@cyanheads/protein-mcp-server 0.4.0 → 0.4.1

package/AGENTS.md

@@ -1,11 +1,12 @@
 # Developer Protocol
 
 **Server:** protein-mcp-server
-**Version:** 0.4.0
-**Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.10.10`
+**Version:** 0.4.1
+**Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.11.5`
 **Engines:** Bun ≥1.3.0, Node ≥24.0.0
-**MCP SDK:** `@modelcontextprotocol/sdk` ^1.29.0
+**MCP SDK:** `@modelcontextprotocol/sdk` ^1.30.0
 **Zod:** ^4.4.3
+**TypeScript:** ^7.0.2
 
 > **Read the framework docs first:** `node_modules/@cyanheads/mcp-ts-core/CLAUDE.md` contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.
 
@@ -188,12 +189,14 @@ Handlers receive a unified `ctx` object. Key properties:
 | Property | Description |
 |:---------|:------------|
 | `ctx.log` | Request-scoped logger — `.debug()`, `.info()`, `.notice()`, `.warning()`, `.error()`. Auto-correlates requestId, traceId, tenantId. |
-| `ctx.state` | Tenant-scoped KV — `.get(key)`, `.set(key, value, { ttl? })`, `.delete(key)`, `.list(prefix, { cursor, limit })`. Accepts any serializable value. |
+| `ctx.state` | Tenant-scoped KV — `.get(key)`, `.set(key, value, { ttl? })`, `.delete(key)`, `.getMany(keys)`, `.list(prefix, { cursor, limit })`. Accepts any serializable value. |
 | `ctx.elicit` | Ask user for structured input — form call `(message, schema)` or `.url(message, url)` for an external link. **Check for presence first:** `if (ctx.elicit) { ... }` |
+| `ctx.enrich` | Success-path agent context (empty-result notices, query echo, pagination totals) — `ctx.enrich(...)` or `.notice()` / `.total()` / `.echo()` / `.truncated()`. Reaches `structuredContent` and `content[]`; lands only when the definition declares an `enrichment` block (no-op otherwise). |
+| `ctx.content` | Non-text content blocks — `.image(data, mimeType)`, `.audio(data, mimeType)`, or `ctx.content(block)` for a raw block. Prepended to `content[]` after `format()`; never enters `structuredContent`. |
 | `ctx.signal` | `AbortSignal` for cancellation. |
 | `ctx.progress` | Task progress (present when `task: true`) — `.setTotal(n)`, `.increment()`, `.update(message)`. |
 | `ctx.requestId` | Unique request ID. |
-| `ctx.tenantId` | Tenant ID from JWT or `'default'` for stdio. |
+| `ctx.tenantId` | Tenant ID from JWT; `'default'` for stdio or HTTP with auth off. |
 
 ---
 
@@ -201,7 +204,7 @@ Handlers receive a unified `ctx` object. Key properties:
 
 Handlers throw — the framework catches, classifies, and formats.
 
-**Recommended: typed error contract.** Declare `errors: [{ reason, code, when, recovery, retryable? }]` on `tool()` / `resource()` to receive `ctx.fail(reason, …)` typed against the reason union. TypeScript catches typos at compile time, `data.reason` is auto-populated for observability, linter enforces conformance against the handler body. `recovery` is required descriptive metadata for the agent's next move (≥ 5 words, lint-validated); for the wire `data.recovery.hint` (mirrored into `content[]` text), pass explicitly at the throw site when dynamic context matters: `ctx.fail('reason', msg, { recovery: { hint: '...' } })`. Baseline codes (`InternalError`, `ServiceUnavailable`, `Timeout`, `ValidationError`, `SerializationError`) bubble freely and don't need declaring.
+**Recommended: typed error contract.** Declare `errors: [{ reason, code, when, recovery, retryable? }]` on `tool()` / `resource()` to receive `ctx.fail(reason, …)` typed against the reason union. TypeScript catches typos at compile time, `data.reason` is auto-populated for observability, linter enforces conformance against the handler body. `recovery` is required (≥ 5 words, lint-validated) — the single source of truth for the agent's next move. Pass `ctx.recoveryFor('reason')` as the throw's data to put it on the wire (`data.recovery.hint`, mirrored into `content[]` text); override with an explicit `{ recovery: { hint: '...' } }` when dynamic runtime context matters. Baseline codes (`InternalError`, `ServiceUnavailable`, `Timeout`, `ValidationError`, `SerializationError`) bubble freely and don't need declaring.
 
 ```ts
 import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
@@ -213,7 +216,7 @@ errors: [
 ],
 async handler(input, ctx) {
   const item = await db.find(input.id);
-  if (!item) throw ctx.fail('no_match', `No item ${input.id}`);
+  if (!item) throw ctx.fail('no_match', `No item ${input.id}`, ctx.recoveryFor('no_match'));
   return item;
 }
 ```
@@ -279,7 +282,7 @@ src/
 
 ## Skills
 
-Skills are modular instructions in `skills/` at the project root. Read them directly when a task matches — e.g., `skills/add-tool/SKILL.md` when adding a tool.
+Skills are modular instructions in `skills/` at the project root. Read them directly when a task matches — e.g., `skills/add-tool/SKILL.md` when adding a tool. `bun run list-skills` prints the full registry.
 
 **Agent skill directory:** Copy skills into the directory your agent discovers (Claude Code: `.claude/skills/`, others: equivalent). Skills then load as context without referencing `skills/` paths. After framework updates, run the `maintenance` skill — Phase B re-syncs the agent directory.
 
