From 58be45b35e97c8e615fc7948470c58f1d5f66e42 Mon Sep 17 00:00:00 2001 From: xarmian Date: Thu, 8 Oct 2026 15:15:26 -0400 Subject: [PATCH] feat(mcp): remote /mcp writes are agent writes named by clientInfo; refused claims say lease_held (BUG-2772, BUG-3496) (#1903) * feat(mcp): remote /mcp writes are agent writes, named by the client's declared clientInfo (BUG-2772) A write over remote /mcp reached the handlers with no X-Pad-Agent and was recorded as the human. It is now an agent write, named by the client's own MCP clientInfo.name: a modern request's _meta clientInfo, else the clientInfo its session sent at initialize (remembered by the Mcp-Session-Id pad issued; mcp-go's session state does not survive pad's stateless transport), else unnamed; never the human, never a guessed name. Each initialize logs the declared client (name, version, protocol, transport; no tokens). A remote call's default lease holder is that name plus a short session id (claude-code#3f9a12), inside defaultLeaseHolder so claim and next/ready agree; two connections of one client no longer share a lease. Folds TASK-3495. ToolSurfaceVersion 0.77. Co-Authored-By: Claude * fix(mcp): a refused claim reaches both transports as lease_held with its holder (BUG-3496) * test(mcp): register WriteLeaseHeldError in the stdio marker vocabulary table (BUG-3496) * fix(mcp): a remembered client name is bound to the account that declared it (BUG-2772 codex r1) * fix(mcp): the remote lease holder carries eight hex digits of the session id (BUG-2772 lead ruling) --------- Co-authored-by: Claude --- README.md | 4 +- cmd/pad/bug3142_stdio_classify_test.go | 44 ++ cmd/pad/cmd_server_chatgpt.go | 6 + cmd/pad/cmd_server_mcp.go | 6 +- cmd/pad/main.go | 5 + .../testdata/mcp_wire/remote_initialize.json | 4 +- .../testdata/mcp_wire/stdio_initialize.json | 4 +- docs/mcp.md | 17 +- internal/cli/client.go | 35 ++ .../mcp/bug2772_remote_agent_identity_test.go | 381 ++++++++++++++++++ internal/mcp/client_identity.go | 234 +++++++++++ internal/mcp/dispatch_http.go | 11 + internal/mcp/errors.go | 20 + internal/mcp/instructions.md | 2 +- internal/mcp/server.go | 15 +- internal/mcp/too_large_test.go | 3 + internal/mcp/version.go | 23 +- internal/server/context.go | 26 ++ internal/server/handlers_documents.go | 6 +- internal/server/handlers_item_lease.go | 13 +- 20 files changed, 840 insertions(+), 19 deletions(-) create mode 100644 internal/mcp/bug2772_remote_agent_identity_test.go create mode 100644 internal/mcp/client_identity.go diff --git a/README.md b/README.md index a56489292..ed0725db9 100644 --- a/README.md +++ b/README.md @@ -399,7 +399,7 @@ directory for `claude-code`, and an `[mcp_servers.pad]` table in project-scoped, it's install-on-request only — `--all` and `pad mcp status` cover the per-user clients (including Codex) and skip it. -**Tool catalog (v0.76)** — ten resource × action tools plus `pad_set_workspace`. Undeclared input keys are rejected with a structured error rather than silently dropped, and field values are typed against the collection schema on the server: +**Tool catalog (v0.77)** — ten resource × action tools plus `pad_set_workspace`. Undeclared input keys are rejected with a structured error rather than silently dropped, and field values are typed against the collection schema on the server: | Tool | Actions | |---|---| @@ -423,7 +423,7 @@ Plus resources at `pad://workspaces`, `pad://workspace/{ws}/dashboard`, and `pad://_meta/version`. **Stability contract.** The catalog is versioned -(`tool_surface_version: "0.76"`) and advertised in the initialize handshake and at +(`tool_surface_version: "0.77"`) and advertised in the initialize handshake and at `pad://_meta/version`, so external agents can pin against it; the per-version changelog lives in [`internal/mcp/version.go`](internal/mcp/version.go). Errors come back as structured envelopes (`{error: {code, message, hint, ...}}`) from a diff --git a/cmd/pad/bug3142_stdio_classify_test.go b/cmd/pad/bug3142_stdio_classify_test.go index f43d68a32..edb636aeb 100644 --- a/cmd/pad/bug3142_stdio_classify_test.go +++ b/cmd/pad/bug3142_stdio_classify_test.go @@ -250,3 +250,47 @@ func TestStdioCommentDeletedClassifies(t *testing.T) { t.Fatalf("hint = %q, want the shared CommentDeletedHint", env.Error.Hint) } } + +// BUG-3496, end to end on stdio: a claim on an item another holder leases +// reaches the caller as lease_held with the holder and expiry, instead of +// server_error. The fake answers with the bytes writeLeaseHeldError writes. +func TestStdioLeaseHeldClassifies(t *testing.T) { + srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + w.Header().Set("Content-Type", "application/json") + w.WriteHeader(http.StatusConflict) + _, _ = w.Write([]byte(`{"error":{"code":"lease_held","message":"item is leased to claude-code#3f9a12","details":{"ref":"TASK-1","holder":"claude-code#3f9a12","acquired_at":"2026-10-08T10:00:00Z","expires_at":"2026-10-08T10:30:00Z"}}}`)) + })) + defer srv.Close() + + t.Setenv(padHelperEnv, "1") + t.Setenv("HOME", t.TempDir()) + bin, err := os.Executable() + if err != nil { + t.Fatalf("os.Executable: %v", err) + } + d := &mcp.ExecDispatcher{Binary: bin} + res, err := d.Dispatch(context.Background(), []string{"item", "claim"}, + []string{"--url", srv.URL, "--workspace", "ws", "--format", "json", "--", "TASK-1"}) + if err != nil { + t.Fatalf("Dispatch: %v", err) + } + env, ok := res.StructuredContent.(mcp.ErrorEnvelope) + if !ok { + t.Fatalf("PRECONDITION: the call should have failed; got %T", res.StructuredContent) + } + if env.Error.Code != mcp.ErrLeaseHeld { + t.Fatalf("code = %q (message %q, hint %q), want %q", + env.Error.Code, env.Error.Message, env.Error.Hint, mcp.ErrLeaseHeld) + } + if env.Error.Hint != mcp.LeaseHeldHint { + t.Fatalf("hint = %q, want the shared LeaseHeldHint", env.Error.Hint) + } + var details struct { + Holder string `json:"holder"` + ExpiresAt string `json:"expires_at"` + } + if err := json.Unmarshal(env.Error.Details, &details); err != nil || + details.Holder != "claude-code#3f9a12" || details.ExpiresAt != "2026-10-08T10:30:00Z" { + t.Fatalf("details = %s, want the holder and expires_at (err %v)", env.Error.Details, err) + } +} diff --git a/cmd/pad/cmd_server_chatgpt.go b/cmd/pad/cmd_server_chatgpt.go index 996df4b11..22dace895 100644 --- a/cmd/pad/cmd_server_chatgpt.go +++ b/cmd/pad/cmd_server_chatgpt.go @@ -18,10 +18,16 @@ import ( // and experimental capabilities. Not mounted yet; TASK-3321 U2 serves it at // its own URL behind a setting. func newChatGPTMCPServer(doc *cmdhelp.Document, dispatcher mcpserver.Dispatcher) (*mcpserver.Server, error) { + // The same declared-client registry the dispatcher reads (BUG-2772). + var clients *mcpserver.ClientRegistry + if hd, ok := dispatcher.(*mcpserver.HTTPHandlerDispatcher); ok { + clients = hd.Clients + } srv := mcpserver.NewServer(mcpserver.Options{ Version: fullVersion(), Instructions: mcpserver.ChatGPTInstructions, Experimental: mcpserver.ChatGPTExperimentalCapabilities(), + Clients: clients, }) if _, err := mcpserver.RegisterChatGPTCatalog(srv.MCP(), mcpserver.ChatGPTCatalogOptions{ Catalog: mcpserver.CatalogOptions{ diff --git a/cmd/pad/cmd_server_mcp.go b/cmd/pad/cmd_server_mcp.go index 9bd5576fe..fbf44ad8d 100644 --- a/cmd/pad/cmd_server_mcp.go +++ b/cmd/pad/cmd_server_mcp.go @@ -76,7 +76,10 @@ func wireMCP(cmd *cobra.Command, srv *server.Server, s *store.Store, ep config.M Homepage: padHomepage, MaxDepth: -1, }) - mcpSrv := mcpserver.NewServer(mcpserver.Options{Version: fullVersion()}) + // One registry of declared MCP clients (BUG-2772): both remote servers + // record into it at initialize, and the dispatcher reads it per call. + mcpClients := mcpserver.NewClientRegistry() + mcpSrv := mcpserver.NewServer(mcpserver.Options{Version: fullVersion(), Clients: mcpClients}) // CurrentUserFromContext returns (*User, bool); the dispatcher's // UserResolver signature is just (ctx) *User. The bool is "found", // which equals "non-nil pointer" for the path the MCP middleware @@ -84,6 +87,7 @@ func wireMCP(cmd *cobra.Command, srv *server.Server, s *store.Store, ep config.M // flatten with a closure. dispatcher := &mcpserver.HTTPHandlerDispatcher{ Handler: srv, + Clients: mcpClients, UserResolver: func(ctx context.Context) *models.User { u, _ := server.CurrentUserFromContext(ctx) return u diff --git a/cmd/pad/main.go b/cmd/pad/main.go index 68b9384a3..24adb32a2 100644 --- a/cmd/pad/main.go +++ b/cmd/pad/main.go @@ -85,6 +85,11 @@ func writeRootStructuredError(w io.Writer, err error) { // BUG-3252: an edit, reply or reaction addressed to a tombstone. if apiErr, ok := cli.IsCommentDeleted(err); ok { cli.WriteCommentDeletedError(w, apiErr) + return + } + // BUG-3496: a claim on an item another holder leases. + if apiErr, ok := cli.IsLeaseHeld(err); ok { + cli.WriteLeaseHeldError(w, apiErr) } } diff --git a/cmd/pad/testdata/mcp_wire/remote_initialize.json b/cmd/pad/testdata/mcp_wire/remote_initialize.json index e25f3129e..db75e7d4a 100644 --- a/cmd/pad/testdata/mcp_wire/remote_initialize.json +++ b/cmd/pad/testdata/mcp_wire/remote_initialize.json @@ -8,7 +8,7 @@ }, "padToolSurface": { "tool_surface_stable": true, - "version": "0.76" + "version": "0.77" } }, "prompts": {}, @@ -21,5 +21,5 @@ "name": "pad-mcp", "version": "" }, - "instructions": "Pad is a project tracker for developers and AI agents — issues (TASK, BUG), plans (PLAN), ideas (IDEA), docs (DOC), conventions, comments, and dependencies. Use this server when a user mentions:\n\n- Issue refs like `TASK-5`, `BUG-12`, `PLAN-3`, `IDEA-8` — they are stable, human-readable IDs and the canonical way to address items. Use them, never slugs; they are what audit trails and PR titles show.\n- Tasks / issues / items / plans / progress / \"what's on my plate\" / \"what to work on next\" / standup / changelog / retrospective.\n- Project conventions, decision records, or \"how should this team do X.\"\n\nIf the user is asking general code questions with no project-management thread, you don't need this server.\n\n## Tool surface (v0.76)\n\nTen resource × action tools, plus `pad_set_workspace`. Eleven tools total.\n\nInputs are validated strictly: an undeclared top-level key is rejected with a structured `validation_failed` naming it, never accepted and silently dropped.\n\n- `pad_item` — Items: create / update / delete / get / list / move / restore / link / unlink / deps / star / unstar / starred / comment / list-comments / edit-comment / delete-comment / backlinks / bulk-update / note / decide / export / import / history / remind / ack-reminder / claim / release. On create/update, field values may be passed as a `fields` OBJECT (the same shape reads return, e.g. `{\"status\":\"done\",\"effort\":\"l\"}`) — it merges into the same path as the dedicated params and `field: [\"key=value\"]`; the same key in two places with CONFLICTING values is refused, not silently resolved. `list` accepts `unparented: true` to keep items with no parent or implements relationship (mutually exclusive with `parent`). `list` results are SUMMARY-shaped by default on both transports — no content bodies; pass `full: true` for complete bodies (token-expensive), or prefer `get` for a single item's body. `update` field writes are a server-side field-level merge (only the keys you set change); pass `expected_seq` for optimistic concurrency — the `seq` you last read, which is on every item AND every list summary — and a stale value fails with a structured 409 `update_conflict` whose details carry `actual_seq` to retry with. PREFER IT over `expected_updated_at`, which cannot tell two writes inside one second apart; that one still works, and if you send both, seq decides. A token cannot see a browser tab's unsaved edits, so `content` sent WITH one is refused with 409 `content_pending_flush` while any exist; re-reading will not clear it. Wait for the editor to save, or pass `overwrite_pending_edits: true` to replace them. `content_state: \"superseded_set_aside\"` is different and wins when both apply: an editor upgrade set aside edits no tab can restore, so EVERY content write is refused (token or not; `details.set_aside_rows`) and waiting never clears it. Tell the user, or pass `overwrite_pending_edits: true` to discard them. Writing `content` while a browser tab has the item open routes the markdown through that live document, and the stored copy is updated only by a later collab-snapshot flush — usually from the tab that applied it, though any such write updates the row, and nothing guarantees one happens: the 200 echoes the content you SENT and carries `warnings.content_outcome: \"applied_pending_flush\"`, which describes that WRITE — the content went to the document, not the row — rather than being a live reading of the row, which a concurrent flush may already have updated. A `get` (or a `list` with `full: true` — a default list carries no content at all) before such a flush lands reads the stored copy and answers with the PREVIOUS content, which is the lag rather than a failed write, so do not re-send on the strength of it. You do not have to infer that from the write, and you will also see it when someone ELSE's tab holds the unflushed edits and you wrote nothing: a read that serves a body the server knows is behind the live document carries `content_state: \"applied_pending_flush\"` — same value as the write warning, different question (what the ROW is, not what your REQUEST did). Treat it as re-read later, never as re-send, and do not wait on it in a loop: the server normally recovers the stored copy itself about a minute after the last tab leaves the item, but that is not guaranteed (a recovery can fail, and an operator can turn it off), and otherwise the row catches up only when a tab next opens the item. The stored form may also not be byte-identical to what you sent, since the markdown round-trips through the editor (bullet markers, emphasis characters, list numbering and blank-line runs normalise; already-canonical markdown survives unchanged), so compare on meaning rather than bytes. `move` changes an item's COLLECTION within its workspace: system metadata (implementation notes, decision log, linked PR) survives it, and any field value the target schema has no home for is dropped AND reported in the move's activity entry — check there rather than assuming a move is lossless. A carried unique-field collision is dropped, named in `warnings.not_unique`. Three system keys — `implementation_notes`, `decision_log`, `convention` — cannot be set through `field` on update or move; the call is refused with `validation_failed`, naming the key and the write path that does maintain it (`note`, `decide`, and library activation respectively). `github_pr` is refused as well (BUG-2696): a `field` value arrived as a string, so the PR data was stored double-encoded and no link appeared. Its writer is `pad github link` / `unlink`, which needs a local git checkout, and there is no PR-link action on this surface yet, so treat linking a PR as something to hand to a human rather than a call to retry. On `create` they are refused too (BUG-3163), with the same `validation_failed`: create the item first, then use `note` / `decide` on it; convention metadata comes from library activation. `history` returns read-only item version metadata (newest-first), bounded to the NEWEST 50 versions by default (max 300 — pass `limit` to change the window); pass `full: true` to include each version's resolved content body (token-expensive). There is no `offset`: versions are stored as reverse patches, so only a newest-end window is cheap to reconstruct. Unassign or detach with the `clear_assigned_user` / `clear_agent_role` / `clear_parent` booleans; an empty `assign` / `role` / `parent` does NOT clear. `remind` / `ack-reminder`: a fired reminder shows in `pad_project` next / ready (the delivery path on an instance with no webhook) until acknowledged, and one on a completed item is hidden there. `claim` / `release`: claim an item before you work it; a loser's 409 is `lease_held` (pick another, don't retry), and a lease bumps neither `updated_at` nor `seq`. The holder defaults to your agent name, and `pad_project` next / ready leave out items another holder has leased. `edit-comment` / `delete-comment` take a `comment_id` from `list-comments` (whose rows carry `edited`); only a comment's author may edit it. Correct a comment in place rather than appending a correction. Deleting a comment that has replies leaves a placeholder (`deleted: true`, empty body) so the replies keep their parent; editing, replying to or reacting to it answers 409 `comment_deleted`. (Two older forms still work and are not deprecated: `field: [\"assigned_user_id=\"]` on either transport, and a direct `assigned_user_id: \"\"` param over remote `/mcp` only — prefer the boolean, which is the only one this schema advertises.)\n\n**List filters must name a field (v0.75).** A `pad_item` `list` filter on a key no collection in scope declares, and no item stores, is refused with `validation_failed` (\"invalid list filter\"), where it used to return an empty list; a stored undeclared key still filters. Check the schema; don't retry.\n\n**Library words in a blank workspace (v0.67).** A brand-new blank workspace lists one convention trigger (`always`) and one scope (`all`). Activating a library entry, or creating a convention or playbook with a trigger or scope the library itself uses, adds that word to the collection's options and says so in `warnings.options_added`. A trigger you invent is still refused until the workspace owner adds it to the collection's schema.\n\n**App attribution (v0.65).** An item an installed app created, a comment an app wrote and a history row an app's write made carry `via_app` (the install id) and `via_app_name` (the app's name). On an item they name the app that CREATED it, not the last writer. They are absent for anything a person or an agent wrote.\n\n**Relation fields (v0.31).** A `relation` value may be a UUID, an issue ref (`COLO-3`) or the target's EXACT TITLE, tried in that order (a title that is also a ref resolves as the ref). A title matches only inside the declared collection, among items you can see; found only elsewhere, it is refused naming that collection; several matches are `ambiguous`. Full rules: docs/mcp.md.\n\nReads carry a `relation_targets` member beside `fields`: field key → `{id, ref, title}`, so you can render a relation without a request per value. `fields` still holds the canonical id, which is what you write back. An entry with an `id` and NO `ref`/`title` means the target is gone **or** you may not see it — the two are deliberately indistinguishable, so do not render it as either \"deleted\" or \"hidden\"; \"unavailable\" is the honest word. An entry with `stored_as_text: true` differs: the stored value is not UUID-shaped, so it was never an id (an imported title, legacy text). Render it as text, not as unavailable.\n\n**`multi_relation` fields (v0.33).** An ORDERED LIST of references, each resolved like a `relation` (UUID, ref, or exact title in the declared collection). Declare one as `owners:multi_relation:people`; the target collection is required. Rules: `[]` means absent; a blank element is refused by index; order is part of the value; duplicates are refused after resolution (`duplicate_referent`); any failing element refuses the whole write; `required` needs one resolved element; a cross-workspace copy drops the whole value (in `warnings.dropped_fields`). `relation_targets` holds an ARRAY of `{id, ref, title}` in stored order (`id`-only where unresolved); scalar keys stay single objects. Full rules: docs/mcp.md.\n\n- `pad_workspace` — Workspaces: list / members / invite / storage / audit-log / create / claim / deleted / restore.\n- `pad_collection` — Collections: list / create / update / delete / list-archived / restore. `delete` archives: the collection and its items leave every view, and `restore` brings them back. An `update` that removes a field or a select option still in use answers with `warnings.orphaned`: tell the user how many items keep the removed value.\n- `pad_project` — Project intelligence: dashboard / next / ready / stale / standup / changelog / report / activity. Use `ready` for the ranked top items to work on next (blocked work is left out) and `stale` for items needing attention; `activity` to catch up on what other agents/users changed since you last worked (non-streaming feed with item refs + change details).\n- `pad_role` — Agent roles: list / create / update / delete.\n- `pad_search` — Full-text search across items: query.\n- `pad_playbook` — Invokable procedures: list / get / run / match. Use `run` to bind args against a playbook's declared spec and get the rendered body back; side-effect-free. `run` refuses a playbook whose status isn't `active` (a draft still being authored) with a `playbook_not_active` error — pass `allow_draft: true` to override. Both `run` and `get` echo the playbook's `status`. Both may also carry `content_state` (`\"applied_pending_flush\"`, or `\"superseded_set_aside\"` as under `pad_item`), meaning the BODY you are about to execute is behind the item's live collaborative document — an editor holds unflushed edits, so the steps may be superseded. It is a reason to re-read or to ask, not a reason to refuse to run; the body is still the best the server has. `match` finds a playbook from text.\n- `pad_library` — Convention + playbook library (the global catalog of pre-built entries workspaces activate): list / get / activate.\n- `pad_attachment` — Read-only attachment metadata: list / show. `list` enumerates a workspace's attachments (filter by item / category / collection / attached / unattached); `show` returns one attachment's MIME, size, filename, and ETag via a HEAD request. Uploading and general file downloads stay CLI-only; bounded image bytes are available through the attachment resource below.\n- `pad_meta` — Server introspection: server-info / version / tool-surface / bootstrap. The `bootstrap` action returns one-shot workspace context (user + collections + always-on conventions + a metadata-only `convention_index` of every active convention + roles + playbook metadata + dashboard + recent activity).\n- `pad_set_workspace` — Load workspace context; response embeds the bootstrap blob so you load context in one call. Whether it also pins a session default: see Workspace context below. Takes `workspace: \u003cslug\u003e` only (no `action`).\n\nFor the ten resource × action tools, always pass `action` as a top-level field. Per-action required parameters are documented in each tool's description.\n\n## Resources are cheaper than tool calls\n\nRead these directly when you need workspace state (described in the resource listings): `pad://workspaces`, `pad://workspace/{ws}/dashboard`, `.../collections`, `.../items` (use `pad_item` `list` to filter), `.../items/{ref}` (markdown), `.../attachments/{id}` (images only, at most 1 MiB, as base64 `thumb-md`), `.../bootstrap` (the same payload as `pad_meta` `bootstrap`), and `pad://_meta/version`. A host can prefetch them once per session.\n\nLoad the bootstrap resource once per workspace and reuse its collections, conventions, roles, and playbook metadata. Refresh it after switching workspaces, after changing those configuration surfaces, when Pad reports stale schema/context, or when the user asks. For changing work state, read the affected item or use a targeted project tool instead of fetching the whole bootstrap again.\n\n## Workspace context\n\nEvery action that operates within a workspace accepts an optional `workspace` parameter. Resolution order:\n\n1. Explicit `workspace` argument on the call (always wins).\n2. On a single-user local server only: the session default set via `pad_set_workspace`.\n3. On a single-user local server only: the CWD-linked workspace from `.pad.toml`.\n\nA multi-user/remote server does **not** persist a session default — pass `workspace` explicitly on every call. If none resolves, the action returns a structured `no_workspace` error with `available_workspaces`, on both the local and the remote transport.\n\n## Update flow: read first, then patch\n\nFor `pad_item.action: update`, the server merges your patch with the item's current state. Pass only the fields you want to change. When changing `status`, ALWAYS include a `comment` explaining why — it builds the audit trail that helps the team understand history.\n\n## One error code you must not retry\n\nErrors come back as a structured envelope with a `code`. Most failures are worth a retry after you fix something, and a `server_error` may be transient. `stored_state_unreadable` is neither.\n\nIt means the ITEM'S STORED DATA cannot be decoded — your input was fine. Today it fires when `note` / `decide` would append to an `implementation_notes` / `decision_log` value that is not a list of entries. The operation is refused precisely because completing it would overwrite that value. The refusal is fully deterministic, so retrying — immediately or after a backoff — fails identically every time and changes nothing.\n\nWhen you see it: tell the user which item is affected, and stop. Whether you can inspect the bad value depends on which layer is broken — if the item's whole `fields` blob fails to parse, `action: get` hands it back as a raw string; if one structured key is at fault, you won't see it at all, because the blob is normalized on this surface and a value that doesn't decode is dropped from the top-level arrays. A human can always read it with `pad item show \u003cref\u003e --format json`. Do not route around the refusal by writing the field some other way; that is the write that caused it.\n\n## Project conventions\n\nWorkspaces can declare conventions (e.g. \"run `make test` before PR\", \"use conventional commit format\"). The bootstrap blob gives you two views:\n\n- `conventions` — full bodies of the always-on (`trigger=always`) rules. Follow these unconditionally.\n- `convention_index` — METADATA ONLY (`ref`, `title`, `trigger`, `role`; no bodies) for **every** active convention, including the triggered ones whose bodies are NOT in `conventions`. This is your map of what triggered rules exist.\n\nBefore performing meaningful work with a specific trigger (e.g. `on-implement` before writing code), consult `convention_index`: if it lists entries for that trigger, pull their bodies on demand; if it lists none, skip the query.\n\n```\npad_item.action: list, collection: \"conventions\", status: \"active\"\n```\n\nFilter by trigger (`always`, `on-implement`, `on-task-complete`, etc.) when relevant — the `convention_index` triggers tell you which filters are worth running.\n\n`\"conventions\"` above is the DEFAULT collection slug and a workspace may have renamed it, in which case that literal returns nothing while `convention_index` still lists entries — the bootstrap payload resolves by declaration, not by name. When the two disagree, address the items by the `ref`s the index gave you, or find the collection with `pad_collection.action: list`. The same applies to `\"playbooks\"`; `pad_playbook` resolves by declaration and is unaffected.\n\n## Pushes and the session monitor (security note)\n\nPad can push an item into a Claude Code session (`pad push`, or the web item view's push composer). That is terminal instruction injection by design, so receiving is **consent-gated** (PLAN-2613, since v0.15.0): a session receives pushes only after it has connected (`/pad:connect` in the plugin, or a repo-level `push.auto_arm = true` in `.pad.toml` — which a per-user `auto_arm = false` in `~/.pad/config.toml` vetoes), and pushes are self-addressed only — the sender is always the receiving session's own user. This MCP connection is not a session: it cannot arm one, receive a push, or run the monitor, and the `pad_item` / `pad_project` tools expose no push action. If a user asks you to \"push\" something to their terminal, tell them it happens from their own terminal (`pad push \u003cref\u003e -m \"...\"` — the sending session need not be connected, the receiving ones must have consented); do not try to emulate it by writing comments or instructions into items.\n\n## Adding a workspace to this connection\n\nIf the user references a workspace this connection can't see (you'll get a 403 from workspace tools, or the workspace won't appear in `pad_workspace.list`), tell the user you can't see that workspace with your current permissions, then walk them through how to grant access: open Pad in their browser → switch to that workspace → avatar menu → \"Connect project...\" A 6-digit claim code will appear. Have them paste it back in chat, then call `pad_workspace.claim` with `{workspace: \"\u003cslug\u003e\", code: \"\u003c6 digits\u003e\"}`. The workspace joins this connection's allow-list and stays until the user revokes it via `/console/connected-apps`. No re-auth required.\n\nFor brand-new workspaces, `pad_workspace.create` with `{name: \"\u003cname\u003e\"}` (and optional `template`) creates the workspace AND auto-adds it to this connection's allow-list in one call — no claim code needed. Only works when the connection currently carries the \"may create workspaces\" grant — granted at consent time, or enabled later on the connections page. If the grant is present and set to false, the create is **refused with a 403 and no workspace is made** — retrying won't help and neither will the claim flow, since there is nothing to claim. Tell the user this connection isn't permitted to create workspaces, and offer them the two ways forward: create the workspace themselves in the browser and grant access with a claim code, or re-authorize this connection with \"Let this app create new workspaces\" enabled (`/console/connected-apps` can also flip it on an existing connection).\n\n## New workspace: offer to set it up\n\nThe bootstrap blob carries `needs_onboarding: bool` — true when the workspace has zero user-created items (template seeds don't count). When it's true, **lead with an active offer before anything else**: *\"This workspace is brand new and isn't set up yet. Want me to set it up? I'll ask a few quick questions and adapt it to your project.\"*\n\nThis is an **offer, not an auto-run** — wait for the user to say yes before running onboarding. If they accept, run the `onboard` playbook (use the `pad_onboard` prompt, or load the body via `pad_playbook` `action: get`, `ref: onboard`). If they decline, or already declined earlier in the session, respect that and skip the offer. The flag flips to false the moment any item exists, so it won't nag past first setup.\n\n## Built-in updates: mention once\n\nThe bootstrap blob may carry `builtin_updates: int` (absent when there are none): how many of the conventions and playbooks Pad ships have newer text in Pad's library than this workspace's copy. When it is present, mention it **once per session**, in one line, then carry on. **Never apply an update yourself**: a person reviews each one and accepts it or not.\n\n## Multi-step workflows\n\nFour prompts ship with the server: `pad_plan`, `pad_ideate`, `pad_retro`, `pad_onboard`. Use them when the user wants help planning, brainstorming, retrospecting, or onboarding into a workspace — they encode the multi-step Pad-aware playbook for each.\n" + "instructions": "Pad is a project tracker for developers and AI agents — issues (TASK, BUG), plans (PLAN), ideas (IDEA), docs (DOC), conventions, comments, and dependencies. Use this server when a user mentions:\n\n- Issue refs like `TASK-5`, `BUG-12`, `PLAN-3`, `IDEA-8` — they are stable, human-readable IDs and the canonical way to address items. Use them, never slugs; they are what audit trails and PR titles show.\n- Tasks / issues / items / plans / progress / \"what's on my plate\" / \"what to work on next\" / standup / changelog / retrospective.\n- Project conventions, decision records, or \"how should this team do X.\"\n\nIf the user is asking general code questions with no project-management thread, you don't need this server.\n\n## Tool surface (v0.77)\n\nTen resource × action tools, plus `pad_set_workspace`. Eleven tools total.\n\nInputs are validated strictly: an undeclared top-level key is rejected with a structured `validation_failed` naming it, never accepted and silently dropped.