@cyanheads/wsdot-mcp-server 0.2.5 → 0.2.6

package/AGENTS.md

@@ -1,11 +1,11 @@
 # Developer Protocol
 
 **Server:** @cyanheads/wsdot-mcp-server
-**Version:** 0.2.5
-**Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.12.3`
-**Engines:** Bun ≥1.3.0, Node ≥24.0.0
+**Version:** 0.2.6
+**Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.13.6`
+**Engines:** Bun ≥1.4.0, Node ≥24.0.0
 **MCP SDK:** `@modelcontextprotocol/server` ^2.0.0 (protocol revisions 2026-07-28 and 2025-*)
-**Zod:** ^4.4.3
+**Zod:** ^4.6.5
 
 > **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.
 
@@ -18,6 +18,7 @@
 - **Use `ctx.state`** for tenant-scoped storage. Never access persistence directly.
 - **Need input the caller didn't supply?** `return ctx.requestInput(...)` and read `ctx.inputs` when the handler is re-entered. Never `await` for user input mid-handler.
 - **Secrets in env vars only** — never hardcoded.
+- **Cut noise.** Add only what earns its place: no speculative generality, no guards for states the framework already prevents (Zod-validated params, classified errors), no abstraction until a third caller proves it, no option nothing sets.
 - **Close the loop on issues.** When implementing work tracked by a GitHub issue, comment on the issue with what landed and close it. Do both — a comment without a close leaves stale issues open; a close without a comment leaves no record of what shipped. The comment is for future readers — state the concrete changes, not the conversation that produced them.
 
 ---
@@ -83,6 +84,22 @@ export function getServerConfig() {
 
 For env booleans use `z.stringbool()`, never `z.coerce.boolean()` — `Boolean("false")` is `true`, so a coerced flag can't be disabled through the environment. `z.stringbool()` parses `true/false/1/0/yes/no/on/off` and rejects anything else, so `=false` actually disables.
 
+### Session posture and shutdown
+
+Two more `createApp()` options shape how the server runs rather than how it presents itself:
+
+```ts
+await createApp({
+  sessionMode: 'stateless',          // or { default: 'stateful', require: 'stateful' }
+  setup(core) { startMyWatcher(core.config); },
+  async teardown() { await stopMyWatcher(); },
+});
+```
+
+`sessionMode` declares the HTTP session posture in `src/` instead of leaving it to a deployment's `MCP_SESSION_MODE`, which still wins whenever it carries a meaningful value (an empty string and an unsubstituted `${…}` placeholder read as unset and fall through to the option). Add `require: 'stateful'` when a tool asks the caller for input mid-handler via `ctx.requestInput`: startup then fails with a `ConfigurationError` rather than serving a mode in which a 2025-era client can never answer the prompt. Stdio is never refused. This server declares `sessionMode: 'stateless'` — no tool calls `ctx.requestInput`.
+
+`teardown(core)` is the `setup()` counterpart — release a watcher, socket, or non-`unref()`'d timer there. It runs after the transport stops and before the logger closes, on every shutdown path, and a signal-triggered shutdown then exits the process explicitly (0, or 1 if a step never settles within the framework's 10 s ceiling). Neither WSDOT service holds one, so no `teardown` is declared.
+
 ---
 