@@ -299,7 +302,7 @@ Available skills:
 | `tool-defs-analysis` | Read-only audit of MCP definition language across the surface — voice, leaks, defaults, recovery hints, output descriptions |
 | `security-pass` | Audit server for MCP-flavored security gaps: output injection, scope blast radius, input sinks, tenant isolation |
 | `code-simplifier` | Post-session cleanup against `git diff` — modernize syntax, consolidate duplication, align with the codebase |
-| `devcheck` | Lint, format, typecheck, audit |
+| `techniques` | Catalog of response/data-shaping techniques — overflow handling, payload shaping, retrieval patterns |
 | `polish-docs-meta` | Finalize docs, README, metadata, and agent protocol for shipping |
 | `git-wrapup` | Land working-tree changes as a versioned commit + annotated tag — version bump, changelog, verify, tag. Local only. |
 | `release-and-publish` | Push + npm + MCP Registry + GH Release + Docker. Picks up from `git-wrapup` |
@@ -313,6 +316,7 @@ Available skills:
 | `api-context` | Context interface, logger, state, progress |
 | `api-errors` | McpError, JsonRpcErrorCode, error patterns |
 | `api-linter` | Definition linter rule catalog — invoked by `bun run lint:mcp` and `devcheck` |
+| `api-mirror` | MirrorService: persistent self-refreshing local mirror (embedded SQLite + FTS5) of a bulk upstream dataset — Tier 3 opt-in |
 | `api-services` | LLM, Speech, Graph services |
 | `api-testing` | createMockContext, test patterns |
 | `api-utils` | Formatting, parsing, security, pagination, scheduling, telemetry helpers |
@@ -331,26 +335,29 @@ When you complete a skill's checklist, check the boxes and add a completion time
 
 | Command | Purpose |
 |:--------|:--------|
-| `npm run build` | Compile TypeScript |
-| `npm run rebuild` | Clean + build |
-| `npm run clean` | Remove build artifacts |
-| `npm run devcheck` | Lint + format + typecheck + security + changelog sync |
+| `bun run build` | Compile TypeScript |
+| `bun run rebuild` | Clean + build |
+| `bun run clean` | Remove build artifacts |
+| `bun run devcheck` | Lint + format + typecheck + security + changelog sync |
 | `bun run audit:refresh` | Delete `bun.lock`, reinstall, and re-run `bun audit`. Use when `devcheck` flags a transitive advisory — Bun's `update` is sticky on transitive resolutions, so the advisory may be a stale-lockfile false positive. If it survives the refresh, it's real. |
-| `npm run tree` | Generate directory structure doc |
-| `npm run format` | Auto-fix formatting (safe fixes only) |
-| `npm run format:unsafe` | Also apply Biome's unsafe autofixes — review the diff; they can change behavior |
-| `npm test` | Run tests |
-| `npm run start:stdio` | Production mode (stdio) |
-| `npm run start:http` | Production mode (HTTP) |
-| `npm run changelog:build` | Regenerate `CHANGELOG.md` from `changelog/*.md` |
-| `npm run changelog:check` | Verify `CHANGELOG.md` is in sync (used by devcheck) |
-| `npm run bundle` | Build, pack, and clean a `.mcpb` for one-click Claude Desktop install |
+| `bun run lint:mcp` | Run the MCP definition linter standalone (rule catalog: `api-linter` skill) |
+| `bun run lint:packaging` | Packaging surface checks — `server.json`/`manifest.json` env-var parity (run by devcheck) |
+| `bun run list-skills` | Print the skill registry |
+| `bun run tree` | Generate directory structure doc |
+| `bun run format` | Auto-fix formatting (safe fixes only) |
+| `bun run format:unsafe` | Also apply Biome's unsafe autofixes — review the diff; they can change behavior |
+| `bun run test` | Run tests (Vitest — use `bun run test`, not `bun test`) |
+| `bun run start:stdio` | Production mode (stdio) |
+| `bun run start:http` | Production mode (HTTP) |
+| `bun run changelog:build` | Regenerate `CHANGELOG.md` from `changelog/*.md` |
+| `bun run changelog:check` | Verify `CHANGELOG.md` is in sync (used by devcheck) |
+| `bun run bundle` | Build, pack, and clean a `.mcpb` for one-click Claude Desktop install |
 
 ---
 
 ## Bundling
 
-`npm run bundle` produces a `.mcpb` extension bundle for one-click install in Claude Desktop. The pack step is followed by `scripts/clean-mcpb.ts`, which prunes dev dependencies (`mcpb clean`) and strips dependency-shipped agent docs (`node_modules/**` `skills/`, `.claude/`, `.agents/`, `SKILL.md`) that root-anchored `.mcpbignore` patterns cannot reach. MCPB is stdio-only — HTTP and Cloudflare Workers deployments are unaffected. Consumers who don't need it can delete `manifest.json` and `.mcpbignore`; `lint:packaging` skips cleanly.
+`bun run bundle` produces a `.mcpb` extension bundle for one-click install in Claude Desktop. The pack step is followed by `scripts/clean-mcpb.ts`, which prunes dev dependencies (`mcpb clean`) and strips two classes of `node_modules/**` content that root-anchored `.mcpbignore` patterns cannot reach: dependency-shipped agent docs (`skills/`, `.claude/`, `.agents/`, `SKILL.md`) and platform-specific native bindings, which would otherwise lock the bundle to the platform it was packed on. MCPB is stdio-only — HTTP and Cloudflare Workers deployments are unaffected. Consumers who don't need it can delete `manifest.json` and `.mcpbignore`; `lint:packaging` skips cleanly.
 
 **Adding an env var requires both files:** `server.json` (registry discovery, `environmentVariables[]`) and `manifest.json` (bundle install UX, `mcp_config.env` + `user_config`). `lint:packaging` (run by `devcheck`) verifies the env var names match.
 
@@ -368,14 +375,14 @@ Each per-version file opens with YAML frontmatter:
 ---
 summary: "One-line headline, ≤350 chars"  # required — powers the rollup index
 breaking: false                            # optional — true flags breaking changes
-security: false                            # optional — true flags security fixes
+security: false                            # optional — true ONLY for a source-code security fix, never a dependency CVE bump
 ---
 