\n\n- `pad_item` — Items: create / update / delete / get / list / move / restore / link / unlink / deps / star / unstar / starred / comment / list-comments / edit-comment / delete-comment / backlinks / bulk-update / note / decide / export / import / history / remind / ack-reminder / claim / release. On create/update, field values may be passed as a `fields` OBJECT (the same shape reads return, e.g. `{\"status\":\"done\",\"effort\":\"l\"}`) — it merges into the same path as the dedicated params and `field: [\"key=value\"]`; the same key in two places with CONFLICTING values is refused, not silently resolved. `list` accepts `unparented: true` to keep items with no parent or implements relationship (mutually exclusive with `parent`). `list` results are SUMMARY-shaped by default on both transports — no content bodies; pass `full: true` for complete bodies (token-expensive), or prefer `get` for a single item's body. `update` field writes are a server-side field-level merge (only the keys you set change); pass `expected_seq` for optimistic concurrency — the `seq` you last read, which is on every item AND every list summary — and a stale value fails with a structured 409 `update_conflict` whose details carry `actual_seq` to retry with. PREFER IT over `expected_updated_at`, which cannot tell two writes inside one second apart; that one still works, and if you send both, seq decides. A token cannot see a browser tab's unsaved edits, so `content` sent WITH one is refused with 409 `content_pending_flush` while any exist; re-reading will not clear it. Wait for the editor to save, or pass `overwrite_pending_edits: true` to replace them. `content_state: \"superseded_set_aside\"` is different and wins when both apply: an editor upgrade set aside edits no tab can restore, so EVERY content write is refused (token or not; `details.set_aside_rows`) and waiting never clears it. Tell the user, or pass `overwrite_pending_edits: true` to discard them. Writing `content` while a browser tab has the item open routes the markdown through that live document, and the stored copy is updated only by a later collab-snapshot flush — usually from the tab that applied it, though any such write updates the row, and nothing guarantees one happens: the 200 echoes the content you SENT and carries `warnings.content_outcome: \"applied_pending_flush\"`, which describes that WRITE — the content went to the document, not the row — rather than being a live reading of the row, which a concurrent flush may already have updated. A `get` (or a `list` with `full: true` — a default list carries no content at all) before such a flush lands reads the stored copy and answers with the PREVIOUS content, which is the lag rather than a failed write, so do not re-send on the strength of it. You do not have to infer that from the write, and you will also see it when someone ELSE's tab holds the unflushed edits and you wrote nothing: a read that serves a body the server knows is behind the live document carries `content_state: \"applied_pending_flush\"` — same value as the write warning, different question (what the ROW is, not what your REQUEST did). Treat it as re-read later, never as re-send, and do not wait on it in a loop: the server normally recovers the stored copy itself about a minute after the last tab leaves the item, but that is not guaranteed (a recovery can fail, and an operator can turn it off), and otherwise the row catches up only when a tab next opens the item. The stored form may also not be byte-identical to what you sent, since the markdown round-trips through the editor (bullet markers, emphasis characters, list numbering and blank-line runs normalise; already-canonical markdown survives unchanged), so compare on meaning rather than bytes. `move` changes an item's COLLECTION within its workspace: system metadata (implementation notes, decision log, linked PR) survives it, and any field value the target schema has no home for is dropped AND reported in the move's activity entry — check there rather than assuming a move is lossless. A carried unique-field collision is dropped, named in `warnings.not_unique`. Three system keys — `implementation_notes`, `decision_log`, `convention` — cannot be set through `field` on update or move; the call is refused with `validation_failed`, naming the key and the write path that does maintain it (`note`, `decide`, and library activation respectively). `github_pr` is refused as well (BUG-2696): a `field` value arrived as a string, so the PR data was stored double-encoded and no link appeared. Its writer is `pad github link` / `unlink`, which needs a local git checkout, and there is no PR-link action on this surface yet, so treat linking a PR as something to hand to a human rather than a call to retry. On `create` they are refused too (BUG-3163), with the same `validation_failed`: create the item first, then use `note` / `decide` on it; convention metadata comes from library activation. `history` returns read-only item version metadata (newest-first), bounded to the NEWEST 50 versions by default (max 300 — pass `limit` to change the window); pass `full: true` to include each version's resolved content body (token-expensive). There is no `offset`: versions are stored as reverse patches, so only a newest-end window is cheap to reconstruct. Unassign or detach with the `clear_assigned_user` / `clear_agent_role` / `clear_parent` booleans; an empty `assign` / `role` / `parent` does NOT clear. `remind` / `ack-reminder`: a fired reminder shows in `pad_project` next / ready (the delivery path on an instance with no webhook) until acknowledged, and one on a completed item is hidden there. `claim` / `release`: claim an item before you work it; a loser's 409 is `lease_held` (pick another, don't retry), and a lease bumps neither `updated_at` nor `seq`. The holder defaults to your agent name, and `pad_project` next / ready leave out items another holder has leased. `edit-comment` / `delete-comment` take a `comment_id` from `list-comments` (whose rows carry `edited`); only a comment's author may edit it. Correct a comment in place rather than appending a correction. Deleting a comment that has replies leaves a placeholder (`deleted: true`, empty body) so the replies keep their parent; editing, replying to or reacting to it answers 409 `comment_deleted`. (Two older forms still work and are not deprecated: `field: [\"assigned_user_id=\"]` on either transport, and a direct `assigned_user_id: \"\"` param over remote `/mcp` only — prefer the boolean, which is the only one this schema advertises.)\n\n**List filters must name a field (v0.75).** A `pad_item` `list` filter on a key no collection in scope declares, and no item stores, is refused with `validation_failed` (\"invalid list filter\"), where it used to return an empty list; a stored undeclared key still filters. Check the schema; don't retry.\n\n**Library words in a blank workspace (v0.67).** A brand-new blank workspace lists one convention trigger (`always`) and one scope (`all`). Activating a library entry, or creating a convention or playbook with a trigger or scope the library itself uses, adds that word to the collection's options and says so in `warnings.options_added`. A trigger you invent is still refused until the workspace owner adds it to the collection's schema.\n\n**App attribution (v0.65).** An item an installed app created, a comment an app wrote and a history row an app's write made carry `via_app` (the install id) and `via_app_name` (the app's name). On an item they name the app that CREATED it, not the last writer. They are absent for anything a person or an agent wrote.\n\n**Relation fields (v0.31).** A `relation` value may be a UUID, an issue ref (`COLO-3`) or the target's EXACT TITLE, tried in that order (a title that is also a ref resolves as the ref). A title matches only inside the declared collection, among items you can see; found only elsewhere, it is refused naming that collection; several matches are `ambiguous`. Full rules: docs/mcp.md.\n\nReads carry a `relation_targets` member beside `fields`: field key → `{id, ref, title}`, so you can render a relation without a request per value. `fields` still holds the canonical id, which is what you write back. An entry with an `id` and NO `ref`/`title` means the target is gone **or** you may not see it — the two are deliberately indistinguishable, so do not render it as either \"deleted\" or \"hidden\"; \"unavailable\" is the honest word. An entry with `stored_as_text: true` differs: the stored value is not UUID-shaped, so it was never an id (an imported title, legacy text). Render it as text, not as unavailable.\n\n**`multi_relation` fields (v0.33).** An ORDERED LIST of references, each resolved like a `relation` (UUID, ref, or exact title in the declared collection). Declare one as `owners:multi_relation:people`; the target collection is required. Rules: `[]` means absent; a blank element is refused by index; order is part of the value; duplicates are refused after resolution (`duplicate_referent`); any failing element refuses the whole write; `required` needs one resolved element; a cross-workspace copy drops the whole value (in `warnings.dropped_fields`). `relation_targets` holds an ARRAY of `{id, ref, title}` in stored order (`id`-only where unresolved); scalar keys stay single objects. Full rules: docs/mcp.md.\n\n- `pad_workspace` — Workspaces: list / members / invite / storage / audit-log / create / claim / deleted / restore.\n- `pad_collection` — Collections: list / create / update / delete / list-archived / restore. `delete` archives: the collection and its items leave every view, and `restore` brings them back. An `update` that removes a field or a select option still in use answers with `warnings.orphaned`: tell the user how many items keep the removed value.\n- `pad_project` — Project intelligence: dashboard / next / ready / stale / standup / changelog / report / activity. Use `ready` for the ranked top items to work on next (blocked work is left out) and `stale` for items needing attention; `activity` to catch up on what other agents/users changed since you last worked (non-streaming feed with item refs + change details).\n- `pad_role` — Agent roles: list / create / update / delete.\n- `pad_search` — Full-text search across items: query.\n- `pad_playbook` — Invokable procedures: list / get / run / match. Use `run` to bind args against a playbook's declared spec and get the rendered body back; side-effect-free. `run` refuses a playbook whose status isn't `active` (a draft still being authored) with a `playbook_not_active` error — pass `allow_draft: true` to override. Both `run` and `get` echo the playbook's `status`. Both may also carry `content_state` (`\"applied_pending_flush\"`, or `\"superseded_set_aside\"` as under `pad_item`), meaning the BODY you are about to execute is behind the item's live collaborative document — an editor holds unflushed edits, so the steps may be superseded. It is a reason to re-read or to ask, not a reason to refuse to run; the body is still the best the server has. `match` finds a playbook from text.\n- `pad_library` — Convention + playbook library (the global catalog of pre-built entries workspaces activate): list / get / activate.\n- `pad_attachment` — Read-only attachment metadata: list / show. `list` enumerates a workspace's attachments (filter by item / category / collection / attached / unattached); `show` returns one attachment's MIME, size, filename, and ETag via a HEAD request. Uploading and general file downloads stay CLI-only; bounded image bytes are available through the attachment resource below.\n- `pad_meta` — Server introspection: server-info / version / tool-surface / bootstrap. The `bootstrap` action returns one-shot workspace context (user + collections + always-on conventions + a metadata-only `convention_index` of every active convention + roles + playbook metadata + dashboard + recent activity).\n- `pad_set_workspace` — Load workspace context; response embeds the bootstrap blob so you load context in one call. Whether it also pins a session default: see Workspace context below. Takes `workspace: \u003cslug\u003e` only (no `action`).\n\nFor the ten resource × action tools, always pass `action` as a top-level field. Per-action required parameters are documented in each tool's description.\n\n## Resources are cheaper than tool calls\n\nRead these directly when you need workspace state (described in the resource listings): `pad://workspaces`, `pad://workspace/{ws}/dashboard`, `.../collections`, `.../items` (use `pad_item` `list` to filter), `.../items/{ref}` (markdown), `.../attachments/{id}` (images only, at most 1 MiB, as base64 `thumb-md`), `.../bootstrap` (the same payload as `pad_meta` `bootstrap`), and `pad://_meta/version`. A host can prefetch them once per session.\n\nLoad the bootstrap resource once per workspace and reuse its collections, conventions, roles, and playbook metadata. Refresh it after switching workspaces, after changing those configuration surfaces, when Pad reports stale schema/context, or when the user asks. For changing work state, read the affected item or use a targeted project tool instead of fetching the whole bootstrap again.\n\n## Workspace context\n\nEvery action that operates within a workspace accepts an optional `workspace` parameter. Resolution order:\n\n1. Explicit `workspace` argument on the call (always wins).\n2. On a single-user local server only: the session default set via `pad_set_workspace`.\n3. On a single-user local server only: the CWD-linked workspace from `.pad.toml`.\n\nA multi-user/remote server does **not** persist a session default — pass `workspace` explicitly on every call. If none resolves, the action returns a structured `no_workspace` error with `available_workspaces`, on both the local and the remote transport.\n\n## Update flow: read first, then patch\n\nFor `pad_item.action: update`, the server merges your patch with the item's current state. Pass only the fields you want to change. When changing `status`, ALWAYS include a `comment` explaining why — it builds the audit trail that helps the team understand history.\n\n## One error code you must not retry\n\nErrors come back as a structured envelope with a `code`. Most failures are worth a retry after you fix something, and a `server_error` may be transient. `stored_state_unreadable` is neither.\n\nIt means the ITEM'S STORED DATA cannot be decoded — your input was fine. Today it fires when `note` / `decide` would append to an `implementation_notes` / `decision_log` value that is not a list of entries. The operation is refused precisely because completing it would overwrite that value. The refusal is fully deterministic, so retrying — immediately or after a backoff — fails identically every time and changes nothing.\n\nWhen you see it: tell the user which item is affected, and stop. Whether you can inspect the bad value depends on which layer is broken — if the item's whole `fields` blob fails to parse, `action: get` hands it back as a raw string; if one structured key is at fault, you won't see it at all, because the blob is normalized on this surface and a value that doesn't decode is dropped from the top-level arrays. A human can always read it with `pad item show \u003cref\u003e --format json`. Do not route around the refusal by writing the field some other way; that is the write that caused it.\n\n## Project conventions\n\nWorkspaces can declare conventions (e.g. \"run `make test` before PR\", \"use conventional commit format\"). The bootstrap blob gives you two views:\n\n- `conventions` — full bodies of the always-on (`trigger=always`) rules. Follow these unconditionally.\n- `convention_index` — METADATA ONLY (`ref`, `title`, `trigger`, `role`; no bodies) for **every** active convention, including the triggered ones whose bodies are NOT in `conventions`. This is your map of what triggered rules exist.\n\nBefore performing meaningful work with a specific trigger (e.g. `on-implement` before writing code), consult `convention_index`: if it lists entries for that trigger, pull their bodies on demand; if it lists none, skip the query.\n\n```\npad_item.action: list, collection: \"conventions\", status: \"active\"\n```\n\nFilter by trigger (`always`, `on-implement`, `on-task-complete`, etc.) when relevant — the `convention_index` triggers tell you which filters are worth running.\n\n`\"conventions\"` above is the DEFAULT collection slug and a workspace may have renamed it, in which case that literal returns nothing while `convention_index` still lists entries — the bootstrap payload resolves by declaration, not by name. When the two disagree, address the items by the `ref`s the index gave you, or find the collection with `pad_collection.action: list`. The same applies to `\"playbooks\"`; `pad_playbook` resolves by declaration and is unaffected.\n\n## Pushes and the session monitor (security note)\n\nPad can push an item into a Claude Code session (`pad push`, or the web item view's push composer). That is terminal instruction injection by design, so receiving is **consent-gated** (PLAN-2613, since v0.15.0): a session receives pushes only after it has connected (`/pad:connect` in the plugin, or a repo-level `push.auto_arm = true` in `.pad.toml` — which a per-user `auto_arm = false` in `~/.pad/config.toml` vetoes), and pushes are self-addressed only — the sender is always the receiving session's own user. This MCP connection is not a session: it cannot arm one, receive a push, or run the monitor, and the `pad_item` / `pad_project` tools expose no push action. If a user asks you to \"push\" something to their terminal, tell them it happens from their own terminal (`pad push \u003cref\u003e -m \"...\"` — the sending session need not be connected, the receiving ones must have consented); do not try to emulate it by writing comments or instructions into items.\n\n## Adding a workspace to this connection\n\nIf the user references a workspace this connection can't see (you'll get a 403 from workspace tools, or the workspace won't appear in `pad_workspace.list`), tell the user you can't see that workspace with your current permissions, then walk them through how to grant access: open Pad in their browser → switch to that workspace → avatar menu → \"Connect project...\" A 6-digit claim code will appear. Have them paste it back in chat, then call `pad_workspace.claim` with `{workspace: \"\u003cslug\u003e\", code: \"\u003c6 digits\u003e\"}`. The workspace joins this connection's allow-list and stays until the user revokes it via `/console/connected-apps`. No re-auth required.\n\nFor brand-new workspaces, `pad_workspace.create` with `{name: \"\u003cname\u003e\"}` (and optional `template`) creates the workspace AND auto-adds it to this connection's allow-list in one call — no claim code needed. Only works when the connection currently carries the \"may create workspaces\" grant — granted at consent time, or enabled later on the connections page. If the grant is present and set to false, the create is **refused with a 403 and no workspace is made** — retrying won't help and neither will the claim flow, since there is nothing to claim. Tell the user this connection isn't permitted to create workspaces, and offer them the two ways forward: create the workspace themselves in the browser and grant access with a claim code, or re-authorize this connection with \"Let this app create new workspaces\" enabled (`/console/connected-apps` can also flip it on an existing connection).\n\n## New workspace: offer to set it up\n\nThe bootstrap blob carries `needs_onboarding: bool` — true when the workspace has zero user-created items (template seeds don't count). When it's true, **lead with an active offer before anything else**: *\"This workspace is brand new and isn't set up yet. Want me to set it up? I'll ask a few quick questions and adapt it to your project.\"*\n\nThis is an **offer, not an auto-run** — wait for the user to say yes before running onboarding. If they accept, run the `onboard` playbook (use the `pad_onboard` prompt, or load the body via `pad_playbook` `action: get`, `ref: onboard`). If they decline, or already declined earlier in the session, respect that and skip the offer. The flag flips to false the moment any item exists, so it won't nag past first setup.\n\n## Built-in updates: mention once\n\nThe bootstrap blob may carry `builtin_updates: int` (absent when there are none): how many of the conventions and playbooks Pad ships have newer text in Pad's library than this workspace's copy. When it is present, mention it **once per session**, in one line, then carry on. **Never apply an update yourself**: a person reviews each one and accepts it or not.\n\n## Multi-step workflows\n\nFour prompts ship with the server: `pad_plan`, `pad_ideate`, `pad_retro`, `pad_onboard`. Use them when the user wants help planning, brainstorming, retrospecting, or onboarding into a workspace — they encode the multi-step Pad-aware playbook for each.\n" } diff --git a/cmd/pad/testdata/mcp_wire/stdio_initialize.json b/cmd/pad/testdata/mcp_wire/stdio_initialize.json index e25f3129e..db75e7d4a 100644 --- a/cmd/pad/testdata/mcp_wire/stdio_initialize.json +++ b/cmd/pad/testdata/mcp_wire/stdio_initialize.json @@ -8,7 +8,7 @@ }, "padToolSurface": { "tool_surface_stable": true, - "version": "0.76" + "version": "0.77" } }, "prompts": {}, @@ -21,5 +21,5 @@ "name": "pad-mcp", "version": "" }, - "instructions": "Pad is a project tracker for developers and AI agents — issues (TASK, BUG), plans (PLAN), ideas (IDEA), docs (DOC), conventions, comments, and dependencies. Use this server when a user mentions:\n\n- Issue refs like `TASK-5`, `BUG-12`, `PLAN-3`, `IDEA-8` — they are stable, human-readable IDs and the canonical way to address items. Use them, never slugs; they are what audit trails and PR titles show.\n- Tasks / issues / items / plans / progress / \"what's on my plate\" / \"what to work on next\" / standup / changelog / retrospective.\n- Project conventions, decision records, or \"how should this team do X.\"\n\nIf the user is asking general code questions with no project-management thread, you don't need this server.\n\n## Tool surface (v0.76)\n\nTen resource × action tools, plus `pad_set_workspace`. Eleven tools total.\n\nInputs are validated strictly: an undeclared top-level key is rejected with a structured `validation_failed` naming it, never accepted and silently dropped.\n\n- `pad_item` — Items: create / update / delete / get / list / move / restore / link / unlink / deps / star / unstar / starred / comment / list-comments / edit-comment / delete-comment / backlinks / bulk-update / note / decide / export / import / history / remind / ack-reminder / claim / release. On create/update, field values may be passed as a `fields` OBJECT (the same shape reads return, e.g. `{\"status\":\"done\",\"effort\":\"l\"}`) — it merges into the same path as the dedicated params and `field: [\"key=value\"]`; the same key in two places with CONFLICTING values is refused, not silently resolved. `list` accepts `unparented: true` to keep items with no parent or implements relationship (mutually exclusive with `parent`). `list` results are SUMMARY-shaped by default on both transports — no content bodies; pass `full: true` for complete bodies (token-expensive), or prefer `get` for a single item's body. `update` field writes are a server-side field-level merge (only the keys you set change); pass `expected_seq` for optimistic concurrency — the `seq` you last read, which is on every item AND every list summary — and a stale value fails with a structured 409 `update_conflict` whose details carry `actual_seq` to retry with. PREFER IT over `expected_updated_at`, which cannot tell two writes inside one second apart; that one still works, and if you send both, seq decides. A token cannot see a browser tab's unsaved edits, so `content` sent WITH one is refused with 409 `content_pending_flush` while any exist; re-reading will not clear it. Wait for the editor to save, or pass `overwrite_pending_edits: true` to replace them. `content_state: \"superseded_set_aside\"` is different and wins when both apply: an editor upgrade set aside edits no tab can restore, so EVERY content write is refused (token or not; `details.set_aside_rows`) and waiting never clears it. Tell the user, or pass `overwrite_pending_edits: true` to discard them. Writing `content` while a browser tab has the item open routes the markdown through that live document, and the stored copy is updated only by a later collab-snapshot flush — usually from the tab that applied it, though any such write updates the row, and nothing guarantees one happens: the 200 echoes the content you SENT and carries `warnings.content_outcome: \"applied_pending_flush\"`, which describes that WRITE — the content went to the document, not the row — rather than being a live reading of the row, which a concurrent flush may already have updated. A `get` (or a `list` with `full: true` — a default list carries no content at all) before such a flush lands reads the stored copy and answers with the PREVIOUS content, which is the lag rather than a failed write, so do not re-send on the strength of it. You do not have to infer that from the write, and you will also see it when someone ELSE's tab holds the unflushed edits and you wrote nothing: a read that serves a body the server knows is behind the live document carries `content_state: \"applied_pending_flush\"` — same value as the write warning, different question (what the ROW is, not what your REQUEST did). Treat it as re-read later, never as re-send, and do not wait on it in a loop: the server normally recovers the stored copy itself about a minute after the last tab leaves the item, but that is not guaranteed (a recovery can fail, and an operator can turn it off), and otherwise the row catches up only when a tab next opens the item. The stored form may also not be byte-identical to what you sent, since the markdown round-trips through the editor (bullet markers, emphasis characters, list numbering and blank-line runs normalise; already-canonical markdown survives unchanged), so compare on meaning rather than bytes. `move` changes an item's COLLECTION within its workspace: system metadata (implementation notes, decision log, linked PR) survives it, and any field value the target schema has no home for is dropped AND reported in the move's activity entry — check there rather than assuming a move is lossless. A carried unique-field collision is dropped, named in `warnings.not_unique`. Three system keys — `implementation_notes`, `decision_log`, `convention` — cannot be set through `field` on update or move; the call is refused with `validation_failed`, naming the key and the write path that does maintain it (`note`, `decide`, and library activation respectively). `github_pr` is refused as well (BUG-2696): a `field` value arrived as a string, so the PR data was stored double-encoded and no link appeared. Its writer is `pad github link` / `unlink`, which needs a local git checkout, and there is no PR-link action on this surface yet, so treat linking a PR as something to hand to a human rather than a call to retry. On `create` they are refused too (BUG-3163), with the same `validation_failed`: create the item first, then use `note` / `decide` on it; convention metadata comes from library activation. `history` returns read-only item version metadata (newest-first), bounded to the NEWEST 50 versions by default (max 300 — pass `limit` to change the window); pass `full: true` to include each version's resolved content body (token-expensive). There is no `offset`: versions are stored as reverse patches, so only a newest-end window is cheap to reconstruct. Unassign or detach with the `clear_assigned_user` / `clear_agent_role` / `clear_parent` booleans; an empty `assign` / `role` / `parent` does NOT clear. `remind` / `ack-reminder`: a fired reminder shows in `pad_project` next / ready (the delivery path on an instance with no webhook) until acknowledged, and one on a completed item is hidden there. `claim` / `release`: claim an item before you work it; a loser's 409 is `lease_held` (pick another, don't retry), and a lease bumps neither `updated_at` nor `seq`. The holder defaults to your agent name, and `pad_project` next / ready leave out items another holder has leased. `edit-comment` / `delete-comment` take a `comment_id` from `list-comments` (whose rows carry `edited`); only a comment's author may edit it. Correct a comment in place rather than appending a correction. Deleting a comment that has replies leaves a placeholder (`deleted: true`, empty body) so the replies keep their parent; editing, replying to or reacting to it answers 409 `comment_deleted`. (Two older forms still work and are not deprecated: `field: [\"assigned_user_id=\"]` on either transport, and a direct `assigned_user_id: \"\"` param over remote `/mcp` only — prefer the boolean, which is the only one this schema advertises.)\n\n**List filters must name a field (v0.75).** A `pad_item` `list` filter on a key no collection in scope declares, and no item stores, is refused with `validation_failed` (\"invalid list filter\"), where it used to return an empty list; a stored undeclared key still filters. Check the schema; don't retry.\n\n**Library words in a blank workspace (v0.67).** A brand-new blank workspace lists one convention trigger (`always`) and one scope (`all`). Activating a library entry, or creating a convention or playbook with a trigger or scope the library itself uses, adds that word to the collection's options and says so in `warnings.options_added`. A trigger you invent is still refused until the workspace owner adds it to the collection's schema.\n\n**App attribution (v0.65).** An item an installed app created, a comment an app wrote and a history row an app's write made carry `via_app` (the install id) and `via_app_name` (the app's name). On an item they name the app that CREATED it, not the last writer. They are absent for anything a person or an agent wrote.\n\n**Relation fields (v0.31).** A `relation` value may be a UUID, an issue ref (`COLO-3`) or the target's EXACT TITLE, tried in that order (a title that is also a ref resolves as the ref). A title matches only inside the declared collection, among items you can see; found only elsewhere, it is refused naming that collection; several matches are `ambiguous`. Full rules: docs/mcp.md.\n\nReads carry a `relation_targets` member beside `fields`: field key → `{id, ref, title}`, so you can render a relation without a request per value. `fields` still holds the canonical id, which is what you write back. An entry with an `id` and NO `ref`/`title` means the target is gone **or** you may not see it — the two are deliberately indistinguishable, so do not render it as either \"deleted\" or \"hidden\"; \"unavailable\" is the honest word. An entry with `stored_as_text: true` differs: the stored value is not UUID-shaped, so it was never an id (an imported title, legacy text). Render it as text, not as unavailable.\n\n**`multi_relation` fields (v0.33).** An ORDERED LIST of references, each resolved like a `relation` (UUID, ref, or exact title in the declared collection). Declare one as `owners:multi_relation:people`; the target collection is required. Rules: `[]` means absent; a blank element is refused by index; order is part of the value; duplicates are refused after resolution (`duplicate_referent`); any failing element refuses the whole write; `required` needs one resolved element; a cross-workspace copy drops the whole value (in `warnings.dropped_fields`). `relation_targets` holds an ARRAY of `{id, ref, title}` in stored order (`id`-only where unresolved); scalar keys stay single objects. Full rules: docs/mcp.md.\n\n- `pad_workspace` — Workspaces: list / members / invite / storage / audit-log / create / claim / deleted / restore.\n- `pad_collection` — Collections: list / create / update / delete / list-archived / restore. `delete` archives: the collection and its items leave every view, and `restore` brings them back. An `update` that removes a field or a select option still in use answers with `warnings.orphaned`: tell the user how many items keep the removed value.\n- `pad_project` — Project intelligence: dashboard / next / ready / stale / standup / changelog / report / activity. Use `ready` for the ranked top items to work on next (blocked work is left out) and `stale` for items needing attention; `activity` to catch up on what other agents/users changed since you last worked (non-streaming feed with item refs + change details).