 ## Context
@@ -107,7 +124,7 @@ 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 (≥ 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.
+**Recommended: typed error contract.** Declare `errors: [{ reason, code, when, recovery, retryable?, severity?, thrownBy? }]` 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 unless the message already contains it verbatim); override with an explicit `{ recovery: { hint: '...' } }` when dynamic runtime context matters. Forwarding it is lint-enforced per throw site (`error-contract-recovery-unforwarded`). Mark an entry the service layer throws with `thrownBy: 'service'` so `error-contract-unthrown` skips it — lint-only metadata, nothing at runtime reads it. Baseline codes (`InternalError`, `ServiceUnavailable`, `Timeout`, `ValidationError`, `SerializationError`, `RequestCancelled`) bubble freely and don't need declaring.
 
 ```ts
 import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
@@ -192,9 +209,9 @@ 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. `bun run list-skills` prints the full registry.
+Skills are modular instructions in `framework-skills/` at the project root. Read them directly when a task matches — e.g., `framework-skills/add-tool/SKILL.md` when adding a tool. `bun run list-skills` prints the full registry. The directory is deliberately not `skills/`: Claude Code and Codex auto-load a plugin's root `skills/`, so a server that ships `.claude-plugin/` or `.codex-plugin/` would hand these development skills to every agent that installs it. Keep `skills/` free for skills meant for those agents.
 
-**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.
+**Agent skill directory:** Copy skills into the directory your agent discovers (Claude Code: `.claude/skills/`, others: equivalent). Skills then load as context without referencing `framework-skills/` paths. After framework updates, run the `maintenance` skill — Phase B re-syncs the agent directory.
 
 Available skills:
 
@@ -213,8 +230,9 @@ Available skills:
 | `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 |
 | `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` |
+| `git-wrapup` | Land working-tree changes as a commit stack — version bump, changelog, verify, commit by concern, release commit on top. No tag, no push to main; opens the release PR when the project declares release PR mode |
+| `release-pr-review` | Review pass on an open release PR — simplifier + correctness review, fixes as ordinary commits on top of the stack, PR body kept in sync. Release PR mode only |
+| `release-and-publish` | Fast-forward merge (release PR mode) + tag + push + npm + MCP Registry + GH Release + Docker. Picks up from `git-wrapup` |
 | `maintenance` | Investigate changelogs, adopt upstream changes, sync skills to agent dirs |
 | `orchestrations` | Chain task skills into a gated multi-phase pipeline — build-out, QA-fix, update-ship — when you can spawn sub-agents |
 | `report-issue-framework` | File a bug or feature request against `@cyanheads/mcp-ts-core` via `gh` CLI |
@@ -233,7 +251,7 @@ Available skills:
 | `api-telemetry` | OTel catalog: spans, metrics, completion logs, env config, cardinality rules |
 | `api-workers` | Cloudflare Workers runtime |
 
-**Chaining skills into pipelines.** When the user wants a multi-phase effort — build this server out, QA-and-fix the surface, update-and-ship — *and you can spawn sub-agents*, `skills/orchestrations/SKILL.md` sequences the task skills above into a gated pipeline with verification at each step. Read it to drive the run. Optional: skip it if you can't orchestrate sub-agents, and ignore it entirely if you were *spawned* as one — you've already been scoped to a single phase.
+**Chaining skills into pipelines.** When the user wants a multi-phase effort — build this server out, QA-and-fix the surface, update-and-ship — *and you can spawn sub-agents*, `framework-skills/orchestrations/SKILL.md` sequences the task skills above into a gated pipeline with verification at each step. Read it to drive the run. Optional: skip it if you can't orchestrate sub-agents, and ignore it entirely if you were *spawned* as one — you've already been scoped to a single phase.
 
 When you complete a skill's checklist, check the boxes and add a completion timestamp at the end (e.g., `Completed: 2026-03-11`).
 
@@ -249,7 +267,8 @@ When you complete a skill's checklist, check the boxes and add a completion time
 | `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. |
+| `bun run audit:fix` | `bun audit fix` — upgrade vulnerable packages to the lowest safe version within existing ranges (`--dry-run` previews, `--latest` rewrites ranges). First response when `devcheck` flags a transitive advisory; then `bun update <name>`, then `bun dedupe` |
+| `bun run audit:refresh` | Delete `bun.lock` and reinstall. Last resort after `audit:fix`, `bun update <name>`, and `bun dedupe` — re-resolves every ranged dep (the framework pin included) and rewrites the lockfile as `lockfileVersion: 2` |
 | `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 |
@@ -263,15 +282,17 @@ When you complete a skill's checklist, check the boxes and add a completion time
 | `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 |
 
+**CI is one file.** `.github/workflows/codeql.yml` (scaffolded) is the only GitHub Actions workflow: CodeQL is GitHub-owned end to end, and the file runs only while the repo's CodeQL *default setup* is turned off. Verification — `devcheck`, tests, the release gates — runs locally; don't add a workflow that re-runs it.
+
 ---
 
 ## Bundling
 
-`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.
+`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 (`framework-skills/`, `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.
+**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, that every `user_config` option is wired into `mcp_config.env` as `"X": "${user_config.X}"` (the host substitutes nothing else — `"${X}"` reaches the server as that literal string), and that an optional string option carries `"default": ""`.
 
-**README install badges** (Claude Desktop `.mcpb`, Cursor, VS Code) and the `base64` / `encodeURIComponent` config-generation commands are ship-time concerns — run the `polish-docs-meta` skill, which carries the badge format, layout, and generation snippets in `skills/polish-docs-meta/references/readme.md`.
+**README install badges** (Claude Desktop `.mcpb`, Cursor, VS Code) and the `base64` / `encodeURIComponent` config-generation commands are ship-time concerns — run the `polish-docs-meta` skill, which carries the badge format, layout, and generation snippets in `framework-skills/polish-docs-meta/references/readme.md`.
 
 ---
 
@@ -296,12 +317,18 @@ security: false                            # optional — true ONLY for a source
 
 `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.
 
-**Section order** (Keep a Changelog): Added, Changed, Deprecated, Removed, Fixed, Security. Include only sections with entries — don't ship empty headers.
+**Section order:** the Keep a Changelog sequence — Added, Changed, Deprecated, Removed, Fixed, Security — then `Dependencies` last. Include only sections with entries — don't ship empty headers.
 
 **Tag annotations** render as GitHub Release bodies via `--notes-from-tag`. They must be structured markdown — never a flat comma-separated string. Subject omits the version number (GitHub prepends it). See `changelog/template.md` for the full format reference.
 
 ---
 
+## Publishing
+
+**Every release goes through a release PR, straight-through** — `git-wrapup`'s "Release PR mode", mode `straight-through`. One run: `git-wrapup` lands the commit stack on `release/<version>`, pushes it, and opens the PR (title = the release commit subject, body = the changelog entry plus a gates section); `release-and-publish` then fast-forwards `main` locally with `git merge --ff-only`, creates the tag on `main`'s tip, pushes `main` and the tag, deletes the branch, and publishes. A caller's brief may run a given release as `gated` instead — a `release-pr-review` pass on the open PR before `release-and-publish`. **Never merge through the GitHub UI or `gh pr merge`**: squash and rebase-merge are disabled in the repo settings because both rewrite the stack (rebase-merge also strips the SSH signatures), and a merge commit breaks the linear history.
+
+---
+
 ## Imports
 
