toolfunnel 0.6.0 → 0.7.1

package/docs/KNOWN_BUGS.md

@@ -1,99 +1,80 @@
-# Known issues & roadmap
-
-This file tracks the state of the 0.6.0 dual-era work, the deliberately-deferred items, and any
-limitations worth knowing about.
-
-## 0.6.0 - the 2026-07-28 MCP specification
-
-The 2026-07-28 MCP revision is a **breaking** change to the protocol: it removes the `initialize`
-handshake, protocol-level sessions, and the standalone GET/SSE endpoint, and adds new required
-behaviours - per-request protocol metadata, `Mcp-Method` / `Mcp-Name` request headers, a
-`server/discover` endpoint, a `subscriptions/listen` change-notification stream, and
-`resultType` / `ttlMs` / `cacheScope` result fields.
-
-Implemented in 0.6.0 (built against the RC spec; a reconciliation pass against the finalised
-spec lands after 28 July):
-
-- **Dual-era transport** (2024-11-05 + 2026-07-28) - old and new clients both work.
-- `server/discover`, request-header validation, and the `subscriptions/listen` stream.
-- A **dual-era client**: ToolFunnel speaks modern to modern upstream servers (stdio).
-- An **opt-in, per-upstream legacy-protocol shim** (`legacyPin`) - off by default, names the exact
-  version it drops to, warns at startup and on every call, and is enforced (skips the era probe).
-- **Passthrough wrap** (`toolfunnel wrap <upstreamId>`): one command turns the gateway into a
-  transparent, both-era wrapper for one upstream MCP - verbatim identity, tool definitions,
-  results, errors, notifications, and per-URI resource subscriptions (forwarded, and replayed
-  across silent upstream reconnects), with every call still passing the PreToolUse gate.
-- **Elicitation bridging**: a wrapped legacy server's mid-call questions are translated into the
-  modern `input_required` + retry pattern and back - multi-round, single-use tokens, TTL'd -
-  tested end-to-end against real published elicitation servers.
-- **Cancel translation** (stdio): a client's cancel reaches the upstream in the upstream's own
-  request-id space, for forwarded methods and wrapped tool calls alike.
-- **Identity settings + wrap mirroring**: `toolfunnel.json` gains `clientName`/`clientVersion`
-  (the identity upstreams see); under a wrap on stdio the real downstream client's identity is
-  mirrored upstream automatically.
-- **UI**: a Settings tab (identity + ports), a per-upstream legacy-pin toggle, and the wrap
-  security notice surfaced on the UI wrap path (parity with the CLI).
-- **Agent-facing docs**: `toolfunnel_howto` gains `wrap` and `configure` topics, so a plain agent
-  can learn the wrap and the whole no-code config map from inside the protocol.
-- **Method-class timeouts**: tool calls (`tools/call`, `prompts/get`, `resources/read`) wait
-  120 s by default - configurable per upstream via `"timeoutMs"` - and a progress report from
-  the tool re-arms the window, so a slow-but-alive tool never dies to the clock. The 10 s
-  handshake/list window stays fixed as the dead-upstream detector.
-- **Async shell execution**: `shell`-invoke register tools no longer block the event loop
-  (was `spawnSync` since 0.5.0) - concurrent HTTP clients keep being served during a long
-  shell tool.
-- **Config-home visibility**: every start prints the resolved config home to stderr, with a
-  relocation hint when it defaulted to the package root - running from a git clone no longer
-  writes config into the repo silently.
-- **Bounded listen streams**: the HTTP transport caps concurrent `subscriptions/listen`
-  streams (64) and refuses new ones past the cap with a clear error; existing streams are
-  never evicted.
-
-## Deliberately deferred (documented dispositions, target: the 28-July reconciliation pass)
-
-- **Legacy version family**: ToolFunnel currently speaks the oldest legacy dialect (`2024-11-05`)
-  to legacy upstreams and clamps a wrapped handshake to what the upstream negotiated. A client and
-  upstream that both speak a newer legacy revision (e.g. `2025-06-18`) are negotiated down.