 # 0.1.0 — YYYY-MM-DD
 ...
 ```
 
-`breaking: true` renders a `· ⚠️ Breaking` badge — use it when consumers must update code on upgrade (signature changes, removed APIs, config renames). `security: true` renders a `· 🛡️ Security` badge and pairs with a `## Security` body section. When both are set, badges render `· ⚠️ Breaking · 🛡️ Security`.
+`breaking: true` renders a `· ⚠️ Breaking` badge — use it when consumers must update code on upgrade (signature changes, removed APIs, config renames). `security: true` renders a `· 🛡️ Security` badge and pairs with a `## Security` body section — set it only for a security fix in this server's *own source code*, never for a routine dependency or transitive CVE bump (record those under `## Dependencies`). When both are set, badges render `· ⚠️ Breaking · 🛡️ Security`.
 
 `agent-notes` is an optional free-form field for maintenance agents processing the release downstream. Content here won't appear in the rendered CHANGELOG — it's consumed by agents running the `maintenance` skill. Use it for adoption instructions that don't fit the human-facing sections: new files to create, fields to populate, one-time migration steps. Omit entirely when there's nothing to say.
 

package/CLAUDE.md

@@ -1,11 +1,12 @@
 # Developer Protocol
 
 **Server:** protein-mcp-server
-**Version:** 0.4.0
-**Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.10.10`
+**Version:** 0.4.1
+**Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.11.5`
 **Engines:** Bun ≥1.3.0, Node ≥24.0.0
-**MCP SDK:** `@modelcontextprotocol/sdk` ^1.29.0
+**MCP SDK:** `@modelcontextprotocol/sdk` ^1.30.0
 **Zod:** ^4.4.3
+**TypeScript:** ^7.0.2
 
 > **Read the framework docs first:** `node_modules/@cyanheads/mcp-ts-core/CLAUDE.md` contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.
 
@@ -188,12 +189,14 @@ Handlers receive a unified `ctx` object. Key properties:
 | Property | Description |
 |:---------|:------------|
 | `ctx.log` | Request-scoped logger — `.debug()`, `.info()`, `.notice()`, `.warning()`, `.error()`. Auto-correlates requestId, traceId, tenantId. |
-| `ctx.state` | Tenant-scoped KV — `.get(key)`, `.set(key, value, { ttl? })`, `.delete(key)`, `.list(prefix, { cursor, limit })`. Accepts any serializable value. |
+| `ctx.state` | Tenant-scoped KV — `.get(key)`, `.set(key, value, { ttl? })`, `.delete(key)`, `.getMany(keys)`, `.list(prefix, { cursor, limit })`. Accepts any serializable value. |
 | `ctx.elicit` | Ask user for structured input — form call `(message, schema)` or `.url(message, url)` for an external link. **Check for presence first:** `if (ctx.elicit) { ... }` |
+| `ctx.enrich` | Success-path agent context (empty-result notices, query echo, pagination totals) — `ctx.enrich(...)` or `.notice()` / `.total()` / `.echo()` / `.truncated()`. Reaches `structuredContent` and `content[]`; lands only when the definition declares an `enrichment` block (no-op otherwise). |
+| `ctx.content` | Non-text content blocks — `.image(data, mimeType)`, `.audio(data, mimeType)`, or `ctx.content(block)` for a raw block. Prepended to `content[]` after `format()`; never enters `structuredContent`. |
 | `ctx.signal` | `AbortSignal` for cancellation. |
 | `ctx.progress` | Task progress (present when `task: true`) — `.setTotal(n)`, `.increment()`, `.update(message)`. |
 | `ctx.requestId` | Unique request ID. |
-| `ctx.tenantId` | Tenant ID from JWT or `'default'` for stdio. |
+| `ctx.tenantId` | Tenant ID from JWT; `'default'` for stdio or HTTP with auth off. |
 
 ---
 
@@ -201,7 +204,7 @@ Handlers receive a unified `ctx` object. Key properties:
 
 Handlers throw — the framework catches, classifies, and formats.
 
-**Recommended: typed error contract.** Declare `errors: [{ reason, code, when, recovery, retryable? }]` on `tool()` / `resource()` to receive `ctx.fail(reason, …)` typed against the reason union. TypeScript catches typos at compile time, `data.reason` is auto-populated for observability, linter enforces conformance against the handler body. `recovery` is required descriptive metadata for the agent's next move (≥ 5 words, lint-validated); for the wire `data.recovery.hint` (mirrored into `content[]` text), pass explicitly at the throw site when dynamic context matters: `ctx.fail('reason', msg, { recovery: { hint: '...' } })`. Baseline codes (`InternalError`, `ServiceUnavailable`, `Timeout`, `ValidationError`, `SerializationError`) bubble freely and don't need declaring.
+**Recommended: typed error contract.** Declare `errors: [{ reason, code, when, recovery, retryable? }]` on `tool()` / `resource()` to receive `ctx.fail(reason, …)` typed against the reason union. TypeScript catches typos at compile time, `data.reason` is auto-populated for observability, linter enforces conformance against the handler body. `recovery` is required (≥ 5 words, lint-validated) — the single source of truth for the agent's next move. Pass `ctx.recoveryFor('reason')` as the throw's data to put it on the wire (`data.recovery.hint`, mirrored into `content[]` text); override with an explicit `{ recovery: { hint: '...' } }` when dynamic runtime context matters. Baseline codes (`InternalError`, `ServiceUnavailable`, `Timeout`, `ValidationError`, `SerializationError`) bubble freely and don't need declaring.
 