 ```ts
@@ -328,7 +355,7 @@ import { getMyService } from '@/services/my-domain/my-service.js';
 - [ ] If wrapping external API: tests include at least one sparse payload case with omitted upstream fields
 - [ ] Registered in `createApp()` arrays (directly or via barrel exports)
 - [ ] Tests use `createMockContext()` from `@cyanheads/mcp-ts-core/testing`
-- [ ] `.codex-plugin/plugin.json` populated — `name`, `version`, `description`, `repository`, `license` from `package.json`; `interface.displayName` = package name; `interface.shortDescription` from `package.json` description
-- [ ] `.codex-plugin/mcp.json` updated — server name key matches `package.json` name; env vars added for any required API keys
-- [ ] `.claude-plugin/plugin.json` populated — `name`, `version`, `description`, `repository`, `license` from `package.json`; inline `mcpServers` entry with server name key, env vars for any required API keys
+- [ ] `.codex-plugin/plugin.json` populated — `name`, `version`, `description`, `repository`, `license` from `package.json`; `interface.displayName` = the unscoped repo name (never the npm scope — `lint:packaging` enforces this); `interface.shortDescription` from `package.json` description
+- [ ] `.codex-plugin/mcp.json` updated — server name key is the unscoped repo name; every user-supplied variable (API key, contact email, instance URL) is listed in `env_vars` so Codex forwards it from the user's environment. Never write `"KEY": ""` into `env` — an empty value replaces the user's exported key and is read as unset
+- [ ] `.claude-plugin/plugin.json` populated — `name`, `version`, `description`, `author`, `repository`, `license`, `keywords` from `package.json`; inline `mcpServers` entry keyed by the unscoped repo name. Every user-supplied variable is declared under `userConfig` (`type`, `title`, `description`; `sensitive: true` for keys and tokens; `required: true` or `default: ""`) and referenced from `env` as `"KEY": "${user_config.<option>}"` — mirror the `user_config` block in `manifest.json`. Never write `"KEY": ""` into `env`
 - [ ] `npm run devcheck` passes

package/CLAUDE.md

@@ -1,11 +1,11 @@
 # Developer Protocol
 
 **Server:** @cyanheads/wsdot-mcp-server
-**Version:** 0.2.5
-**Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.12.3`
-**Engines:** Bun ≥1.3.0, Node ≥24.0.0
+**Version:** 0.2.6
+**Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.13.6`
+**Engines:** Bun ≥1.4.0, Node ≥24.0.0
 **MCP SDK:** `@modelcontextprotocol/server` ^2.0.0 (protocol revisions 2026-07-28 and 2025-*)
-**Zod:** ^4.4.3
+**Zod:** ^4.6.5
 
 > **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.
 
@@ -18,6 +18,7 @@
 - **Use `ctx.state`** for tenant-scoped storage. Never access persistence directly.
 - **Need input the caller didn't supply?** `return ctx.requestInput(...)` and read `ctx.inputs` when the handler is re-entered. Never `await` for user input mid-handler.
 - **Secrets in env vars only** — never hardcoded.
+- **Cut noise.** Add only what earns its place: no speculative generality, no guards for states the framework already prevents (Zod-validated params, classified errors), no abstraction until a third caller proves it, no option nothing sets.
 - **Close the loop on issues.** When implementing work tracked by a GitHub issue, comment on the issue with what landed and close it. Do both — a comment without a close leaves stale issues open; a close without a comment leaves no record of what shipped. The comment is for future readers — state the concrete changes, not the conversation that produced them.
 
 ---
@@ -83,6 +84,22 @@ export function getServerConfig() {
 
 For env booleans use `z.stringbool()`, never `z.coerce.boolean()` — `Boolean("false")` is `true`, so a coerced flag can't be disabled through the environment. `z.stringbool()` parses `true/false/1/0/yes/no/on/off` and rejects anything else, so `=false` actually disables.
 
+### Session posture and shutdown
+
+Two more `createApp()` options shape how the server runs rather than how it presents itself:
+
+```ts
+await createApp({
+  sessionMode: 'stateless',          // or { default: 'stateful', require: 'stateful' }
+  setup(core) { startMyWatcher(core.config); },
+  async teardown() { await stopMyWatcher(); },
+});
+```
+
+`sessionMode` declares the HTTP session posture in `src/` instead of leaving it to a deployment's `MCP_SESSION_MODE`, which still wins whenever it carries a meaningful value (an empty string and an unsubstituted `${…}` placeholder read as unset and fall through to the option). Add `require: 'stateful'` when a tool asks the caller for input mid-handler via `ctx.requestInput`: startup then fails with a `ConfigurationError` rather than serving a mode in which a 2025-era client can never answer the prompt. Stdio is never refused. This server declares `sessionMode: 'stateless'` — no tool calls `ctx.requestInput`.
+
+`teardown(core)` is the `setup()` counterpart — release a watcher, socket, or non-`unref()`'d timer there. It runs after the transport stops and before the logger closes, on every shutdown path, and a signal-triggered shutdown then exits the process explicitly (0, or 1 if a step never settles within the framework's 10 s ceiling). Neither WSDOT service holds one, so no `teardown` is declared.
+
 ---
 