\n- `pad_role` — Agent roles: list / create / update / delete.\n- `pad_search` — Full-text search across items: query.\n- `pad_playbook` — Invokable procedures: list / get / run / match. Use `run` to bind args against a playbook's declared spec and get the rendered body back; side-effect-free. `run` refuses a playbook whose status isn't `active` (a draft still being authored) with a `playbook_not_active` error — pass `allow_draft: true` to override. Both `run` and `get` echo the playbook's `status`. Both may also carry `content_state` (`\"applied_pending_flush\"`, or `\"superseded_set_aside\"` as under `pad_item`), meaning the BODY you are about to execute is behind the item's live collaborative document — an editor holds unflushed edits, so the steps may be superseded. It is a reason to re-read or to ask, not a reason to refuse to run; the body is still the best the server has. `match` finds a playbook from text.\n- `pad_library` — Convention + playbook library (the global catalog of pre-built entries workspaces activate): list / get / activate.\n- `pad_attachment` — Read-only attachment metadata: list / show. `list` enumerates a workspace's attachments (filter by item / category / collection / attached / unattached); `show` returns one attachment's MIME, size, filename, and ETag via a HEAD request. Uploading and general file downloads stay CLI-only; bounded image bytes are available through the attachment resource below.\n- `pad_meta` — Server introspection: server-info / version / tool-surface / bootstrap. The `bootstrap` action returns one-shot workspace context (user + collections + always-on conventions + a metadata-only `convention_index` of every active convention + roles + playbook metadata + dashboard + recent activity).\n- `pad_set_workspace` — Load workspace context; response embeds the bootstrap blob so you load context in one call. Whether it also pins a session default: see Workspace context below. Takes `workspace: \u003cslug\u003e` only (no `action`).\n\nFor the ten resource × action tools, always pass `action` as a top-level field. Per-action required parameters are documented in each tool's description.\n\n## Resources are cheaper than tool calls\n\nRead these directly when you need workspace state (described in the resource listings): `pad://workspaces`, `pad://workspace/{ws}/dashboard`, `.../collections`, `.../items` (use `pad_item` `list` to filter), `.../items/{ref}` (markdown), `.../attachments/{id}` (images only, at most 1 MiB, as base64 `thumb-md`), `.../bootstrap` (the same payload as `pad_meta` `bootstrap`), and `pad://_meta/version`. A host can prefetch them once per session.\n\nLoad the bootstrap resource once per workspace and reuse its collections, conventions, roles, and playbook metadata. Refresh it after switching workspaces, after changing those configuration surfaces, when Pad reports stale schema/context, or when the user asks. For changing work state, read the affected item or use a targeted project tool instead of fetching the whole bootstrap again.\n\n## Workspace context\n\nEvery action that operates within a workspace accepts an optional `workspace` parameter. Resolution order:\n\n1. Explicit `workspace` argument on the call (always wins).\n2. On a single-user local server only: the session default set via `pad_set_workspace`.\n3. On a single-user local server only: the CWD-linked workspace from `.pad.toml`.\n\nA multi-user/remote server does **not** persist a session default — pass `workspace` explicitly on every call. If none resolves, the action returns a structured `no_workspace` error with `available_workspaces`, on both the local and the remote transport.\n\n## Update flow: read first, then patch\n\nFor `pad_item.action: update`, the server merges your patch with the item's current state. Pass only the fields you want to change. When changing `status`, ALWAYS include a `comment` explaining why — it builds the audit trail that helps the team understand history.\n\n## One error code you must not retry\n\nErrors come back as a structured envelope with a `code`. Most failures are worth a retry after you fix something, and a `server_error` may be transient. `stored_state_unreadable` is neither.\n\nIt means the ITEM'S STORED DATA cannot be decoded — your input was fine. Today it fires when `note` / `decide` would append to an `implementation_notes` / `decision_log` value that is not a list of entries. The operation is refused precisely because completing it would overwrite that value. The refusal is fully deterministic, so retrying — immediately or after a backoff — fails identically every time and changes nothing.\n\nWhen you see it: tell the user which item is affected, and stop. Whether you can inspect the bad value depends on which layer is broken — if the item's whole `fields` blob fails to parse, `action: get` hands it back as a raw string; if one structured key is at fault, you won't see it at all, because the blob is normalized on this surface and a value that doesn't decode is dropped from the top-level arrays. A human can always read it with `pad item show \u003cref\u003e --format json`. Do not route around the refusal by writing the field some other way; that is the write that caused it.\n\n## Project conventions\n\nWorkspaces can declare conventions (e.g. \"run `make test` before PR\", \"use conventional commit format\"). The bootstrap blob gives you two views:\n\n- `conventions` — full bodies of the always-on (`trigger=always`) rules. Follow these unconditionally.\n- `convention_index` — METADATA ONLY (`ref`, `title`, `trigger`, `role`; no bodies) for **every** active convention, including the triggered ones whose bodies are NOT in `conventions`. This is your map of what triggered rules exist.\n\nBefore performing meaningful work with a specific trigger (e.g. `on-implement` before writing code), consult `convention_index`: if it lists entries for that trigger, pull their bodies on demand; if it lists none, skip the query.\n\n```\npad_item.action: list, collection: \"conventions\", status: \"active\"\n```\n\nFilter by trigger (`always`, `on-implement`, `on-task-complete`, etc.) when relevant — the `convention_index` triggers tell you which filters are worth running.\n\n`\"conventions\"` above is the DEFAULT collection slug and a workspace may have renamed it, in which case that literal returns nothing while `convention_index` still lists entries — the bootstrap payload resolves by declaration, not by name. When the two disagree, address the items by the `ref`s the index gave you, or find the collection with `pad_collection.action: list`. The same applies to `\"playbooks\"`; `pad_playbook` resolves by declaration and is unaffected.\n\n## Pushes and the session monitor (security note)\n\nPad can push an item into a Claude Code session (`pad push`, or the web item view's push composer). That is terminal instruction injection by design, so receiving is **consent-gated** (PLAN-2613, since v0.15.0): a session receives pushes only after it has connected (`/pad:connect` in the plugin, or a repo-level `push.auto_arm = true` in `.pad.toml` — which a per-user `auto_arm = false` in `~/.pad/config.toml` vetoes), and pushes are self-addressed only — the sender is always the receiving session's own user. This MCP connection is not a session: it cannot arm one, receive a push, or run the monitor, and the `pad_item` / `pad_project` tools expose no push action. If a user asks you to \"push\" something to their terminal, tell them it happens from their own terminal (`pad push \u003cref\u003e -m \"...\"` — the sending session need not be connected, the receiving ones must have consented); do not try to emulate it by writing comments or instructions into items.\n\n## Adding a workspace to this connection\n\nIf the user references a workspace this connection can't see (you'll get a 403 from workspace tools, or the workspace won't appear in `pad_workspace.list`), tell the user you can't see that workspace with your current permissions, then walk them through how to grant access: open Pad in their browser → switch to that workspace → avatar menu → \"Connect project...\" A 6-digit claim code will appear. Have them paste it back in chat, then call `pad_workspace.claim` with `{workspace: \"\u003cslug\u003e\", code: \"\u003c6 digits\u003e\"}`. The workspace joins this connection's allow-list and stays until the user revokes it via `/console/connected-apps`. No re-auth required.\n\nFor brand-new workspaces, `pad_workspace.create` with `{name: \"\u003cname\u003e\"}` (and optional `template`) creates the workspace AND auto-adds it to this connection's allow-list in one call — no claim code needed. Only works when the connection currently carries the \"may create workspaces\" grant — granted at consent time, or enabled later on the connections page. If the grant is present and set to false, the create is **refused with a 403 and no workspace is made** — retrying won't help and neither will the claim flow, since there is nothing to claim. Tell the user this connection isn't permitted to create workspaces, and offer them the two ways forward: create the workspace themselves in the browser and grant access with a claim code, or re-authorize this connection with \"Let this app create new workspaces\" enabled (`/console/connected-apps` can also flip it on an existing connection).\n\n## New workspace: offer to set it up\n\nThe bootstrap blob carries `needs_onboarding: bool` — true when the workspace has zero user-created items (template seeds don't count). When it's true, **lead with an active offer before anything else**: *\"This workspace is brand new and isn't set up yet. Want me to set it up? I'll ask a few quick questions and adapt it to your project.\"*\n\nThis is an **offer, not an auto-run** — wait for the user to say yes before running onboarding. If they accept, run the `onboard` playbook (use the `pad_onboard` prompt, or load the body via `pad_playbook` `action: get`, `ref: onboard`). If they decline, or already declined earlier in the session, respect that and skip the offer. The flag flips to false the moment any item exists, so it won't nag past first setup.\n\n## Built-in updates: mention once\n\nThe bootstrap blob may carry `builtin_updates: int` (absent when there are none): how many of the conventions and playbooks Pad ships have newer text in Pad's library than this workspace's copy. When it is present, mention it **once per session**, in one line, then carry on. **Never apply an update yourself**: a person reviews each one and accepts it or not.\n\n## Multi-step workflows\n\nFour prompts ship with the server: `pad_plan`, `pad_ideate`, `pad_retro`, `pad_onboard`. Use them when the user wants help planning, brainstorming, retrospecting, or onboarding into a workspace — they encode the multi-step Pad-aware playbook for each.\n" + "instructions": "Pad is a project tracker for developers and AI agents — issues (TASK, BUG), plans (PLAN), ideas (IDEA), docs (DOC), conventions, comments, and dependencies. Use this server when a user mentions:\n\n- Issue refs like `TASK-5`, `BUG-12`, `PLAN-3`, `IDEA-8` — they are stable, human-readable IDs and the canonical way to address items. Use them, never slugs; they are what audit trails and PR titles show.\n- Tasks / issues / items / plans / progress / \"what's on my plate\" / \"what to work on next\" / standup / changelog / retrospective.\n- Project conventions, decision records, or \"how should this team do X.\"\n\nIf the user is asking general code questions with no project-management thread, you don't need this server.\n\n## Tool surface (v0.77)\n\nTen resource × action tools, plus `pad_set_workspace`. Eleven tools total.\n\nInputs are validated strictly: an undeclared top-level key is rejected with a structured `validation_failed` naming it, never accepted and silently dropped.\n\n- `pad_item` — Items: create / update / delete / get / list / move / restore / link / unlink / deps / star / unstar / starred / comment / list-comments / edit-comment / delete-comment / backlinks / bulk-update / note / decide / export / import / history / remind / ack-reminder / claim / release. On create/update, field values may be passed as a `fields` OBJECT (the same shape reads return, e.g. `{\"status\":\"done\",\"effort\":\"l\"}`) — it merges into the same path as the dedicated params and `field: [\"key=value\"]`; the same key in two places with CONFLICTING values is refused, not silently resolved. `list` accepts `unparented: true` to keep items with no parent or implements relationship (mutually exclusive with `parent`). `list` results are SUMMARY-shaped by default on both transports — no content bodies; pass `full: true` for complete bodies (token-expensive), or prefer `get` for a single item's body. `update` field writes are a server-side field-level merge (only the keys you set change); pass `expected_seq` for optimistic concurrency — the `seq` you last read, which is on every item AND every list summary — and a stale value fails with a structured 409 `update_conflict` whose details carry `actual_seq` to retry with. PREFER IT over `expected_updated_at`, which cannot tell two writes inside one second apart; that one still works, and if you send both, seq decides. A token cannot see a browser tab's unsaved edits, so `content` sent WITH one is refused with 409 `content_pending_flush` while any exist; re-reading will not clear it. Wait for the editor to save, or pass `overwrite_pending_edits: true` to replace them. `content_state: \"superseded_set_aside\"` is different and wins when both apply: an editor upgrade set aside edits no tab can restore, so EVERY content write is refused (token or not; `details.set_aside_rows`) and waiting never clears it. Tell the user, or pass `overwrite_pending_edits: true` to discard them. Writing `content` while a browser tab has the item open routes the markdown through that live document, and the stored copy is updated only by a later collab-snapshot flush — usually from the tab that applied it, though any such write updates the row, and nothing guarantees one happens: the 200 echoes the content you SENT and carries `warnings.content_outcome: \"applied_pending_flush\"`, which describes that WRITE — the content went to the document, not the row — rather than being a live reading of the row, which a concurrent flush may already have updated. A `get` (or a `list` with `full: true` — a default list carries no content at all) before such a flush lands reads the stored copy and answers with the PREVIOUS content, which is the lag rather than a failed write, so do not re-send on the strength of it. You do not have to infer that from the write, and you will also see it when someone ELSE's tab holds the unflushed edits and you wrote nothing: a read that serves a body the server knows is behind the live document carries `content_state: \"applied_pending_flush\"` — same value as the write warning, different question (what the ROW is, not what your REQUEST did). Treat it as re-read later, never as re-send, and do not wait on it in a loop: the server normally recovers the stored copy itself about a minute after the last tab leaves the item, but that is not guaranteed (a recovery can fail, and an operator can turn it off), and otherwise the row catches up only when a tab next opens the item. The stored form may also not be byte-identical to what you sent, since the markdown round-trips through the editor (bullet markers, emphasis characters, list numbering and blank-line runs normalise; already-canonical markdown survives unchanged), so compare on meaning rather than bytes. `move` changes an item's COLLECTION within its workspace: system metadata (implementation notes, decision log, linked PR) survives it, and any field value the target schema has no home for is dropped AND reported in the move's activity entry — check there rather than assuming a move is lossless. A carried unique-field collision is dropped, named in `warnings.not_unique`. Three system keys — `implementation_notes`, `decision_log`, `convention` — cannot be set through `field` on update or move; the call is refused with `validation_failed`, naming the key and the write path that does maintain it (`note`, `decide`, and library activation respectively). `github_pr` is refused as well (BUG-2696): a `field` value arrived as a string, so the PR data was stored double-encoded and no link appeared. Its writer is `pad github link` / `unlink`, which needs a local git checkout, and there is no PR-link action on this surface yet, so treat linking a PR as something to hand to a human rather than a call to retry. On `create` they are refused too (BUG-3163), with the same `validation_failed`: create the item first, then use `note` / `decide` on it; convention metadata comes from library activation. `history` returns read-only item version metadata (newest-first), bounded to the NEWEST 50 versions by default (max 300 — pass `limit` to change the window); pass `full: true` to include each version's resolved content body (token-expensive). There is no `offset`: versions are stored as reverse patches, so only a newest-end window is cheap to reconstruct. Unassign or detach with the `clear_assigned_user` / `clear_agent_role` / `clear_parent` booleans; an empty `assign` / `role` / `parent` does NOT clear. `remind` / `ack-reminder`: a fired reminder shows in `pad_project` next / ready (the delivery path on an instance with no webhook) until acknowledged, and one on a completed item is hidden there. `claim` / `release`: claim an item before you work it; a loser's 409 is `lease_held` (pick another, don't retry), and a lease bumps neither `updated_at` nor `seq`. The holder defaults to your agent name, and `pad_project` next / ready leave out items another holder has leased. `edit-comment` / `delete-comment` take a `comment_id` from `list-comments` (whose rows carry `edited`); only a comment's author may edit it. Correct a comment in place rather than appending a correction. Deleting a comment that has replies leaves a placeholder (`deleted: true`, empty body) so the replies keep their parent; editing, replying to or reacting to it answers 409 `comment_deleted`. (Two older forms still work and are not deprecated: `field: [\"assigned_user_id=\"]` on either transport, and a direct `assigned_user_id: \"\"` param over remote `/mcp` only — prefer the boolean, which is the only one this schema advertises.)\n\n**List filters must name a field (v0.75).** A `pad_item` `list` filter on a key no collection in scope declares, and no item stores, is refused with `validation_failed` (\"invalid list filter\"), where it used to return an empty list; a stored undeclared key still filters. Check the schema; don't retry.\n\n**Library words in a blank workspace (v0.67).** A brand-new blank workspace lists one convention trigger (`always`) and one scope (`all`). Activating a library entry, or creating a convention or playbook with a trigger or scope the library itself uses, adds that word to the collection's options and says so in `warnings.options_added`. A trigger you invent is still refused until the workspace owner adds it to the collection's schema.\n\n**App attribution (v0.65).** An item an installed app created, a comment an app wrote and a history row an app's write made carry `via_app` (the install id) and `via_app_name` (the app's name). On an item they name the app that CREATED it, not the last writer. They are absent for anything a person or an agent wrote.\n\n**Relation fields (v0.31).** A `relation` value may be a UUID, an issue ref (`COLO-3`) or the target's EXACT TITLE, tried in that order (a title that is also a ref resolves as the ref). A title matches only inside the declared collection, among items you can see; found only elsewhere, it is refused naming that collection; several matches are `ambiguous`. Full rules: docs/mcp.md.\n\nReads carry a `relation_targets` member beside `fields`: field key → `{id, ref, title}`, so you can render a relation without a request per value. `fields` still holds the canonical id, which is what you write back. An entry with an `id` and NO `ref`/`title` means the target is gone **or** you may not see it — the two are deliberately indistinguishable, so do not render it as either \"deleted\" or \"hidden\"; \"unavailable\" is the honest word. An entry with `stored_as_text: true` differs: the stored value is not UUID-shaped, so it was never an id (an imported title, legacy text). Render it as text, not as unavailable.\n\n**`multi_relation` fields (v0.33).** An ORDERED LIST of references, each resolved like a `relation` (UUID, ref, or exact title in the declared collection). Declare one as `owners:multi_relation:people`; the target collection is required. Rules: `[]` means absent; a blank element is refused by index; order is part of the value; duplicates are refused after resolution (`duplicate_referent`); any failing element refuses the whole write; `required` needs one resolved element; a cross-workspace copy drops the whole value (in `warnings.dropped_fields`). `relation_targets` holds an ARRAY of `{id, ref, title}` in stored order (`id`-only where unresolved); scalar keys stay single objects. Full rules: docs/mcp.md.\n\n- `pad_workspace` — Workspaces: list / members / invite / storage / audit-log / create / claim / deleted / restore.\n- `pad_collection` — Collections: list / create / update / delete / list-archived / restore. `delete` archives: the collection and its items leave every view, and `restore` brings them back. An `update` that removes a field or a select option still in use answers with `warnings.orphaned`: tell the user how many items keep the removed value.\n- `pad_project` — Project intelligence: dashboard / next / ready / stale / standup / changelog / report / activity. Use `ready` for the ranked top items to work on next (blocked work is left out) and `stale` for items needing attention; `activity` to catch up on what other agents/users changed since you last worked (non-streaming feed with item refs + change details).\n- `pad_role` — Agent roles: list / create / update / delete.\n- `pad_search` — Full-text search across items: query.\n- `pad_playbook` — Invokable procedures: list / get / run / match. Use `run` to bind args against a playbook's declared spec and get the rendered body back; side-effect-free. `run` refuses a playbook whose status isn't `active` (a draft still being authored) with a `playbook_not_active` error — pass `allow_draft: true` to override. Both `run` and `get` echo the playbook's `status`. Both may also carry `content_state` (`\"applied_pending_flush\"`, or `\"superseded_set_aside\"` as under `pad_item`), meaning the BODY you are about to execute is behind the item's live collaborative document — an editor holds unflushed edits, so the steps may be superseded. It is a reason to re-read or to ask, not a reason to refuse to run; the body is still the best the server has. `match` finds a playbook from text.\n- `pad_library` — Convention + playbook library (the global catalog of pre-built entries workspaces activate): list / get / activate.\n- `pad_attachment` — Read-only attachment metadata: list / show. `list` enumerates a workspace's attachments (filter by item / category / collection / attached / unattached); `show` returns one attachment's MIME, size, filename, and ETag via a HEAD request. Uploading and general file downloads stay CLI-only; bounded image bytes are available through the attachment resource below.\n- `pad_meta` — Server introspection: server-info / version / tool-surface / bootstrap. The `bootstrap` action returns one-shot workspace context (user + collections + always-on conventions + a metadata-only `convention_index` of every active convention + roles + playbook metadata + dashboard + recent activity).\n- `pad_set_workspace` — Load workspace context; response embeds the bootstrap blob so you load context in one call. Whether it also pins a session default: see Workspace context below. Takes `workspace: \u003cslug\u003e` only (no `action`).\n\nFor the ten resource × action tools, always pass `action` as a top-level field. Per-action required parameters are documented in each tool's description.\n\n## Resources are cheaper than tool calls\n\nRead these directly when you need workspace state (described in the resource listings): `pad://workspaces`, `pad://workspace/{ws}/dashboard`, `.../collections`, `.../items` (use `pad_item` `list` to filter), `.../items/{ref}` (markdown), `.../attachments/{id}` (images only, at most 1 MiB, as base64 `thumb-md`), `.../bootstrap` (the same payload as `pad_meta` `bootstrap`), and `pad://_meta/version`. A host can prefetch them once per session.\n\nLoad the bootstrap resource once per workspace and reuse its collections, conventions, roles, and playbook metadata. Refresh it after switching workspaces, after changing those configuration surfaces, when Pad reports stale schema/context, or when the user asks. For changing work state, read the affected item or use a targeted project tool instead of fetching the whole bootstrap again.\n\n## Workspace context\n\nEvery action that operates within a workspace accepts an optional `workspace` parameter. Resolution order:\n\n1. Explicit `workspace` argument on the call (always wins).\n2. On a single-user local server only: the session default set via `pad_set_workspace`.\n3. On a single-user local server only: the CWD-linked workspace from `.pad.toml`.\n\nA multi-user/remote server does **not** persist a session default — pass `workspace` explicitly on every call. If none resolves, the action returns a structured `no_workspace` error with `available_workspaces`, on both the local and the remote transport.\n\n## Update flow: read first, then patch\n\nFor `pad_item.action: update`, the server merges your patch with the item's current state. Pass only the fields you want to change. When changing `status`, ALWAYS include a `comment` explaining why — it builds the audit trail that helps the team understand history.\n\n## One error code you must not retry\n\nErrors come back as a structured envelope with a `code`. Most failures are worth a retry after you fix something, and a `server_error` may be transient. `stored_state_unreadable` is neither.\n\nIt means the ITEM'S STORED DATA cannot be decoded — your input was fine. Today it fires when `note` / `decide` would append to an `implementation_notes` / `decision_log` value that is not a list of entries. The operation is refused precisely because completing it would overwrite that value. The refusal is fully deterministic, so retrying — immediately or after a backoff — fails identically every time and changes nothing.\n\nWhen you see it: tell the user which item is affected, and stop. Whether you can inspect the bad value depends on which layer is broken — if the item's whole `fields` blob fails to parse, `action: get` hands it back as a raw string; if one structured key is at fault, you won't see it at all, because the blob is normalized on this surface and a value that doesn't decode is dropped from the top-level arrays. A human can always read it with `pad item show \u003cref\u003e --format json`. Do not route around the refusal by writing the field some other way; that is the write that caused it.\n\n## Project conventions\n\nWorkspaces can declare conventions (e.g. \"run `make test` before PR\", \"use conventional commit format\"). The bootstrap blob gives you two views:\n\n- `conventions` — full bodies of the always-on (`trigger=always`) rules. Follow these unconditionally.\n- `convention_index` — METADATA ONLY (`ref`, `title`, `trigger`, `role`; no bodies) for **every** active convention, including the triggered ones whose bodies are NOT in `conventions`. This is your map of what triggered rules exist.\n\nBefore performing meaningful work with a specific trigger (e.g. `on-implement` before writing code), consult `convention_index`: if it lists entries for that trigger, pull their bodies on demand; if it lists none, skip the query.\n\n```\npad_item.action: list, collection: \"conventions\", status: \"active\"\n```\n\nFilter by trigger (`always`, `on-implement`, `on-task-complete`, etc.) when relevant — the `convention_index` triggers tell you which filters are worth running.\n\n`\"conventions\"` above is the DEFAULT collection slug and a workspace may have renamed it, in which case that literal returns nothing while `convention_index` still lists entries — the bootstrap payload resolves by declaration, not by name. When the two disagree, address the items by the `ref`s the index gave you, or find the collection with `pad_collection.action: list`. The same applies to `\"playbooks\"`; `pad_playbook` resolves by declaration and is unaffected.\n\n## Pushes and the session monitor (security note)\n\nPad can push an item into a Claude Code session (`pad push`, or the web item view's push composer). That is terminal instruction injection by design, so receiving is **consent-gated** (PLAN-2613, since v0.15.0): a session receives pushes only after it has connected (`/pad:connect` in the plugin, or a repo-level `push.auto_arm = true` in `.pad.toml` — which a per-user `auto_arm = false` in `~/.pad/config.toml` vetoes), and pushes are self-addressed only — the sender is always the receiving session's own user. This MCP connection is not a session: it cannot arm one, receive a push, or run the monitor, and the `pad_item` / `pad_project` tools expose no push action. If a user asks you to \"push\" something to their terminal, tell them it happens from their own terminal (`pad push \u003cref\u003e -m \"...\"` — the sending session need not be connected, the receiving ones must have consented); do not try to emulate it by writing comments or instructions into items.\n\n## Adding a workspace to this connection\n\nIf the user references a workspace this connection can't see (you'll get a 403 from workspace tools, or the workspace won't appear in `pad_workspace.list`), tell the user you can't see that workspace with your current permissions, then walk them through how to grant access: open Pad in their browser → switch to that workspace → avatar menu → \"Connect project...\" A 6-digit claim code will appear. Have them paste it back in chat, then call `pad_workspace.claim` with `{workspace: \"\u003cslug\u003e\", code: \"\u003c6 digits\u003e\"}`. The workspace joins this connection's allow-list and stays until the user revokes it via `/console/connected-apps`. No re-auth required.\n\nFor brand-new workspaces, `pad_workspace.create` with `{name: \"\u003cname\u003e\"}` (and optional `template`) creates the workspace AND auto-adds it to this connection's allow-list in one call — no claim code needed. Only works when the connection currently carries the \"may create workspaces\" grant — granted at consent time, or enabled later on the connections page. If the grant is present and set to false, the create is **refused with a 403 and no workspace is made** — retrying won't help and neither will the claim flow, since there is nothing to claim. Tell the user this connection isn't permitted to create workspaces, and offer them the two ways forward: create the workspace themselves in the browser and grant access with a claim code, or re-authorize this connection with \"Let this app create new workspaces\" enabled (`/console/connected-apps` can also flip it on an existing connection).\n\n## New workspace: offer to set it up\n\nThe bootstrap blob carries `needs_onboarding: bool` — true when the workspace has zero user-created items (template seeds don't count). When it's true, **lead with an active offer before anything else**: *\"This workspace is brand new and isn't set up yet. Want me to set it up? I'll ask a few quick questions and adapt it to your project.\"*\n\nThis is an **offer, not an auto-run** — wait for the user to say yes before running onboarding. If they accept, run the `onboard` playbook (use the `pad_onboard` prompt, or load the body via `pad_playbook` `action: get`, `ref: onboard`). If they decline, or already declined earlier in the session, respect that and skip the offer. The flag flips to false the moment any item exists, so it won't nag past first setup.