 ```ts
 import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
@@ -213,7 +216,7 @@ errors: [
 ],
 async handler(input, ctx) {
   const item = await db.find(input.id);
-  if (!item) throw ctx.fail('no_match', `No item ${input.id}`);
+  if (!item) throw ctx.fail('no_match', `No item ${input.id}`, ctx.recoveryFor('no_match'));
   return item;
 }
 ```
@@ -279,7 +282,7 @@ src/
 
 ## Skills
 
-Skills are modular instructions in `skills/` at the project root. Read them directly when a task matches — e.g., `skills/add-tool/SKILL.md` when adding a tool.
+Skills are modular instructions in `skills/` at the project root. Read them directly when a task matches — e.g., `skills/add-tool/SKILL.md` when adding a tool. `bun run list-skills` prints the full registry.
 
 **Agent skill directory:** Copy skills into the directory your agent discovers (Claude Code: `.claude/skills/`, others: equivalent). Skills then load as context without referencing `skills/` paths. After framework updates, run the `maintenance` skill — Phase B re-syncs the agent directory.
 
@@ -299,7 +302,7 @@ Available skills:
 | `tool-defs-analysis` | Read-only audit of MCP definition language across the surface — voice, leaks, defaults, recovery hints, output descriptions |
 | `security-pass` | Audit server for MCP-flavored security gaps: output injection, scope blast radius, input sinks, tenant isolation |
 | `code-simplifier` | Post-session cleanup against `git diff` — modernize syntax, consolidate duplication, align with the codebase |
-| `devcheck` | Lint, format, typecheck, audit |
+| `techniques` | Catalog of response/data-shaping techniques — overflow handling, payload shaping, retrieval patterns |
 | `polish-docs-meta` | Finalize docs, README, metadata, and agent protocol for shipping |
 | `git-wrapup` | Land working-tree changes as a versioned commit + annotated tag — version bump, changelog, verify, tag. Local only. |
 | `release-and-publish` | Push + npm + MCP Registry + GH Release + Docker. Picks up from `git-wrapup` |
@@ -313,6 +316,7 @@ Available skills:
 | `api-context` | Context interface, logger, state, progress |
 | `api-errors` | McpError, JsonRpcErrorCode, error patterns |
 | `api-linter` | Definition linter rule catalog — invoked by `bun run lint:mcp` and `devcheck` |
+| `api-mirror` | MirrorService: persistent self-refreshing local mirror (embedded SQLite + FTS5) of a bulk upstream dataset — Tier 3 opt-in |
 | `api-services` | LLM, Speech, Graph services |
 | `api-testing` | createMockContext, test patterns |
 | `api-utils` | Formatting, parsing, security, pagination, scheduling, telemetry helpers |
@@ -331,26 +335,29 @@ When you complete a skill's checklist, check the boxes and add a completion time
 
 | Command | Purpose |
 |:--------|:--------|
-| `npm run build` | Compile TypeScript |
-| `npm run rebuild` | Clean + build |
-| `npm run clean` | Remove build artifacts |
-| `npm run devcheck` | Lint + format + typecheck + security + changelog sync |
+| `bun run build` | Compile TypeScript |
+| `bun run rebuild` | Clean + build |
+| `bun run clean` | Remove build artifacts |
+| `bun run devcheck` | Lint + format + typecheck + security + changelog sync |
 | `bun run audit:refresh` | Delete `bun.lock`, reinstall, and re-run `bun audit`. Use when `devcheck` flags a transitive advisory — Bun's `update` is sticky on transitive resolutions, so the advisory may be a stale-lockfile false positive. If it survives the refresh, it's real. |
-| `npm run tree` | Generate directory structure doc |
-| `npm run format` | Auto-fix formatting (safe fixes only) |
-| `npm run format:unsafe` | Also apply Biome's unsafe autofixes — review the diff; they can change behavior |
-| `npm test` | Run tests |
-| `npm run start:stdio` | Production mode (stdio) |
-| `npm run start:http` | Production mode (HTTP) |
-| `npm run changelog:build` | Regenerate `CHANGELOG.md` from `changelog/*.md` |
-| `npm run changelog:check` | Verify `CHANGELOG.md` is in sync (used by devcheck) |
-| `npm run bundle` | Build, pack, and clean a `.mcpb` for one-click Claude Desktop install |
+| `bun run lint:mcp` | Run the MCP definition linter standalone (rule catalog: `api-linter` skill) |
+| `bun run lint:packaging` | Packaging surface checks — `server.json`/`manifest.json` env-var parity (run by devcheck) |
+| `bun run list-skills` | Print the skill registry |
+| `bun run tree` | Generate directory structure doc |
+| `bun run format` | Auto-fix formatting (safe fixes only) |
+| `bun run format:unsafe` | Also apply Biome's unsafe autofixes — review the diff; they can change behavior |
+| `bun run test` | Run tests (Vitest — use `bun run test`, not `bun test`) |
+| `bun run start:stdio` | Production mode (stdio) |
+| `bun run start:http` | Production mode (HTTP) |
+| `bun run changelog:build` | Regenerate `CHANGELOG.md` from `changelog/*.md` |
+| `bun run changelog:check` | Verify `CHANGELOG.md` is in sync (used by devcheck) |
+| `bun run bundle` | Build, pack, and clean a `.mcpb` for one-click Claude Desktop install |
 
 ---
 
 ## Bundling
 
-`npm run bundle` produces a `.mcpb` extension bundle for one-click install in Claude Desktop. The pack step is followed by `scripts/clean-mcpb.ts`, which prunes dev dependencies (`mcpb clean`) and strips dependency-shipped agent docs (`node_modules/**` `skills/`, `.claude/`, `.agents/`, `SKILL.md`) that root-anchored `.mcpbignore` patterns cannot reach. MCPB is stdio-only — HTTP and Cloudflare Workers deployments are unaffected. Consumers who don't need it can delete `manifest.json` and `.mcpbignore`; `lint:packaging` skips cleanly.
+`bun run bundle` produces a `.mcpb` extension bundle for one-click install in Claude Desktop. The pack step is followed by `scripts/clean-mcpb.ts`, which prunes dev dependencies (`mcpb clean`) and strips two classes of `node_modules/**` content that root-anchored `.mcpbignore` patterns cannot reach: dependency-shipped agent docs (`skills/`, `.claude/`, `.agents/`, `SKILL.md`) and platform-specific native bindings, which would otherwise lock the bundle to the platform it was packed on. MCPB is stdio-only — HTTP and Cloudflare Workers deployments are unaffected. Consumers who don't need it can delete `manifest.json` and `.mcpbignore`; `lint:packaging` skips cleanly.
 
 **Adding an env var requires both files:** `server.json` (registry discovery, `environmentVariables[]`) and `manifest.json` (bundle install UX, `mcp_config.env` + `user_config`). `lint:packaging` (run by `devcheck`) verifies the env var names match.
 
@@ -368,14 +375,14 @@ Each per-version file opens with YAML frontmatter:
 ---
 summary: "One-line headline, ≤350 chars"  # required — powers the rollup index
 breaking: false                            # optional — true flags breaking changes
-security: false                            # optional — true flags security fixes
+security: false                            # optional — true ONLY for a source-code security fix, never a dependency CVE bump
 ---
 
 # 0.1.0 — YYYY-MM-DD
 ...
 ```
 
-`breaking: true` renders a `· ⚠️ Breaking` badge — use it when consumers must update code on upgrade (signature changes, removed APIs, config renames). `security: true` renders a `· 🛡️ Security` badge and pairs with a `## Security` body section. When both are set, badges render `· ⚠️ Breaking · 🛡️ Security`.
+`breaking: true` renders a `· ⚠️ Breaking` badge — use it when consumers must update code on upgrade (signature changes, removed APIs, config renames). `security: true` renders a `· 🛡️ Security` badge and pairs with a `## Security` body section — set it only for a security fix in this server's *own source code*, never for a routine dependency or transitive CVE bump (record those under `## Dependencies`). When both are set, badges render `· ⚠️ Breaking · 🛡️ Security`.
 