 ## Context
@@ -107,7 +124,7 @@ 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 (≥ 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.
+**Recommended: typed error contract.** Declare `errors: [{ reason, code, when, recovery, retryable?, severity?, thrownBy? }]` 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 unless the message already contains it verbatim); override with an explicit `{ recovery: { hint: '...' } }` when dynamic runtime context matters. Forwarding it is lint-enforced per throw site (`error-contract-recovery-unforwarded`). Mark an entry the service layer throws with `thrownBy: 'service'` so `error-contract-unthrown` skips it — lint-only metadata, nothing at runtime reads it. Baseline codes (`InternalError`, `ServiceUnavailable`, `Timeout`, `ValidationError`, `SerializationError`, `RequestCancelled`) bubble freely and don't need declaring.
 
 ```ts
 import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
@@ -192,9 +209,9 @@ 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. `bun run list-skills` prints the full registry.
+Skills are modular instructions in `framework-skills/` at the project root. Read them directly when a task matches — e.g., `framework-skills/add-tool/SKILL.md` when adding a tool. `bun run list-skills` prints the full registry. The directory is deliberately not `skills/`: Claude Code and Codex auto-load a plugin's root `skills/`, so a server that ships `.claude-plugin/` or `.codex-plugin/` would hand these development skills to every agent that installs it. Keep `skills/` free for skills meant for those agents.
 
-**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.
+**Agent skill directory:** Copy skills into the directory your agent discovers (Claude Code: `.claude/skills/`, others: equivalent). Skills then load as context without referencing `framework-skills/` paths. After framework updates, run the `maintenance` skill — Phase B re-syncs the agent directory.
 
 Available skills:
 
@@ -213,8 +230,9 @@ Available skills:
 | `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 |
 | `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` |
+| `git-wrapup` | Land working-tree changes as a commit stack — version bump, changelog, verify, commit by concern, release commit on top. No tag, no push to main; opens the release PR when the project declares release PR mode |
+| `release-pr-review` | Review pass on an open release PR — simplifier + correctness review, fixes as ordinary commits on top of the stack, PR body kept in sync. Release PR mode only |
+| `release-and-publish` | Fast-forward merge (release PR mode) + tag + push + npm + MCP Registry + GH Release + Docker. Picks up from `git-wrapup` |
 | `maintenance` | Investigate changelogs, adopt upstream changes, sync skills to agent dirs |
 | `orchestrations` | Chain task skills into a gated multi-phase pipeline — build-out, QA-fix, update-ship — when you can spawn sub-agents |
 | `report-issue-framework` | File a bug or feature request against `@cyanheads/mcp-ts-core` via `gh` CLI |
@@ -233,7 +251,7 @@ Available skills:
 | `api-telemetry` | OTel catalog: spans, metrics, completion logs, env config, cardinality rules |
 | `api-workers` | Cloudflare Workers runtime |
 
-**Chaining skills into pipelines.** When the user wants a multi-phase effort — build this server out, QA-and-fix the surface, update-and-ship — *and you can spawn sub-agents*, `skills/orchestrations/SKILL.md` sequences the task skills above into a gated pipeline with verification at each step. Read it to drive the run. Optional: skip it if you can't orchestrate sub-agents, and ignore it entirely if you were *spawned* as one — you've already been scoped to a single phase.
+**Chaining skills into pipelines.** When the user wants a multi-phase effort — build this server out, QA-and-fix the surface, update-and-ship — *and you can spawn sub-agents*, `framework-skills/orchestrations/SKILL.md` sequences the task skills above into a gated pipeline with verification at each step. Read it to drive the run. Optional: skip it if you can't orchestrate sub-agents, and ignore it entirely if you were *spawned* as one — you've already been scoped to a single phase.
 
 When you complete a skill's checklist, check the boxes and add a completion timestamp at the end (e.g., `Completed: 2026-03-11`).
 
@@ -249,7 +267,8 @@ When you complete a skill's checklist, check the boxes and add a completion time
 | `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. |
+| `bun run audit:fix` | `bun audit fix` — upgrade vulnerable packages to the lowest safe version within existing ranges (`--dry-run` previews, `--latest` rewrites ranges). First response when `devcheck` flags a transitive advisory; then `bun update <name>`, then `bun dedupe` |
+| `bun run audit:refresh` | Delete `bun.lock` and reinstall. Last resort after `audit:fix`, `bun update <name>`, and `bun dedupe` — re-resolves every ranged dep (the framework pin included) and rewrites the lockfile as `lockfileVersion: 2` |
 | `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 |
@@ -263,15 +282,17 @@ When you complete a skill's checklist, check the boxes and add a completion time
 | `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 |
 
+**CI is one file.** `.github/workflows/codeql.yml` (scaffolded) is the only GitHub Actions workflow: CodeQL is GitHub-owned end to end, and the file runs only while the repo's CodeQL *default setup* is turned off. Verification — `devcheck`, tests, the release gates — runs locally; don't add a workflow that re-runs it.
+
 ---
 
 ## Bundling
 
-`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.
+`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 (`framework-skills/`, `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.
+**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, that every `user_config` option is wired into `mcp_config.env` as `"X": "${user_config.X}"` (the host substitutes nothing else — `"${X}"` reaches the server as that literal string), and that an optional string option carries `"default": ""`.
 
-**README install badges** (Claude Desktop `.mcpb`, Cursor, VS Code) and the `base64` / `encodeURIComponent` config-generation commands are ship-time concerns — run the `polish-docs-meta` skill, which carries the badge format, layout, and generation snippets in `skills/polish-docs-meta/references/readme.md`.
+**README install badges** (Claude Desktop `.mcpb`, Cursor, VS Code) and the `base64` / `encodeURIComponent` config-generation commands are ship-time concerns — run the `polish-docs-meta` skill, which carries the badge format, layout, and generation snippets in `framework-skills/polish-docs-meta/references/readme.md`.
 
 ---
 
@@ -296,12 +317,18 @@ security: false                            # optional — true ONLY for a source
 
 `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.
 
-**Section order** (Keep a Changelog): Added, Changed, Deprecated, Removed, Fixed, Security. Include only sections with entries — don't ship empty headers.
+**Section order:** the Keep a Changelog sequence — Added, Changed, Deprecated, Removed, Fixed, Security — then `Dependencies` last. Include only sections with entries — don't ship empty headers.
 
 **Tag annotations** render as GitHub Release bodies via `--notes-from-tag`. They must be structured markdown — never a flat comma-separated string. Subject omits the version number (GitHub prepends it). See `changelog/template.md` for the full format reference.
 
 ---
 
+## Publishing
+
+**Every release goes through a release PR, straight-through** — `git-wrapup`'s "Release PR mode", mode `straight-through`. One run: `git-wrapup` lands the commit stack on `release/<version>`, pushes it, and opens the PR (title = the release commit subject, body = the changelog entry plus a gates section); `release-and-publish` then fast-forwards `main` locally with `git merge --ff-only`, creates the tag on `main`'s tip, pushes `main` and the tag, deletes the branch, and publishes. A caller's brief may run a given release as `gated` instead — a `release-pr-review` pass on the open PR before `release-and-publish`. **Never merge through the GitHub UI or `gh pr merge`**: squash and rebase-merge are disabled in the repo settings because both rewrite the stack (rebase-merge also strips the SSH signatures), and a merge commit breaks the linear history.
+
+---
+
 ## Imports
 