-  Fidelity of the *fields* is unaffected (verified against real servers - nothing version-gated is
-  dropped), but the advertised version string is older than either end requires. DECIDED
-  (2026-07-17): best-version negotiation in BOTH directions - newest each peer speaks, modern
-  first, legacy fallback. Lands with the reconciliation pass, sequenced after the elicitation
-  bridge (a newer legacy offer invites server-initiated requests the client must handle first).
-- **Modern-upstream subscriptions**: the client does not yet open a `subscriptions/listen` stream
-  to modern upstreams, so their change-notifications are not received; the listen ack honestly
-  refuses `resourceSubscriptions` when no legacy subscribe-capable upstream is in scope.
-- **Elicitation bridge scope**: a wrapped upstream's mid-call `elicitation/create` bridges to
-  modern clients as MRTR (`input_required` + retry - built and wire-tested). A LEGACY client
-  gets an automatic decline instead (relaying backwards requests to legacy clients is future
-  work), and `sampling/createMessage` / `roots/list` from upstreams are answered -32601 for now.
-  An elicitation can only be bound to a call when exactly ONE wrapped call is in flight for that
-  upstream (always true on stdio); ambiguous concurrent HTTP calls decline rather than guess.
-- Header validation reports `-32020` where `-32022` would be more specific in one path.
-- Two-store wrap state read (expose.json + tools.state.json) has a benign TOCTOU window.
-- A meta-less `server/discover` is answered rather than refused (permissive-by-design).
-- The wrap's identity-mirror reconnect re-runs the full era negotiation - worst case ~3 s extra
-  on the first handshake against an upstream that ignores `server/discover`. Reusing the
-  already-known era on reconnect is a deferred optimisation.
-- HTTP cancel translation: the sessionless modern era gives a POST no connection identity, so a
-  client `notifications/cancelled` over HTTP is dropped rather than risk cancelling another
-  client's call. stdio (one client per pipe) translates and forwards cancels for both forwarded
-  methods and wrapped tools/call; the remaining best-effort windows are sub-millisecond (a cancel
-  racing the instant a forward is issued) plus the PreToolUse gate-evaluation phase of a tool
-  call (registered at upstream-issue time, post-gate).
-- `io.modelcontextprotocol/logLevel` (the modern per-request log level) is stripped with the rest
-  of the protocol `_meta` keys on wrapped forwards and not re-injected for modern upstreams -
-  part of the modern-upstream work above.
-- Discover on a DISABLED upstream works (inspect its tools before enabling - an explicit
-  allowance on the discover path only; the disabled upstream never reaches the tool surface).
-
-## Current limitations
-
-- The OAuth 2.1 resource-server and Streamable-HTTP support are recent and less battle-tested than
-  the core - test your setup before relying on them in a networked deployment.
-- No Prometheus / OpenTelemetry metrics - a toggleable JSONL audit log and in-memory `/health`
-  call counters only.
-- One gateway instance per process: the bridge/cancel state is process-global, so embedding two
-  gateway instances in one Node process is not a supported configuration (running two processes
-  is fine, and is the normal deployment).
-
-Found a bug, or want to help with the 0.6.0 work? Issues and PRs are welcome.
+# Known bugs
+
+The **Open** list is what remains open as of 0.7.0. **Fixed in 0.7.0** marks the items from
+0.6.0's file that this release closed - kept and marked rather than silently deleted, so a
+0.6.0 reader can see their fate. The full change list is in the
+[release notes](https://github.com/Rendeverance/toolfunnel/releases).
+
+## Open
+
+- **OPEN - Modern-upstream subscriptions are not received.** The client does not yet open a
+  `subscriptions/listen` stream to modern upstreams, so their change-notifications never arrive;
+  the listen ack honestly refuses `resourceSubscriptions` when no legacy subscribe-capable
+  upstream is in scope.
