `docs/`, no mention in `README.md` or `AGENTS.md`, and the marketplace is scoped to the team.
+
+This matters more than a normal documentation gap. The pipeline is the most concrete evidence for the AI-native pillar. Any framework can claim "works great with AI"; very few ship an opinionated, reviewed, test-driven delivery process as installable tooling. In the Django/Rails analogy it is the missing half of `manage.py`: not just "generate a model" but "take this ticket to a mergeable PR with tests and independent review".
+
+The audit that produced this program missed the plugin entirely. If an agent reading the whole repository missed it, every prospective user will too.
+
+## Non-Goals
+
+- Redesigning the pipeline. The five stages work; this is packaging, documentation, and positioning.
+- Porting the pipeline to every agent runtime. Cursor is the reference; note what would be required for others.
+- Replacing the repo's existing `.rulesync/skills/` (`submit`, `autobot`, `check-watcher`, `respond-to-review`) — but the overlap needs resolving, because right now two pipelines cover similar ground.
+- Building a plugin marketplace of our own.
+
+## Blocking questions
+
+**Recorded 2026-07-29** (see program [P11](oss-launch-program.md#blocking-questions-program-level)).
+
+| # | Question | Decision |
+|---|----------|----------|
+| AP1 | Marketplace public or team-only? | **A** — public at launch (gated on portability) |
+| AP2 | PHI/HIPAA handling | **B** — generalize to "sensitive data (PHI, PII, secrets)" |
+| AP3 | Stage names | **Coffee theme retained.** New five-stage flow: **grow → harvest → roast → brew → taste**. Skills: `/terreno-1-grow`, `/terreno-2-harvest`, `/terreno-3-roast`, `/terreno-4-brew`, `/terreno-5-taste`. **Aliases required** in docs and skill frontmatter (see mapping below) |
+| AP4 | Consumer apps or monorepo only? | **B** — must work in consumer apps |
+| AP5 | Overlap with `submit` / `autobot` | **A** — deprecate `submit` and `autobot` in favor of the plugin. **Fold all `autobot` behavior into Taste (`/terreno-5-taste`)**. Taste should be **self-contained** (inline the full submit → CI → review loop) rather than delegating to other skills — delegation has been unreliable inside the plugin (sub-agents and cross-skill calls do not always resolve). Accept larger skill files / context cost over broken orchestration |
+| AP6 | Agent runtimes | **B** — Cursor + rulesync-generated variants |
+| AP7 | Plugin versioning | **A** — independent versioning; declare compatible Terreno versions |
+
+### Stage mapping (rename + aliases)
+
+| # | New name | Role | Replaces | Aliases (docs + deprecated skill names) |
+|---|----------|------|----------|----------------------------------------|
+| 1 | **grow** | Plan — IP + tasks, blocking questions first | blend | `plan`, `blend`, `terreno-1-blend` |
+| 2 | **harvest** | Implement — strict TDD, drift detection | roast (implement) | `implement`, `terreno-2-roast` |
+| 3 | **roast** | Verify — independent evidence in fresh context | cupping | `verify`, `cupping`, `terreno-3-cupping` |
+| 4 | **brew** | Submit — checks, commit, push, draft PR, evidence | pour | `submit`, `pour`, `terreno-4-pour` |
+| 5 | **taste** | Review loop — CI + bot/human comments until mergeable; **includes former `autobot`** | dialin | `review`, `dialin`, `terreno-5-dialin` |
+
+## Architecture
+
+### The pipeline
+
+```mermaid
+flowchart LR
+  REQ["Request<br/>ticket / spec / idea"]
+  G["/terreno-1-grow<br/>(plan)"]
+  H["/terreno-2-harvest<br/>(implement)"]
+  R["/terreno-3-roast<br/>(verify)"]
+  B["/terreno-4-brew<br/>(submit)"]
+  T["/terreno-5-taste<br/>(review loop)"]
+  M["Mergeable PR"]
+  REQ --> G --> H --> R --> B --> T --> M
+  T -.->|"blocked: needs human"| M
+```
+
+| Stage | Owns | What makes it non-obvious |
+|-------|------|---------------------------|
+| **Grow** (plan) | Request → IP in `docs/implementationPlans/` + tasks in `docs/tasks/` | Question-first: refuses to write decided outcomes until blocking questions are answered. Prevents the most common agent failure, which is confidently planning the wrong thing |