 ```ts
@@ -328,7 +355,7 @@ import { getMyService } from '@/services/my-domain/my-service.js';
 - [ ] If wrapping external API: tests include at least one sparse payload case with omitted upstream fields
 - [ ] Registered in `createApp()` arrays (directly or via barrel exports)
 - [ ] Tests use `createMockContext()` from `@cyanheads/mcp-ts-core/testing`
-- [ ] `.codex-plugin/plugin.json` populated — `name`, `version`, `description`, `repository`, `license` from `package.json`; `interface.displayName` = package name; `interface.shortDescription` from `package.json` description
-- [ ] `.codex-plugin/mcp.json` updated — server name key matches `package.json` name; env vars added for any required API keys
-- [ ] `.claude-plugin/plugin.json` populated — `name`, `version`, `description`, `repository`, `license` from `package.json`; inline `mcpServers` entry with server name key, env vars for any required API keys
+- [ ] `.codex-plugin/plugin.json` populated — `name`, `version`, `description`, `repository`, `license` from `package.json`; `interface.displayName` = the unscoped repo name (never the npm scope — `lint:packaging` enforces this); `interface.shortDescription` from `package.json` description
+- [ ] `.codex-plugin/mcp.json` updated — server name key is the unscoped repo name; every user-supplied variable (API key, contact email, instance URL) is listed in `env_vars` so Codex forwards it from the user's environment. Never write `"KEY": ""` into `env` — an empty value replaces the user's exported key and is read as unset
+- [ ] `.claude-plugin/plugin.json` populated — `name`, `version`, `description`, `author`, `repository`, `license`, `keywords` from `package.json`; inline `mcpServers` entry keyed by the unscoped repo name. Every user-supplied variable is declared under `userConfig` (`type`, `title`, `description`; `sensitive: true` for keys and tokens; `required: true` or `default: ""`) and referenced from `env` as `"KEY": "${user_config.<option>}"` — mirror the `user_config` block in `manifest.json`. Never write `"KEY": ""` into `env`
 - [ ] `npm run devcheck` passes

package/README.md

@@ -7,7 +7,7 @@
 
 <div align="center">
 
-[![Version](https://img.shields.io/badge/Version-0.2.5-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/wsdot-mcp-server) [![MCP SDK](https://img.shields.io/badge/MCP%20SDK-^2.0.0-green.svg?style=flat-square)](https://modelcontextprotocol.io/) [![npm](https://img.shields.io/npm/v/@cyanheads/wsdot-mcp-server?style=flat-square&logo=npm&logoColor=white)](https://www.npmjs.com/package/@cyanheads/wsdot-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-v1.3.0+-blueviolet.svg?style=flat-square)](https://bun.sh/)
+[![Version](https://img.shields.io/badge/Version-0.2.6-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/wsdot-mcp-server) [![MCP SDK](https://img.shields.io/badge/MCP%20SDK-^2.0.0-green.svg?style=flat-square)](https://modelcontextprotocol.io/) [![npm](https://img.shields.io/npm/v/@cyanheads/wsdot-mcp-server?style=flat-square&logo=npm&logoColor=white)](https://www.npmjs.com/package/@cyanheads/wsdot-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-v1.4.0%2B-blueviolet.svg?style=flat-square)](https://bun.sh/)
 