 `agent-notes` is an optional free-form field for maintenance agents processing the release downstream. Content here won't appear in the rendered CHANGELOG — it's consumed by agents running the `maintenance` skill. Use it for adoption instructions that don't fit the human-facing sections: new files to create, fields to populate, one-time migration steps. Omit entirely when there's nothing to say.
 

package/Dockerfile

@@ -4,15 +4,17 @@
 # This stage installs all dependencies (including dev), builds the TypeScript
 # source code into JavaScript, and prepares the production assets.
 # ==============================================================================
-FROM oven/bun:1.3 AS build
+FROM oven/bun:1.3.14 AS build
 
 WORKDIR /usr/src/app
 
 # Copy dependency manifests for optimized layer caching
 COPY package.json bun.lock ./
 
-# Install all dependencies (including dev dependencies for building)
-RUN bun install --frozen-lockfile
+# Install all dependencies (including dev dependencies for building).
+# The BuildKit cache mount persists Bun's global package cache across builds.
+RUN --mount=type=cache,target=/root/.bun/install/cache \
+    bun install --frozen-lockfile --ignore-scripts
 
 # Copy the rest of the source code
 COPY . .
@@ -28,7 +30,7 @@ RUN bun run build
 # application. It uses a slim base image and only includes production
 # dependencies and build artifacts.
 # ==============================================================================
-FROM oven/bun:1.3-slim AS production
+FROM oven/bun:1.3.14-slim AS production
 
 WORKDIR /usr/src/app
 
@@ -49,14 +51,21 @@ COPY package.json bun.lock ./
 
 # Install only production dependencies, ignoring any lifecycle scripts (like 'prepare')
 # that are not needed in the final production image.
-RUN bun install --production --frozen-lockfile --ignore-scripts
+# `--omit=peer` drops the framework's optional peer tiers (test runner, service
+# SDKs, parsers) that Bun would otherwise auto-install. Anything this server
+# actually imports belongs in its own `dependencies`, so nothing needed at
+# runtime is lost. The OTEL step below carries the same flag — without it, that
+# install re-resolves the graph and pulls every optional peer back in.
+RUN --mount=type=cache,target=/root/.bun/install/cache \
+    bun install --production --omit=peer --frozen-lockfile --ignore-scripts
 
 # Conditionally install OpenTelemetry optional peer dependencies (Tier 3).
 # These are not bundled by default to keep the base image lean. Enable at build time
 # with: docker build --build-arg OTEL_ENABLED=true
 ARG OTEL_ENABLED=true
-RUN if [ "$OTEL_ENABLED" = "true" ]; then \
-      bun add @hono/otel \
+RUN --mount=type=cache,target=/root/.bun/install/cache \
+    if [ "$OTEL_ENABLED" = "true" ]; then \
+      bun add --omit=dev --omit=peer --ignore-scripts @hono/otel \
         @opentelemetry/instrumentation-http \
         @opentelemetry/exporter-metrics-otlp-http \
         @opentelemetry/exporter-trace-otlp-http \

package/LICENSE

@@ -186,7 +186,7 @@ Apache License
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2025 Casey Hand @cyanheads
+   Copyright 2026 Casey Hand @cyanheads
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

package/README.md

@@ -7,7 +7,7 @@
 
 <div align="center">
 
-[![Version](https://img.shields.io/badge/Version-0.4.0-blue.svg?style=flat-square)](./CHANGELOG.md) [![License](https://img.shields.io/badge/License-Apache%202.0-orange.svg?style=flat-square)](./LICENSE) [![Docker](https://img.shields.io/badge/Docker-ghcr.io-2496ED?style=flat-square&logo=docker&logoColor=white)](https://github.com/users/cyanheads/packages/container/package/protein-mcp-server) [![MCP SDK](https://img.shields.io/badge/MCP%20SDK-^1.29.0-green.svg?style=flat-square)](https://modelcontextprotocol.io/) [![npm](https://img.shields.io/npm/v/@cyanheads/protein-mcp-server?style=flat-square&logo=npm&logoColor=white)](https://www.npmjs.com/package/@cyanheads/protein-mcp-server) [![TypeScript](https://img.shields.io/badge/TypeScript-^6.0.3-3178C6.svg?style=flat-square)](https://www.typescriptlang.org/) [![Bun](https://img.shields.io/badge/Bun-v1.3.2-blueviolet.svg?style=flat-square)](https://bun.sh/)
+[![Version](https://img.shields.io/badge/Version-0.4.1-blue.svg?style=flat-square)](./CHANGELOG.md) [![License](https://img.shields.io/badge/License-Apache%202.0-orange.svg?style=flat-square)](./LICENSE) [![Docker](https://img.shields.io/badge/Docker-ghcr.io-2496ED?style=flat-square&logo=docker&logoColor=white)](https://github.com/users/cyanheads/packages/container/package/protein-mcp-server) [![MCP SDK](https://img.shields.io/badge/MCP%20SDK-^1.30.0-green.svg?style=flat-square)](https://modelcontextprotocol.io/) [![npm](https://img.shields.io/npm/v/@cyanheads/protein-mcp-server?style=flat-square&logo=npm&logoColor=white)](https://www.npmjs.com/package/@cyanheads/protein-mcp-server) [![TypeScript](https://img.shields.io/badge/TypeScript-^7.0.2-3178C6.svg?style=flat-square)](https://www.typescriptlang.org/) [![Bun](https://img.shields.io/badge/Bun-v1.3.14-blueviolet.svg?style=flat-square)](https://bun.sh/)
 
 </div>
 
@@ -46,9 +46,9 @@ Seven tools spanning the structure-research arc — discover, fetch, find homolo
 Federated search across experimental (PDB) and predicted (computed-model) structures via RCSB Search v2.
 