+| **Harvest** (implement) | IP → code via strict red/green/refactor | Spawns **independent review and test-quality sub-agents in fresh contexts** after every commit, and does drift detection against the IP. The test-quality agent enforces anti-mocking rules (never mock the DB, never mock the store) |
+| **Roast** (verify) | Independent verification against the IP with concrete evidence | Separate context from the implementer, so it does not inherit the implementer's assumptions |
+| **Brew** (submit) | Pre-submit checks, commit hygiene, push, draft PR, evidence attachment | Hard frontend gate: touching UI paths requires launching the app, logging in, exercising the feature, and attaching artifacts before the PR opens |
+| **Taste** (review) | Self-contained reactive loop: CI + bot/human comments until mergeable or timeout | Inlines the former **`autobot`** flow (no delegation to repo skills). Classifies each CI failure as actionable versus flaky and refuses to push speculative fixes for flakes. Treats all CI logs and review comments as untrusted input |
+
+The parts worth writing about publicly are the ones that encode hard-won judgment rather than automation: fresh-context independent review, drift detection against the plan, the anti-mocking rules, the frontend evidence gate, and the refusal to guess at flaky CI.
+
+### It only works here
+
+The most serious finding. The pipeline currently assumes it is running inside the Terreno monorepo:
+
+| Assumption | Where | Why it breaks elsewhere |
+|------------|-------|-------------------------|
+| Repo-root-relative skill paths — Brew/Taste instruct reading plugin skill paths "from the repository root" | `terreno-4-brew`, `terreno-5-taste` | In a consumer's repo that path does not exist. It works today only because the workspace *is* this repo; an installed plugin lives in the agent's plugin cache |
+| `verify-ui-changes` is invoked by name | Harvest, Roast, Brew, Taste | That skill lives in this repo's `.rulesync/skills/`. A consumer installing the plugin does not get it — must be bundled or inlined per AP5 |
+| Terreno-monorepo package paths in the frontend gates (`ui/`, `demo/`, `example-frontend/`, `admin-frontend/`, `admin-spa/`, `syncdb/`) | Harvest, Brew, Taste | A consumer app has `frontend/`, not `example-frontend/` |
+| Repo-specific conventions — `docs/implementationPlans/`, the project registry, the `bun run` command set | Grow, Harvest | A consumer may have none of these |
+| A hardcoded branch suffix (`cursor/<descriptive-name>-dcb3`) | Brew | Suffixes are per-agent-run, not fixed; a literal `dcb3` will produce wrong branch names |
+
+Fixing this is the difference between "our internal process, published" and "tooling Terreno users can adopt". It means parameterizing paths, bundling or declaring the skill dependencies, and detecting project layout instead of assuming it.
+
+### Overlap with existing repo skills
+
+| Plugin stage | Repo skill (deprecated) |
+|--------------|-------------------------|
+| Brew | `.rulesync/skills/submit/`, `commit/`, `create-pr/` |
+| Taste | `.rulesync/skills/autobot/`, `check-watcher/`, `respond-to-review/` — **logic inlined into Taste; skills deprecated** |
+| Grow | `.rulesync/skills/ip/`, `design-blend/` |
+| Harvest | `.rulesync/skills/implement/` |
+
+Per AP5, **`submit` and `autobot` are deprecated** once Taste ships self-contained. Do not document two parallel pipelines.
+
+### Positioning
+
+The pipeline belongs in the **AI-native** pillar, alongside the MCP server. They are complementary and the distinction should be stated plainly:
+
+- **MCP server** = the *tool* layer. What an agent can see and do: search docs, generate conventional code, read merged logs, inspect client state, drive the running app.
+- **SDLC plugin** = the *process* layer. How an agent should sequence work: plan before coding, test-drive, review in a fresh context, verify independently, gate on evidence, then own the review loop.