 </div>
 
@@ -23,9 +23,11 @@
 
 ---
 
-## Tools
+## Overview
 
-12 tools split across two domains — traffic (WSDOT Traveler API) and ferries (WSF Ferry API):
+Washington State transportation data from the WSDOT Traveler API and the WSF Ferry API. Query mountain pass and highway conditions, search alerts and cameras, and track ferry schedules, vessel locations, and terminal space from any MCP client. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.
+
+### Tools
 
 | Tool | Description |
 |:---|:---|
@@ -42,112 +44,96 @@
 | `wsdot_get_terminal_space` | Drive-up and reservable vehicle space available at WSF terminals for upcoming sailings. |
 | `wsdot_get_ferry_alerts` | Active WSF service disruptions and bulletins with impacted route IDs. |
 
-### `wsdot_get_mountain_passes`
+## Capability reference
 
-Current road conditions for all WA mountain passes.
+### `wsdot_get_mountain_passes` <sub>tool</sub>
 
-- Covers all 16 passes: Snoqualmie, Stevens, White, Blewett, Cayuse, and others
-- Fields include status (Open/Closed/Caution), road surface, active traction law, temperature, and elevation
-- Use for "is the pass open?", traction law checks, or winter driving planning
+- No input parameters — returns current conditions for all 16 WA mountain passes (Snoqualmie, Stevens, White, Blewett, Cayuse, and others) in one call
+- Fields include road condition, weather, temperature, elevation, and up to two directional traction/travel restrictions
+- Use for "is the pass open?", traction-law checks, or winter driving planning
 
 ---
 
-### `wsdot_search_alerts`
-
-Active WA highway alerts — incidents, construction, closures, restrictions.
+### `wsdot_search_alerts` <sub>tool</sub>
 
 - Filter by state route — natural forms all work: `"I-90"`, `"90"`, `"090"`, or `"SR 520"` / `"520"`
 - Filter by WSDOT region: Northwest, Olympic, Southwest, South Central, North Central, Eastern
 - Filter by milepost range to scope to a corridor — an alert matches when its extent overlaps the range, so a closure that spans the boundary is returned
 - Omit all filters to return all current statewide alerts
-- Descriptions are plain text — upstream authors them with markup, and a link is rendered inline as `link text (url)` so the destination survives
-- Results are ordered by `alertId` and paged (default 50, max 500) — pass `offset`/`limit` to page through the full statewide set; the notice reports the next offset. Upstream returns the same alert set in more than one row order, so the ordering is imposed here to keep a given offset reproducible
+- Descriptions are normalized to plain text; a link renders inline as `link text (url)`
+- Results ordered by `alertId` and paged (default 50, max 500) — pass `offset`/`limit`; the notice reports the next offset
 
 ---
 
-### `wsdot_get_travel_times`
-
-Current vs. average travel times for named WA highway corridors.
+### `wsdot_get_travel_times` <sub>tool</sub>
 
 - Covers I-5, I-90, SR 520, SR 99, I-405, SR 167, and others
 - Filter by route (`"I-5"`, `"5"`, `"SR 520"`) to get every corridor measured on it, or by any text to match corridor names (`"Everett"`)
 - When current time exceeds average, the corridor is congested; the delta is the delay
 - Reversible express-lane corridors report no travel time while closed in the queried direction — those figures are omitted rather than reported as zero minutes
-- Results are paged (default 50, max 500) — pass `offset`/`limit` to page through the full statewide set; the notice reports the next offset
+- Results are paged (default 50, max 500) — pass `offset`/`limit`; the notice reports the next offset
 
 ---
 
-### `wsdot_get_toll_rates`
-
-Current dynamic toll rates for WA tolled facilities.
+### `wsdot_get_toll_rates` <sub>tool</sub>
 
-- SR 99 (WSDOT Tunnel), SR 167 HOT Lanes, I-405 Express Lanes, the SR 509 tolled segment, and the SR 520 Bridge
+- Covers SR 99 (WSDOT Tunnel), SR 167 HOT Lanes, I-405 Express Lanes, the SR 509 tolled segment, and the SR 520 Bridge
 - Rates are time-banded and change dynamically based on traffic conditions
 - `stateRoute` is a bare, zero-padded route number (`"099"`, `"405"`) with no route type; the rendered text resolves the posted designation, so I-405 reads as `I-405` rather than `SR 405`
 - Each entry leads with its readable `startLocationName → endLocationName` segment; the opaque upstream trip key stays available as `tripName`
-- Results are paged (default 50, max 500) — pass `offset`/`limit` to page through the full statewide set; the notice reports the next offset
+- Results are paged (default 50, max 500) — pass `offset`/`limit`; the notice reports the next offset
 
 ---
 
-### `wsdot_get_border_waits`
+### `wsdot_get_border_waits` <sub>tool</sub>
 
-Current vehicle wait times at WA/Canada land border crossings.
-
-- Covers I-5 (Peace Arch, Blaine), SR 543 (Pacific Highway, Blaine), SR 539 (Lynden), and SR 9 (Sumas)
+- No input parameters — covers I-5 (Peace Arch, Blaine), SR 543 (Pacific Highway, Blaine), SR 539 (Lynden), and SR 9 (Sumas)
 - Each crossing reports a general-purpose lane and a Nexus lane; SR 539 adds a truck lane and SR 543 adds truck and FAST truck lanes — eleven entries in `crossings[]`, one per lane
 - `crossingName` is a route code (e.g. `I5`, `SR543Trucks`); `location.description` holds the readable name
 - Wait times in minutes; `updateTime` is ISO 8601. A crossing reporting no current data is still returned — only `waitTimeInMinutes` is omitted, and the rendered text reads `Not available`
 