 - Free-text, protein-sequence (triggers an mmseqs2 similarity search), and organism / method / resolution filters
-- `content_type` scopes the search to `experimental`, `predicted`, or `all`
-- Experimental hits are enriched with title, method, resolution, and organism
-- Optional `facets` return a method / organism / release-year breakdown alongside the hits at no extra call
+- `content_type` scopes the search to `experimental`, `predicted`, or `all` — the default `all` is a genuine union of both universes, so computed models appear alongside PDB entries
+- Every hit names its `source`; experimental hits are enriched with title, method, resolution, and organism, while computed models carry the UniProt accession parsed from their ID
+- Optional `facets` return a method / organism / release-year breakdown alongside the hits at no extra call, each reporting how many matches carry no value for that dimension
 - Chain hit IDs straight into `protein_get_structure`
 
 ---
@@ -57,7 +57,7 @@ Federated search across experimental (PDB) and predicted (computed-model) struct
 
 Fetch structures with metadata and coordinate-file URLs, resolving across providers by `source`.
 
-- `source: experimental` takes PDB entry IDs, batched in one RCSB GraphQL call
+- `source: experimental` takes PDB entry IDs, batched in one RCSB GraphQL call; it also resolves the computed-model IDs search returns (`AF_*` / `MA_*`), which come back as `source: predicted` credited to their modelling provider
 - `source: predicted` takes UniProt accessions and returns the AlphaFold model with pLDDT/PAE confidence
 - `source: best_available` takes UniProt accessions and returns the top federated model (experimental if one exists, else the best prediction)
 - Per-ID partial success — unresolved IDs are listed in `failed[]`, not a batch-level error
@@ -111,6 +111,7 @@ Profile the PDB into distributions and trends over an optional scoping query —
 - `interval` sets the bin width for value histograms or the period for date histograms (`year` / `month` / `quarter`)
 - Scope with a free-text `query`, `organism`, `method`, or `max_resolution`; `content_type` selects the structure universe
 - `bucket_limit` caps buckets per dimension; truncation is flagged in the response
+- Every dimension reports `missingValueCount` — matches in scope carrying no value for that attribute, which therefore fall in no bucket (a `resolution` breakdown does not cover NMR entries, and neither `method` nor `resolution` covers computed models)
 
 ---
 
@@ -351,6 +352,7 @@ Structure and annotation data comes from public upstream databases, each under i
 |:---|:---|:---|
 | [RCSB PDB](https://www.rcsb.org/) | `protein_get_structure` — experimental records | CC0 1.0 Universal |
 | [AlphaFold DB](https://alphafold.ebi.ac.uk/) | `protein_get_structure` — predicted models | CC BY 4.0 |
+| [ModelArchive](https://www.modelarchive.org/) | `protein_get_structure` — `MA_*` computed models | CC BY 4.0 |
 | [SWISS-MODEL](https://swissmodel.expasy.org/) | `protein_get_structure` — `best_available` models | CC BY-SA 4.0 |
 | [BFVD](https://bfvd.steineggerlab.workers.dev/) | `protein_get_structure` — `best_available` models | CC BY 4.0 |
 | [UniProt](https://www.uniprot.org/) | `protein_get_annotations` | CC BY 4.0 |

package/changelog/0.4.x/0.4.1.md

@@ -0,0 +1,32 @@
+---
+summary: "protein_search_structures' default content_type union now returns computed models, facet dimensions disclose coverage gaps and empty-dimension explanations, and protein_get_structure credits computed-model IDs to their modelling provider instead of the PDB."
+breaking: false
+security: false
+---
+
+# 0.4.1 — 2026-08-16
+
+## Added
+
+- **`protein_search_structures` / `protein_analyze_collection` facets** — every dimension now reports `missingValueCount`, the count of in-scope matches carrying no value for that attribute; a materially incomplete dimension (≥1% gap) adds an advisory to the shared `notice` field. ([#32](https://github.com/cyanheads/protein-mcp-server/issues/32))
+- **`protein_analyze_collection`** — `group_by` on `method` or `resolution` under `content_type: "predicted"` now emits a notice naming the empty dimension, since computed models carry no experimental method or resolution metadata. ([#27](https://github.com/cyanheads/protein-mcp-server/issues/27))
+
+## Changed
+
+- **Dependencies:**
+  - `@cyanheads/mcp-ts-core` ^0.10.10 → ^0.11.5
+  - `@modelcontextprotocol/sdk` ^1.29.0 → ^1.30.0 (transitive via mcp-ts-core)
+  - `typescript` ^6.0.3 → ^7.0.2 (dev)
+  - `@biomejs/biome` 2.5.2 → 2.5.8 (dev)
+  - `@types/node` 26.1.0 → 26.2.0 (dev)
+  - `tsc-alias` ^1.8.17 → ^1.9.1 (dev)
+  - `vitest` ^4.1.9 → ^4.1.10 (dev)
+  - `ignore` ^7.0.5 → ^7.0.6 (dev)
+  - `@socketsecurity/bun-security-scanner` ^1.1.2 added (dev) — wired as `bunfig.toml`'s `install.security` scanner
+  - Bun packageManager pin 1.3.2 → 1.3.14
+
+## Fixed
+
+- **`protein_search_structures` / `protein_analyze_collection`** — `content_type: "all"` (the default on `protein_search_structures`) now sends `results_content_type: ["experimental", "computational"]` explicitly; omitting the option, as before, is RCSB's experimental-only default, so `"all"` silently dropped every computed model. ([#29](https://github.com/cyanheads/protein-mcp-server/issues/29))
+- **`renderFacets()`** — a facet dimension with zero buckets no longer renders a bare `**dimension**` heading with nothing under it; both tools now emit an explicit "no data in this scope" line. ([#26](https://github.com/cyanheads/protein-mcp-server/issues/26))
+- **`protein_get_structure`** — a computed-model ID (`AF_*`/`MA_*`) resolved via `source: "experimental"` now comes back `source: "predicted"` with its modelling provider (AlphaFold DB, ModelArchive) named, credited to that provider's license instead of the PDB's CC0.

package/changelog/template.md

@@ -4,10 +4,11 @@
 # to author a new release. Set that file's H1 to `# <version> — YYYY-MM-DD`
 # with a concrete date.
 