+
+In the Django/Rails comparison table, this fills the row that currently reads "MCP server tools + skills — agent-driven rather than CLI-driven". Better framing: Django gives you `manage.py startapp`; Terreno gives you a reviewed path from ticket to mergeable PR.
+
+## Models / APIs / Notifications / UI
+
+None.
+
+## Phases
+
+1. **Decide and sanitize** — answer AP2, generalize PHI language, remove Flourish specifics, fix the hardcoded branch suffix.
+2. **Rename stages** — grow/harvest/roast/brew/taste with aliases; bump plugin minor version (AP3).
+3. **Make it portable** — parameterize paths, bundle `verify-ui-changes` (or equivalent), detect project layout (AP4).
+4. **Consolidate Taste** — inline `autobot` + review-loop behavior; deprecate `submit`/`autobot` repo skills (AP5).
+5. **Document** — `plugins/README.md`, docs-site explainer and how-to, per-stage reference with alias callouts.
+6. **Position** — README, docs landing, comparison table, agent context files.
+7. **Distribute** — publish the marketplace; generate non-Cursor variants via rulesync (AP6).
+
+## Feature Flags & Migrations
+
+None. Renaming or aliasing stages (AP3) is a breaking change for anyone with the plugin installed — bump the plugin minor version and note it in `plugins/README.md`.
+
+## Not Included / Future Work
+
+- A healthcare-specific plugin variant retaining explicit PHI handling (AP2 option C).
+- Additional stages (design review, release, incident response).
+- Telemetry on stage usage or success rates.
+- Publishing to a public Cursor plugin directory beyond this repo's marketplace, if one exists.
+
+## Files to Create / Modify
+
+**Create**
+
+- `plugins/README.md`
+- `docs/explanation/agentic-sdlc.md`
+- `docs/how-to/use-the-terreno-plugin.md`
+- `docs/reference/sdlc-plugin.md`
+- `plugins/terreno-planning/LICENSE`
+
+**Modify**
+
+- `plugins/terreno-planning/skills/*/SKILL.md` (all five: sanitization, portability, delegation)
+- `plugins/terreno-planning/.cursor-plugin/plugin.json`, `.cursor-plugin/marketplace.json`
+- `README.md`, `docs/README.md`, `docs/explanation/positioning.md`
+- `AGENTS.md` / `.rulesync/rules/00-root.md`, `CLAUDE-consumer.md`
+- `.rulesync/skills/submit/SKILL.md`, `autobot/SKILL.md` (cross-reference the plugin)
+- `scripts/check-license-coverage.ts` (cover `plugins/`)
+- `.rulesync/skills/build-terreno-app/SKILL.md` (use the pipeline if public)
+
+## Task List
+
+See [`docs/tasks/agentic-sdlc-plugin.md`](../tasks/agentic-sdlc-plugin.md).
+
+## Acceptance Criteria
+
+- [ ] `plugins/README.md` explains the five stages, installation, and when to use each, in under 150 lines.
+- [ ] No plugin skill contains Flourish-specific vocabulary; sensitive-data handling is generalized per AP2.
+- [ ] No plugin skill contains a hardcoded branch suffix or a repo-root-relative path to a sibling skill.
+- [ ] The pipeline runs end to end in a **consumer app scaffolded by `terreno_bootstrap_app`**, not just in this monorepo — verified by taking one small feature from request to open PR.
+- [ ] Every skill dependency (`verify-ui-changes` at minimum) is either bundled with the plugin or declared with installation instructions.
+- [ ] Frontend path gates are derived from the project's actual layout rather than hardcoded monorepo package names.
+- [ ] Pour and Taste are self-contained per AP5; deprecated `submit`/`autobot` repo skills point to the plugin; no rule is stated in two places with different wording.
+- [ ] `docs/explanation/agentic-sdlc.md` explains the process layer versus the MCP tool layer and why fresh-context independent review matters.
+- [ ] `docs/how-to/use-the-terreno-plugin.md` takes a reader from installation to a merged PR.