+- **OPEN - The elicitation bridge does not cover legacy clients.** A wrapped upstream's mid-call
+  `elicitation/create` bridges to MODERN clients as MRTR (`input_required` + retry), form and url
+  mode, gated on the caller's declared capability (0.7.0). A LEGACY client gets an automatic
+  decline instead - relaying backwards requests to legacy clients is unbuilt - and
+  `sampling/createMessage` / `roots/list` from upstreams are answered `-32601`. An elicitation can
+  only be bound to a call when exactly ONE wrapped call is in flight for that upstream (always
+  true on stdio); ambiguous concurrent HTTP calls decline rather than guess.
+- **OPEN (deferred) - HTTP cancels are dropped rather than translated.** The sessionless modern
+  era gives a POST no connection identity, so a client `notifications/cancelled` arriving over
+  HTTP is dropped rather than risk cancelling another client's call. Fixing this needs design
+  thought - identifying the caller without reintroducing sessions - so it is deferred rather than
+  patched. stdio (one client per pipe) translates and forwards cancels for both forwarded methods
+  and wrapped tool calls; the remaining best-effort windows there are sub-millisecond (a cancel
+  racing the instant a forward is issued) plus the PreToolUse gate-evaluation phase of a tool
+  call (registered at upstream-issue time, post-gate).
+
+## Fixed in 0.7.0
+
+- ***FIXED*** - **Legacy version negotiation.** 0.6.0 answered every `initialize` with
+  2024-11-05 whatever the client asked for, and supported exactly one legacy revision. The
+  gateway now echoes the requested version when it supports it (else answers its latest legacy),
+  and the legacy set spans 2024-11-05 / 2025-03-26 / 2025-06-18 / 2025-11-25. Pinned by
+  `test/negotiation.test.js`. One direction remains conservative: the client still offers
+  2024-11-05 to legacy upstreams (field fidelity is unaffected; only the advertised version
+  string is older than either end requires).
+- ***FIXED*** - **Header validation used a generic error code for an unsupported version.** An
+  unsupported `MCP-Protocol-Version` header answered the generic `-32600`; it now answers
+  `-32022` with `data.supported` and `data.requested` - the same code and shape the `_meta`
+  path already used for the same condition, so a client can renegotiate without parsing prose.
+  Pinned by `test/header-enforcement.test.js`.
+- ***FIXED*** - **The wrap's identity-mirror reconnect re-ran the full era negotiation** (worst
+  case roughly 3 s per respawn against an upstream that ignores `server/discover`). The
+  negotiated era is now remembered per upstream, and a death-driven reconnect goes straight to
+  the era it knows. A failed hinted connect or an explicit reconnect re-negotiates in full, so
+  an upstream upgraded across a restart is never pinned down an era. Pinned by
+  `test/reconnect-era-memo.test.js`.
+- ***FIXED*** - **`io.modelcontextprotocol/logLevel` was stripped on wrapped forwards.** Now
+  era-keyed at the client boundary: a modern upstream gets the caller's level verbatim in
+  `_meta`; a legacy upstream that declared the `logging` capability gets `logging/setLevel`
+  issued before the call (and the key never leaks into legacy `_meta`). Pinned by
+  `test/loglevel.test.js`.
+
+## By design (not bugs)
+
+These answer "why doesn't it do X". They are considered decisions, not defects.
+
+- **The config home defaults to the package root.** A git clone keeps working unchanged, and
+  seeding protects it from `npm update`, with an every-start relocation hint. Defaulting it to a
+  per-user directory instead needs a migration story for existing installs, so it ships as its own
+  release rather than as a rider. (`preuninstall` as a rescue mechanism is tested DEAD on npm
+  11.9.0 - it will not be built.)
+- **Funnel-mode curated descriptions carry an `[upstream]` title prefix** that lean passthrough
+  does not. A toggle to reconcile the two is cosmetic.
+- **The `command` slot is not path-guarded, and `PATH` is deliberately permitted.** The command
+  names the interpreter (`node`, a system binary), which by definition lives outside the config
+  home, and guarding `PATH` would break how commands resolve at all - so an upstream entry
+  combining `command: "node"` with a caller-supplied `env.PATH` runs whatever that PATH resolves.