-# Required. One-line GitHub Release-style headline. 350 character cap.
-# Default short and scannable. Don't pad, don't stitch unrelated changes with
-# semicolons — pick the headline. Quotes required: unquoted YAML treats `: `
-# inside the value as a key separator and fails GitHub's strict parser.
+# Required. One-line GitHub Release-style headline. 350 character cap — a
+# ceiling, not a target. Default short and scannable. Don't pad, don't stitch
+# unrelated changes with commas/semicolons into an inventory — pick the
+# headline, like a tag's theme line. Quotes required: unquoted YAML treats
+# `: ` inside the value as a key separator and fails GitHub's strict parser.
 summary: ""
 
 # Set `true` when consumers must change code to upgrade: API removals,
@@ -15,16 +16,19 @@ summary: ""
 # usage. Flagged as `Breaking` in the rollup.
 breaking: false
 
-# Set `true` if this release contains any security fix. Pairs with the
-# `## Security` section below. Flagged as `Security` in the rollup so
-# users can triage upgrade urgency at a glance.
+# Set `true` ONLY for a security fix in THIS project's own source code — a
+# vulnerability or hardening in code you ship. A dependency or transitive CVE
+# bump is routine maintenance, NOT a security release: record it under
+# `## Dependencies` (with the advisory ID) and leave this `false`. When true,
+# pairs with the `## Security` section below and flags `Security` in the rollup.
 security: false
 
 # Optional free-form notes for maintenance agents processing this release.
 # Not rendered in CHANGELOG — consumed by agents running `maintenance` on
-# downstream servers. Use for adoption instructions that don't fit the
-# human-facing sections: new files to create, fields to populate, one-time
-# migration steps. Omit the field entirely when there's nothing to say.
+# downstream servers. ADOPTION STEPS ONLY — new files to create, fields to
+# populate, one-time migration steps. Never a second rendering of the body:
+# if a body bullet already says it, name the bullet's symbol instead of
+# re-explaining. Omit the field entirely when there's nothing to say.
 # agent-notes: |
 #   <instructions for downstream maintenance agents>
 ---
@@ -39,17 +43,54 @@ security: false
   each bullet with the symbol or concept name in **bold** so they can skip
   what's irrelevant and zoom in on what's not.
 
-  Tone: terse, fact-dense, not verbose. Default to one sentence per bullet —
-  name the symbol, state what changed, stop. Use a second sentence only when
-  it carries weight. If a bullet feels long, it is.
-
-  Cut: mechanism walkthroughs (those belong in JSDoc, CLAUDE.md/AGENTS.md, or the
-  relevant skill), ceremonial framings ("This release introduces…",
-  backwards-compat paragraphs), file-by-file test enumerations, internal
-  implementation notes. Prefer code/symbol names over English re-explanations.
+  Tone: terse, fact-dense, not verbose. Bullet shape: **symbol** + what
+  changed + at most one consumer-facing caveat. One sentence by default, two
+  when the second carries weight — a bullet past ~40 words or three sentences
+  is wrong. The depth lives one hop away: the linked issue carries the why,
+  the commit diff carries the how. The changelog names what changed and what
+  a consumer does about it; a reader who wants mechanism opens the link.
+
+  Model length on THIS guide, never on the previous entry — entries modeled
+  on entries compound.
+
+  Cut (each has shipped as a wall of text; these are the cruft):
+  - History/justification narration — how the bug worked, why the old
+    behavior was wrong. One short clause at most; the issue carries the story.
+  - Design-rationale defense — "chosen over Y because…", "guarding the
+    getter is not enough…". That is the author arguing with a reviewer;
+    reviewers read the PR, not the changelog.
+  - Defensive unchanged-clauses — "X is unchanged", "byte-identical to
+    <prev>". Keep one only where its absence would cause a real misread,
+    as a short parenthetical.
+  - Edge-case inventories — marker lists, not-flagged lists, escape tables.
+    Tests and the issue carry those.
+  - Mechanism walkthroughs (JSDoc, CLAUDE.md/AGENTS.md, or the relevant
+    skill own those), ceremonial framings ("This release introduces…"),
+    backwards-compat paragraphs, file-by-file test enumerations. Prefer
+    code/symbol names over English re-explanations.
+
+  Verified ≠ included: the every-claim-verified-from-the-diff rule bounds
+  the TRUTH of what you write, never the AMOUNT.
+
+  Example — same fact, right size:
+
+    TOO LONG: **`fetchWithTimeout`'s `timeoutMs` bounds the whole exchange**
+    (#341). `fetch` resolves once headers arrive and the deadline was
+    cleared as the helper returned, so a peer that answered promptly and
+    then stalled the stream held the request open indefinitely. A 2xx
+    carrying a body now comes back as a passthrough wrapper that disarms
+    the deadline when the body closes, errors, or is cancelled; …
+    [+90 more words of mechanism and edge cases]
+
+    RIGHT: **`fetchWithTimeout`'s `timeoutMs` now bounds the whole
+    exchange, not just the headers** (#341). A stalled body aborts with
+    the same `Timeout` error; the returned `Response` is a wrapper, so
+    identity assertions (`toBe(response)`) no longer hold.
 
   Narrative intro: skip by default. Add one short sentence only when the
-  release theme genuinely needs framing the bullets can't carry.
+  release theme genuinely needs framing the bullets can't carry. When many
+  bullets share one upgrade consequence, state it ONCE — intro line or
+  agent-notes — never per bullet.
 