+- [ ] `docs/reference/sdlc-plugin.md` documents each stage's scope, inputs, outputs, and boundaries.
+- [ ] `README.md` and `docs/README.md` name the pipeline under the AI-native pillar; the Django/Rails comparison table's generator row cites it.
+- [ ] Every public reference to a coffee-named stage gives its plain-language meaning at least once per page.
+- [ ] The marketplace is installable by the audience chosen in AP1, verified by a fresh install.
+- [ ] `plugins/` is covered by the license-coverage check.
+- [ ] `bun run rules:check` and `bun run check` pass.

package/src/docs/versioned/0.30.0/implementationPlans/ai-dev-loop-boost.md

@@ -0,0 +1,174 @@
+# Implementation Plan: The AI Development Loop (Boost)
+
+**Status:** Draft — key decisions recorded (2026-07-29)
+**Priority:** High
+**Effort:** Big batch
+**Owner:** unassigned
+**Created:** 2026-07-27
+**Program:** [OSS launch](oss-launch-program.md)
+**Depends on:** PR [#802](https://github.com/flourishhealth/terreno/pull/802) merging (assumed)
+**RTK deprecation flag:** **Partial** — `get_rtk_state` and `installTerrenoDevConsoleLogger` are RTK-named surfaces delivered by #802 that must be renamed or relocated after #869. Marked tasks are blocked on both PRs.
+
+## Goal
+
+Turn Terreno's AI-native pillar from a claim into a documented, demonstrable loop. The machinery mostly exists after PR #802 lands: an agent can search current docs, generate conventional code, run the app, read merged logs from four sources, see the last error with a stack, inspect client state, and drive navigation. What does not exist is any document that explains this as a single workflow, so nobody outside the team knows it is there.
+
+This IP writes the story and closes the gaps that become obvious once the story is written down.
+
+## Non-Goals
+
+- Building new MCP tools beyond renames and small gap-fillers.
+- Re-implementing UI automation — #802 deliberately composes `expo-mcp`, Playwright MCP, and Maestro rather than building tap/screenshot tooling.
+- The tutorial itself (that is [`docs-tutorials-ai-first`](docs-tutorials-ai-first.md), which depends on this IP's reference content).
+- Langfuse/observability for AI features inside consumer apps (that is `terreno-langfuse-integration.md`).
+
+## Blocking questions
+
+**Recorded 2026-07-29** (defaults accepted).
+
+| # | Question | Decision |
+|---|----------|----------|
+| AI1 | Replace `get_rtk_state` | **A** — `get_client_state` with a `layer` field |
+| AI2 | `installTerrenoDevConsoleLogger` location | **B** — move to `@terreno/syncdb`, re-export from rtk during support window |
+| AI3 | Document `evaluate` publicly? | **A** — yes, with `TERRENO_MCP_EVAL=1` gate |
+| AI4 | Compose `expo-mcp` + Playwright MCP? | **A** — yes, with configuration |
+| AI5 | Hosted MCP auth / rate limiting | **B** — rate limiting by IP before public launch |
+| AI6 | MCP URL (→ P4) | **`https://mcp.terreno.app`** |
+
+## Architecture
+
+### The loop, named
+
+```mermaid
+flowchart LR
+  ASK["1. Ask<br/>terreno_search_docs<br/>terreno_get_component_docs"]
+  GEN["2. Generate<br/>generate_model / route / screen<br/>validate_model_schema"]
+  RUN["3. Run<br/>bun run backend:dev<br/>expo start"]
+  OBS["4. Observe<br/>read_logs (backend/app/metro/browser)<br/>last_error<br/>get_client_state"]
+  FIX["5. Fix<br/>navigate + screenshot<br/>regenerate typed client"]
+  ASK --> GEN --> RUN --> OBS --> FIX
+  FIX -->|"iterate"| ASK
+```
+
+The claim worth making is narrow and true: **the agent sees what the app actually did, not a description of it.** Everything else in the *tool* story is table stakes that other frameworks can match.