+  This is a documented boundary, not an oversight: an upstream entry already specifies an
+  arbitrary command to execute, so the isolation guard is a **tripwire** for configs that quietly
+  reach outside an auditable config home - not a sandbox against an untrusted pack author.
+  Installing a pack is installing software (see [SECURITY.md](../SECURITY.md)).
+- **A meta-less `server/discover` is answered rather than refused** - permissive by design.
+- **Discover works on a DISABLED upstream**, so its tools can be inspected before enabling. An
+  explicit allowance on the discover path only; the disabled upstream never reaches the tool
+  surface.
+
+Found a bug, or want to help with the open work? Issues and PRs are welcome.

package/docs/design.md

@@ -1,70 +1,84 @@
-# Design decisions
-
-Short notes on the decisions that shape ToolFunnel, so you can judge the reasoning without
-reading the source. Each one is also documented at the place in the code where it bites.
-
-## 1. Zero runtime dependencies
-
-ToolFunnel sits in a privileged position: it executes tools and enforces policy. Every
-transitive dependency in that position is something you have to trust or audit. So the gateway
-uses Node built-ins only; "dependencies" in package.json is empty and stays empty. The one
-exception is deliberate and opt-in: OAuth token validation uses jose, installed only when you
-run `toolfunnel install-oauth`, version-pinned, because hand-rolled JWT crypto is how security
-holes are born. Dev tooling for the test suite (jose, the MCP SDK for interop tests) never
-ships.
-
-## 2. No SDK
-
-The gateway hand-rolls JSON-RPC over stdio and HTTP rather than building on the official MCP
-SDK. Two reasons. First, the zero-dependency stance above. Second, ToolFunnel has to speak two
-protocol eras at once, on both sides, which the SDK does not do; owning the wire layer is what
-makes the dual-era serving and the wrap possible at all.
-
-## 3. The gate fails closed
-
-Every server-side execution path goes through one function, gatedRun, and that function treats
-every failure as a deny: a hook that blocks, a hook engine that crashes, a malformed engine
-result, all of them mean the tool does not run. Denies carry a flag distinguishing operator
-policy ("your hook said no") from wiring failure ("the gate itself broke"), so a broken gate
-can never be mistaken for an approving one. The invariant has its own test.
-
-## 4. The isolation boundary
-
-Upstream server definitions can name any executable but their path-shaped arguments must stay
-inside the config home. The command is the interpreter you chose; the args are what it can
-reach, so the args are what the guard checks. Wrapping suspends the guard for the wrapped
-server only, because a wrap is an explicit statement that this one server is your entire
-surface, and it warns you when that happens.
-
-## 5. Two eras, served per request
-
-The 2026-07-28 revision removes the handshake that defines the older protocol, so "which era"
-is a property of each request, and that is how the gateway treats it: era detection per
-request, no mode switch, no configuration. Legacy answers stay byte-identical to what a
-pre-0.6.0 client saw; the gateway's own modern decoration only ever appears on modern
-requests. (A wrapped modern upstream's results are relayed verbatim, whatever era the
-caller speaks - stripping a server's own fields would be data loss and a wrapper tell.)
-
-## 6. Config lives in one folder
-
-Everything mutable (tools, upstreams, hooks, identity, logs) lives in the config home,
-relocatable with `--config-dir` or `TOOLFUNNEL_HOME`, seeded once, never overwritten by
-updates. One folder to back up, one folder to package, one folder to hand a colleague. The
-gateway prints the resolved home at every start so there is never any doubt about where state
-lives.
-
-## 7. Single operator by design
-
-Each ToolFunnel instance serves one operator. That is a decision, not an oversight: one
-instance per user gives process isolation, crash containment, per-user wrap state, and a
-security boundary you can reason about in one sentence. Multi-user deployment composes *in
-front of* the gateway rather than inside it - an authenticating proxy at the OAuth boundary
-(ToolFunnel is already an OAuth 2.1 resource server) routing each authenticated user to their
-own instance, with the per-request `_meta` lane carrying user context through to upstreams
-that want it. Nothing in the core couples the operator to a token subject, so that door stays
-open without the core ever growing user-shaped complexity.