 ---
 
-### `wsdot_search_cameras`
-
-WSDOT highway camera metadata and image URLs.
+### `wsdot_search_cameras` <sub>tool</sub>
 
 - Filter by state route (`"I-90"`, `"90"`, `"SR 520"`, or `"520"` all work), WSDOT region, or milepost range
 - Camera road names carry a route-type prefix, so `"SR 26"` excludes US 26 and `"US 97"` excludes US 97A; a bare `"26"` returns both
 - Returns metadata and image URLs — camera images are copyright WSDOT, not fetched as bytes
-- Results are ordered by `cameraId` and paged (default 50, max 500) — pass `offset`/`limit` to page through the full statewide set; the notice reports the next offset. Upstream returns the same camera set in more than one row order, so the ordering is imposed here to keep a given offset reproducible
+- Results are ordered by `cameraId` and paged (default 50, max 500) — pass `offset`/`limit`; the notice reports the next offset
 
 ---
 
-### `wsdot_get_ferry_terminals`
-
-All WSF ferry terminals with numeric IDs.
+### `wsdot_get_ferry_terminals` <sub>tool</sub>
 
-- 20 terminals; the list rarely changes
+- No input parameters — returns all 20 WSF ferry terminals; the list rarely changes
 - Call this first to resolve human-readable names (e.g. "Bainbridge Island", "Seattle", "Kingston") to the numeric IDs required by `wsdot_get_ferry_schedule` and `wsdot_get_terminal_space`
+- Each terminal also carries an abbreviation and coordinates when reported
 
 ---
 
-### `wsdot_get_ferry_routes`
-
-WSF ferry routes operating on a given date.
+### `wsdot_get_ferry_routes` <sub>tool</sub>
 
+- Optional `tripDate` (ISO 8601 `YYYY-MM-DD`); defaults to today
 - Returns each route's ID, abbreviation, and description
 - Route IDs correspond to `impactedRouteIds` in `wsdot_get_ferry_alerts` — use this tool to resolve alert route IDs to route names
 - Use to discover which routes are running; for the numeric terminal IDs that schedule and space lookups need, call `wsdot_get_ferry_terminals`
 
 ---
 
-### `wsdot_get_ferry_schedule`
-
-Departure times for a specific WSF ferry route.
+### `wsdot_get_ferry_schedule` <sub>tool</sub>
 
-- Requires numeric terminal IDs — use `wsdot_get_ferry_terminals` first
-- `remainingOnly: true` returns only future departures for today (useful for "next ferry" queries)
-- For future dates, all sailings for that day are returned
+- Requires numeric `departingTerminalId` and `arrivingTerminalId` — use `wsdot_get_ferry_terminals` first
+- Optional `tripDate` (defaults to today) and `remainingOnly: true` (only future departures for today; ignored for future dates)
 - `departureTime` and `arrivalTime` are ISO 8601 **UTC**, while `tripDate` is the Pacific service day — an evening sailing therefore carries the following UTC calendar date and will not match `tripDate`. Convert to `America/Los_Angeles` before quoting a clock time
 - `arrivalTime` is populated on some routes and absent on others
 - No cancellation status — WSF drops a cancelled sailing from the schedule rather than flagging it, so a listed sailing is not confirmation it will run; check `wsdot_get_ferry_alerts`, which reports disruptions at route level
+- An invalid or non-through terminal pair returns a typed `invalid_terminal_pair` error rather than an empty schedule
 
 ---
 
-### `wsdot_get_vessel_locations`
+### `wsdot_get_vessel_locations` <sub>tool</sub>
 
-Real-time AIS positions for all active WSF vessels.
-
-- Fields include position, speed, heading, ETA, and dock status
+- No input parameters — fields include position, speed, heading, ETA, and dock status for every active WSF vessel
 - Use for "where is the ferry now?" or checking if a specific vessel is in service
 - Position data may lag 30–60 seconds; many fields are null for vessels not currently operating
 - Coordinates render at full upstream AIS precision — no rounding, so both response surfaces report the same position
@@ -155,55 +141,60 @@ Real-time AIS positions for all active WSF vessels.
 
 ---
 
-### `wsdot_get_terminal_space`
-
-Real-time vehicle space availability at WSF terminals for upcoming sailings.
+### `wsdot_get_terminal_space` <sub>tool</sub>
 
+- Filter to a specific terminal by ID (from `wsdot_get_ferry_terminals`); omit for all terminals
 - `driveUpSpaceCount` is the key field — zero means the drive-up lane is full. Oversubscribed sailings report a negative count upstream; it is floored to zero so the value never reads as available space
 - `arrivingTerminalIds` lists the terminals a sailing serves and chains straight into `wsdot_get_ferry_schedule`; `itineraryLabel` is a display string that may name several stops, not a single destination
-- Filter to a specific terminal by ID (from `wsdot_get_ferry_terminals`)
-- Use for "will I make the ferry?" or "how full is the next sailing?" queries
 - Results are paged by terminal (default 5, max 20) — `offset`/`limit` select whole terminals and `totalCount` counts matching terminals, not sailings; every sailing of a returned terminal is included, so page size varies with how many departures each terminal carries
 