\n\n## Built-in updates: mention once\n\nThe bootstrap blob may carry `builtin_updates: int` (absent when there are none): how many of the conventions and playbooks Pad ships have newer text in Pad's library than this workspace's copy. When it is present, mention it **once per session**, in one line, then carry on. **Never apply an update yourself**: a person reviews each one and accepts it or not.\n\n## Multi-step workflows\n\nFour prompts ship with the server: `pad_plan`, `pad_ideate`, `pad_retro`, `pad_onboard`. Use them when the user wants help planning, brainstorming, retrospecting, or onboarding into a workspace — they encode the multi-step Pad-aware playbook for each.\n" } diff --git a/docs/mcp.md b/docs/mcp.md index 549a63b17..ae4d7aba9 100644 --- a/docs/mcp.md +++ b/docs/mcp.md @@ -4,7 +4,7 @@ Moved verbatim from CLAUDE.md (TASK-3485), where it had pushed the file past Cla ## MCP server -Pad runs as a local Model Context Protocol server so Claude Desktop / Cursor / Windsurf can call non-interactive `pad` commands as tools. The same catalog is also served as remote MCP over HTTP at `/mcp` (Streamable HTTP): always on Pad Cloud, and on a self-hosted install off by default until an admin turns it on (`GET/PUT /api/v1/admin/mcp` above; OAuth plus PATs when the issuer URL is https, PATs only on http; operator docs in `docs/deployment.md`). The tool surface is a **hand-curated catalog** (currently v0.76) in `internal/mcp/catalog_*.go` — one ToolDef per resource (`pad_item`, `pad_workspace`, `pad_collection`, `pad_project`, `pad_role`, `pad_search`, `pad_meta`, `pad_playbook`, `pad_library`, `pad_attachment`) with an `action` enum dispatching to underlying CLI commands. v0.33 (PLAN-2857 U4 / TASK-2999) adds a **`multi_relation`** field type — an ORDERED LIST of references, each element resolving through the same UUID→ref→exact-title ladder a scalar `relation` uses, declared through the DSL as `owners:multi_relation:people` (third part = target collection; a bare `owners:multi_relation` is refused at parse time rather than minting a field no write can satisfy). The TYPE is additive — every rule is reachable only through a field whose schema says `multi_relation`, which no existing schema can contain — so the bump is owed by the READ shape: `relation_targets[key]` now carries EITHER the scalar object v0.31 emitted OR a JSON **ARRAY** of those objects, in stored order and one per stored element (an `id`-only entry for an element that names nothing, so a position lines up with the same position in `fields`). A scalar entry is byte-identical to v0.31's — pinned against a literal, not against another call into the same code — so a consumer with no such fields sees nothing new, while one that acquires such a field must handle the array. ONE map, not a parallel `multi_relation_targets` key: the field's type already says which shape to expect. Value rules, all NEW rather than inherited because scalar `relation` had nothing coherent to inherit (see BUG-3028 — a required scalar relation WAS satisfied by `""`, with three stored spellings of "no target", until v0.40 converged it on this same key-absent rule): exactly ONE stored form for none, the key ABSENT, with `[]` normalising to it at the write door; an empty or whitespace-only ELEMENT REFUSED rather than skipped, naming its index; `required` meaning >=1 RESOLVED element; order part of the value; duplicates REFUSED with a new `duplicate_referent` reason, detected AFTER resolution because two elements naming one item are usually different strings. Any failing element refuses the WHOLE write — never a partial list — and a cross-workspace copy drops the value whole, reported once, so an import can never change an element count. **0.32 is RESERVED for PR #1337**, which claims it and was opened first; this unit took 0.33 rather than contest the number, so 0.32 may be skipped if #1337 is abandoned — a gap is cheaper than a collision resolved under merge pressure. v0.31 (PLAN-2857 U6 / TASK-2996) lets a `relation` value be an EXACT TITLE, scoped to the collection that field declares, alongside the UUID and ref v0.29 accepted; adds a `relation_targets` member to reads hydrating each stored id to `{id, ref, title}`; and makes the `fields` DSL take the target collection slug as a relation's third part. The first two are additive — a title is a THIRD spelling, and `relation_targets` is `omitempty` — so the bump is owed by the DSL: `fields="owner:relation"` used to be ACCEPTED and is now REFUSED, because the old parser put the third part into `Options` for every type and therefore built a relation with NO target, a field every subsequent write refused with `target_missing`. Scoping is the point: a title unique only workspace-wide refuses and names the collection searched, and two matches inside the declared collection get their own `ambiguous` reason rather than `not_found`, which would state the opposite of what happened. The ladder is UUID, then ref, then title, so an item literally TITLED `COLO-3` is unreachable by title while the ref resolves. An id-only `relation_targets` entry means the target is GONE **or** the caller may not SEE it — the two are made indistinguishable deliberately, matching the write side's `wrong_collection`→`not_found` collapse, so no consumer may render it as either. v0.30 (BUG-2870) makes one `--field key=value` entry mean ONE thing at every door. Six sites parsed that entry independently — `item create`, `item list`, `item update`, `item move` and `item copy` in `cmd/pad`, plus `ingestFieldKVP` on the remote door — in four spellings, so `field:[" effort=l"]` stored an undeclared field literally named `" effort"` through the CLI while the remote door trimmed and wrote `effort`: the same call storing two different keys, decided by the transport. All six now call `items.SplitFieldEntry`, under two deliberately asymmetric rules — a padded KEY is REFUSED everywhere (trimming silently retargets the write to a field the caller did not type), a VALUE is carried VERBATIM everywhere (trimming reinterprets a caller's bytes, and on a text field the padding is content). The catalog's conflict pass is re-grounded on the same change, since its rules were derived from that trimming: comparisons are RAW, a padded entry is refused in the pass rather than skipped, `parseFieldArray`'s refusal is PROPAGATED rather than swallowed (it had no second owner on the no-`fields` path, where four existing refusals were landing as successes), and canonicalization and the re-emission path are gone — nothing rewrites a caller's key any more. v0.29 (PLAN-2857 / TASK-2878) makes a `relation` field value have to NAME A LIVE ITEM in the collection that field declares. `internal/items` only ever checked the SHAPE of a relation ("must be a string") because that package is DB-free, so any string at all was accepted and stored and no client could render it honestly. Every write door now refuses a value that names nothing, names an item in the WRONG collection, sits in a field declaring no target collection, or is a SLUG (deliberate divergence from `ResolveItem` — a slug is neither an ID nor stable). A CARRIED value, already on the item and asserted by nobody, is never refused: within a workspace it resolves and survives; across a boundary it is dropped without a lookup and reported in `warnings.dropped_fields`. v0.28 (IDEA-2641) adds two ADDITIVE `pad_item` actions — `remind` (arm a one-shot reminder at an RFC3339 `remind_at` instant) and `ack-reminder` (acknowledge a fired one by `reminder_id`). Agents already RECEIVED reminders, since the poll surface is `pad_project.next` / `ready`; what was missing is the other half — deferring work is exactly when an agent knows it wants to be asked again. A bare date is refused rather than read as midnight. Re-arm and disarm stay CLI-only until a listing action exists to discover an id. v0.27 (BUG-2850) typed field values server-side, carried the `fields` object with its JSON types intact, named undeclared keys back in `warnings.undeclared_fields`, and replaced the per-site conflict guards with one check that refuses two names for one target in a single call. v0.26 (IDEA-2756) makes `pad_workspace.create` REFUSE with a 403 when the calling OAuth connection's grant carries `may_create_workspaces=false` — that consent checkbox previously gated only the post-creation auto-add, so a connection whose user declined it created workspaces anyway — invisible to it when the connection carried an explicit allow-list, visible when it carried the `all_current_workspaces` wildcard; the consent mismatch is the defect in both cases. The same gate covers `POST /workspaces/import` (a second door onto `store.ImportWorkspace` → `CreateWorkspace`, with no MCP action today). No escape-hatch param, deliberately: the gate expresses the USER's consent decision, so only the user can lift it — by re-authorizing, or by enabling the flag on the existing connection at `/console/connected-apps`. v0.25 (TASK-2657 / BUG-2702) makes `pad_library.activate` resolve its destination collection from the target's declared artifact kind rather than the literal `conventions` / `playbooks` slugs, and surfaces a lookup ERROR instead of falling back. v0.24 (#1066) makes the `pad_item` `fields` OBJECT a real write form on create/update — reads return `fields` as a native object (BUG-991 normalization), and writing that shape back was a silent no-op: not a declared param, no `additionalProperties`, so it was accepted, never mapped by `BuildCLIArgs`, and dropped while the PATCH still bumped `updated_at`. The alias merges into the same path as `field: ["key=value"]` / the dedicated params (`catalog_item_fields.go`), refusing the same key in two places with conflicting values; and input validation is now STRICT across all catalog tools — an undeclared top-level key fails with a structured `validation_failed` naming it, instead of being silently dropped (a small documented compat list survives: pad_item's v0.16 `assigned_user_id` / `agent_role_id` remote clear form). One bump covers both halves — they are one contract change. v0.23 (BUG-2627 part 2 + BUG-2675, PR #1166) refuses raw `field` setters naming system-metadata keys in `fields_patch` on every transport (`github_pr` exempt on UPDATE only — the sole remote writer, itself broken — until v0.47 closed it: BUG-2696) and adds the retry-hostile `stored_state_unreadable` error code. v0.22 (BUG-2674, PR #1165) makes reserved metadata survive a move and refuses `field` setters naming those keys on move/copy — see `internal/mcp/version.go` for both full entries. v0.21 (BUG-2608) bounds `pad_item.action=history`, which was unbounded on every surface: the `limit` param now covers it (default 50, max 300 — the NEWEST N versions, with no `offset`, because reverse-patch storage makes only a newest-end window cheap to reconstruct), applied in the CATALOG action so it lands on both transports, and summary mode now asks the server to skip patch resolution (`?summary=true`) instead of resolving every body and discarding it. Additive param bump — `limit` already existed and nothing changed shape. v0.20 (BUG-2302 + BUG-2305, one bump) adds explicit MCP tool annotations (`readOnlyHint`/`destructiveHint`/`idempotentHint` derived from the catalog's own write-shape knowledge, fixing read-only tools that advertised `destructiveHint:true`) and makes `pad_item.list` summary-shaped on the REMOTE /mcp transport too (the hand-written `dispatchItemList` projects via `cli.ToItemSummaries`; `full=true` opts back into complete bodies) — see `internal/mcp/version.go` for the authoritative per-version changelog. Post-0.20 without a bump (BUG-2304): `item backlinks` / `item history` / `project report` gained HTTP route coverage — they were advertised but answered "not yet implemented over HTTP transport" — and a catalog↔route parity test (`dispatch_http_parity_test.go`) now drives every catalog action and fails on any future advertised-but-unrouted action; no names, enums, or shapes changed, hence no bump. v0.19 adds a `clear_parent` boolean to `pad_item` — the canonical, schema-discoverable way to detach an item from its parent, backed by a new `--clear-parent` bareword flag on `pad item update` (BUG-2078). v0.18 adds `clear_assigned_user` / `clear_agent_role` booleans to `pad_item` — the canonical, schema-discoverable way to unassign, backed by new `--clear-assigned-user` / `--clear-agent-role` bareword flags on `pad item update` (IDEA-2584). Update-only, deliberately asymmetric with create. v0.17 carries the empty-string clear to the LOCAL STDIO transport, which shells out to the CLI — `cmd/pad/cmd_item.go` now lifts `assigned_user_id` / `agent_role_id` onto their columns instead of into the fields blob, on create and update (BUG-2583). v0.16 makes an empty-string `assigned_user_id` / `agent_role_id` CLEAR the assignment instead of being silently dropped, so an MCP agent can finally unassign an item (TASK-2571). v0.15 adds the `pad_item.list` `unparented` boolean, mutually exclusive with `parent`, for items with no parent or implements relationship (TASK-2096). v0.2 introduced the catalog (PLAN-969 / TASK-981); v0.3 added `pad_playbook`, `pad_meta.action: bootstrap`, `pad_set_workspace`'s embedded-bootstrap response, and the `pad://workspace/{ws}/bootstrap` resource (PLAN-1377 / TASK-1380); v0.4 trimmed the bootstrap payload by ~40% (PLAN-1410) — slim `BootstrapCollection` + `BootstrapRole` projections (no UUIDs/timestamps/settings; nested `schema` object; redundant labels omitted), removed top-level `recent_activity` duplicate, dropped convention `slug`, and added a `BootstrapDashboard` wrapper that caps five sub-arrays (`attention`, `recent_activity`, `active_items`, `active_plans`, `by_role`) at 5 entries each with parallel `*_overflow_count` fields. The pre-catalog v0.1 cmdhelp leaf walker is retired. +Pad runs as a local Model Context Protocol server so Claude Desktop / Cursor / Windsurf can call non-interactive `pad` commands as tools. The same catalog is also served as remote MCP over HTTP at `/mcp` (Streamable HTTP): always on Pad Cloud, and on a self-hosted install off by default until an admin turns it on (`GET/PUT /api/v1/admin/mcp` above; OAuth plus PATs when the issuer URL is https, PATs only on http; operator docs in `docs/deployment.md`). The tool surface is a **hand-curated catalog** (currently v0.77) in `internal/mcp/catalog_*.go` — one ToolDef per resource (`pad_item`, `pad_workspace`, `pad_collection`, `pad_project`, `pad_role`, `pad_search`, `pad_meta`, `pad_playbook`, `pad_library`, `pad_attachment`) with an `action` enum dispatching to underlying CLI commands. v0.33 (PLAN-2857 U4 / TASK-2999) adds a **`multi_relation`** field type — an ORDERED LIST of references, each element resolving through the same UUID→ref→exact-title ladder a scalar `relation` uses, declared through the DSL as `owners:multi_relation:people` (third part = target collection; a bare `owners:multi_relation` is refused at parse time rather than minting a field no write can satisfy). The TYPE is additive — every rule is reachable only through a field whose schema says `multi_relation`, which no existing schema can contain — so the bump is owed by the READ shape: `relation_targets[key]` now carries EITHER the scalar object v0.31 emitted OR a JSON **ARRAY** of those objects, in stored order and one per stored element (an `id`-only entry for an element that names nothing, so a position lines up with the same position in `fields`). A scalar entry is byte-identical to v0.31's — pinned against a literal, not against another call into the same code — so a consumer with no such fields sees nothing new, while one that acquires such a field must handle the array. ONE map, not a parallel `multi_relation_targets` key: the field's type already says which shape to expect. Value rules, all NEW rather than inherited because scalar `relation` had nothing coherent to inherit (see BUG-3028 — a required scalar relation WAS satisfied by `""`, with three stored spellings of "no target", until v0.40 converged it on this same key-absent rule): exactly ONE stored form for none, the key ABSENT, with `[]` normalising to it at the write door; an empty or whitespace-only ELEMENT REFUSED rather than skipped, naming its index; `required` meaning >=1 RESOLVED element; order part of the value; duplicates REFUSED with a new `duplicate_referent` reason, detected AFTER resolution because two elements naming one item are usually different strings. Any failing element refuses the WHOLE write — never a partial list — and a cross-workspace copy drops the value whole, reported once, so an import can never change an element count. **0.32 is RESERVED for PR #1337**, which claims it and was opened first; this unit took 0.33 rather than contest the number, so 0.32 may be skipped if #1337 is abandoned — a gap is cheaper than a collision resolved under merge pressure. v0.31 (PLAN-2857 U6 / TASK-2996) lets a `relation` value be an EXACT TITLE, scoped to the collection that field declares, alongside the UUID and ref v0.29 accepted; adds a `relation_targets` member to reads hydrating each stored id to `{id, ref, title}`; and makes the `fields` DSL take the target collection slug as a relation's third part. The first two are additive — a title is a THIRD spelling, and `relation_targets` is `omitempty` — so the bump is owed by the DSL: `fields="owner:relation"` used to be ACCEPTED and is now REFUSED, because the old parser put the third part into `Options` for every type and therefore built a relation with NO target, a field every subsequent write refused with `target_missing`. Scoping is the point: a title unique only workspace-wide refuses and names the collection searched, and two matches inside the declared collection get their own `ambiguous` reason rather than `not_found`, which would state the opposite of what happened. The ladder is UUID, then ref, then title, so an item literally TITLED `COLO-3` is unreachable by title while the ref resolves. An id-only `relation_targets` entry means the target is GONE **or** the caller may not SEE it — the two are made indistinguishable deliberately, matching the write side's `wrong_collection`→`not_found` collapse, so no consumer may render it as either. v0.30 (BUG-2870) makes one `--field key=value` entry mean ONE thing at every door. Six sites parsed that entry independently — `item create`, `item list`, `item update`, `item move` and `item copy` in `cmd/pad`, plus `ingestFieldKVP` on the remote door — in four spellings, so `field:[" effort=l"]` stored an undeclared field literally named `" effort"` through the CLI while the remote door trimmed and wrote `effort`: the same call storing two different keys, decided by the transport. All six now call `items.SplitFieldEntry`, under two deliberately asymmetric rules — a padded KEY is REFUSED everywhere (trimming silently retargets the write to a field the caller did not type), a VALUE is carried VERBATIM everywhere (trimming reinterprets a caller's bytes, and on a text field the padding is content). The catalog's conflict pass is re-grounded on the same change, since its rules were derived from that trimming: comparisons are RAW, a padded entry is refused in the pass rather than skipped, `parseFieldArray`'s refusal is PROPAGATED rather than swallowed (it had no second owner on the no-`fields` path, where four existing refusals were landing as successes), and canonicalization and the re-emission path are gone — nothing rewrites a caller's key any more. v0.29 (PLAN-2857 / TASK-2878) makes a `relation` field value have to NAME A LIVE ITEM in the collection that field declares. `internal/items` only ever checked the SHAPE of a relation ("must be a string") because that package is DB-free, so any string at all was accepted and stored and no client could render it honestly. Every write door now refuses a value that names nothing, names an item in the WRONG collection, sits in a field declaring no target collection, or is a SLUG (deliberate divergence from `ResolveItem` — a slug is neither an ID nor stable). A CARRIED value, already on the item and asserted by nobody, is never refused: within a workspace it resolves and survives; across a boundary it is dropped without a lookup and reported in `warnings.dropped_fields`. v0.28 (IDEA-2641) adds two ADDITIVE `pad_item` actions — `remind` (arm a one-shot reminder at an RFC3339 `remind_at` instant) and `ack-reminder` (acknowledge a fired one by `reminder_id`). Agents already RECEIVED reminders, since the poll surface is `pad_project.next` / `ready`; what was missing is the other half — deferring work is exactly when an agent knows it wants to be asked again. A bare date is refused rather than read as midnight. Re-arm and disarm stay CLI-only until a listing action exists to discover an id. v0.27 (BUG-2850) typed field values server-side, carried the `fields` object with its JSON types intact, named undeclared keys back in `warnings.undeclared_fields`, and replaced the per-site conflict guards with one check that refuses two names for one target in a single call. v0.26 (IDEA-2756) makes `pad_workspace.create` REFUSE with a 403 when the calling OAuth connection's grant carries `may_create_workspaces=false` — that consent checkbox previously gated only the post-creation auto-add, so a connection whose user declined it created workspaces anyway — invisible to it when the connection carried an explicit allow-list, visible when it carried the `all_current_workspaces` wildcard; the consent mismatch is the defect in both cases. The same gate covers `POST /workspaces/import` (a second door onto `store.ImportWorkspace` → `CreateWorkspace`, with no MCP action today). No escape-hatch param, deliberately: the gate expresses the USER's consent decision, so only the user can lift it — by re-authorizing, or by enabling the flag on the existing connection at `/console/connected-apps`. v0.25 (TASK-2657 / BUG-2702) makes `pad_library.activate` resolve its destination collection from the target's declared artifact kind rather than the literal `conventions` / `playbooks` slugs, and surfaces a lookup ERROR instead of falling back. v0.24 (#1066) makes the `pad_item` `fields` OBJECT a real write form on create/update — reads return `fields` as a native object (BUG-991 normalization), and writing that shape back was a silent no-op: not a declared param, no `additionalProperties`, so it was accepted, never mapped by `BuildCLIArgs`, and dropped while the PATCH still bumped `updated_at`. The alias merges into the same path as `field: ["key=value"]` / the dedicated params (`catalog_item_fields.go`), refusing the same key in two places with conflicting values; and input validation is now STRICT across all catalog tools — an undeclared top-level key fails with a structured `validation_failed` naming it, instead of being silently dropped (a small documented compat list survives: pad_item's v0.16 `assigned_user_id` / `agent_role_id` remote clear form). One bump covers both halves — they are one contract change. v0.23 (BUG-2627 part 2 + BUG-2675, PR #1166) refuses raw `field` setters naming system-metadata keys in `fields_patch` on every transport (`github_pr` exempt on UPDATE only — the sole remote writer, itself broken — until v0.47 closed it: BUG-2696) and adds the retry-hostile `stored_state_unreadable` error code. v0.22 (BUG-2674, PR #1165) makes reserved metadata survive a move and refuses `field` setters naming those keys on move/copy — see `internal/mcp/version.go` for both full entries. v0.21 (BUG-2608) bounds `pad_item.action=history`, which was unbounded on every surface: the `limit` param now covers it (default 50, max 300 — the NEWEST N versions, with no `offset`, because reverse-patch storage makes only a newest-end window cheap to reconstruct), applied in the CATALOG action so it lands on both transports, and summary mode now asks the server to skip patch resolution (`?summary=true`) instead of resolving every body and discarding it. Additive param bump — `limit` already existed and nothing changed shape. v0.20 (BUG-2302 + BUG-2305, one bump) adds explicit MCP tool annotations (`readOnlyHint`/`destructiveHint`/`idempotentHint` derived from the catalog's own write-shape knowledge, fixing read-only tools that advertised `destructiveHint:true`) and makes `pad_item.list` summary-shaped on the REMOTE /mcp transport too (the hand-written `dispatchItemList` projects via `cli.ToItemSummaries`; `full=true` opts back into complete bodies) — see `internal/mcp/version.go` for the authoritative per-version changelog. Post-0.20 without a bump (BUG-2304): `item backlinks` / `item history` / `project report` gained HTTP route coverage — they were advertised but answered "not yet implemented over HTTP transport" — and a catalog↔route parity test (`dispatch_http_parity_test.go`) now drives every catalog action and fails on any future advertised-but-unrouted action; no names, enums, or shapes changed, hence no bump. v0.19 adds a `clear_parent` boolean to `pad_item` — the canonical, schema-discoverable way to detach an item from its parent, backed by a new `--clear-parent` bareword flag on `pad item update` (BUG-2078). v0.18 adds `clear_assigned_user` / `clear_agent_role` booleans to `pad_item` — the canonical, schema-discoverable way to unassign, backed by new `--clear-assigned-user` / `--clear-agent-role` bareword flags on `pad item update` (IDEA-2584). Update-only, deliberately asymmetric with create. v0.17 carries the empty-string clear to the LOCAL STDIO transport, which shells out to the CLI — `cmd/pad/cmd_item.go` now lifts `assigned_user_id` / `agent_role_id` onto their columns instead of into the fields blob, on create and update (BUG-2583). v0.16 makes an empty-string `assigned_user_id` / `agent_role_id` CLEAR the assignment instead of being silently dropped, so an MCP agent can finally unassign an item (TASK-2571). v0.15 adds the `pad_item.list` `unparented` boolean, mutually exclusive with `parent`, for items with no parent or implements relationship (TASK-2096). v0.2 introduced the catalog (PLAN-969 / TASK-981); v0.3 added `pad_playbook`, `pad_meta.action: bootstrap`, `pad_set_workspace`'s embedded-bootstrap response, and the `pad://workspace/{ws}/bootstrap` resource (PLAN-1377 / TASK-1380); v0.4 trimmed the bootstrap payload by ~40% (PLAN-1410) — slim `BootstrapCollection` + `BootstrapRole` projections (no UUIDs/timestamps/settings; nested `schema` object; redundant labels omitted), removed top-level `recent_activity` duplicate, dropped convention `slug`, and added a `BootstrapDashboard` wrapper that caps five sub-arrays (`attention`, `recent_activity`, `active_items`, `active_plans`, `by_role`) at 5 entries each with parallel `*_overflow_count` fields. The pre-catalog v0.1 cmdhelp leaf walker is retired. cmdhelp is still consumed at dispatch time — `BuildCLIArgs` reads individual command schemas to translate the catalog's snake_case input map into CLI args. cmdhelp no longer drives tool naming or count. @@ -18,7 +18,7 @@ pad mcp status # Install state across supported clients ``` Surface: -- **Tools:** the v0.76 catalog — ten resource × action tools (`pad_item`, `pad_workspace`, `pad_collection`, `pad_project`, `pad_role`, `pad_search`, `pad_meta`, `pad_playbook`, `pad_library`, `pad_attachment`) plus `pad_set_workspace` (takes a `workspace` slug only — no action enum). The ten resource × action tools take `action: ` to choose what they do. `pad_item` (v0.19) exposes `clear_parent` as the canonical parent-detach (update only); (v0.18) exposes `clear_assigned_user` / `clear_agent_role` booleans as the canonical unassign (update only); (v0.17) treats an empty-string `assigned_user_id` / `agent_role_id` as a clear on BOTH transports via `field: ["assigned_user_id="]` — the direct param form is remote-only, since it isn't schema-declared and stdio's BuildCLIArgs drops unknown keys (IDEA-2584); v0.16 fixed remote only; (v0.15) adds the `unparented` list parameter; v0.14 added `history` + `expected_updated_at`. `pad_project` (v0.13) adds `ready` (actionable backlog) + `stale` (items needing attention); `pad_project.activity` (v0.12) is the non-streaming, bounded activity feed — catch up on what other agents/users changed since you last worked. `pad_attachment` is the read-only attachment-metadata surface — `list`/`show` (upload/download/view stay CLI-only). `pad_library` is the convention+playbook library surface — `list`/`get`/`activate`. `pad_playbook` is the playbook surface from PLAN-1377 — `list`/`get`/`run` mirror the CLI's `pad playbook` subcommands; `run` is side-effect-free and returns the body + bound args for the agent to execute. v0.4 (PLAN-1410) didn't change the tool/action surface; it trimmed the bootstrap JSON those tools/resources return — see the Stability contract subsection below for details. +- **Tools:** the v0.77 catalog — ten resource × action tools (`pad_item`, `pad_workspace`, `pad_collection`, `pad_project`, `pad_role`, `pad_search`, `pad_meta`, `pad_playbook`, `pad_library`, `pad_attachment`) plus `pad_set_workspace` (takes a `workspace` slug only — no action enum). The ten resource × action tools take `action: ` to choose what they do. `pad_item` (v0.19) exposes `clear_parent` as the canonical parent-detach (update only); (v0.18) exposes `clear_assigned_user` / `clear_agent_role` booleans as the canonical unassign (update only); (v0.17) treats an empty-string `assigned_user_id` / `agent_role_id` as a clear on BOTH transports via `field: ["assigned_user_id="]` — the direct param form is remote-only, since it isn't schema-declared and stdio's BuildCLIArgs drops unknown keys (IDEA-2584); v0.16 fixed remote only; (v0.15) adds the `unparented` list parameter; v0.14 added `history` + `expected_updated_at`. `pad_project` (v0.13) adds `ready` (actionable backlog) + `stale` (items needing attention); `pad_project.activity` (v0.12) is the non-streaming, bounded activity feed — catch up on what other agents/users changed since you last worked. `pad_attachment` is the read-only attachment-metadata surface — `list`/`show` (upload/download/view stay CLI-only). `pad_library` is the convention+playbook library surface — `list`/`get`/`activate`. `pad_playbook` is the playbook surface from PLAN-1377 — `list`/`get`/`run` mirror the CLI's `pad playbook` subcommands; `run` is side-effect-free and returns the body + bound args for the agent to execute. v0.4 (PLAN-1410) didn't change the tool/action surface; it trimmed the bootstrap JSON those tools/resources return — see the Stability contract subsection below for details. - **Resources:** `pad://workspace/{ws}/items/{ref}`, `pad://workspace/{ws}/items`, `pad://workspace/{ws}/dashboard`, `pad://workspace/{ws}/collections`, `pad://workspace/{ws}/attachments/{id}` (bounded base64 image via `thumb-md`; non-images and image bytes over 1 MiB (pre-base64) rejected), `pad://workspace/{ws}/bootstrap` (one-shot workspace overview — user + collections + always-on conventions + roles + playbook metadata + dashboard + recent activity), plus the server-wide `pad://_meta/version`. - **Prompts:** `pad_plan`, `pad_ideate`, `pad_retro`, `pad_onboard` — multi-step workflows lifted from `skills/pad/SKILL.md`. @@ -26,7 +26,7 @@ Surface: **Stability contract.