-
-A Team edition built on this pattern - per-user identity, audit trails, quotas, per-user
-policy - is on the roadmap if there is interest. If your team wants that sooner, or you need a
-bespoke gateway built on ToolFunnel for your own requirements, open an issue on this
-repository titled `enquiry` - tailored builds are available.
+# Design decisions
+
+Short notes on the decisions that shape ToolFunnel, so you can judge the reasoning without
+reading the source. Each one is also documented at the place in the code where it bites.
+
+## 1. Zero runtime dependencies
+
+ToolFunnel sits in a privileged position: it executes tools and enforces policy. Every
+transitive dependency in that position is something you have to trust or audit. So the gateway
+uses Node built-ins only; "dependencies" in package.json is empty and stays empty. The one
+exception is deliberate and opt-in: OAuth token validation uses jose, installed only when you
+run `toolfunnel install-oauth`, version-pinned, because hand-rolled JWT crypto is how security
+holes are born. Dev tooling for the test suite (jose, the MCP SDK for interop tests) never
+ships.
+
+## 2. No SDK
+
+The gateway hand-rolls JSON-RPC over stdio and HTTP rather than building on the official MCP
+SDK. Two reasons. First, the zero-dependency stance above. Second, ToolFunnel has to speak two
+protocol eras at once, on both sides, which the SDK does not do; owning the wire layer is what
+makes the dual-era serving and the wrap possible at all.
+
+## 3. The gate: a deny is absolute, an unreadable decision is a deny
+
+Every server-side execution path goes through one function, gatedRun, and that function treats
+every failure it can *see* as a deny: a hook that blocks, a hook engine that crashes, a malformed
+engine result, a decision too large or too mangled to parse - all of them mean the tool does not
+run. An answer we cannot read is never treated as permission. Denies carry a flag distinguishing
+operator policy ("your hook said no") from wiring failure ("the gate itself broke"), so a broken
+gate can never be mistaken for an approving one.
+
+The line is drawn at a hook that never answered at all. A hook *script* that crashes, is missing,
+or hangs past its timeout is a non-blocking error and the call proceeds. That is Claude Code's
+hook protocol and it is a deliberate trade: denying there would mean a single broken hook file -
+a typo, a deleted script, a slow disk - silently taking every tool in the gateway offline, and an
+operator debugging that has no signal to follow. So the runtime failure is reported and the call
+continues, while the *decision* path stays strict. The consequence for anyone writing a gate is
+concrete: deny with `exit 2`, never with a bare non-zero, and if your policy cannot decide, exit 2
+deliberately. Both halves of this contract are pinned by test/gate-semantics.test.js.
+
+## 4. The isolation boundary
+
+Upstream server definitions can name any executable, but every field that decides what code the
+spawned process runs must stay inside the config home: path-shaped arguments (including the
+value after `=` in a `--flag=value` form), the working directory (`cwd`) bare arguments resolve
+against, and the small set of environment variables that load code on their own (`NODE_OPTIONS`,
+`NODE_PATH`, and their equivalents for other runtimes). The command is not guarded - it is the
+interpreter you chose, not the code it runs. The guard relaxes only by explicit opt-out, each
+per upstream and each with a warning naming itself: wrapping (a wrap is an explicit statement
+that this one server is your entire surface), `allowOutsidePaths: true` on the upstream's own
+entry (its paths and path-list env), and `allowCodeLoadingEnv: true` (the env class on its own).
+
+## 5. Two eras, served per request
+
+The 2026-07-28 revision removes the handshake that defines the older protocol, so "which era"
+is a property of each request, and that is how the gateway treats it: era detection per
+request, no mode switch, no configuration. Legacy answers stay byte-identical to what a
+pre-0.6.0 client saw; the gateway's own modern decoration only ever appears on modern
+requests. (A wrapped modern upstream's results are relayed verbatim, whatever era the
+caller speaks - stripping a server's own fields would be data loss and a wrapper tell.)