 ---
 
-### `wsdot_get_ferry_alerts`
-
-Active WSF ferry service disruptions, delays, and bulletins.
+### `wsdot_get_ferry_alerts` <sub>tool</sub>
 
+- No input parameters — active WSF ferry service disruptions, delays, and bulletins
 - Each alert carries the bulletin's `alertTitle`, its one-line `alertDescription`, and the full `bulletinText` — detail such as a replacement sailing appears only in the body
 - `bulletinText` is plain text: upstream authors it as HTML, and a link is rendered inline as `link text (url)`
 - Each alert includes `impactedRouteIds` — cross-reference with `wsdot_get_ferry_routes` to map route IDs to names
 - `affectsAllRoutes: true` marks a fleet-wide alert, which need not enumerate routes — an empty `impactedRouteIds` then means every route rather than none
 
----
-
 ## Features
 
-Built on [`@cyanheads/mcp-ts-core`](https://www.npmjs.com/package/@cyanheads/mcp-ts-core):
-
-- Declarative tool definitions — single file per tool, framework handles registration and validation
-- Unified error handling across all tools
-- Pluggable auth (`none`, `jwt`, `oauth`)
-- Swappable storage backends: `in-memory`, `filesystem`, `Supabase`, `Cloudflare KV/R2/D1`
-- Structured logging with optional OpenTelemetry tracing
-- STDIO and Streamable HTTP transports
+Built on [`@cyanheads/mcp-ts-core`](https://github.com/cyanheads/mcp-ts-core): stdio and Streamable HTTP transports, pluggable auth (`none` / `jwt` / `oauth`), swappable storage (`in-memory`, `filesystem`, `Supabase`, `Cloudflare KV/R2/D1`), structured logging with optional OpenTelemetry tracing.
 
 WSDOT-specific:
 
-- Dual API integration — WSDOT Traffic API and WSF Ferry API from a single access code
-- Retry, timeout, and HTML-detection guards on all upstream requests
-- Normalized response shapes across both APIs — sparse upstream fields surfaced as optional rather than omitted
+- Dual API integration — WSDOT Traffic API and WSF Ferry API share a single `WSDOT_ACCESS_CODE`
+- Cross-tool linking built into tool descriptions — ferry tools point to `wsdot_get_ferry_terminals` / `wsdot_get_ferry_routes` for ID resolution before a lookup
+- Normalized response shapes across both APIs — sparse upstream fields surface as optional rather than omitted or defaulted
+- Stable pagination — the alert and camera feeds return the same set in more than one row order upstream, so results are sorted by ID to keep a given offset reproducible
 
 Agent-friendly output:
 
-- Cross-tool linking built into descriptions — ferry tools document which tool to call first for terminal and route ID resolution
-- `driveUpSpaceCount: 0` and congestion delta fields give agents actionable signal without string parsing
-- Partial data preserved — sparse upstream payloads surface `null`/`undefined` rather than synthetic defaults
+- Typed failure — `invalid_access_code` and `api_unavailable` errors carry an explicit recovery hint distinguishing configuration faults from transient upstream ones
+- `driveUpSpaceCount: 0` and congestion delta fields (`delayInMinutes`) give agents actionable signal without string parsing
+- Partial data preserved — sparse upstream payloads surface `null`/`undefined` rather than synthetic defaults (e.g. an omitted `waitTimeInMinutes`, an absent `arrivalTime`)
 - `content[]` and `structuredContent` carry the same values, not just the same fields — a `false` flag, an empty list, and one populated half of a coordinate pair all render rather than dropping out of the markdown surface that some clients read
 
 ## Getting started
 
+### Public Hosted Instance
+
+A public instance is available at `https://wsdot.caseyjhand.com/mcp` — no installation required. Point any MCP client at it via Streamable HTTP:
+
+```json
+{
+  "mcpServers": {
+    "wsdot-mcp-server": {
+      "type": "streamable-http",
+      "url": "https://wsdot.caseyjhand.com/mcp"
+    }
+  }
+}
+```
+
+### Self-Hosted / Local
+
 Add the following to your MCP client configuration file. You'll need a WSDOT Traveler API access code — register at [wsdot.wa.gov/Traffic/api/](https://wsdot.wa.gov/Traffic/api/).
 
 ```json
@@ -270,7 +261,7 @@ MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 WSDOT_ACCESS_CODE=your-access-code bu
 
 ### Prerequisites
 
-- [Bun v1.3.0](https://bun.sh/) or higher (or Node.js v24+).
+- [Bun v1.4.0](https://bun.sh/) or higher (or Node.js v24+).
 - A WSDOT Traveler API access code. Register at [wsdot.wa.gov/Traffic/api/](https://wsdot.wa.gov/Traffic/api/) — registration is free.
 
 ### Installation
@@ -376,7 +367,7 @@ See [`CLAUDE.md`](./CLAUDE.md) for development guidelines and architectural rule
 
 ## Contributing
 
-Issues and pull requests are welcome. Run checks and tests before submitting:
+Issues are welcome. Run checks and tests before submitting:
 
 ```sh
 bun run devcheck