** Two version constants live in `internal/mcp/version.go`, advertised in the handshake under `capabilities.experimental.padCmdhelp` and `capabilities.experimental.padToolSurface`: - `CmdhelpVersion` (currently `"0.1"`) — the cmdhelp CLI help-tree contract. Bump when CLI flag/arg schemas change incompatibly. -- `ToolSurfaceVersion` (currently `"0.76"`) — the MCP tool catalog contract. Bump when tool names, action enums, or parameter shapes change incompatibly. **v0.76** (TASK-1809) makes a `pad_item` `claim` / `release` with no `holder` hold the lease under the caller's agent name (the `X-Pad-Agent` the CLI sends), else the account's email, where it was the email alone: several agents on one account silently shared one lease, a second claim answering 200 by refreshing the first. It now answers 409 `lease_held` naming the first agent. `pad_project.action=next` / `ready` leave out items whose live lease a claim by the caller would lose (same identity, the claim's own predicate, filtered before the cap of three; reminders are not filtered). Remote /mcp sends no agent name, so its default is still the email (TASK-3495). A lease taken before the upgrade is another holder's to the same agent for up to its TTL. BEHAVIOR bump on the v0.70 grounds. **v0.75** (BUG-3480) makes `pad_item.action=list` on both transports refuse a filter key no schema in scope declares and no item in scope stores (400 `validation_failed`, "invalid list filter ..."), where it answered an empty list, and refuse a key that is not a field key, which the store used to drop (answering the unfiltered list). BEHAVIOR bump on the v0.43 / v0.29 grounds; see the item list endpoint bullet under API. **v0.74** (TASK-2188) makes `pad_collection.action=update` answer, on both transports, with an `omitempty` `warnings.orphaned` [{field, option?, items}] naming each field, or select option, its schema removed that live items still hold. Nothing is refused. ADDITIVE, the v0.67 grounds; 0.73 is BUG-3480's. **v0.72** (TASK-2189) adds `pad_collection` `list-archived` (read-only) and `restore` (owner-only, by slug or id), backed by the new `GET /workspaces/{ws}/archived-collections` and `POST /workspaces/{ws}/archived-collections/{ref}/restore`: an agent's archive is recoverable by an agent. ADDITIVE. **v0.71** (TASK-3462 U3a) adds an `omitempty` `builtin_updates` count to the bootstrap on every door that returns it (the conventions and playbooks Pad ships whose library text changed since the workspace's copy, among the items the caller sees in full), and a server-instructions section telling the agent to mention it once and never apply an update itself. ADDITIVE. **v0.70** (BUG-3453) makes `pad_project.action=next` / `ready` fill any slot the existing tiers leave empty with ordinary open items from non-system collections that declare `priority` or `severity` (an initial status like `new` counts), ranked below every item admitted before, so a full list is unchanged and a moved-in backlog with no priorities is no longer "nothing ready". BEHAVIOR bump on the v0.49 grounds. **v0.69** (TASK-2314) makes every REMOTE route that needs a workspace and lacks one answer `no_workspace` with `available_workspaces` and a hint, as stdio always did, where it answered `validation_failed` "workspace is required"; the single-workspace default now runs before the `assign` / `role` resolvers. BEHAVIOR bump on the v0.42 / v0.45 grounds. **v0.68** (BUG-3448) makes the item resource render a structured field as compact JSON instead of Go's map syntax, keep a number above 2^53 to its digits and render a JSON null as `null`; the agent projection stops rounding large numbers. BEHAVIOR bump on the v0.62 / v0.64 grounds: an output shape changed, no name, enum or param moved; scalar fields render as before. **v0.67** (BUG-3446) lets a create in a system conventions or playbooks collection ADD a trigger/scope word the library itself uses to the select options instead of refusing it, so `pad_library.activate` and B3's literal create succeed in a `blank` workspace, and adds an `omitempty` `warnings.options_added` to the create result on both transports. A word the library does not use is refused as before. ADDITIVE. **v0.66** (BUG-2136) makes `pad_workspace.action=invite` always create a pending invitation, never add an existing account directly; see `internal/mcp/version.go`. **v0.65** (TASK-3413, SPEC-6 U9c) adds `omitempty` `via_app` and `via_app_name` to items an installed app CREATED (items.created_via_app, never the last app writer), comments an app wrote and version rows an app's write made, on both transports (`pad_item` get, list summary and full, comments, history summary and full). The name is the app's bot display name, else its origin, and survives uninstall. ADDITIVE. **v0.64** (BUG-3379) adds an `omitempty` `imported: true` to comments, attachment rows and version rows a workspace import wrote, on both transports (`pad_item` comments, `pad_attachment.list`, and `pad_item.history` with `full: true`; history summary rows and attachment `show` do not carry it): import keeps the export's author strings and uploader ids verbatim, and the flag says they were not verified here. ADDITIVE. **v0.63** (TASK-3321) adds an `omitempty` `actor_name` to every `pad_item.action=history` summary row on both transports, the display name of who made the change, where rows said only `user` or `agent`. ADDITIVE. **v0.62** (BUG-3326) makes remote /mcp `pad_set_workspace` embed the workspace bootstrap, as stdio always did: the in-process bootstrap resource read, run as the token's user under the same scope/consent perimeter, so a workspace the caller cannot read embeds nothing. ADDITIVE; no name, enum or param changed, and stdio is unchanged. **v0.61** (TASK-3321 U0b) marks `pad_workspace` destructiveHint:true and openWorldHint:true, because `invite` sends an email to an arbitrary address, and `pad_playbook` openWorldHint:true, because `match` sends text to the decision provider. Annotation-only BEHAVIOR bump on the v0.20 grounds; every other tool's block is unchanged. **v0.60** (TASK-2198 U4) makes `content_state: "applied_pending_flush"` clear ON ITS OWN on every door that carries it: after the item's collab room closes (or a one-minute sweep finds it dormant) the server rebuilds the body from the op-log and stores it, moving `seq` (a held `expected_seq` then answers `update_conflict` instead of `content_pending_flush`) and adding a `system` / `recovery` version. BEHAVIOR bump on the v0.59 / v0.39 grounds; no name, enum or param changed. Not a guarantee (failures, set-aside rows, `PAD_MATERIALIZE=off`), so re-read later, never re-send, still stands. **v0.59** (BUG-3252, tombstone ruled over cascade) makes `pad_item.action=delete-comment` on a comment with replies SUCCEED, leaving a tombstone (body emptied, author and timestamps kept, additive `deleted: true`) its replies stay under; it is removed when its last reply is deleted. `edit-comment` on a tombstone answers 409 `comment_deleted` on every transport. BEHAVIOR bump on the v0.58 grounds; `comment_has_replies` stays classified for older servers. **v0.58** (BUG-3252) makes `pad_item.action=delete-comment` on a comment that still has replies answer 409 `comment_has_replies` (details `comment_id`, `reply_count`) on every transport instead of `server_error`: `comments.parent_id` has no ON DELETE, so the delete failed the FK inside the store. Nothing is deleted either way. Tombstone was then ruled over cascade; v0.59 replaced this refusal with it. BEHAVIOR bump on the v0.45 grounds. **v0.57** (TASK-2695) adds `pad_item` `edit-comment` (ref, comment_id, message) and `delete-comment` (ref, comment_id) on all three transports, backed by the item-scoped routes `PATCH/DELETE /workspaces/{ws}/items/{ref}/comments/{id}`, which answer 404 unless the comment is on `ref` and otherwise run the workspace routes' handlers (edit author-only, delete item-edit). CLI: `pad item comment-edit` / `comment-delete`, refused against a server without the `item_scoped_comment_writes` capability. Every serialised comment gains a derived `edited` bool (updated_at > created_at), and `pad item comments` prints each comment's id. ADDITIVE. **v0.56** (BUG-3244) gives `content_state` a second value, `superseded_set_aside`, on every MCP door that carries it (`pad_item` get / full list, `pad_playbook` run, the item resource's line above the body): edits an editor schema-version rebuild set aside, which opening the item will NOT restore, so the resource line and the `content_pending_flush` hint (chosen by `details.set_aside_rows`) name `pad item set-aside` and `overwrite_pending_edits` instead. ADDITIVE bump: no name, enum or param changed, but an agent branching on the one-word vocabulary meets a word whose remedy differs. Reading or discarding the rows alone is not on the catalog. **v0.55** (BUG-2659) sends `pad_item.action=search`'s `collection` to /search as typed, and /search resolves it exact-first per workspace in scope (the item routes' resolver). In a workspace holding both `task` and `tasks`, `collection: "task"` now answers from `task` instead of `tasks`; every other workspace is unchanged, because the shorthand still resolves server-side. Stdio reaches it through the CLI, which sends the name as typed only to a server advertising `search_collection_resolution`. BEHAVIOR bump on the v0.36 / v0.40 grounds. **v0.54** (BUG-3217) keeps a `fields` number's literal through MCP on both transports (mcp-go's argument decode rounded anything above 2^53, and stdio's `--field` stringify carried the rounded value), and REFUSES a `fields` number beside a `field` entry for the same key when they differ as exact numbers — two values that differ only above 2^53 used to collapse into one rounded write; a matching pair (3.0 beside n=3) still collapses. BEHAVIOR bump on the v0.48 grounds. **v0.53** (BUG-2819) adds `filename_source` (caller / normalised / substituted / derived / unknown) to every `pad_attachment.action=list` row on both transports, because a stored filename cannot say whether the caller sent it or the server substituted it. ADDITIVE, the v0.28 / v0.13 disposition; `show` does not carry it, and `mcp_audit_log.tool_name_source` reaches no catalog action. Rows written before it read `unknown`, never `caller`. **v0.52** (BUG-2367 item 4) refuses a move or copy (every migrate door) that would change an item between open, done and abandoned unless the caller names the destination done field. Only the STATE is compared, so two values that both mean done carry. Move answers 400 `state_change_requires_value` with details `{field, options, from, to}`; bulk move puts it in a `failed[]` row; the copy answers 400 `validation_error` with the same sentence; the preflight emits a needs_value row with reason `state_change`, which the web dialog picker renders. A destination with no done select field is exempt. BEHAVIOR bump. **v0.51** (BUG-2367) stops every migrate door (single move, bulk move, cross-workspace copy and its preflight) carrying a value into a field the destination marks `computed` (preflight drop reason `target_computed`) or a value that collides on a destination `unique_scope` field. Provenance decides, the TASK-2878 rule: a CARRIED collision is dropped and reported (`not_unique`), a supplied override or injected default that collides is refused 409 `conflict`, and a required field emptied by the drop is refused as required, which is the existing needs_value route. Before it, single move answered 500 on the indexed `invocation_slug`, bulk move leaked the SQL error, and an unindexed unique field stored a duplicate. Reporting is additive and omitempty: `warnings.not_unique` [{key, value, holder?, message}] on the move response, bulk `updated[]` rows and the copy response, and a `detail` sentence on the preflight's dropped row. `holder` is present only when the caller may see that item, so the drop is not an existence oracle. BEHAVIOR bump on the v0.43 / v0.29 grounds. **v0.50** (BUG-3014) adds an ADDITIVE `omitempty` `stored_as_text: true` to a `relation_targets` entry whose stored value is not UUID-shaped (a title a bundle import carried verbatim, or legacy free text). Such a value was never an id and used to hydrate as a plain id-only entry, which reads as "gone or hidden"; an id-only entry without the flag keeps that meaning, and a UUID-shaped value, resolved or not, is byte-identical to v0.49. The predicate is syntactic, decided from the stored bytes and never from a lookup, so it discloses nothing, and deliberately not coupled to the resolver ladder. The CLI prints `"" (text, not a reference)` and the web chip says the same. **v0.49** (BUG-2410) makes `pad_project.action=report` with no `collections` param leave out SYSTEM collections (`Collection.IsSystem`: Conventions and Playbooks), which were counted in Insights' created, WIP and status totals; naming one explicitly still includes it. BEHAVIOR bump on the v0.40 / v0.42 grounds: a default call's content changed for every caller (web Insights, print, `pad project report`, both MCP transports, all through the one store rule). **v0.48** (BUG-3163) makes `pad_item.action=create` REFUSE a `field` / `fields` entry naming any reserved metadata key (`implementation_notes`, `decision_log`, `github_pr`, `convention`) on every transport, with 400 `validation_error`, creating nothing: create was the last door that stored one, as a string no extractor reads. Library activation, its one system writer, moves to an additive typed `convention` create member (not on the catalog; `pad_library.activate` is unchanged), and the CLI verifies from the stored fields that it landed, because an older server ignores the member and answers 201. BEHAVIOR bump on the v0.47 grounds. **v0.47** (BUG-2696) makes `pad_item.action=update` REFUSE a field setter naming `github_pr` on every transport (400 `validation_error` naming `pad github link` / `unlink`), closing the exemption v0.23 left: that door stored the PR as an unreadable string, so no link ever rendered. The writer is a new additive, typed update member (`github_pr` object + `clear_github_pr`) used by `pad github link` / `unlink` / `project reconcile`, deliberately NOT on the catalog (a remote PR-link action waits on the catalog-trim decision). BEHAVIOR bump; item create is BUG-3163. **v0.46** (BUG-3156) makes `pad_item.action=bulk-update` over stdio and remote REFUSE, per item, a status or priority change on an item whose collection does not declare that field, writing nothing for that item: the answer WebMCP has given since v0.44, so the three transports agree. Rows keep each transport's shape (stdio `failed[]` with `validation_error`, remote `results[]` with `validation_failed` and the server message in `hint`). The mechanism is the update door's new `refuse_undeclared_fields` member, which both bulk-update transports set; `pad_item.update` does not, and still accepts-and-warns. A server that predates the member ignores it, which is the old accept-and-warn. BEHAVIOR bump on the v0.44 / v0.43 grounds. **v0.45** (BUG-2829) reports an HTTP 413 as `too_large` on BOTH transports, with the server's own code in `details.reason`, where it used to be `server_error`: three deliberate caps are reachable from the catalog (a title rename's link cascade, an oversized outbox event, an oversized artifact import), and the old code read as transient and invited a retry that fails identically. Remote maps 413 in `classifyHTTPStatusKind`; stdio gets it from a structured marker the CLI root writes for any 413, and `too_large` joins `allowedStructuredErrorCodes`, which a test now proves contains every code any CLI marker writer emits. BEHAVIOR bump on the v0.42 grounds; no name, enum or param shape changed. **v0.44** (BUG-3154) makes `pad_item.action=bulk-update` over the WebMCP browser transport REFUSE, per item, a status or priority change on an item whose collection does not declare that field: the item lands in the bulk response's `failed` array with `validation_error` naming the collection and field, nothing is written, and the rest of the call applies. The door is `POST /items/bulk` (`set-priority`, and `move` with a `status`, with or without a `collection`, where the target's schema decides), where the request carries an operation and a value and the SERVER chooses the key; it used to store an orphan field and report the item updated. BEHAVIOR bump on the v0.43 / v0.40 grounds. The transports disagreed after it, stated rather than implied: stdio and remote issued a per-item PATCH, the single-item update door, which ACCEPTED the key with `warnings.undeclared_fields` (v0.27), until v0.46 converged them. **v0.43** (BUG-2379) makes `pad_item.action=move` REFUSE a field override naming a field the destination schema does not declare, with 400 `malformed_override` — the same check, code and message the cross-workspace copy already used. BEHAVIOR bump on the v0.40 / v0.29 grounds: a write door refuses a call it used to accept, where it used to store the key as an orphan field no schema renders. Create and update still ACCEPT undeclared keys with `warnings.undeclared_fields` (v0.27), because callers round-trip the whole fields blob; an override is a fresh assertion about the destination schema, not round-tripped state. **v0.42** (BUG-3142 + BUG-3147) changes the error CODE a LOCAL STDIO caller receives for two failure families that used to arrive as retryable `server_error`: an argv refusal (cobra/pflag: unknown flag, arg count, …) is now `validation_failed` with its message kept, and a 429 on any command is now `rate_limited` with `details.retry_after_seconds`, via the structured marker line the CLI writes at its root. It also stops the refusal that caused most of the first family: `BuildCLIArgs` now emits flags first and the positionals behind `--`, so free text starting with `-` (`item search "-ship it"`) is no longer parsed as a flag. BEHAVIOR bump; no name, enum or param shape changed, and the remote transport is untouched. **v0.41** (PLAN-3114 U5 / TASK-3120) adds a `match` action to `pad_playbook`: given free `text`, a Choice question over the workspace's ACTIVE playbooks plus a reserved `"none"` option returns the best match's ref (or `"none"`), confidence, per-option probabilities and the model. No provider configured → 404 `decision_provider_unavailable`; a provider error or an out-of-set answer → 502 `decision_provider_error`. Pure ADDITIVE bump (new action + param, nothing existing moved), read-only and side-effect-free. **v0.40** (BUG-3028) gives a scalar `relation` ONE stored form for "no target", the key ABSENT, converging on multi_relation's rule. A blank (`""` or whitespace) a write SETS — create, `fields_patch`, a changed value in full `fields`, a move/copy override — is normalised to absent before validation, so a `required` relation is refused as required (a patch blanking it now gets the answer deleting it always got). A legacy blank a write only CARRIES — an untouched key under `fields_patch` (normalised by the store under its write lock, via `ItemUpdate.BlankRelationKeys`), an unchanged value in full `fields`, move, copy, artifact import — is normalised after validation and never refused. An empty list filter on a scalar relation key of a collection-scoped list (`owner=`) matches all three spellings. BEHAVIOR bump; no shape change. Workspace import (`store.ImportWorkspace`) still stores blobs verbatim; its legacy blanks normalise on the next write. **v0.39** (BUG-3133) refuses `pad_item.update` that sets content WITH a version token (`expected_seq` / `expected_updated_at`) while the item's op-log holds content-bearing rows above its flush watermark, with 409 `content_pending_flush` (details `ref`, `pending_rows`). BEHAVIOR bump on the v0.35 / v0.36 grounds, carrying one additive param: `overwrite_pending_edits` lifts it, on the API, the CLI (`--overwrite-pending-edits`; `pad item edit --force` sets it on the save) and MCP alike, because an agent must be able to clear the refusal without a browser. The token guards the ROW and a tab's unflushed typing is not in it, so the write used to replace those edits — through the applier's setContent with a tab open, and by the direct path's op-log prune, which DELETES them, with none. Its own code rather than `update_conflict` because re-reading returns the same row and seq. A write without a token, without content, or to an item with nothing pending is unchanged, except that a direct write now reports `warnings.pruned_pending_edits` (additive, omitempty) when its prune deleted such rows. The check runs in the write's own tx; on the direct path it is under the item lock and appendMu and exact, on the applier path a tab can still type in the one server hop between the check and setContent. (v0.37 and v0.38 — the `agent` projection on `pad_item.get` and `claim` / `release` — are in `internal/mcp/version.go`; this paragraph had stopped at v0.36.) **v0.36** (BUG-3082) stops a REF-SHAPED `relation` value falling back to matching by item NUMBER when its prefix names a collection that is LIVE in the workspace; such a value is now `not_found`. BEHAVIOR bump on the v0.35 / v0.30 / v0.29 / v0.16 grounds — no tool name, action enum or param shape changed, but a write door refuses a value it used to accept. It finishes v0.29: that entry closed free-text corruption ("red" resolving to whatever is slugged `red` today) and left the same corruption open for anything shaped like a REF, which is the spelling the docs tell callers to prefer. Item numbers are workspace-unique and sequential ACROSS collections, so `CONVE-1` and `SECRE-1` are never both real — the fallback dropped the prefix, matched on the number alone, and landed on an item that was usually inside the field's declared collection, so the wrong-collection check above it passed and NOTHING was raised: a caller wrote `CONVE-1`, the item stored a different item's UUID, and the write answered 201 with the substitution visible only in `relation_targets`. The predicate is about the PREFIX rather than the item because a collection RENAME changes its prefix and a relation already written as the old ref must keep resolving (BUG-2873) — that ref's prefix names nothing afterwards, so the fallback still fires for it, while a prefix that IS live and simply holds no item at that number is the caller naming a real collection that does not contain what they said. A SOFT-DELETED collection counts as absent IN THAT PREDICATE, for the same reason a renamed one does — a claim about the fallback only: the exact-prefix lookup ahead of it never filtered on the collection’s own `deleted_at`, so an item whose collection was soft-deleted still matches THERE and never reaches the predicate. That is left alone rather than made consistent, because it cannot retarget — the downstream collection check refuses it. RESIDUAL, stated rather than implied and pinned by a test: a ref pasted from ANOTHER workspace whose prefix also names no collection here still resolves by number, because nothing in the value distinguishes it from a rename's leftover. No escape hatch, for v0.29's reason. Out of scope and unchanged: `GetItemByRef`, the navigational read path, where landing on the moved item is the helpful answer. **v0.35** (BUG-3079) makes an injected schema DEFAULT take the same `validateFieldType` check a caller-supplied value takes; one that fails is DISCARDED and named in `warnings.dropped_fields` instead of being stored. BEHAVIOR bump on the v0.30 / v0.29 / v0.16 grounds — no tool name, action enum or param shape changed, but a write door stores something different from what it stored before. Unlike v0.29, which turned an accepted value into a refusal, this turns a stored value into a reported drop: a create that used to land WITH a bad field still lands, without it. What it closes is two doors disagreeing about one value, decided only by who put it there. It also widens `dropped_fields` from the single relation case v0.29 introduced to a field of ANY type. No escape hatch, for v0.29's reason. ONE exception, which is the rule finishing its sentence rather than a carve-out: dropping leaves a REQUIRED field absent, which is exactly what the required check reports, so such a write is refused — naming the default as the cause, because a bare "field is required" points its reader at a request that never mentioned the field. **v0.34** (BUG-3037) adds an `expected_seq` param to `pad_item.action=update` — the STRONG optimistic-concurrency token, preferred over `expected_updated_at`. ADDITIVE (the v0.13 / v0.11 / v0.8 disposition): nothing existing moved and `expected_updated_at` still works. It is needed rather than nice because `updated_at` is stored at ONE-SECOND resolution, so two writes to a row inside one second both match the token and NEITHER conflicts — the loser is accepted and silently overwrites the winner, both callers seeing success. That is the shape of agent traffic, so the token agents were offered could not refuse the race it exists to refuse. `seq` is bumped on every mutation of the row under the write lock. Raising `updated_at`'s resolution instead was measured and REJECTED: the column is TEXT on both dialects and compared LEXICALLY in SQL (the since-cursor read plus eight `ORDER BY` sites), and Go's `RFC3339Nano` omits trailing zeros, so a sub-second value sorts BEFORE a whole-second value of the same second and the cursor would start skipping rows. The read side is what makes the token reachable: `seq` now serialises without `omitempty` on `models.Item` AND on the item SUMMARY shape (`cli.ItemSummary`), which is what `pad_item.list` returns by default since v0.9 — a token absent from the shape a caller reads is a token that caller cannot send. A value below 1 is a 400, not a 409: the server never issues one, so a 409 would read as contention that never clears. **v0.30** (BUG-2870) is a BEHAVIOR bump on the v0.29/v0.27/v0.26/v0.16/v0.10/v0.9 grounds — no tool name, action enum or param shape changed. **Every door refuses a padded KEY now**, and each was accepting it differently: /mcp trimmed it and wrote the declared field, the CLI stored a ghost field beside it — so both refuse something they used to accept. What is /mcp-only is the VALUE half, which it used to trim and type and now passes through to the same validation the CLI has always applied. A caller writing canonical entries sees no difference at either door. A second, separately-noticeable fix rides with it: `detectFieldConflicts` swallowed `parseFieldArray`'s refusal as "the caller owns this error surface", which held only while the sole possible error was a shape error — `reshapeItemFields` returns early with no `fields` object, so on the no-`fields` path (this bug's own path) four existing refusals were landing as successes. No escape hatch, for v0.29's reason: there is no legitimate call this refuses, only calls whose two readings a door used to choose between silently. **v0.29** (PLAN-2857 U1 / TASK-2878) is a BEHAVIOR bump on the v0.27/v0.26/v0.16/v0.10/v0.9 grounds (NOT v0.28's, which was purely additive) — no tool name, action enum, or param shape changed, but a `relation` field value must now name a live item in the collection that field declares, so every write door refuses values it used to store. Refused: names nothing (`not_found`), names an item in the wrong collection, the field declares no target collection (`target_missing`), or the value is a SLUG — a deliberate divergence from `ResolveItem`'s UUID→ref→slug ladder, since a slug is neither an ID nor stable and free text like "red" resolving to whatever is slugged `red` today is exactly the corruption this closes. Ordinary `validation_error`, no new code and no new details key, because stdio classifies errors by matching CLI stderr prose. A CARRIED value — already on the item, asserted by nobody — is never refused, since refusing would make every legacy item un-updatable, un-movable and un-copyable: within a workspace it resolves and SURVIVES, across a workspace boundary it is dropped without a lookup (a source-workspace id cannot mean anything in the destination) and reported through the same `warnings.dropped_fields` channel BUG-2674 established. No escape hatch, deliberately: unlike v0.10's `allow_draft` there is no legitimate call this refuses, and the case with a real claim to leniency is already exempt by provenance rather than by a flag. **v0.28** (IDEA-2641 / GitHub #1010) adds two ADDITIVE `pad_item` actions and two optional params: `remind` arms a one-shot reminder at an RFC3339 `remind_at` INSTANT, and `ack-reminder` acknowledges a fired one by `reminder_id`. Purely additive — nothing existing moved, and a v0.27 consumer that enumerates neither action is unaffected; same disposition as v0.13 / v0.11 / v0.8, which likewise wired existing CLI verbs onto the catalog. Agents already RECEIVED reminders (the poll surface is `pad_project.next` / `ready`, long exposed); what was missing is the half where an agent that defers work can say when it wants to be asked again. `remind_at` REFUSES a bare date rather than reading it as midnight — the `date` schema type accepts `YYYY-MM-DD` so a caller will try it, but a bare date names a 24-hour span and choosing an hour inside it would fire at a time nobody picked. Re-arm and disarm stay CLI-only: both address a reminder by an id the agent would have to list first, and no listing action exists on this surface yet — a door with no handle. **v0.27** (BUG-2850) types field values SERVER-SIDE at all eight validate sites, carries the `fields` object to the remote door with its JSON types intact, accepts undeclared keys while NAMING them in `warnings.undeclared_fields`, and replaces five accreted conflict guards with one canonical pass; the merge refuses several ambiguities it used to resolve silently. (This entry was missing from CLAUDE.md — the 0.27 unit swept `instructions.md` and `README.md` and not this file.) **v0.27** (BUG-2850) types field values server-side at all eight `Validate*` call sites so a declared number/json field is writable from the remote transport at all, carries the `fields` OBJECT with its JSON types intact, names undeclared keys back in `warnings.undeclared_fields` (accepted rather than refused — a census of 1012 items found 14 such keys across 168 live values, so refusing would have broken read-modify-write on items nobody had edited wrongly), and replaces the accreted per-site conflict guards with ONE check over a canonical view of every source; that check refuses ambiguities v0.26 resolved silently, chiefly two names for one target in a single call (`parent`/`plan`, `assign`/`assigned_user_id`, `role`/`agent_role_id`), refused even when the values match because the names address one thing through incomparable vocabularies and the two doors resolved them differently. **v0.26** (IDEA-2756) is a BEHAVIOR bump on the v0.9/v0.16/v0.25 grounds — no tool name, action enum, or param shape changed, but `pad_workspace.create` now refuses a call it used to permit. Closest precedent is v0.10, which likewise turned a server-side gate into a structured refusal; unlike v0.10 there is no `allow_draft`-style override, because the gate encodes a decision the USER made at consent time and a bypass param would be the app overriding its own grant. `POST /workspaces/import` is gated by the same shared helper (import mints a workspace through `store.ImportWorkspace`), though it has no MCP action today. **v0.25** (TASK-2657 / BUG-2702) resolves `pad_library.activate`'s destination collection from the target's declared artifact kind rather than the literal `conventions` / `playbooks` slugs, so activating into a workspace that renamed either collection lands correctly; a lookup ERROR is surfaced rather than silently falling back. **v0.24** (#1066) adds the `fields` OBJECT param to `pad_item` create/update — an alias merging into the same path as `field`/the dedicated params, so the shape reads return is finally a valid write shape; the same key supplied twice with conflicting values is REFUSED (refuse-on-ambiguity, the v0.18/v0.19 disposition), equal duplicates collapse to one write, and non-writer actions refuse a `fields` param loudly. It also makes input validation STRICT for every catalog tool: undeclared top-level keys are rejected with a structured error naming them, instead of being accepted and silently dropped by `BuildCLIArgs` — which is the mechanism that made the `fields` object a session-scoped silent no-op in the first place. Compat carve-out: `pad_item`'s v0.16 `assigned_user_id` / `agent_role_id` remote-transport clear form stays accepted (documented, undeprecated, deliberately never schema-declared). The strict half changes behaviour for inputs that previously "succeeded", but that reliance was indistinguishable from a caller bug (the key never did anything), so the break is the fix; one bump covers both halves. **v0.23** (BUG-2627 part 2 + BUG-2675) refuses system-metadata keys through `fields_patch` on all three doors at once, `github_pr` exempt on update (move/copy still refuse it), and adds the retry-hostile `stored_state_unreadable` code. **v0.22** (BUG-2674) stops `pad_item.action=move` destroying system metadata and refuses `field` setters naming the reserved keys there. **v0.21** bounds `pad_item.action=history` (BUG-2608): the `limit` param now covers it, default 50 / max 300, applied in the CATALOG action so it reaches both transports (HTTP reads the input; stdio gets the CLI's new `--limit` via BuildCLIArgs). The window is the NEWEST N and there is deliberately no `offset` — versions are reverse patches, so only a newest-end window is cheap to reconstruct. Additive param bump; a v0.20 consumer sending no limit now receives the newest 50 rather than every version, which is the fix. Summary mode additionally asks the server to skip patch resolution rather than resolving bodies the dispatcher discards. **v0.19** adds a `clear_parent` boolean to `pad_item` (BUG-2078) — an ADDITIVE param bump, same grounds as v0.18; nothing existing changed shape. The server has supported clearing a parent since BUG-2013 (`extractParentLink` treats a present-but-empty `parent` key in `fields_patch` as detach), but neither client surface could reach it — `--parent ""` was a silent no-op on the CLI and the MCP `parent` param has the same "empty means not provided" convention every other declared string on the tool has. Boolean rather than overloading the empty string, same two reasons as v0.18: keeps that invariant intact for every other param, and only a boolean reaches LOCAL STDIO via `BuildCLIArgs`, mapping to a new `--clear-parent` bareword flag exactly as `clear_assigned_user` maps to `--clear-assigned-user`. Update-only, same asymmetry as v0.18. A simultaneous `parent` + `clear_parent` — including via `field: ["parent=..."]