+
+## 6. Config lives in one folder
+
+Everything mutable (tools, upstreams, hooks, identity, logs) lives in the config home,
+relocatable with `--config-dir` or `TOOLFUNNEL_HOME`, seeded once, never overwritten by
+updates. One folder to back up, one folder to package, one folder to hand a colleague. The
+gateway prints the resolved home at every start so there is never any doubt about where state
+lives.
+
+## 7. Single operator by design
+
+Each ToolFunnel instance serves one operator. That is a decision, not an oversight: one
+instance per user gives process isolation, crash containment, per-user wrap state, and a
+security boundary you can reason about in one sentence. Multi-user deployment composes *in
+front of* the gateway rather than inside it - an authenticating proxy at the OAuth boundary
+(ToolFunnel is already an OAuth 2.1 resource server) routing each authenticated user to their
+own instance, with the per-request `_meta` lane carrying user context through to upstreams
+that want it. Nothing in the core couples the operator to a token subject, so that door stays
+open without the core ever growing user-shaped complexity.
+
+A Team edition built on this pattern - per-user identity, audit trails, quotas, per-user
+policy - is on the roadmap if there is interest. If your team wants that sooner, or you need a
+bespoke gateway built on ToolFunnel for your own requirements, open an issue on this
+repository titled `enquiry` - tailored builds are available.

package/docs/packaging.md

@@ -1,115 +1,115 @@
-# Packaging: ship what you built
-
-ToolFunnel's config is a folder. That single fact is the whole packaging story: everything you
-build in a gateway - your tools and their scripts, which of them are promoted hot or hidden, the
-upstream MCPs you attached and the tools you chose to expose from them, the policy hooks that gate
-every call, and the identity the server introduces itself with - lives in one directory tree, the
-**config home**. Ship the tree and you have shipped the product.
-
-## The config home
-
-By default the home is the package/clone root - a git clone works exactly as it always did. Point
-the gateway elsewhere and the config lives there instead:
-
-```
-toolfunnel --config-dir D:\my-setup     # flag (wins)
-TOOLFUNNEL_HOME=D:\my-setup toolfunnel  # env var
-```
-
-An empty home is **seeded** on first use from the shipped defaults (the register + management
-scripts, an empty `mcp/expose.json`, the default hooks manifest) and is **never overwritten**
-afterwards - which is the point: with the home outside the package, `npm update toolfunnel`
-can never eat your tools.
-
-```
-<home>/
-  toolfunnel.json         # identity (serverName/serverVersion), port defaults, `requires`
-  tools/
-    tools.register.json   # your tool entries (incl. their inputSchema)
-    tools.state.json      # the hot/hidden/enabled curation - part of the product
-    scripts/              # the tool scripts
-  mcp/expose.json         # upstream references + curated exposure
-  hooks/                  # the policy gate: manifest + hook scripts
-```
-
-## `tf_pack` - one call to a deployment artifact
-
-The `tf_pack` management tool snapshots the LIVE setup into `<home>/dist/<name>/` - always a
-separate location, never the live tree. `auth/` (environment-specific) and `logs/` never ship.
-
-**`{ format: "home" }`** → a portable config home. Zip it, commit it to a repo, or run it as-is:
-
-```
-toolfunnel --config-dir path/to/the-pack
-```
-
-**`{ format: "npm", name: "my-mcp", version: "1.0.0" }`** → a publishable npm package:
-
-```
-dist/my-mcp/
-  package.json      # name, bin, files, dependencies: { "toolfunnel": "^<current version>" }
-  bin/my-mcp.js     # 2 lines: pin --config-dir at ../home, delegate to toolfunnel
-  home/             # the bundled config home (identity rewritten to my-mcp@1.0.0)
-  README.md         # a stub to make your own
-```
-
-Review it, then `cd dist/my-mcp && npm publish`. Your users run `npx my-mcp` and get **your**
-server: your name in the MCP `initialize` handshake, your tools with your schemas, your curation,
-and - the part nobody else can say - **your gate**. The hooks travel inside the pack and enforce
-your policy on the recipient's machine regardless of which MCP client calls it.