+
+### Tool layer versus process layer
+
+This loop is only half the AI story, and documenting it alone undersells it. The other half is the `/terreno-*` SDLC pipeline shipped in `plugins/terreno-planning/` — plan, implement test-first, verify in a fresh context, submit with evidence, own the review loop. [`agentic-sdlc-plugin`](agentic-sdlc-plugin.md) owns publishing and documenting it.
+
+| Layer | Answers | Delivered by |
+|-------|---------|--------------|
+| **Tool** | What can the agent see and do? | MCP servers: docs search, codegen, merged logs, client state, navigation |
+| **Process** | In what order should the agent work, and who checks it? | `/terreno-*`: question-first planning, TDD, fresh-context independent review, evidence gates, reactive review loop |
+
+Every document produced by this IP must name both and explain that they compose: the pipeline's implement stage uses the loop's tools, and the loop's tools are most useful when driven by the pipeline's sequencing. `docs/explanation/ai-development-loop.md` and `docs/explanation/agentic-sdlc.md` are companion pages and must cross-link.
+
+### Tool surface after #802
+
+| Tool | Server | Purpose |
+|------|--------|---------|
+| `terreno_search_docs` | hosted | BM25 search over the docs corpus, multi-query |
+| `terreno_get_component_docs` | hosted | Full props table for a `@terreno/ui` component |
+| `terreno_get_upgrade_guide` | hosted | Concatenated upgrade notes for a version range |
+| `terreno_bootstrap_app` / `terreno_bootstrap_ai_rules` | hosted | Scaffold an app / agent rules |
+| `terreno_generate_*`, `terreno_validate_model_schema`, `terreno_install_admin` | hosted | Codegen |
+| `application_info` | local | `@terreno/*` and toolchain versions |
+| `database_schema` / `database_query` | local | Mongo introspection, read-only allowlist |
+| `read_logs` | local | Merged backend + app (CDP) + Metro + browser logs |
+| `last_error` | local | Most recent error with stack across sources |
+| `get_rtk_state` → `get_client_state` | local | Store and cache inspection |
+| `evaluate` / `navigate` | local | CDP runtime, `TERRENO_MCP_EVAL=1` gated |
+
+### Gaps that surface once the story is written
+
+1. **Naming**: `get_rtk_state` is named after a package being deprecated (AI1).
+2. **Discovery**: nothing tells a developer to install `terreno-mcp-local`. `docs/reference/mcp-server.md` documents it, but no getting-started path mentions it.
+3. **Hermes single-connection contention**: opening React Native DevTools steals the CDP connection the log tools need. #802 mitigates with lazy connect/release and status reporting; users need to know the symptom.
+4. **No end-to-end setup guide**: MCP configuration is scattered across the README and the reference page, per-editor, with no single how-to.
+5. **Hosted server has no rate limiting** (AI5) — a launch risk.
+6. **Composition is undocumented**: `expo-mcp` and Playwright MCP wiring exists in bootstrap output but is not explained (AI4).
+
+### Documentation to produce
+
+| Document | Purpose |
+|----------|---------|
+| `docs/explanation/ai-development-loop.md` | The five-stage loop, why it is different, what the agent can and cannot see |
+| `docs/how-to/set-up-terreno-mcp.md` | Per-editor configuration for both Terreno servers plus composed servers |
+| `docs/how-to/debug-with-mcp.md` | Using `read_logs`, `last_error`, `get_client_state`, `navigate` on a real failure |
+| `docs/reference/mcp-server.md` | Updated with the complete post-#802 tool surface and every environment variable |
+| `docs/explanation/agent-guidelines.md` | How per-package `.ai/` guidelines and `.rulesync/` rules reach an agent, and how consumers extend them |
+
+Companion page owned elsewhere: `docs/explanation/agentic-sdlc.md` (the process layer) from [`agentic-sdlc-plugin`](agentic-sdlc-plugin.md). Neither page should duplicate the other; each links the other as the missing half.
+
+## Models / APIs
+
+No new models. `POST /__terreno/browser-logs` (dev-only, from #802) needs documenting including its production-disabled behavior and the `TERRENO_BROWSER_LOGS` override.
+
+## Notifications
+
+None.