` or the `plan` alias `extractParentLink` also accepts — is REFUSED on both transports, not silently resolved (codex round 1). Also refused, not silently applied: `clear_parent` against a collection whose schema declares its own `parent`/`plan` field — `extractParentLink` skips hierarchy handling entirely for a schema-shadowed key and lets it fall through as an ordinary field write, so the wire shape `{"parent":""}` can no longer distinguish clear-hierarchy intent from a legitimate blank-a-real-field write once it reaches the server; the ambiguity is created at the client surface that accepted `clear_parent`, so that surface refuses rather than guessing (codex round 2). **v0.18** adds `clear_assigned_user` / `clear_agent_role` booleans to `pad_item` (IDEA-2584) — an ADDITIVE param bump (v0.5/v0.6 precedent); nothing existing changed shape and v0.16/v0.17's empty-string forms still work, undeprecated. v0.16 and v0.17 made the clear WORK; nothing advertised it, because the params that do it were never in the catalog, so an agent reading the schema reached for `assign: ""` (a no-op, and it stays one). Booleans rather than declaring the string params, for two reasons: an empty DECLARED string is inert everywhere else on the tool, so giving one a destructive meaning would let a param-padding client silently unassign everything; and only a boolean can reach LOCAL STDIO, since `BuildCLIArgs` emits the CLI's real flags and a param with no flag behind it is dropped — these map to new `--clear-assigned-user` / `--clear-agent-role` bareword flags, exactly as `allow_draft` maps to `--allow-draft`. Update-only, deliberately asymmetric with create (clearing at create has no honest behaviour but a no-op; a test fails if someone adds them there). Server-side it is wiring, not new semantics: `models.ItemUpdate.ClearAssignedUser`/`ClearAgentRole` already existed with store support since BUG-2566. **v0.17** closes the transport gap v0.16 documented: local stdio MCP shells out to the CLI, which wrote `--field assigned_user_id=` into the item's FIELDS BLOB while the column stayed stale and then printed "Updated TASK-9". `cmd/pad/cmd_item.go` now lifts `columnFieldKeys` onto the columns on create AND update, mirroring `liftFieldsToColumns` and its INVARIANT. Two compat changes, ruled separately: non-empty values move to the column and stop writing the blob key (relying on the old behaviour is relying on a shadowing defect), and empty values clear (falls out of the lift, inherits BUG-2566). Existing stray blob keys are left alone — the fix stops minting new ones. Another behaviour-only bump (BUG-2583). **v0.16** lets an MCP agent UNASSIGN an item over the REMOTE transport (TASK-2571). No tool/action/param shape changed — this is a BEHAVIOR bump on the same grounds as v0.9: an empty-string `assigned_user_id` / `agent_role_id`, passed at the top level or as `field: ["assigned_user_id="]`, was silently dropped by two dispatch-path filters (`mapItemUpdate`, `liftFieldsToColumns`) and is now forwarded as a clear-to-NULL. The store has had defined clear semantics for exactly these two columns since BUG-2566 and HTTP inherited them, so this is uniformity restoration — MCP was the only surface with no way to unassign. Compat posture accepted deliberately: today's `""` senders get a no-op, and a no-op is the surprising reading. The empty-string filter on `tags` at the same call site STAYS (codex #547 r3 P2) — `tags: ""` is a corrupt JSONB/TEXT write, not a clear; same-looking guard, opposite justification. `clear_assigned_user` / `clear_agent_role` schema flags (option (b)) deliberately skipped as additive sugar, though codex review reopened the case — the catalog exposes `assign` / `role`, NOT the ID params, so an agent reading the schema still can't discover the clear (IDEA-2584); an empty `assign` is deliberately left inert because every other schema-declared string on that mapper treats empty as not-provided. **Transport scope:** v0.16 fixed the REMOTE /mcp transport only; v0.17 (BUG-2583) closed the local-stdio half at the CLI. **v0.15** adds the `unparented` boolean to `pad_item.list`, mutually exclusive with `parent`, for structural loose-item filtering (TASK-2096). **v0.14** added a `history` action to `pad_item` (read-only item version history — newest-first metadata; content body omitted for token thrift) and an `expected_updated_at` param for optimistic concurrency on `update` (round-trip the `updated_at` you last read; a stale value fails with a structured 409 `code=update_conflict`). The `update` action's field writes are now a server-side field-level MERGE (only the keys you set change) rather than a full-blob replace, closing the concurrent-update lost-write race (IDEA-1480 / TASK-2022) — pure addition to the action enum + param vocabulary; existing `pad_item` actions/params are unchanged and backwards-compatible. **v0.13** adds `ready` + `stale` actions to `pad_project`, mirroring the existing CLI `pad project ready` / `pad project stale` (TASK-2019): `ready` (read-only) returns the actionable backlog — the query-oriented counterpart to `next`, reusing the dashboard's suggested-next logic; `stale` (read-only) lists items needing attention (stalled, blocked, overdue, or out of the active workflow). Both HTTP dispatchers already existed (`dispatch_http_project.go`); this just wires them onto the catalog. `pad project reconcile` stays CLI-only (shells out to `gh` for live PR state — a local-git dependency MCP agents lack). Pure addition of two read-only actions — existing actions unchanged; backwards-compatible for v0.12 consumers that don't enumerate the new actions. **v0.12** adds an `activity` action to `pad_project`, mirroring the new CLI `pad project activity [--limit N] [--actor user|agent] [--since DATE]` (TASK-2018) — the non-streaming, bounded query counterpart to the CLI-only `pad project watch` SSE stream. Read-only snapshot of the workspace's enriched activity feed (item refs, titles, field-level change details) backed by the existing `GET /workspaces/{ws}/activity` endpoint (previously web-UI-only, now extended with a server-side `since` date filter so `limit`/`actor`/`since` behave identically across CLI, stdio MCP, and cloud HTTP), so agents can catch up on what other agents/users did since they last worked. Adds `actor` + `limit` params to the `pad_project` vocabulary (`since` already existed for changelog); pure addition — existing actions unchanged; backwards-compatible for v0.11 consumers that don't enumerate the new action. **v0.11** adds the read-only `pad_attachment` tool (the tenth resource × action tool) with `list` + `show` actions, mirroring the CLI `pad attachment list` / `pad attachment show` (TASK-2017): `list` enumerates a workspace's attachments (optional filters: item / category / collection / attached / unattached / sort / limit / offset); `show` returns one attachment's metadata (MIME, size, filename, ETag, last-modified) via a HEAD request without transferring bytes. Both HTTP dispatchers already existed (`dispatch_http_attachments.go`); this just wires them onto the catalog. Upload / download / view stay CLI-only (filesystem-bound, excluded per the catalog's exclusion rules). Pure addition — existing tools/actions unchanged; backwards-compatible for v0.10 consumers that don't enumerate the new tool. The base64 image RESOURCE for multimodal agents (`pad://workspace/{ws}/attachments/{id}`) shipped later in TASK-2077 (PR #930) as a bounded, image-only resource; TASK-2101 brought it — and the full read-only resource set — to the remote /mcp transport via the in-process `HTTPResourceFetcher`, so resources are no longer local-stdio-only. **v0.10** enforces the draft-playbook gate server-side: `pad_playbook.run` (and the underlying `POST /playbooks/{ref}/run`) now refuses a playbook whose `status` isn't `active` with a structured `playbook_not_active` error, adds an `allow_draft` boolean param (bareword `--allow-draft` on the CLI) as the escape hatch, and echoes the playbook `status` on both the `run` and `get` responses (BUG-2020). **v0.9** makes `pad_item.list` summary-shaped by default (drops item `content`, adds a default result limit of 50 / hard max 300 on MCP; CLI `--full` restores the complete shape) — a behavior change to the tool's return shape, hence the bump, though tool names, action enums, and parameter shapes are unchanged (TASK-2000). **v0.8** adds `restore` + `deleted` actions to `pad_workspace`, mirroring the CLI `pad workspace restore` / `pad workspace deleted` (TASK-1972): `deleted` (read-only) lists the caller's soft-deleted workspaces still inside the 30-day restore window; `restore` (mutating, not destructive, owner-only) un-soft-deletes a workspace by `slug` while it's still restorable. Both reuse the existing `slug` param — no new params; pure addition. **v0.7** adds `export` + `import` actions to `pad_item`, mirroring the CLI `pad item export` / `pad item import` (covers playbooks AND conventions). `export` (read-only) takes `ref` and returns the portable artifact text — it forces the CLI's stdout sink (`-o -`) so the bytes come back as the result instead of a file. `import` (mutating, not destructive) takes a new `artifact` param (the full artifact text) and returns `{ref, slug, warnings}`; the ExecDispatcher can't pipe stdin, so it spills the artifact to a temp file and dispatches `item import `. v0.6 added the `pad_item.backlinks` action; v0.5 added `pad_library`. v0.3 (PLAN-1377 / TASK-1380) introduced `pad_meta.action: bootstrap`, `pad_set_workspace`'s embedded-bootstrap response, and the `pad://workspace/{ws}/bootstrap` resource. **v0.4 (PLAN-1410)** is a comprehensive bootstrap-payload trim — same tool catalog, slimmer JSON shape inside bootstrap responses: `BootstrapCollection` projection drops `id`/`workspace_id`/timestamps/`settings` and emits `schema` as a nested object; `BootstrapRole` projection drops UUIDs/timestamps/`tools`; convention `slug` dropped; top-level `recent_activity` (a duplicate of `dashboard.recent_activity`) removed; new `BootstrapDashboard` wrapper caps five sub-arrays (`attention`, `recent_activity`, `active_items`, `active_plans`, `by_role`) at 5 entries each with parallel `*_overflow_count` fields; redundant schema labels omitted when `label == TitleCase(key)`. Cumulative size reduction: ~40% on a representative workspace, ~54% on the fixture (see PLAN-1410's Result section for per-section deltas). Compatibility: most changes are subtractive (dropped fields) or additive (overflow counts), but **one type change is breaking**: `collections[].schema` went from a JSON-encoded string to a nested JSON object — clients that JSON.parse()'d the string need to consume it directly as an object now. The dropped fields (UUIDs, timestamps, settings, duplicate `recent_activity`, convention `slug`) have canonical alternatives (slugs for addressing; `pad collection list` / `pad role list` for the full models when needed). +- `ToolSurfaceVersion` (currently `"0.77"`) — the MCP tool catalog contract. Bump when tool names, action enums, or parameter shapes change incompatibly. **v0.77** (BUG-2772) records a remote `/mcp` write as an AGENT write named by the client's declared MCP `clientInfo.name`, where it was recorded as the human, and gives a remote call a per-connection default lease holder (`claude-code#3f9a12c4`); see "Remote caller identity" below. A claim on an item another holder leases now answers `lease_held` with `details.holder` and `details.expires_at` on both transports, where remote said `conflict` and stdio `server_error` (BUG-3496). BEHAVIOR bump. **v0.76** (TASK-1809) makes a `pad_item` `claim` / `release` with no `holder` hold the lease under the caller's agent name (the `X-Pad-Agent` the CLI sends), else the account's email, where it was the email alone: several agents on one account silently shared one lease, a second claim answering 200 by refreshing the first. It now answers 409 `lease_held` naming the first agent. `pad_project.action=next` / `ready` leave out items whose live lease a claim by the caller would lose (same identity, the claim's own predicate, filtered before the cap of three; reminders are not filtered). Remote /mcp sends no agent name, so its default is still the email (TASK-3495). A lease taken before the upgrade is another holder's to the same agent for up to its TTL. BEHAVIOR bump on the v0.70 grounds. **v0.75** (BUG-3480) makes `pad_item.action=list` on both transports refuse a filter key no schema in scope declares and no item in scope stores (400 `validation_failed`, "invalid list filter ..."), where it answered an empty list, and refuse a key that is not a field key, which the store used to drop (answering the unfiltered list). BEHAVIOR bump on the v0.43 / v0.29 grounds; see the item list endpoint bullet under API. **v0.74** (TASK-2188) makes `pad_collection.action=update` answer, on both transports, with an `omitempty` `warnings.orphaned` [{field, option?, items}] naming each field, or select option, its schema removed that live items still hold. Nothing is refused. ADDITIVE, the v0.67 grounds; 0.73 is BUG-3480's. **v0.72** (TASK-2189) adds `pad_collection` `list-archived` (read-only) and `restore` (owner-only, by slug or id), backed by the new `GET /workspaces/{ws}/archived-collections` and `POST /workspaces/{ws}/archived-collections/{ref}/restore`: an agent's archive is recoverable by an agent. ADDITIVE. **v0.71** (TASK-3462 U3a) adds an `omitempty` `builtin_updates` count to the bootstrap on every door that returns it (the conventions and playbooks Pad ships whose library text changed since the workspace's copy, among the items the caller sees in full), and a server-instructions section telling the agent to mention it once and never apply an update itself. ADDITIVE. **v0.70** (BUG-3453) makes `pad_project.action=next` / `ready` fill any slot the existing tiers leave empty with ordinary open items from non-system collections that declare `priority` or `severity` (an initial status like `new` counts), ranked below every item admitted before, so a full list is unchanged and a moved-in backlog with no priorities is no longer "nothing ready". BEHAVIOR bump on the v0.49 grounds. **v0.69** (TASK-2314) makes every REMOTE route that needs a workspace and lacks one answer `no_workspace` with `available_workspaces` and a hint, as stdio always did, where it answered `validation_failed` "workspace is required"; the single-workspace default now runs before the `assign` / `role` resolvers. BEHAVIOR bump on the v0.42 / v0.45 grounds. **v0.68** (BUG-3448) makes the item resource render a structured field as compact JSON instead of Go's map syntax, keep a number above 2^53 to its digits and render a JSON null as `null`; the agent projection stops rounding large numbers. BEHAVIOR bump on the v0.62 / v0.64 grounds: an output shape changed, no name, enum or param moved; scalar fields render as before. **v0.67** (BUG-3446) lets a create in a system conventions or playbooks collection ADD a trigger/scope word the library itself uses to the select options instead of refusing it, so `pad_library.activate` and B3's literal create succeed in a `blank` workspace, and adds an `omitempty` `warnings.options_added` to the create result on both transports. A word the library does not use is refused as before. ADDITIVE. **v0.66** (BUG-2136) makes `pad_workspace.action=invite` always create a pending invitation, never add an existing account directly; see `internal/mcp/version.go`. **v0.65** (TASK-3413, SPEC-6 U9c) adds `omitempty` `via_app` and `via_app_name` to items an installed app CREATED (items.created_via_app, never the last app writer), comments an app wrote and version rows an app's write made, on both transports (`pad_item` get, list summary and full, comments, history summary and full). The name is the app's bot display name, else its origin, and survives uninstall. ADDITIVE. **v0.64** (BUG-3379) adds an `omitempty` `imported: true` to comments, attachment rows and version rows a workspace import wrote, on both transports (`pad_item` comments, `pad_attachment.list`, and `pad_item.history` with `full: true`; history summary rows and attachment `show` do not carry it): import keeps the export's author strings and uploader ids verbatim, and the flag says they were not verified here. ADDITIVE. **v0.63** (TASK-3321) adds an `omitempty` `actor_name` to every `pad_item.action=history` summary row on both transports, the display name of who made the change, where rows said only `user` or `agent`. ADDITIVE. **v0.62** (BUG-3326) makes remote /mcp `pad_set_workspace` embed the workspace bootstrap, as stdio always did: the in-process bootstrap resource read, run as the token's user under the same scope/consent perimeter, so a workspace the caller cannot read embeds nothing. ADDITIVE; no name, enum or param changed, and stdio is unchanged. **v0.61** (TASK-3321 U0b) marks `pad_workspace` destructiveHint:true and openWorldHint:true, because `invite` sends an email to an arbitrary address, and `pad_playbook` openWorldHint:true, because `match` sends text to the decision provider. Annotation-only BEHAVIOR bump on the v0.20 grounds; every other tool's block is unchanged. **v0.60** (TASK-2198 U4) makes `content_state: "applied_pending_flush"` clear ON ITS OWN on every door that carries it: after the item's collab room closes (or a one-minute sweep finds it dormant) the server rebuilds the body from the op-log and stores it, moving `seq` (a held `expected_seq` then answers `update_conflict` instead of `content_pending_flush`) and adding a `system` / `recovery` version. BEHAVIOR bump on the v0.59 / v0.39 grounds; no name, enum or param changed. Not a guarantee (failures, set-aside rows, `PAD_MATERIALIZE=off`), so re-read later, never re-send, still stands. **v0.59** (BUG-3252, tombstone ruled over cascade) makes `pad_item.action=delete-comment` on a comment with replies SUCCEED, leaving a tombstone (body emptied, author and timestamps kept, additive `deleted: true`) its replies stay under; it is removed when its last reply is deleted. `edit-comment` on a tombstone answers 409 `comment_deleted` on every transport. BEHAVIOR bump on the v0.58 grounds; `comment_has_replies` stays classified for older servers. **v0.58** (BUG-3252) makes `pad_item.action=delete-comment` on a comment that still has replies answer 409 `comment_has_replies` (details `comment_id`, `reply_count`) on every transport instead of `server_error`: `comments.parent_id` has no ON DELETE, so the delete failed the FK inside the store. Nothing is deleted either way. Tombstone was then ruled over cascade; v0.59 replaced this refusal with it. BEHAVIOR bump on the v0.45 grounds. **v0.57** (TASK-2695) adds `pad_item` `edit-comment` (ref, comment_id, message) and `delete-comment` (ref, comment_id) on all three transports, backed by the item-scoped routes `PATCH/DELETE /workspaces/{ws}/items/{ref}/comments/{id}`, which answer 404 unless the comment is on `ref` and otherwise run the workspace routes' handlers (edit author-only, delete item-edit). CLI: `pad item comment-edit` / `comment-delete`, refused against a server without the `item_scoped_comment_writes` capability. Every serialised comment gains a derived `edited` bool (updated_at > created_at), and `pad item comments` prints each comment's id. ADDITIVE. **v0.56** (BUG-3244) gives `content_state` a second value, `superseded_set_aside`, on every MCP door that carries it (`pad_item` get / full list, `pad_playbook` run, the item resource's line above the body): edits an editor schema-version rebuild set aside, which opening the item will NOT restore, so the resource line and the `content_pending_flush` hint (chosen by `details.set_aside_rows`) name `pad item set-aside` and `overwrite_pending_edits` instead. ADDITIVE bump: no name, enum or param changed, but an agent branching on the one-word vocabulary meets a word whose remedy differs. Reading or discarding the rows alone is not on the catalog. **v0.55** (BUG-2659) sends `pad_item.action=search`'s `collection` to /search as typed, and /search resolves it exact-first per workspace in scope (the item routes' resolver). In a workspace holding both `task` and `tasks`, `collection: "task"` now answers from `task` instead of `tasks`; every other workspace is unchanged, because the shorthand still resolves server-side. Stdio reaches it through the CLI, which sends the name as typed only to a server advertising `search_collection_resolution`. BEHAVIOR bump on the v0.36 / v0.40 grounds. **v0.54** (BUG-3217) keeps a `fields` number's literal through MCP on both transports (mcp-go's argument decode rounded anything above 2^53, and stdio's `--field` stringify carried the rounded value), and REFUSES a `fields` number beside a `field` entry for the same key when they differ as exact numbers — two values that differ only above 2^53 used to collapse into one rounded write; a matching pair (3.0 beside n=3) still collapses. BEHAVIOR bump on the v0.48 grounds. **v0.53** (BUG-2819) adds `filename_source` (caller / normalised / substituted / derived / unknown) to every `pad_attachment.action=list` row on both transports, because a stored filename cannot say whether the caller sent it or the server substituted it. ADDITIVE, the v0.28 / v0.13 disposition; `show` does not carry it, and `mcp_audit_log.tool_name_source` reaches no catalog action. Rows written before it read `unknown`, never `caller`. **v0.52** (BUG-2367 item 4) refuses a move or copy (every migrate door) that would change an item between open, done and abandoned unless the caller names the destination done field. Only the STATE is compared, so two values that both mean done carry. Move answers 400 `state_change_requires_value` with details `{field, options, from, to}`; bulk move puts it in a `failed[]` row; the copy answers 400 `validation_error` with the same sentence; the preflight emits a needs_value row with reason `state_change`, which the web dialog picker renders. A destination with no done select field is exempt. BEHAVIOR bump. **v0.51** (BUG-2367) stops every migrate door (single move, bulk move, cross-workspace copy and its preflight) carrying a value into a field the destination marks `computed` (preflight drop reason `target_computed`) or a value that collides on a destination `unique_scope` field. Provenance decides, the TASK-2878 rule: a CARRIED collision is dropped and reported (`not_unique`), a supplied override or injected default that collides is refused 409 `conflict`, and a required field emptied by the drop is refused as required, which is the existing needs_value route. Before it, single move answered 500 on the indexed `invocation_slug`, bulk move leaked the SQL error, and an unindexed unique field stored a duplicate. Reporting is additive and omitempty: `warnings.not_unique` [{key, value, holder?, message}] on the move response, bulk `updated[]` rows and the copy response, and a `detail` sentence on the preflight's dropped row. `holder` is present only when the caller may see that item, so the drop is not an existence oracle. BEHAVIOR bump on the v0.43 / v0.29 grounds. **v0.50** (BUG-3014) adds an ADDITIVE `omitempty` `stored_as_text: true` to a `relation_targets` entry whose stored value is not UUID-shaped (a title a bundle import carried verbatim, or legacy free text). Such a value was never an id and used to hydrate as a plain id-only entry, which reads as "gone or hidden"; an id-only entry without the flag keeps that meaning, and a UUID-shaped value, resolved or not, is byte-identical to v0.49. The predicate is syntactic, decided from the stored bytes and never from a lookup, so it discloses nothing, and deliberately not coupled to the resolver ladder. The CLI prints `"" (text, not a reference)` and the web chip says the same. **v0.49** (BUG-2410) makes `pad_project.action=report` with no `collections` param leave out SYSTEM collections (`Collection.IsSystem`: Conventions and Playbooks), which were counted in Insights' created, WIP and status totals; naming one explicitly still includes it. BEHAVIOR bump on the v0.40 / v0.42 grounds: a default call's content changed for every caller (web Insights, print, `pad project report`, both MCP transports, all through the one store rule). **v0.48** (BUG-3163) makes `pad_item.action=create` REFUSE a `field` / `fields` entry naming any reserved metadata key (`implementation_notes`, `decision_log`, `github_pr`, `convention`) on every transport, with 400 `validation_error`, creating nothing: create was the last door that stored one, as a string no extractor reads. Library activation, its one system writer, moves to an additive typed `convention` create member (not on the catalog; `pad_library.activate` is unchanged), and the CLI verifies from the stored fields that it landed, because an older server ignores the member and answers 201. BEHAVIOR bump on the v0.47 grounds. **v0.47** (BUG-2696) makes `pad_item.action=update` REFUSE a field setter naming `github_pr` on every transport (400 `validation_error` naming `pad github link` / `unlink`), closing the exemption v0.23 left: that door stored the PR as an unreadable string, so no link ever rendered. The writer is a new additive, typed update member (`github_pr` object + `clear_github_pr`) used by `pad github link` / `unlink` / `project reconcile`, deliberately NOT on the catalog (a remote PR-link action waits on the catalog-trim decision). BEHAVIOR bump; item create is BUG-3163. **v0.46** (BUG-3156) makes `pad_item.action=bulk-update` over stdio and remote REFUSE, per item, a status or priority change on an item whose collection does not declare that field, writing nothing for that item: the answer WebMCP has given since v0.44, so the three transports agree. Rows keep each transport's shape (stdio `failed[]` with `validation_error`, remote `results[]` with `validation_failed` and the server message in `hint`). The mechanism is the update door's new `refuse_undeclared_fields` member, which both bulk-update transports set; `pad_item.update` does not, and still accepts-and-warns. A server that predates the member ignores it, which is the old accept-and-warn. BEHAVIOR bump on the v0.44 / v0.43 grounds. **v0.45** (BUG-2829) reports an HTTP 413 as `too_large` on BOTH transports, with the server's own code in `details.reason`, where it used to be `server_error`: three deliberate caps are reachable from the catalog (a title rename's link cascade, an oversized outbox event, an oversized artifact import), and the old code read as transient and invited a retry that fails identically. Remote maps 413 in `classifyHTTPStatusKind`; stdio gets it from a structured marker the CLI root writes for any 413, and `too_large` joins `allowedStructuredErrorCodes`, which a test now proves contains every code any CLI marker writer emits. BEHAVIOR bump on the v0.42 grounds; no name, enum or param shape changed. **v0.44** (BUG-3154) makes `pad_item.action=bulk-update` over the WebMCP browser transport REFUSE, per item, a status or priority change on an item whose collection does not declare that field: the item lands in the bulk response's `failed` array with `validation_error` naming the collection and field, nothing is written, and the rest of the call applies. The door is `POST /items/bulk` (`set-priority`, and `move` with a `status`, with or without a `collection`, where the target's schema decides), where the request carries an operation and a value and the SERVER chooses the key; it used to store an orphan field and report the item updated. BEHAVIOR bump on the v0.43 / v0.40 grounds. The transports disagreed after it, stated rather than implied: stdio and remote issued a per-item PATCH, the single-item update door, which ACCEPTED the key with `warnings.undeclared_fields` (v0.27), until v0.46 converged them. **v0.43** (BUG-2379) makes `pad_item.action=move` REFUSE a field override naming a field the destination schema does not declare, with 400 `malformed_override` — the same check, code and message the cross-workspace copy already used. BEHAVIOR bump on the v0.40 / v0.29 grounds: a write door refuses a call it used to accept, where it used to store the key as an orphan field no schema renders. Create and update still ACCEPT undeclared keys with `warnings.undeclared_fields` (v0.27), because callers round-trip the whole fields blob; an override is a fresh assertion about the destination schema, not round-tripped state. **v0.42** (BUG-3142 + BUG-3147) changes the error CODE a LOCAL STDIO caller receives for two failure families that used to arrive as retryable `server_error`: an argv refusal (cobra/pflag: unknown flag, arg count, …) is now `validation_failed` with its message kept, and a 429 on any command is now `rate_limited` with `details.retry_after_seconds`, via the structured marker line the CLI writes at its root. It also stops the refusal that caused most of the first family: `BuildCLIArgs` now emits flags first and the positionals behind `--`, so free text starting with `-` (`item search "-ship it"`) is no longer parsed as a flag. BEHAVIOR bump; no name, enum or param shape changed, and the remote transport is untouched. **v0.41** (PLAN-3114 U5 / TASK-3120) adds a `match` action to `pad_playbook`: given free `text`, a Choice question over the workspace's ACTIVE playbooks plus a reserved `"none"` option returns the best match's ref (or `"none"`), confidence, per-option probabilities and the model. No provider configured → 404 `decision_provider_unavailable`; a provider error or an out-of-set answer → 502 `decision_provider_error`. Pure ADDITIVE bump (new action + param, nothing existing moved), read-only and side-effect-free. **v0.40** (BUG-3028) gives a scalar `relation` ONE stored form for "no target", the key ABSENT, converging on multi_relation's rule. A blank (`""` or whitespace) a write SETS — create, `fields_patch`, a changed value in full `fields`, a move/copy override — is normalised to absent before validation, so a `required` relation is refused as required (a patch blanking it now gets the answer deleting it always got). A legacy blank a write only CARRIES — an untouched key under `fields_patch` (normalised by the store under its write lock, via `ItemUpdate.BlankRelationKeys`), an unchanged value in full `fields`, move, copy, artifact import — is normalised after validation and never refused. An empty list filter on a scalar relation key of a collection-scoped list (`owner=`) matches all three spellings. BEHAVIOR bump; no shape change. Workspace import (`store.ImportWorkspace`) still stores blobs verbatim; its legacy blanks normalise on the next write. **v0.39** (BUG-3133) refuses `pad_item.update` that sets content WITH a version token (`expected_seq` / `expected_updated_at`) while the item's op-log holds content-bearing rows above its flush watermark, with 409 `content_pending_flush` (details `ref`, `pending_rows`). BEHAVIOR bump on the v0.35 / v0.36 grounds, carrying one additive param: `overwrite_pending_edits` lifts it, on the API, the CLI (`--overwrite-pending-edits`; `pad item edit --force` sets it on the save) and MCP alike, because an agent must be able to clear the refusal without a browser. The token guards the ROW and a tab's unflushed typing is not in it, so