-
-### Depend, never copy
-
-The generated package **depends on** `toolfunnel` (caret range) rather than vendoring it. Your own
-runtime dependencies go in **your** `package.json` exactly as with any npm package - npm installs
-the whole tree on `npx my-mcp`; toolfunnel itself adds zero. Why depending matters:
-
-- security and bug fixes reach every wrapped MCP through a normal `npm update` (the pack pins the caret range of the version that built it, so patch releases flow automatically) - no stale forks
-  carrying old bugs;
-- your package stays a few KB of config instead of a copied engine;
-- (and honestly) every install of your MCP counts as a toolfunnel download, which keeps the thing
-  you depend on alive.
-
-Your users can move the bundled home out of `node_modules` (so *their* edits survive *your*
-updates) via the `<NAME>_HOME` env var the generated launcher supports.
-
-## Declaring runtimes: `requires`
-
-Your tools may need runtimes the gateway doesn't (python, git, ffmpeg...). Declare them in the
-home's `toolfunnel.json` and they travel with every pack:
-
-```json
-{
-  "serverName": "my-mcp",
-  "requires": [
-    { "command": "python", "min": "3.10", "why": "the pdf-extract tools" },
-    { "command": "git" }
-  ]
-}
-```
-
-The gateway probes them once at startup and prints one clear stderr line per problem - found
-version vs needed, plus your `why`. Advisory by design: a missing runtime breaks only the tools
-that need it, so the server still starts and everything else keeps working.
-
-## Composite packs
-
-A pack is not just your own scripts. Because `mcp/expose.json` lives in the home, a pack carries
-**upstream references too**: "attach `@example/weather-mcp` (pin the version) and expose exactly
-these four tools under these names." The upstream itself travels as a *reference* - `npx` fetches
-it on the recipient's machine - while your **curation** and your **gate** travel as config. One
-pack = your tools + other people's servers, curated, renamed, and policed, as a single artifact.
-
-## Audit honesty
-
-Packs spawn commands - that is what they are for. Before you run anyone's pack (including one of
-ours), read **three files** - every command it can run is declared in plain JSON:
-
-- `tools/tools.register.json` - the tool invokes (scripts and shell commands);
-- `mcp/expose.json` - the upstream server commands it will spawn;
-- `toolfunnel.json` - the `requires` probes. Note these run **at gateway startup** (each declared
-  program is executed once with its version flag), which is why a `requires` command must be a
-  bare program name - the gateway rejects paths, spaces, and shell characters outright.
-
-Ship your own packs expecting the same scrutiny, and say so in your README (the `tf_pack` stub
-already does).
+# Packaging: ship what you built
+
+ToolFunnel's config is a folder. That single fact is the whole packaging story: everything you
+build in a gateway - your tools and their scripts, which of them are promoted hot or hidden, the
+upstream MCPs you attached and the tools you chose to expose from them, the policy hooks that gate
+every call, and the identity the server introduces itself with - lives in one directory tree, the
+**config home**. Ship the tree and you have shipped the product.
+
+## The config home
+
+By default the home is the package/clone root - a git clone works exactly as it always did. Point
+the gateway elsewhere and the config lives there instead:
+
+```
+toolfunnel --config-dir D:\my-setup     # flag (wins)
+TOOLFUNNEL_HOME=D:\my-setup toolfunnel  # env var
+```
+
+An empty home is **seeded** on first use from the shipped defaults (the register + management
+scripts, an empty `mcp/expose.json`, the default hooks manifest) and is **never overwritten**
+afterwards - which is the point: with the home outside the package, `npm update toolfunnel`
+can never eat your tools.