+
+## UI
+
+None. `installTerrenoDevConsoleLogger` is invisible instrumentation.
+
+## Phases
+
+1. **Reconcile with merged #802** — verify the actual tool names, parameters, and environment variables.
+2. **Reference completeness** — update `docs/reference/mcp-server.md` to the real surface.
+3. **The loop explainer** — `ai-development-loop.md`.
+4. **Setup and debug how-tos** — including composed servers.
+5. **Gap fixes** — the `get_client_state` rename (post-#869), logger relocation, hosted rate limiting, discovery paths.
+6. **Agent guidelines explainer** — how guidelines reach agents and how consumers extend them.
+
+## Feature Flags & Migrations
+
+- `TERRENO_MCP_EVAL=1` gates `evaluate` and `navigate`; never enabled by bootstrap defaults.
+- `TERRENO_BROWSER_LOGS` and `NODE_ENV` gate the browser-log route.
+- Renaming `get_rtk_state` to `get_client_state` is a breaking MCP tool change: keep the old name as an alias for one release with a deprecation note in its description.
+
+## Not Included / Future Work
+
+- Semantic/vector docs search (BM25 is the v1 answer).
+- CDP multiplexing proxy for the Hermes single-connection limit (the fallback plan in #802 if contention proves painful).
+- Terreno-authored simulator automation.
+- MCP tools generated for consumer app APIs (`model-router-mcp.md`).
+
+## Files to Create / Modify
+
+**Create**
+
+- `docs/explanation/ai-development-loop.md`
+- `docs/how-to/set-up-terreno-mcp.md`
+- `docs/how-to/debug-with-mcp.md`
+- `docs/explanation/agent-guidelines.md`
+
+**Modify**
+
+- `docs/reference/mcp-server.md`, `mcp-server/README.md`
+- `mcp-server/src/local/tools/runtime.ts` (tool rename + alias)
+- `mcp-server/src/local/localTools.ts` (tool registration)
+- `mcp-server/src/index.ts` (rate limiting)
+- `rtk/src/devConsoleLogger.ts` → `syncdb/src/devConsoleLogger.ts` (with re-export)
+- `docs/reference/environment-variables.md`
+- `README.md` (MCP section links the new how-to)
+
+## Task List
+
+See [`docs/tasks/ai-dev-loop-boost.md`](../tasks/ai-dev-loop-boost.md).
+
+## Acceptance Criteria
+
+- [ ] `docs/reference/mcp-server.md` lists every tool, prompt, and resource on both servers, matching the merged code, and every environment variable that affects them.
+- [ ] `docs/explanation/ai-development-loop.md` explains the five stages and states precisely what an agent can and cannot observe.
+- [ ] `docs/explanation/ai-development-loop.md` distinguishes the tool layer from the process layer, and cross-links `docs/explanation/agentic-sdlc.md` as the other half of the AI story.
+- [ ] `docs/how-to/set-up-terreno-mcp.md` gives working configuration for at least Cursor and Claude Code, covering both Terreno servers, and explains when to add `expo-mcp` and Playwright MCP.
+- [ ] `docs/how-to/debug-with-mcp.md` walks a real failure from symptom to fix using `last_error` and `read_logs`, with real tool output.
+- [ ] The Hermes single-CDP-connection limitation is documented with its symptom and the workaround.
+- [ ] `evaluate` and `navigate` are documented with the `TERRENO_MCP_EVAL` gate and the security reasoning for it.
+- [ ] `get_client_state` exists, works against both store types, reports which layer it found, and `get_rtk_state` remains as a deprecated alias for one release.
+- [ ] `installTerrenoDevConsoleLogger` is exported from the supported client package with a re-export from `@terreno/rtk` for the support window.
+- [ ] The hosted MCP server enforces rate limiting, with the limit documented and a clear error response when exceeded.
+- [ ] `POST /__terreno/browser-logs` is documented including that it 404s in production.
+- [ ] A bootstrapped app's generated `mcp.json` matches the setup how-to exactly.
+- [ ] `bun run mcp:build`, `bun run lint`, `bun run compile`, and `bun run rules:check` all pass.