the write used to replace those edits — through the applier's setContent with a tab open, and by the direct path's op-log prune, which DELETES them, with none. Its own code rather than `update_conflict` because re-reading returns the same row and seq. A write without a token, without content, or to an item with nothing pending is unchanged, except that a direct write now reports `warnings.pruned_pending_edits` (additive, omitempty) when its prune deleted such rows. The check runs in the write's own tx; on the direct path it is under the item lock and appendMu and exact, on the applier path a tab can still type in the one server hop between the check and setContent. (v0.37 and v0.38 — the `agent` projection on `pad_item.get` and `claim` / `release` — are in `internal/mcp/version.go`; this paragraph had stopped at v0.36.) **v0.36** (BUG-3082) stops a REF-SHAPED `relation` value falling back to matching by item NUMBER when its prefix names a collection that is LIVE in the workspace; such a value is now `not_found`. BEHAVIOR bump on the v0.35 / v0.30 / v0.29 / v0.16 grounds — no tool name, action enum or param shape changed, but a write door refuses a value it used to accept. It finishes v0.29: that entry closed free-text corruption ("red" resolving to whatever is slugged `red` today) and left the same corruption open for anything shaped like a REF, which is the spelling the docs tell callers to prefer. Item numbers are workspace-unique and sequential ACROSS collections, so `CONVE-1` and `SECRE-1` are never both real — the fallback dropped the prefix, matched on the number alone, and landed on an item that was usually inside the field's declared collection, so the wrong-collection check above it passed and NOTHING was raised: a caller wrote `CONVE-1`, the item stored a different item's UUID, and the write answered 201 with the substitution visible only in `relation_targets`. The predicate is about the PREFIX rather than the item because a collection RENAME changes its prefix and a relation already written as the old ref must keep resolving (BUG-2873) — that ref's prefix names nothing afterwards, so the fallback still fires for it, while a prefix that IS live and simply holds no item at that number is the caller naming a real collection that does not contain what they said. A SOFT-DELETED collection counts as absent IN THAT PREDICATE, for the same reason a renamed one does — a claim about the fallback only: the exact-prefix lookup ahead of it never filtered on the collection’s own `deleted_at`, so an item whose collection was soft-deleted still matches THERE and never reaches the predicate. That is left alone rather than made consistent, because it cannot retarget — the downstream collection check refuses it. RESIDUAL, stated rather than implied and pinned by a test: a ref pasted from ANOTHER workspace whose prefix also names no collection here still resolves by number, because nothing in the value distinguishes it from a rename's leftover. No escape hatch, for v0.29's reason. Out of scope and unchanged: `GetItemByRef`, the navigational read path, where landing on the moved item is the helpful answer. **v0.35** (BUG-3079) makes an injected schema DEFAULT take the same `validateFieldType` check a caller-supplied value takes; one that fails is DISCARDED and named in `warnings.dropped_fields` instead of being stored. BEHAVIOR bump on the v0.30 / v0.29 / v0.16 grounds — no tool name, action enum or param shape changed, but a write door stores something different from what it stored before. Unlike v0.29, which turned an accepted value into a refusal, this turns a stored value into a reported drop: a create that used to land WITH a bad field still lands, without it. What it closes is two doors disagreeing about one value, decided only by who put it there. It also widens `dropped_fields` from the single relation case v0.29 introduced to a field of ANY type. No escape hatch, for v0.29's reason. ONE exception, which is the rule finishing its sentence rather than a carve-out: dropping leaves a REQUIRED field absent, which is exactly what the required check reports, so such a write is refused — naming the default as the cause, because a bare "field is required" points its reader at a request that never mentioned the field. **v0.34** (BUG-3037) adds an `expected_seq` param to `pad_item.action=update` — the STRONG optimistic-concurrency token, preferred over `expected_updated_at`. ADDITIVE (the v0.13 / v0.11 / v0.8 disposition): nothing existing moved and `expected_updated_at` still works. It is needed rather than nice because `updated_at` is stored at ONE-SECOND resolution, so two writes to a row inside one second both match the token and NEITHER conflicts — the loser is accepted and silently overwrites the winner, both callers seeing success. That is the shape of agent traffic, so the token agents were offered could not refuse the race it exists to refuse. `seq` is bumped on every mutation of the row under the write lock. Raising `updated_at`'s resolution instead was measured and REJECTED: the column is TEXT on both dialects and compared LEXICALLY in SQL (the since-cursor read plus eight `ORDER BY` sites), and Go's `RFC3339Nano` omits trailing zeros, so a sub-second value sorts BEFORE a whole-second value of the same second and the cursor would start skipping rows. The read side is what makes the token reachable: `seq` now serialises without `omitempty` on `models.Item` AND on the item SUMMARY shape (`cli.ItemSummary`), which is what `pad_item.list` returns by default since v0.9 — a token absent from the shape a caller reads is a token that caller cannot send. A value below 1 is a 400, not a 409: the server never issues one, so a 409 would read as contention that never clears. **v0.30** (BUG-2870) is a BEHAVIOR bump on the v0.29/v0.27/v0.26/v0.16/v0.10/v0.9 grounds — no tool name, action enum or param shape changed. **Every door refuses a padded KEY now**, and each was accepting it differently: /mcp trimmed it and wrote the declared field, the CLI stored a ghost field beside it — so both refuse something they used to accept. What is /mcp-only is the VALUE half, which it used to trim and type and now passes through to the same validation the CLI has always applied. A caller writing canonical entries sees no difference at either door. A second, separately-noticeable fix rides with it: `detectFieldConflicts` swallowed `parseFieldArray`'s refusal as "the caller owns this error surface", which held only while the sole possible error was a shape error — `reshapeItemFields` returns early with no `fields` object, so on the no-`fields` path (this bug's own path) four existing refusals were landing as successes. No escape hatch, for v0.29's reason: there is no legitimate call this refuses, only calls whose two readings a door used to choose between silently. **v0.29** (PLAN-2857 U1 / TASK-2878) is a BEHAVIOR bump on the v0.27/v0.26/v0.16/v0.10/v0.9 grounds (NOT v0.28's, which was purely additive) — no tool name, action enum, or param shape changed, but a `relation` field value must now name a live item in the collection that field declares, so every write door refuses values it used to store. Refused: names nothing (`not_found`), names an item in the wrong collection, the field declares no target collection (`target_missing`), or the value is a SLUG — a deliberate divergence from `ResolveItem`'s UUID→ref→slug ladder, since a slug is neither an ID nor stable and free text like "red" resolving to whatever is slugged `red` today is exactly the corruption this closes. Ordinary `validation_error`, no new code and no new details key, because stdio classifies errors by matching CLI stderr prose. A CARRIED value — already on the item, asserted by nobody — is never refused, since refusing would make every legacy item un-updatable, un-movable and un-copyable: within a workspace it resolves and SURVIVES, across a workspace boundary it is dropped without a lookup (a source-workspace id cannot mean anything in the destination) and reported through the same `warnings.dropped_fields` channel BUG-2674 established. No escape hatch, deliberately: unlike v0.10's `allow_draft` there is no legitimate call this refuses, and the case with a real claim to leniency is already exempt by provenance rather than by a flag. **v0.28** (IDEA-2641 / GitHub #1010) adds two ADDITIVE `pad_item` actions and two optional params: `remind` arms a one-shot reminder at an RFC3339 `remind_at` INSTANT, and `ack-reminder` acknowledges a fired one by `reminder_id`. Purely additive — nothing existing moved, and a v0.27 consumer that enumerates neither action is unaffected; same disposition as v0.13 / v0.11 / v0.8, which likewise wired existing CLI verbs onto the catalog. Agents already RECEIVED reminders (the poll surface is `pad_project.next` / `ready`, long exposed); what was missing is the half where an agent that defers work can say when it wants to be asked again. `remind_at` REFUSES a bare date rather than reading it as midnight — the `date` schema type accepts `YYYY-MM-DD` so a caller will try it, but a bare date names a 24-hour span and choosing an hour inside it would fire at a time nobody picked. Re-arm and disarm stay CLI-only: both address a reminder by an id the agent would have to list first, and no listing action exists on this surface yet — a door with no handle. **v0.27** (BUG-2850) types field values SERVER-SIDE at all eight validate sites, carries the `fields` object to the remote door with its JSON types intact, accepts undeclared keys while NAMING them in `warnings.undeclared_fields`, and replaces five accreted conflict guards with one canonical pass; the merge refuses several ambiguities it used to resolve silently. (This entry was missing from CLAUDE.md — the 0.27 unit swept `instructions.md` and `README.md` and not this file.) **v0.27** (BUG-2850) types field values server-side at all eight `Validate*` call sites so a declared number/json field is writable from the remote transport at all, carries the `fields` OBJECT with its JSON types intact, names undeclared keys back in `warnings.undeclared_fields` (accepted rather than refused — a census of 1012 items found 14 such keys across 168 live values, so refusing would have broken read-modify-write on items nobody had edited wrongly), and replaces the accreted per-site conflict guards with ONE check over a canonical view of every source; that check refuses ambiguities v0.26 resolved silently, chiefly two names for one target in a single call (`parent`/`plan`, `assign`/`assigned_user_id`, `role`/`agent_role_id`), refused even when the values match because the names address one thing through incomparable vocabularies and the two doors resolved them differently. **v0.26** (IDEA-2756) is a BEHAVIOR bump on the v0.9/v0.16/v0.25 grounds — no tool name, action enum, or param shape changed, but `pad_workspace.create` now refuses a call it used to permit. Closest precedent is v0.10, which likewise turned a server-side gate into a structured refusal; unlike v0.10 there is no `allow_draft`-style override, because the gate encodes a decision the USER made at consent time and a bypass param would be the app overriding its own grant. `POST /workspaces/import` is gated by the same shared helper (import mints a workspace through `store.ImportWorkspace`), though it has no MCP action today. **v0.25** (TASK-2657 / BUG-2702) resolves `pad_library.activate`'s destination collection from the target's declared artifact kind rather than the literal `conventions` / `playbooks` slugs, so activating into a workspace that renamed either collection lands correctly; a lookup ERROR is surfaced rather than silently falling back. **v0.24** (#1066) adds the `fields` OBJECT param to `pad_item` create/update — an alias merging into the same path as `field`/the dedicated params, so the shape reads return is finally a valid write shape; the same key supplied twice with conflicting values is REFUSED (refuse-on-ambiguity, the v0.18/v0.19 disposition), equal duplicates collapse to one write, and non-writer actions refuse a `fields` param loudly. It also makes input validation STRICT for every catalog tool: undeclared top-level keys are rejected with a structured error naming them, instead of being accepted and silently dropped by `BuildCLIArgs` — which is the mechanism that made the `fields` object a session-scoped silent no-op in the first place. Compat carve-out: `pad_item`'s v0.16 `assigned_user_id` / `agent_role_id` remote-transport clear form stays accepted (documented, undeprecated, deliberately never schema-declared). The strict half changes behaviour for inputs that previously "succeeded", but that reliance was indistinguishable from a caller bug (the key never did anything), so the break is the fix; one bump covers both halves. **v0.23** (BUG-2627 part 2 + BUG-2675) refuses system-metadata keys through `fields_patch` on all three doors at once, `github_pr` exempt on update (move/copy still refuse it), and adds the retry-hostile `stored_state_unreadable` code. **v0.22** (BUG-2674) stops `pad_item.action=move` destroying system metadata and refuses `field` setters naming the reserved keys there. **v0.21** bounds `pad_item.action=history` (BUG-2608): the `limit` param now covers it, default 50 / max 300, applied in the CATALOG action so it reaches both transports (HTTP reads the input; stdio gets the CLI's new `--limit` via BuildCLIArgs). The window is the NEWEST N and there is deliberately no `offset` — versions are reverse patches, so only a newest-end window is cheap to reconstruct. Additive param bump; a v0.20 consumer sending no limit now receives the newest 50 rather than every version, which is the fix. Summary mode additionally asks the server to skip patch resolution rather than resolving bodies the dispatcher discards. **v0.19** adds a `clear_parent` boolean to `pad_item` (BUG-2078) — an ADDITIVE param bump, same grounds as v0.18; nothing existing changed shape. The server has supported clearing a parent since BUG-2013 (`extractParentLink` treats a present-but-empty `parent` key in `fields_patch` as detach), but neither client surface could reach it — `--parent ""` was a silent no-op on the CLI and the MCP `parent` param has the same "empty means not provided" convention every other declared string on the tool has. Boolean rather than overloading the empty string, same two reasons as v0.18: keeps that invariant intact for every other param, and only a boolean reaches LOCAL STDIO via `BuildCLIArgs`, mapping to a new `--clear-parent` bareword flag exactly as `clear_assigned_user` maps to `--clear-assigned-user`. Update-only, same asymmetry as v0.18. A simultaneous `parent` + `clear_parent` — including via `field: ["parent=..."]` or the `plan` alias `extractParentLink` also accepts — is REFUSED on both transports, not silently resolved (codex round 1). Also refused, not silently applied: `clear_parent` against a collection whose schema declares its own `parent`/`plan` field — `extractParentLink` skips hierarchy handling entirely for a schema-shadowed key and lets it fall through as an ordinary field write, so the wire shape `{"parent":""}` can no longer distinguish clear-hierarchy intent from a legitimate blank-a-real-field write once it reaches the server; the ambiguity is created at the client surface that accepted `clear_parent`, so that surface refuses rather than guessing (codex round 2). **v0.18** adds `clear_assigned_user` / `clear_agent_role` booleans to `pad_item` (IDEA-2584) — an ADDITIVE param bump (v0.5/v0.6 precedent); nothing existing changed shape and v0.16/v0.17's empty-string forms still work, undeprecated. v0.16 and v0.17 made the clear WORK; nothing advertised it, because the params that do it were never in the catalog, so an agent reading the schema reached for `assign: ""` (a no-op, and it stays one). Booleans rather than declaring the string params, for two reasons: an empty DECLARED string is inert everywhere else on the tool, so giving one a destructive meaning would let a param-padding client silently unassign everything; and only a boolean can reach LOCAL STDIO, since `BuildCLIArgs` emits the CLI's real flags and a param with no flag behind it is dropped — these map to new `--clear-assigned-user` / `--clear-agent-role` bareword flags, exactly as `allow_draft` maps to `--allow-draft`. Update-only, deliberately asymmetric with create (clearing at create has no honest behaviour but a no-op; a test fails if someone adds them there). Server-side it is wiring, not new semantics: `models.ItemUpdate.ClearAssignedUser`/`ClearAgentRole` already existed with store support since BUG-2566. **v0.17** closes the transport gap v0.16 documented: local stdio MCP shells out to the CLI, which wrote `--field assigned_user_id=` into the item's FIELDS BLOB while the column stayed stale and then printed "Updated TASK-9". `cmd/pad/cmd_item.go` now lifts `columnFieldKeys` onto the columns on create AND update, mirroring `liftFieldsToColumns` and its INVARIANT. Two compat changes, ruled separately: non-empty values move to the column and stop writing the blob key (relying on the old behaviour is relying on a shadowing defect), and empty values clear (falls out of the lift, inherits BUG-2566). Existing stray blob keys are left alone — the fix stops minting new ones. Another behaviour-only bump (BUG-2583). **v0.16** lets an MCP agent UNASSIGN an item over the REMOTE transport (TASK-2571). No tool/action/param shape changed — this is a BEHAVIOR bump on the same grounds as v0.9: an empty-string `assigned_user_id` / `agent_role_id`, passed at the top level or as `field: ["assigned_user_id="]`, was silently dropped by two dispatch-path filters (`mapItemUpdate`, `liftFieldsToColumns`) and is now forwarded as a clear-to-NULL. The store has had defined clear semantics for exactly these two columns since BUG-2566 and HTTP inherited them, so this is uniformity restoration — MCP was the only surface with no way to unassign. Compat posture accepted deliberately: today's `""` senders get a no-op, and a no-op is the surprising reading. The empty-string filter on `tags` at the same call site STAYS (codex #547 r3 P2) — `tags: ""` is a corrupt JSONB/TEXT write, not a clear; same-looking guard, opposite justification. `clear_assigned_user` / `clear_agent_role` schema flags (option (b)) deliberately skipped as additive sugar, though codex review reopened the case — the catalog exposes `assign` / `role`, NOT the ID params, so an agent reading the schema still can't discover the clear (IDEA-2584); an empty `assign` is deliberately left inert because every other schema-declared string on that mapper treats empty as not-provided. **Transport scope:** v0.16 fixed the REMOTE /mcp transport only; v0.17 (BUG-2583) closed the local-stdio half at the CLI. **v0.15** adds the `unparented` boolean to `pad_item.list`, mutually exclusive with `parent`, for structural loose-item filtering (TASK-2096). **v0.14** added a `history` action to `pad_item` (read-only item version history — newest-first metadata; content body omitted for token thrift) and an `expected_updated_at` param for optimistic concurrency on `update` (round-trip the `updated_at` you last read; a stale value fails with a structured 409 `code=update_conflict`). The `update` action's field writes are now a server-side field-level MERGE (only the keys you set change) rather than a full-blob replace, closing the concurrent-update lost-write race (IDEA-1480 / TASK-2022) — pure addition to the action enum + param vocabulary; existing `pad_item` actions/params are unchanged and backwards-compatible. **v0.13** adds `ready` + `stale` actions to `pad_project`, mirroring the existing CLI `pad project ready` / `pad project stale` (TASK-2019): `ready` (read-only) returns the actionable backlog — the query-oriented counterpart to `next`, reusing the dashboard's suggested-next logic; `stale` (read-only) lists items needing attention (stalled, blocked, overdue, or out of the active workflow). Both HTTP dispatchers already existed (`dispatch_http_project.go`); this just wires them onto the catalog. `pad project reconcile` stays CLI-only (shells out to `gh` for live PR state — a local-git dependency MCP agents lack). Pure addition of two read-only actions — existing actions unchanged; backwards-compatible for v0.12 consumers that don't enumerate the new actions. **v0.12** adds an `activity` action to `pad_project`, mirroring the new CLI `pad project activity [--limit N] [--actor user|agent] [--since DATE]` (TASK-2018) — the non-streaming, bounded query counterpart to the CLI-only `pad project watch` SSE stream. Read-only snapshot of the workspace's enriched activity feed (item refs, titles, field-level change details) backed by the existing `GET /workspaces/{ws}/activity` endpoint (previously web-UI-only, now extended with a server-side `since` date filter so `limit`/`actor`/`since` behave identically across CLI, stdio MCP, and cloud HTTP), so agents can catch up on what other agents/users did since they last worked. Adds `actor` + `limit` params to the `pad_project` vocabulary (`since` already existed for changelog); pure addition — existing actions unchanged; backwards-compatible for v0.11 consumers that don't enumerate the new action. **v0.11** adds the read-only `pad_attachment` tool (the tenth resource × action tool) with `list` + `show` actions, mirroring the CLI `pad attachment list` / `pad attachment show` (TASK-2017): `list` enumerates a workspace's attachments (optional filters: item / category / collection / attached / unattached / sort / limit / offset); `show` returns one attachment's metadata (MIME, size, filename, ETag, last-modified) via a HEAD request without transferring bytes. Both HTTP dispatchers already existed (`dispatch_http_attachments.go`); this just wires them onto the catalog. Upload / download / view stay CLI-only (filesystem-bound, excluded per the catalog's exclusion rules). Pure addition — existing tools/actions unchanged; backwards-compatible for v0.10 consumers that don't enumerate the new tool. The base64 image RESOURCE for multimodal agents (`pad://workspace/{ws}/attachments/{id}`) shipped later in TASK-2077 (PR #930) as a bounded, image-only resource; TASK-2101 brought it — and the full read-only resource set — to the remote /mcp transport via the in-process `HTTPResourceFetcher`, so resources are no longer local-stdio-only. **v0.10** enforces the draft-playbook gate server-side: `pad_playbook.run` (and the underlying `POST /playbooks/{ref}/run`) now refuses a playbook whose `status` isn't `active` with a structured `playbook_not_active` error, adds an `allow_draft` boolean param (bareword `--allow-draft` on the CLI) as the escape hatch, and echoes the playbook `status` on both the `run` and `get` responses (BUG-2020). **v0.9** makes `pad_item.list` summary-shaped by default (drops item `content`, adds a default result limit of 50 / hard max 300 on MCP; CLI `--full` restores the complete shape) — a behavior change to the tool's return shape, hence the bump, though tool names, action enums, and parameter shapes are unchanged (TASK-2000). **v0.8** adds `restore` + `deleted` actions to `pad_workspace`, mirroring the CLI `pad workspace restore` / `pad workspace deleted` (TASK-1972): `deleted` (read-only) lists the caller's soft-deleted workspaces still inside the 30-day restore window; `restore` (mutating, not destructive, owner-only) un-soft-deletes a workspace by `slug` while it's still restorable. Both reuse the existing `slug` param — no new params; pure addition. **v0.7** adds `export` + `import` actions to `pad_item`, mirroring the CLI `pad item export` / `pad item import` (covers playbooks AND conventions). `export` (read-only) takes `ref` and returns the portable artifact text — it forces the CLI's stdout sink (`-o -`) so the bytes come back as the result instead of a file. `import` (mutating, not destructive) takes a new `artifact` param (the full artifact text) and returns `{ref, slug, warnings}`; the ExecDispatcher can't pipe stdin, so it spills the artifact to a temp file and dispatches `item import `. v0.6 added the `pad_item.backlinks` action; v0.5 added `pad_library`. v0.3 (PLAN-1377 / TASK-1380) introduced `pad_meta.action: bootstrap`, `pad_set_workspace`'s embedded-bootstrap response, and the `pad://workspace/{ws}/bootstrap` resource. **v0.4 (PLAN-1410)** is a comprehensive bootstrap-payload trim — same tool catalog, slimmer JSON shape inside bootstrap responses: `BootstrapCollection` projection drops `id`/`workspace_id`/timestamps/`settings` and emits `schema` as a nested object; `BootstrapRole` projection drops UUIDs/timestamps/`tools`; convention `slug` dropped; top-level `recent_activity` (a duplicate of `dashboard.recent_activity`) removed; new `BootstrapDashboard` wrapper caps five sub-arrays (`attention`, `recent_activity`, `active_items`, `active_plans`, `by_role`) at 5 entries each with parallel `*_overflow_count` fields; redundant schema labels omitted when `label == TitleCase(key)`. Cumulative size reduction: ~40% on a representative workspace, ~54% on the fixture (see PLAN-1410's Result section for per-section deltas). Compatibility: most changes are subtractive (dropped fields) or additive (overflow counts), but **one type change is breaking**: `collections[].schema` went from a JSON-encoded string to a nested JSON object — clients that JSON.parse()'d the string need to consume it directly as an object now. The dropped fields (UUIDs, timestamps, settings, duplicate `recent_activity`, convention `slug`) have canonical alternatives (slugs for addressing; `pad collection list` / `pad role list` for the full models when needed). Post-0.30 without a bump (BUG-2995): a successful content write through the designated applier used to answer with the item's PREVIOUS content — on that path the markdown goes to a live tab's Y.Doc and the row write runs with `Content` nil, so the response described the item as it stood before the request. It now carries the content as SENT plus an additive `omitempty` `warnings.content_outcome: "applied_pending_flush"`. No bump, on the BUG-2304 rather than the v0.9 grounds: v0.9 bumped because list rows LOST fields consumers read, whereas here nothing is removed or retyped — what changed is the VALUE of one field on one path, which a caller does observe. The claim is that no DOCUMENTED OR SUPPORTED reliance breaks, not that none can exist: a consumer could have detected the applier path by noticing the response echoed something other than what it sent, and that stops working — but it was never documented, a genuinely lost write produced the same mismatch, and `warnings.content_outcome` answers that question properly in the same change. Reads are unchanged: during the window a `get` (or `list` with `full: true`) still answers from the row, so the warning means re-read later, not re-send. @@ -71,3 +71,14 @@ If ANY element fails, the whole write is refused and nothing is stored — never In `relation_targets`, a `multi_relation` key carries a JSON **ARRAY** of the same `{id, ref, title}` objects, in stored order and one per stored element — including an `id`-only entry for an element that names nothing, so a position in the list lines up with the same position in `fields`. A scalar key is unchanged: still a single object, byte-identical to v0.31. Decide which shape to expect from the field's declared type, not by probing. +## Remote caller identity + +A write over remote `/mcp` is an **agent** write (BUG-2772, IDEA-2791 Tier B). Every surface that records who wrote something (`created_by`, activity `actor`, the activity `agent` name, comments) records the remote call as `agent`, named by the client's own declaration, MCP `clientInfo.name`, recorded verbatim (self-declared, like the CLI's `X-Pad-Agent`): + +1. a **modern** request (protocol 2026-07-28) carries `clientInfo` in its own `_meta`, used as is; +2. a **legacy** client sends `clientInfo` once, at `initialize`, and echoes the `Mcp-Session-Id` pad issued (measured: Claude Code 2.1.294 sends `{"name":"claude-code"}` and echoes the id). The server remembers the name by that id together with the account that sent it, in memory per instance, for 30 minutes idle, so a caller presenting another account's session id gets no name; +3. otherwise the write is an agent write with **no name**: never the human, and never a guessed name. That covers a client that declared no name, a request landing on another instance, and a restart. + +Each `initialize` logs one line, `mcp client initialized`, with `client_name`, `client_version`, `protocol_version` and `transport` (no tokens or headers), which is how what each client sends gets measured in production. + +**Leases.