+
+```
+<home>/
+  toolfunnel.json         # identity (serverName/serverVersion), port defaults, `requires`
+  tools/
+    tools.register.json   # your tool entries (incl. their inputSchema)
+    tools.state.json      # the hot/hidden/enabled curation - part of the product
+    scripts/              # the tool scripts
+  mcp/expose.json         # upstream references + curated exposure
+  hooks/                  # the policy gate: manifest + hook scripts
+```
+
+## `tf_pack` - one call to a deployment artifact
+
+The `tf_pack` management tool snapshots the LIVE setup into `<home>/dist/<name>/` - always a
+separate location, never the live tree. `auth/` (environment-specific) and `logs/` never ship.
+
+**`{ format: "home" }`** → a portable config home. Zip it, commit it to a repo, or run it as-is:
+
+```
+toolfunnel --config-dir path/to/the-pack
+```
+
+**`{ format: "npm", name: "my-mcp", version: "1.0.0" }`** → a publishable npm package:
+
+```
+dist/my-mcp/
+  package.json      # name, bin, files, dependencies: { "toolfunnel": "^<current version>" }
+  bin/my-mcp.js     # 2 lines: pin --config-dir at ../home, delegate to toolfunnel
+  home/             # the bundled config home (identity rewritten to my-mcp@1.0.0)
+  README.md         # a stub to make your own
+```
+
+Review it, then `cd dist/my-mcp && npm publish`. Your users run `npx my-mcp` and get **your**
+server: your name in the MCP `initialize` handshake, your tools with your schemas, your curation,
+and - the part nobody else can say - **your gate**. The hooks travel inside the pack and enforce
+your policy on the recipient's machine regardless of which MCP client calls it.
+
+### Depend, never copy
+
+The generated package **depends on** `toolfunnel` (caret range) rather than vendoring it. Your own
+runtime dependencies go in **your** `package.json` exactly as with any npm package - npm installs
+the whole tree on `npx my-mcp`; toolfunnel itself adds zero. Why depending matters:
+
+- security and bug fixes reach every wrapped MCP through a normal `npm update` (the pack pins the caret range of the version that built it, so patch releases flow automatically) - no stale forks
+  carrying old bugs;
+- your package stays a few KB of config instead of a copied engine;
+- (and honestly) every install of your MCP counts as a toolfunnel download, which keeps the thing
+  you depend on alive.
+
+Your users can move the bundled home out of `node_modules` (so *their* edits survive *your*
+updates) via the `<NAME>_HOME` env var the generated launcher supports.
+
+## Declaring runtimes: `requires`
+
+Your tools may need runtimes the gateway doesn't (python, git, ffmpeg...). Declare them in the
+home's `toolfunnel.json` and they travel with every pack:
+
+```json
+{
+  "serverName": "my-mcp",
+  "requires": [
+    { "command": "python", "min": "3.10", "why": "the pdf-extract tools" },
+    { "command": "git" }
+  ]
+}
+```
+
+The gateway probes them once at startup and prints one clear stderr line per problem - found
+version vs needed, plus your `why`. Advisory by design: a missing runtime breaks only the tools
+that need it, so the server still starts and everything else keeps working.
+
+## Composite packs
+
+A pack is not just your own scripts. Because `mcp/expose.json` lives in the home, a pack carries
+**upstream references too**: "attach `@example/weather-mcp` (pin the version) and expose exactly
+these four tools under these names." The upstream itself travels as a *reference* - `npx` fetches
+it on the recipient's machine - while your **curation** and your **gate** travel as config. One
+pack = your tools + other people's servers, curated, renamed, and policed, as a single artifact.
+
+## Audit honesty
+
+Packs spawn commands - that is what they are for. Before you run anyone's pack (including one of
+ours), read **three files** - every command it can run is declared in plain JSON:
+
+- `tools/tools.register.json` - the tool invokes (scripts and shell commands);
+- `mcp/expose.json` - the upstream server commands it will spawn;
+- `toolfunnel.json` - the `requires` probes. Note these run **at gateway startup** (each declared
+  program is executed once with its version flag), which is why a `requires` command must be a
+  bare program name - the gateway rejects paths, spaces, and shell characters outright.
+
+Ship your own packs expecting the same scrutiny, and say so in your README (the `tf_pack` stub
+already does).