   Sections: Keep a Changelog order — Added, Changed, Deprecated, Removed,
   Fixed, Security. Include only sections with entries; delete the rest

package/dist/mcp-server/tools/definitions/_schemas.d.ts

@@ -1,12 +1,25 @@
 /**
- * @fileoverview Shared Zod output schemas and helpers for the facet breakdown
- * surfaced by `protein_analyze_collection` and `protein_search_structures`. Nesting
- * is bounded to two levels (a dimension's buckets may each carry one child
- * dimension), matching the deepest cross-tab the facet engine produces.
+ * @fileoverview Shared schemas and helpers for the two tools that expose a facet
+ * breakdown and a `content_type` scope — `protein_analyze_collection` and
+ * `protein_search_structures`. Facet nesting is bounded to two levels (a
+ * dimension's buckets may each carry one child dimension), matching the deepest
+ * cross-tab the facet engine produces. Every dimension position also reports its
+ * coverage gap, so buckets that sum to less than the stated total say so.
  * @module mcp-server/tools/definitions/_schemas
  */
 import { z } from '@cyanheads/mcp-ts-core';
 import type { FacetDimension } from '../../../services/rcsb/types.js';
+/**
+ * The agent-facing `content_type` scope → the RCSB content universes it selects.
+ * `all` names both members explicitly: omitting `results_content_type` upstream
+ * is experimental-only, not a union. Shared so the two tools that expose the
+ * enum cannot drift apart on what a scope means.
+ */
+export declare const CONTENT_TYPE_SCOPES: {
+    experimental: "experimental"[];
+    predicted: "computational"[];
+    all: ("computational" | "experimental")[];
+};
 /** A facet dimension and its buckets. */
 export declare const facetDimensionSchema: z.ZodObject<{
     dimension: z.ZodString;
@@ -24,15 +37,30 @@ export declare const facetDimensionSchema: z.ZodObject<{
                 rangeTo: z.ZodOptional<z.ZodNumber>;
             }, z.core.$strip>>;
             truncated: z.ZodOptional<z.ZodBoolean>;
+            missingValueCount: z.ZodNumber;
         }, z.core.$strip>>>;
     }, z.core.$strip>>;
     truncated: z.ZodOptional<z.ZodBoolean>;
+    missingValueCount: z.ZodNumber;
 }, z.core.$strip>;
 export type FacetDimensionOutput = z.infer<typeof facetDimensionSchema>;
-/** Project a domain {@link FacetDimension} to the output shape, capping buckets. */
-export declare function toFacetOutput(facet: FacetDimension, cap: number): FacetDimensionOutput;
+/**
+ * Project a domain {@link FacetDimension} to the output shape, capping buckets.
+ * `total` is the population the buckets describe — the response total for a
+ * top-level dimension, and the parent bucket's count for a nested one.
+ */
+export declare function toFacetOutput(facet: FacetDimension, cap: number, total: number): FacetDimensionOutput;
 /** Render a list of facet dimensions to markdown lines for `format()` parity. */
 export declare function renderFacets(facets: FacetDimensionOutput[]): string[];
+/**
+ * Advisory fragments for the dimensions whose coverage gap is material, ready to
+ * join into the shared `notice` field alongside a caller's other advisories.
+ *
+ * A dimension that aggregated to nothing at all is skipped: the empty-dimension
+ * line in `format()` (and, where it applies, the caller's scope notice) already
+ * report it, and quantifying a 100% gap on top adds nothing.
+ */
+export declare function coverageNotices(facets: FacetDimensionOutput[], total: number): string[];
 /** License + citation for one upstream data source that contributed to a response. */
 export declare const attributionSchema: z.ZodObject<{
     source: z.ZodString;

package/dist/mcp-server/tools/definitions/_schemas.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"_schemas.d.ts","sourceRoot":"","sources":["../../../../src/mcp-server/tools/definitions/_schemas.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,CAAC,EAAE,MAAM,wBAAwB,CAAC;AAC3C,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,0BAA0B,CAAC;AA4D/D,yCAAyC;AACzC,eAAO,MAAM,oBAAoB;;;;;;;;;;;;;;;;;;;iBAW4B,CAAC;AAE9D,MAAM,MAAM,oBAAoB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,oBAAoB,CAAC,CAAC;AAWxE,oFAAoF;AACpF,wBAAgB,aAAa,CAAC,KAAK,EAAE,cAAc,EAAE,GAAG,EAAE,MAAM,GAAG,oBAAoB,CAsBtF;AAkBD,iFAAiF;AACjF,wBAAgB,YAAY,CAAC,MAAM,EAAE,oBAAoB,EAAE,GAAG,MAAM,EAAE,CAarE;AAED,sFAAsF;AACtF,eAAO,MAAM,iBAAiB;;;;;iBAWmD,CAAC;AAElF,MAAM,MAAM,iBAAiB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,iBAAiB,CAAC,CAAC;AAElE,gGAAgG;AAChG,wBAAgB,iBAAiB,CAAC,YAAY,EAAE,iBAAiB,EAAE,GAAG,MAAM,EAAE,CAM7E"}
+{"version":3,"file":"_schemas.d.ts","sourceRoot":"","sources":["../../../../src/mcp-server/tools/definitions/_schemas.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAE,CAAC,EAAE,MAAM,wBAAwB,CAAC;AAC3C,OAAO,KAAK,EAAe,cAAc,EAAE,MAAM,0BAA0B,CAAC;AAE5E;;;;;GAKG;AACH,eAAO,MAAM,mBAAmB;;;;CAIuC,CAAC;AAiExE,yCAAyC;AACzC,eAAO,MAAM,oBAAoB;;;;;;;;;;;;;;;;;;;;;iBAgB4B,CAAC;AAE9D,MAAM,MAAM,oBAAoB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,oBAAoB,CAAC,CAAC;AAgCxE;;;;GAIG;AACH,wBAAgB,aAAa,CAC3B,KAAK,EAAE,cAAc,EACrB,GAAG,EAAE,MAAM,EACX,KAAK,EAAE,MAAM,GACZ,oBAAoB,CAwBtB;AA0CD,iFAAiF;AACjF,wBAAgB,YAAY,CAAC,MAAM,EAAE,oBAAoB,EAAE,GAAG,MAAM,EAAE,CAoBrE;AAuDD;;;;;;;GAOG;AACH,wBAAgB,eAAe,CAAC,MAAM,EAAE,oBAAoB,EAAE,EAAE,KAAK,EAAE,MAAM,GAAG,MAAM,EAAE,CAcvF;AAED,sFAAsF;AACtF,eAAO,MAAM,iBAAiB;;;;;iBAWmD,CAAC;AAElF,MAAM,MAAM,iBAAiB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,iBAAiB,CAAC,CAAC;AAElE,gGAAgG;AAChG,wBAAgB,iBAAiB,CAAC,YAAY,EAAE,iBAAiB,EAAE,GAAG,MAAM,EAAE,CAM7E"}