** A remote call's default lease holder (a `claim` / `release` with no `holder`, and the identity `next` / `ready` compare leases against) is the client name, or `mcp-client` when none was declared, plus the first eight hex digits of its `Mcp-Session-Id`: `claude-code#3f9a12c4`. Two connections of one client on one account therefore hold leases separately; with the name alone they would silently share one, which defeats the lease. A lease counts as the caller's only when both the holder label and the account match, so two accounts' `claude-code` agents never share one; two sessions of ONE account collide only if they declare the same client name and their ids share the first eight hex digits (about one in 4.3 billion per pair). **Residual:** a reconnect gets a new session id, so an agent's own lease from before the reconnect reads as someone else's until it expires (15 minutes by default). The cost is that the agent skips the item for that window, and the lead ruled that lockout beats two agents doing the same work. A modern (stateless) request has no session id, so its holder is the name alone. A claim refused because another holder has the lease answers `lease_held` on both transports, with `details.holder` and `details.expires_at` (BUG-3496), so an agent can see whose it is and when it frees. diff --git a/internal/cli/client.go b/internal/cli/client.go index ddd386c64..318c28116 100644 --- a/internal/cli/client.go +++ b/internal/cli/client.go @@ -1880,6 +1880,41 @@ func IsCommentHasReplies(err error) (*APIError, bool) { return nil, false } +// LeaseHeldCode is the structured code for a claim on an item another holder +// leases (BUG-3496). Keep it, and the hint, in lockstep with internal/mcp's +// allowedStructuredErrorCodes and LeaseHeldHint. +const LeaseHeldCode = "lease_held" + +// LeaseHeldHint is the recovery guidance for LeaseHeldCode. +const LeaseHeldHint = "Another holder (details.holder) has claimed this item until details.expires_at. " + + "Pick other work, or wait until the lease expires; claiming again before then is refused the same way." + +// IsLeaseHeld reports whether err is the lease refusal. +func IsLeaseHeld(err error) (*APIError, bool) { + var apiErr *APIError + if errors.As(err, &apiErr) && apiErr.Code == LeaseHeldCode { + return apiErr, true + } + return nil, false +} + +// WriteLeaseHeldError writes the structured marker line for the lease +// refusal, so the stdio MCP transport reports lease_held with its holder and +// expiry instead of inferring a code from the prose. +func WriteLeaseHeldError(w io.Writer, apiErr *APIError) { + body := map[string]any{ + "code": LeaseHeldCode, + "message": apiErr.Message, + "hint": LeaseHeldHint, + } + if len(apiErr.Details) > 0 { + body["details"] = apiErr.Details + } + if data, err := json.Marshal(map[string]any{"error": body}); err == nil { + fmt.Fprintln(w, StructuredErrorMarker+string(data)) + } +} + // CommentDeletedCode is the structured code for a write addressed to a // comment tombstone (BUG-3252): an edit, a reply or a reaction. Keep it, and // the hint, in lockstep with internal/mcp's allowedStructuredErrorCodes and diff --git a/internal/mcp/bug2772_remote_agent_identity_test.go b/internal/mcp/bug2772_remote_agent_identity_test.go new file mode 100644 index 000000000..ff8c8f39e --- /dev/null +++ b/internal/mcp/bug2772_remote_agent_identity_test.go @@ -0,0 +1,381 @@ +package mcp + +// BUG-2772: a write over remote /mcp is an AGENT write, named by the client's +// declared clientInfo (IDEA-2791 Tier B): the per-request _meta clientInfo of +// a modern request, else the clientInfo a legacy session sent at initialize +// (remembered by the Mcp-Session-Id pad issued), else unnamed, and never the +// human. Driven end to end: the real Streamable HTTP transport, a tool whose +// handler calls the dispatcher as every catalog action does (its own ctx, +// with WithDispatchInput), the real server and store. + +import ( + "context" + "encoding/json" + "io" + "net/http" + "net/http/httptest" + "strings" + "testing" + + "github.com/google/uuid" + + "github.com/PerpetualSoftware/pad/internal/cli" + "github.com/mark3labs/mcp-go/mcp" + "github.com/mark3labs/mcp-go/server" + + "github.com/PerpetualSoftware/pad/internal/models" + padserver "github.com/PerpetualSoftware/pad/internal/server" + "github.com/PerpetualSoftware/pad/internal/store" + "github.com/PerpetualSoftware/pad/internal/store/storetest" +) + +type bug2772Sessions struct{} + +func (bug2772Sessions) Generate() string { return "pad-mcp-" + uuid.NewString() } +func (bug2772Sessions) Validate(string) (bool, error) { return false, nil } +func (bug2772Sessions) Terminate(string) (bool, error) { return false, nil } + +type bug2772World struct { + t *testing.T + s *store.Store + srv *padserver.Server + ws *models.Workspace + url string + owner *models.User +} + +func newBUG2772World(t *testing.T) *bug2772World { + t.Helper() + s := storetest.NewSQLite(t) + srv := padserver.New(s) + t.Cleanup(srv.Stop) + owner, err := s.CreateUser(models.UserCreate{Email: "mcp-2772@example.com", Name: "Owner", Password: "correct-horse-battery-staple"}) + if err != nil { + t.Fatal(err) + } + ws, err := s.CreateWorkspace(models.WorkspaceCreate{Name: "MCP 2772", Slug: "mcp-2772", OwnerID: owner.ID}) + if err != nil { + t.Fatal(err) + } + if err := s.AddWorkspaceMember(ws.ID, owner.ID, "owner"); err != nil { + t.Fatal(err) + } + if err := s.SeedCollectionsFromTemplate(ws.ID, "startup"); err != nil { + t.Fatal(err) + } + other, err := s.CreateUser(models.UserCreate{Email: "mcp-2772-other@example.com", Name: "Other", Password: "correct-horse-battery-staple"}) + if err != nil { + t.Fatal(err) + } + if err := s.AddWorkspaceMember(ws.ID, other.ID, "editor"); err != nil { + t.Fatal(err) + } + + clients := NewClientRegistry() + d := &HTTPHandlerDispatcher{Handler: srv, Clients: clients, UserResolver: func(ctx context.Context) *models.User { + u, _ := padserver.CurrentUserFromContext(ctx) + return u + }} + mcpSrv := NewServer(Options{Version: "test", Clients: clients}) + mcpSrv.MCP().AddTool(mcp.NewTool("create_task", mcp.WithString("title")), func(ctx context.Context, req mcp.CallToolRequest) (*mcp.CallToolResult, error) { + input := map[string]any{"workspace": ws.Slug, "collection": "tasks", "title": req.GetString("title", "")} + res, err := d.Dispatch(WithDispatchInput(ctx, input), []string{"item", "create"}, nil) + if err != nil { + return nil, err + } + return res, nil + }) + mcpSrv.MCP().AddTool(mcp.NewTool("claim_task", mcp.WithString("ref")), func(ctx context.Context, req mcp.CallToolRequest) (*mcp.CallToolResult, error) { + input := map[string]any{"workspace": ws.Slug, "ref": req.GetString("ref", "")} + return d.Dispatch(WithDispatchInput(ctx, input), []string{"item", "claim"}, nil) + }) + mcpSrv.MCP().AddTool(mcp.NewTool("next"), func(ctx context.Context, req mcp.CallToolRequest) (*mcp.CallToolResult, error) { + return d.Dispatch(WithDispatchInput(ctx, map[string]any{"workspace": ws.Slug}), []string{"project", "next"}, nil) + }) + // Stands in for the /mcp auth middleware: the request's user goes on its + // context, the owner unless the test names the other member. + transport := NewRemoteTransport(mcpSrv.MCP(), bug2772Sessions{}) + ts := httptest.NewServer(http.HandlerFunc(func(rw http.ResponseWriter, r *http.Request) { + u := owner + if r.Header.Get(bug2772UserHeader) == "other" { + u = other + } + transport.ServeHTTP(rw, r.WithContext(padserver.WithCurrentUser(r.Context(), u))) + })) + t.Cleanup(ts.Close) + return &bug2772World{t: t, s: s, srv: srv, ws: ws, url: ts.URL + "/mcp", owner: owner} +} + +// bug2772UserHeader picks the request's user in the test world. +const bug2772UserHeader = "X-Test-User" + +func (w *bug2772World) post(body, session string, headers map[string]string) (string, string) { + w.t.Helper() + req, _ := http.NewRequest(http.MethodPost, w.url, strings.NewReader(body)) + req.Header.Set("Content-Type", "application/json") + req.Header.Set("Accept", "application/json, text/event-stream") + if session != "" { + req.Header.Set("Mcp-Session-Id", session) + } + for k, v := range headers { + req.Header.Set(k, v) + } + resp, err := http.DefaultClient.Do(req) + if err != nil { + w.t.Fatal(err) + } + defer resp.Body.Close() + raw, _ := io.ReadAll(resp.Body) + if resp.StatusCode/100 != 2 { + w.t.Fatalf("POST %s: %d %s", body, resp.StatusCode, raw) + } + return string(raw), resp.Header.Get("Mcp-Session-Id") +} + +// initialize runs a legacy handshake with the given clientInfo name and +// returns the session id pad issued. +func (w *bug2772World) initialize(clientName string) string { + w.t.Helper() + body := `{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":` + mustJSONString(clientName) + `,"version":"9.9"}}}` + _, session := w.post(body, "", nil) + if session == "" { + w.t.Fatal("precondition: initialize issued no Mcp-Session-Id") + } + w.post(`{"jsonrpc":"2.0","method":"notifications/initialized"}`, session, nil) + return session +} + +// create calls the tool and returns the stored item's activity. +func (w *bug2772World) create(title, session string) (createdBy, agent string) { + w.t.Helper() + raw, _ := w.post(`{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"create_task","arguments":{"title":`+mustJSONString(title)+`}}}`, session, map[string]string{"MCP-Protocol-Version": "2025-11-25"}) + if strings.Contains(raw, `"isError":true`) { + w.t.Fatalf("create %q failed: %s", title, raw) + } + return w.stored(title) +} + +func (w *bug2772World) stored(title string) (createdBy, agent string) { + w.t.Helper() + items, err := w.s.ListItems(w.ws.ID, models.ItemListParams{CollectionSlug: "tasks"}) + if err != nil { + w.t.Fatal(err) + } + for _, it := range items { + if it.Title != title { + continue + } + acts, err := w.s.ListDocumentActivity(it.ID, models.ActivityListParams{}) + if err != nil { + w.t.Fatal(err) + } + for _, a := range acts { + if a.Action == "created" { + return it.CreatedBy, models.AgentNameFromMetadata(a.Metadata) + } + } + w.t.Fatalf("no created activity for %q", title) + } + w.t.Fatalf("no item titled %q", title) + return "", "" +} + +// call runs a tool and returns its raw JSON-RPC response. +func (w *bug2772World) call(tool, args, session string) string { + w.t.Helper() + raw, _ := w.post(`{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"`+tool+`","arguments":`+args+`}}`, session, map[string]string{"MCP-Protocol-Version": "2025-11-25"}) + return raw +} + +func mustJSONString(s string) string { + b, _ := json.Marshal(s) + return string(b) +} + +func TestBUG2772_RemoteMCPWritesAreAgentWrites(t *testing.T) { + w := newBUG2772World(t) + + t.Run("a legacy session's declared client names the write", func(t *testing.T) { + session := w.initialize("claude-code") + by, agent := w.create("from claude code", session) + if by != "agent" || agent != "claude-code" { + t.Fatalf("created_by=%q agent=%q, want agent / claude-code", by, agent) + } + }) + + t.Run("two sessions keep their own names", func(t *testing.T) { + a := w.initialize("cursor") + b := w.initialize("chatgpt") + if _, agent := w.create("from cursor", a); agent != "cursor" { + t.Errorf("session a wrote as %q", agent) + } + if _, agent := w.create("from chatgpt", b); agent != "chatgpt" { + t.Errorf("session b wrote as %q", agent) + } + }) + + t.Run("a client that declared no name: still an agent write, unnamed", func(t *testing.T) { + session := w.initialize("") + by, agent := w.create("from a nameless client", session) + if by != "agent" || agent != "" { + t.Fatalf("created_by=%q agent=%q, want agent / (none)", by, agent) + } + }) + + t.Run("a session this instance never saw: an agent write, unnamed, never a guessed name", func(t *testing.T) { + by, agent := w.create("from an unknown session", "pad-mcp-"+uuid.NewString()) + if by != "agent" || agent != "" { + t.Fatalf("created_by=%q agent=%q, want agent / (none)", by, agent) + } + }) + + t.Run("another user's session id carries no name", func(t *testing.T) { + // The transport accepts any Mcp-Session-Id, so a caller who learned + // another account's session id can send it. The name that session + // declared stays with the account that declared it. + session := w.initialize("claude-code") + title := "borrowed session id" + raw, _ := w.post(`{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"create_task","arguments":{"title":`+mustJSONString(title)+`}}}`, + session, map[string]string{"MCP-Protocol-Version": "2025-11-25", bug2772UserHeader: "other"}) + if strings.Contains(raw, `"isError":true`) { + t.Fatalf("create failed: %s", raw) + } + if by, agent := w.stored(title); by != "agent" || agent != "" { + t.Fatalf("created_by=%q agent=%q, want agent / (none): the other user wrote under the owner's session name", by, agent) + } + // The owner, on the same session, still gets its name. + if _, agent := w.create("owner on its own session", session); agent != "claude-code" { + t.Fatalf("the owner's own session lost its name: %q", agent) + } + }) + + t.Run("CONTROL: the dispatcher's own request, minus the remote-caller mark, is the human's", func(t *testing.T) { + // buildHTTPRequest is what the dispatcher sends, without the + // WithRemoteMCPCaller mark: so the mark, and nothing else about the + // in-process request, is what makes the writes above agent writes. + req, err := buildHTTPRequest(context.Background(), http.MethodPost, + "/api/v1/workspaces/"+w.ws.Slug+"/collections/tasks/items", []byte(`{"title":"typed by the human"}`), w.owner) + if err != nil { + t.Fatal(err) + } + rr := httptest.NewRecorder() + w.srv.ServeHTTP(rr, req) + if rr.Code != http.StatusCreated { + t.Fatalf("create: %d %s", rr.Code, rr.Body.String()) + } + if by, agent := w.stored("typed by the human"); by != "user" || agent != "" { + t.Fatalf("created_by=%q agent=%q, want user / (none)", by, agent) + } + }) +} + +func TestBUG2772_RemoteLeaseHolderIsPerConnection(t *testing.T) { + // Lead ruling: a remote caller's default lease holder is its client name + // plus a short session id, so two connections of one client do not + // silently share a claim, and next/ready agree with the claim default + // (both go through defaultLeaseHolder). + w := newBUG2772World(t) + tasks, err := w.s.GetCollectionBySlug(w.ws.ID, "tasks") + if err != nil || tasks == nil { + t.Fatalf("tasks: %v", err) + } + it, err := w.s.CreateItem(w.ws.ID, tasks.ID, models.ItemCreate{Title: "Claim me", Fields: `{"status":"open","priority":"critical"}`}) + if err != nil { + t.Fatal(err) + } + a := w.initialize("claude-code") + b := w.initialize("claude-code") + + if raw := w.call("claim_task", `{"ref":"`+it.Ref+`"}`, a); strings.Contains(raw, `"isError":true`) { + t.Fatalf("session a's claim failed: %s", raw) + } + lease, err := w.s.GetItemLease(it.ID) + if err != nil || lease == nil { + t.Fatalf("no lease stored: %v", err) + } + if want := "claude-code#" + shortSessionID(a); lease.Holder != want { + t.Fatalf("holder = %q, want %q", lease.Holder, want) + } + + // The same client on another connection is a different holder, refused + // as lease_held with the holder and expiry (BUG-3496: the remote + // classifier used to drop that code and answer `conflict`). + raw := w.call("claim_task", `{"ref":"`+it.Ref+`"}`, b) + var resp struct { + Result struct { + IsError bool `json:"isError"` + StructuredContent struct { + Error struct { + Code string `json:"code"` + Hint string `json:"hint"` + Details struct { + Holder string `json:"holder"` + ExpiresAt string `json:"expires_at"` + } `json:"details"` + } `json:"error"` + } `json:"structuredContent"` + } `json:"result"` + } + if err := json.Unmarshal([]byte(raw), &resp); err != nil || !resp.Result.IsError { + t.Fatalf("session b claimed an item session a holds (err %v): %s", err, raw) + } + e := resp.Result.StructuredContent.Error + if e.Code != string(ErrLeaseHeld) || e.Hint != LeaseHeldHint { + t.Fatalf("code = %q hint = %q, want lease_held with LeaseHeldHint: %s", e.Code, e.Hint, raw) + } + if e.Details.Holder != lease.Holder || e.Details.ExpiresAt == "" { + t.Fatalf("details holder = %q expires_at = %q, want %q and an expiry: %s", + e.Details.Holder, e.Details.ExpiresAt, lease.Holder, raw) + } + + // next/ready: the holder still sees its own claim; the other does not. + if raw := w.call("next", `{}`, a); !strings.Contains(raw, it.Ref) { + t.Errorf("session a's own claim was hidden from its next: %s", raw) + } + if raw := w.call("next", `{}`, b); strings.Contains(raw, it.Ref) { + t.Errorf("session b was offered an item session a holds: %s", raw) + } +} + +func TestBUG2772_ResolveRemoteCaller(t *testing.T) { + r := NewClientRegistry() + + t.Run("a modern request's own _meta clientInfo wins", func(t *testing.T) { + ctx := server.WithRequestProtocolInfo(context.Background(), &server.RequestProtocolInfo{ + Modern: true, ClientInfo: &mcp.Implementation{Name: "modern-client"}, + }) + c := r.resolveRemoteCaller(ctx) + if c.Name != "modern-client" || c.LeaseHolder != "modern-client" { + t.Fatalf("got %+v", c) + } + }) + + t.Run("nothing declared and no session: unnamed, with a fallback lease holder", func(t *testing.T) { + c := r.resolveRemoteCaller(context.Background()) + if c.Name != "" || c.LeaseHolder != remoteAgentFallback { + t.Fatalf("got %+v", c) + } + }) + + t.Run("short session id", func(t *testing.T) { + if got := shortSessionID("pad-mcp-3f9a12c4-0000"); got != "3f9a12c4" { + t.Fatalf("got %q", got) + } + }) + + t.Run("a nil registry still resolves (unnamed)", func(t *testing.T) { + var nilReg *ClientRegistry + if c := nilReg.resolveRemoteCaller(context.Background()); c.Name != "" { + t.Fatalf("got %+v", c) + } + }) +} + +func TestCLIAndMCPAgreeOnLeaseHeld(t *testing.T) { + if cli.LeaseHeldCode != string(ErrLeaseHeld) { + t.Errorf("code strings differ: cli %q, mcp %q", cli.LeaseHeldCode, ErrLeaseHeld) + } + if cli.LeaseHeldHint != LeaseHeldHint { + t.Errorf("hints differ:\n cli %q\n mcp %q", cli.LeaseHeldHint, LeaseHeldHint) + } +} diff --git a/internal/mcp/client_identity.go b/internal/mcp/client_identity.go new file mode 100644 index 000000000..1ccc6e916 --- /dev/null +++ b/internal/mcp/client_identity.go @@ -0,0 +1,234 @@ +package mcp + +import ( + "context" + "log/slog" + "strings" + "sync" + "time" + + "github.com/mark3labs/mcp-go/mcp" + "github.com/mark3labs/mcp-go/server" + + padserver "github.com/PerpetualSoftware/pad/internal/server" +) + +// Remote MCP caller identity (BUG-2772, IDEA-2791 Tier B). +// +// A remote /mcp write used to reach the handlers with no X-Pad-Agent, so it +// was recorded as the human. The client's own declaration, MCP clientInfo, is +// now the agent name: +// +// 1. a MODERN request carries clientInfo in its own _meta (stateless; nothing +// to remember, and it works across instances); +// 2. a LEGACY client sends clientInfo once, at initialize, and echoes the +// Mcp-Session-Id pad issued on every later request (measured: Claude Code +// 2.1.294), so ClientRegistry remembers it by that id. mcp-go's own session +// state does not survive pad's stateless transport: a later POST gets an +// ephemeral session that never saw initialize; +// 3. otherwise no name, and the write is STILL an agent write (an app acting +// for the user), never the human and never a guessed name. +// +// Self-declared, recorded verbatim, like the CLI's X-Pad-Agent. + +const ( + // clientRegistryTTL matches the active-sessions tracker's idle window + // (TASK-1120): a session unused this long is forgotten. + clientRegistryTTL = 30 * time.Minute + // clientRegistryMax bounds memory; past it the stalest entry goes. + clientRegistryMax = 10000 + // remoteAgentFallback names a remote caller in its lease holder when it + // declared nothing. Never stored as the agent name. + remoteAgentFallback = "mcp-client" +) + +// ClientRegistry remembers each legacy session's clientInfo by the +// Mcp-Session-Id pad issued at initialize AND the user who initialized it. +// Per instance and in memory: a request that lands on another instance, or +// after a restart, falls back to the nameless agent write. +// +// The user is part of the key because the transport accepts any incoming +// Mcp-Session-Id: keyed on the id alone, a caller who learned another +// session's id could send it and have its own writes carry that session's +// declared name. Keyed on (user, id), the only name a caller can reach is +// one its own account declared. +type ClientRegistry struct { + mu sync.Mutex + entries map[string]*clientEntry + now func() time.Time + // owner returns the authenticated user's id from a request's context, + // "" when there is none (then nothing is recorded or looked up). + owner func(context.Context) string +} + +type clientEntry struct { + name string + seen time.Time +} + +// NewClientRegistry returns an empty registry. +func NewClientRegistry() *ClientRegistry { + return &ClientRegistry{entries: map[string]*clientEntry{}, now: time.Now, owner: currentUserID} +} + +// currentUserID is the id of the user the /mcp auth middleware put on the +// request's context. +func currentUserID(ctx context.Context) string { + if u, ok := padserver.CurrentUserFromContext(ctx); ok && u != nil { + return u.ID + } + return "" +} + +// registryKey binds a session id to the user who presented it; "" when +// either is missing, which records and finds nothing. +func registryKey(userID, sessionID string) string { + if userID == "" || sessionID == "" { + return "" + } + return userID + "\x00" + sessionID +} + +// record stores a session's client name, evicting expired and, past the +// bound, the stalest entries. +func (r *ClientRegistry) record(key, name string) { + if r == nil || key == "" || name == "" { + return + } + r.mu.Lock() + defer r.mu.Unlock() + now := r.now() + if len(r.entries) >= clientRegistryMax { + var oldestID string + var oldest time.Time + for id, e := range r.entries { + if now.Sub(e.seen) > clientRegistryTTL { + delete(r.entries, id) + continue + } + if oldestID == "" || e.seen.Before(oldest) { + oldestID, oldest = id, e.seen + } + } + if len(r.entries) >= clientRegistryMax && oldestID != "" { + delete(r.entries, oldestID) + } + } + r.entries[key] = &clientEntry{name: name, seen: now} +} + +// lookup returns a live session's client name and refreshes it. +func (r *ClientRegistry) lookup(key string) string { + if r == nil || key == "" { + return "" + } + r.mu.Lock() + defer r.mu.Unlock() + e, ok := r.entries[key] + if !ok { + return "" + } + now := r.now() + if now.Sub(e.seen) > clientRegistryTTL { + delete(r.entries, key) + return "" + } + e.seen = now + return e.name +} + +// hooks returns the mcp-go hooks that feed the registry from initialize, and +// log the declared client once per handshake: the data that tells which +// clients send what (BUG-2772). Name, version and protocol only; never a +// token or a header. +func (r *ClientRegistry) hooks() *server.Hooks { + h := &server.Hooks{} + h.AddAfterInitialize(func(ctx context.Context, _ any, msg *mcp.InitializeRequest, _ *mcp.InitializeResult) { + if msg == nil { + return + } + info := msg.Params.ClientInfo + sessionID := "" + if s := server.ClientSessionFromContext(ctx); s != nil { + sessionID = s.SessionID() + } + slog.Info("mcp client initialized", + "client_name", cleanClientName(info.Name), + "client_version", cleanClientName(info.Version), + "protocol_version", msg.Params.ProtocolVersion, + "transport", "streamable-http", + "session_tracked", sessionID != "") + r.record(registryKey(r.owner(ctx), sessionID), cleanClientName(info.Name)) + }) + return h +} + +// cleanClientName trims a client-declared string and drops control +// characters, so a log line or a stored name cannot be forged by it. The +// server's agentNameFromRequest bounds the stored length. +func cleanClientName(s string) string { + var b strings.Builder + for _, c := range strings.TrimSpace(s) { + if c < 0x20 || c == 0x7f { + continue + } + b.WriteRune(c) + } + return b.String() +} + +// RemoteCaller is the identity a remote /mcp request writes under. +type RemoteCaller struct { + // Name is the declared client name ("claude-code"); empty when the + // client declared nothing, which still records an agent write. + Name string + // LeaseHolder is the default lease holder: Name (or remoteAgentFallback) + // plus a short id from the session, so two connections of one client do + // not silently share a lease (lead ruling, BUG-2772). + LeaseHolder string +} + +// resolveRemoteCaller applies the precedence: a modern request's own _meta +// clientInfo, then the legacy session's remembered clientInfo, then nothing. +func (r *ClientRegistry) resolveRemoteCaller(ctx context.Context) RemoteCaller { + name := "" + if info := server.RequestProtocolInfoFromContext(ctx); info != nil && info.ClientInfo != nil { + name = cleanClientName(info.ClientInfo.Name) + } + sessionID := "" + if s := server.ClientSessionFromContext(ctx); s != nil { + sessionID = s.SessionID() + } + if name == "" && r != nil { + name = r.lookup(registryKey(r.owner(ctx), sessionID)) + } + base := name + if base == "" { + base = remoteAgentFallback + } + holder := base + if short := shortSessionID(sessionID); short != "" { + holder = base + "#" + short + } + return RemoteCaller{Name: name, LeaseHolder: holder} +} + +// shortSessionID is the first eight hex characters of the session's UUID +// ("pad-mcp-3f9a12c4-…" gives "3f9a12c4"): enough to tell one user's +// concurrent connections apart, short enough to read in a lease. A lease is +// ours only when its label AND its user match (store.ClaimItemLease), so a +// collision needs two live sessions of one ACCOUNT with the same client name +// and the same eight digits. +func shortSessionID(id string) string { + id = strings.TrimPrefix(id, "pad-mcp-") + var b strings.Builder + for _, c := range id { + if b.Len() == 8 { + break + } + if (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') { + b.WriteRune(c) + } + } + return b.String() +} diff --git a/internal/mcp/dispatch_http.go b/internal/mcp/dispatch_http.go index 2bbcca6e1..e59f579ac 100644 --- a/internal/mcp/dispatch_http.go +++ b/internal/mcp/dispatch_http.go @@ -68,6 +68,10 @@ import ( // yet wire produce a clear "not yet implemented over HTTP transport" // error rather than failing silently — see Dispatch below. type HTTPHandlerDispatcher struct { + // Clients resolves the remote caller's declared identity (BUG-2772). Nil + // still records every write as an agent write, unnamed. + Clients *ClientRegistry + // Handler is the pad-cloud API router. *server.Server already // satisfies http.Handler via its ServeHTTP method. Handler http.Handler @@ -624,10 +628,17 @@ func (d *HTTPHandlerDispatcher) buildAuthedRequest( if isMutatingMethod(method) && d.RequireVerifiedEmail != nil && d.RequireVerifiedEmail(user) { return nil, fmt.Errorf("%s: verify your email address before mutating content over MCP", errEmailNotVerifiedPrefix) } + // Who is writing (BUG-2772): an agent acting for the user, named by the + // client's declared clientInfo when it gave one. + caller := d.Clients.resolveRemoteCaller(ctx) + ctx = server.WithRemoteMCPCaller(ctx, server.RemoteMCPCaller{LeaseHolder: caller.LeaseHolder}) req, err := buildHTTPRequest(ctx, method, urlPath, body, user) if err != nil { return nil, err } + if caller.Name != "" { + req.Header.Set("X-Pad-Agent", caller.Name) + } if d.Apply != nil { req = d.Apply(req) } diff --git a/internal/mcp/errors.go b/internal/mcp/errors.go index 1b7e2d62a..0756bd593 100644 --- a/internal/mcp/errors.go +++ b/internal/mcp/errors.go @@ -203,6 +203,13 @@ const ( // comment_has_replies; that code stays for servers that predate it. ErrCommentDeleted ErrorCode = "comment_deleted" + // ErrLeaseHeld fires on HTTP 409 responses that carry + // error.code="lease_held" (BUG-3496): a claim on an item another holder + // leases. Details carries ref, holder, acquired_at and expires_at, so the + // caller can see who has it and until when. A retry before expires_at + // refuses identically. + ErrLeaseHeld ErrorCode = "lease_held" + // ErrStoredStateUnreadable fires when an operation is refused because // the ITEM'S STORED STATE cannot be decoded — today, an append to an // implementation_notes / decision_log field whose value is not a list @@ -475,6 +482,9 @@ var allowedStructuredErrorCodes = map[string]struct{}{ // BUG-3252 tombstone: a write addressed to a deleted comment that is // kept only to hold its replies. "comment_deleted": {}, + // BUG-3496: a claim on an item someone else leases. details.holder and + // details.expires_at say who and until when. + "lease_held": {}, // BUG-2675. The only entry whose marker is written for a LOCALLY // generated refusal rather than an upstream APIError — the CLI's // append helpers refuse before any request is made (see @@ -1012,6 +1022,10 @@ func classifyHTTPStatusKind( // The tombstone stays a tombstone; no retry changes it. hint = CommentDeletedHint } + if upstream.Code == string(ErrLeaseHeld) { + // The lease stands until it expires or its holder releases it. + hint = LeaseHeldHint + } if upstream.Code == string(ErrStoredStateUnreadable) { // Same reason: the stored value stays undecodable, so every // retry refuses identically. Since BUG-3056 the note/decide @@ -1360,6 +1374,12 @@ const CommentHasRepliesHint = "Nothing was deleted. Delete the replies first (th const CommentDeletedHint = "The comment was deleted and is kept only as a placeholder for its replies, so it cannot be edited, " + "replied to or reacted to. Comment on the item, or reply to one of its replies, instead." +// LeaseHeldHint is the recovery guidance for ErrLeaseHeld on the remote +// transport. Duplicated in internal/cli (LeaseHeldHint), whose marker carries +// it on stdio; keep the two identical. +const LeaseHeldHint = "Another holder (details.holder) has claimed this item until details.expires_at. " + + "Pick other work, or wait until the lease expires; claiming again before then is refused the same way." + // ContentPendingFlushHint is the recovery guidance for ErrContentPendingFlush, // on both transports. Duplicated in internal/cli (ContentPendingFlushHint) for // the same dependency-graph reason StructuredErrorMarker is; a test asserts the diff --git a/internal/mcp/instructions.md b/internal/mcp/instructions.md index 2d3a8547e..5f8b40248 100644 --- a/internal/mcp/instructions.md +++ b/internal/mcp/instructions.md @@ -6,7 +6,7 @@ Pad is a project tracker for developers and AI agents — issues (TASK, BUG), pl If the user is asking general code questions with no project-management thread, you don't need this server. -## Tool surface (v0.76) +## Tool surface (v0.77) Ten resource × action tools, plus `pad_set_workspace`. Eleven tools total. diff --git a/internal/mcp/server.go b/internal/mcp/server.go index 741e0f5b8..a731d4d0a 100644 --- a/internal/mcp/server.go +++ b/internal/mcp/server.go @@ -43,6 +43,10 @@ type Options struct { // Experimental replaces capabilities.experimental when non-nil. Nil // keeps experimentalCapabilities(). Experimental map[string]any + + // Clients, when set, records each session's declared clientInfo at + // initialize for the remote dispatcher (BUG-2772). Remote transports only. + Clients *ClientRegistry } // NewServer constructs a pad MCP server. Call Run(ctx) to start it. @@ -64,9 +68,7 @@ func NewServer(opts Options) *Server { if experimental == nil { experimental = experimentalCapabilities() } - mcp := server.NewMCPServer( - ServerName, - version, + options := []server.ServerOption{ // Declare tool capability up-front so clients know the server // CAN serve tools. The list stays empty until TASK-945 wires // in the cmdhelp-derived registry. @@ -87,7 +89,12 @@ func NewServer(opts Options) *Server { // versioned with the binary; HTTPHandlerDispatcher (PLAN-943) // advertises the same string. server.WithInstructions(instructions), - ) + } + if opts.Clients != nil { + // BUG-2772: record each session's declared client at initialize. + options = append(options, server.WithHooks(opts.Clients.hooks())) + } + mcp := server.NewMCPServer(ServerName, version, options...) return &Server{mcp: mcp, debug: opts.Debug} } diff --git a/internal/mcp/too_large_test.go b/internal/mcp/too_large_test.go index 1e3b23f66..4e89b89f0 100644 --- a/internal/mcp/too_large_test.go +++ b/internal/mcp/too_large_test.go @@ -199,6 +199,9 @@ func TestEveryCLIMarkerCodeIsInTheStdioVocabulary(t *testing.T) { "WriteCommentDeletedError": func(w *bytes.Buffer) { cli.WriteCommentDeletedError(w, api("comment_deleted")) }, + "WriteLeaseHeldError": func(w *bytes.Buffer) { + cli.WriteLeaseHeldError(w, api("lease_held")) + }, } for name, write := range writers { diff --git a/internal/mcp/version.go b/internal/mcp/version.go index 614ad0c57..f9809b6de 100644 --- a/internal/mcp/version.go +++ b/internal/mcp/version.go @@ -1738,6 +1738,27 @@ const CmdhelpVersion = "0.1" // caller cannot read embeds nothing; a failed fetch stays non-fatal, // as on stdio. Stdio is unchanged. // +// 0.77 — BUG-2772 (lead ruling; IDEA-2791 Tier B). BEHAVIOR bump on the +// v0.76 / v0.49 grounds: a write over REMOTE /mcp is now recorded as an +// AGENT write (created_by / actor "agent"), named by the client's declared +// MCP clientInfo.name ("claude-code"), where it was recorded as the +// human. The name comes from a modern request's own _meta clientInfo, +// else the clientInfo the session sent at initialize (remembered per +// instance by the Mcp-Session-Id pad issued and the account that +// presented it, 30-minute idle TTL), else +// none: an unnamed agent write, never the human and never a guessed name. +// The default lease holder of a remote call is that name (or +// "mcp-client") plus a short id from the session, e.g. +// "claude-code#3f9a12c4", so two connections of one client do not share a +// lease; a reconnect gets a new session id, so the agent's own earlier +// lease reads as foreign until it expires (at most 15 minutes by +// default). Stdio is unchanged. No name, enum or param moved. +// BUG-3496 rides with it: a claim refused because another holder has +// the lease reaches the caller as `lease_held` (details ref, holder, +// acquired_at, expires_at, and a hint not to retry before expiry) on +// both transports, where remote answered `conflict` and stdio +// `server_error`. +// // 0.76 — TASK-1809 (lead ruling). BEHAVIOR bump on the v0.70 / v0.49 // grounds: no tool name, action enum or param shape moved. Two // changes, one identity: @@ -1916,7 +1937,7 @@ const CmdhelpVersion = "0.1" // this surface can receive it; the entry exists so a future action does // not collapse it to permission_denied. When an action that can reach // it is added, that addition is the contract change and owns the bump. -const ToolSurfaceVersion = "0.76" +const ToolSurfaceVersion = "0.77" // MetaVersionURI is the canonical URI of the queryable version document. // Lives outside the pad://workspace/{ws}/... namespace because it's a diff --git a/internal/server/context.go b/internal/server/context.go index 66b8693ef..448a6332b 100644 --- a/internal/server/context.go +++ b/internal/server/context.go @@ -281,6 +281,32 @@ func structuredEntryAuthor(r *http.Request) string { return actor } +// ctxRemoteMCPCaller marks an in-process request from the remote /mcp +// dispatcher (BUG-2772). Set only in-process; nothing reads it from the wire. +const ctxRemoteMCPCaller contextKey = "remote_mcp_caller" + +// RemoteMCPCaller is a remote MCP client acting for the authenticated user. +type RemoteMCPCaller struct { + // LeaseHolder is the caller's default lease holder: its declared client + // name, or a fallback, plus a short id from its MCP session, so two + // connections of one client do not share a lease (lead ruling). + LeaseHolder string +} + +// WithRemoteMCPCaller marks ctx as a remote MCP call. Every such write is an +// AGENT write (an app acting for the user), named by X-Pad-Agent when the +// client declared a name and unnamed when it did not, never the human +// (IDEA-2791's degradation contract). +func WithRemoteMCPCaller(ctx context.Context, c RemoteMCPCaller) context.Context { + return context.WithValue(ctx, ctxRemoteMCPCaller, c) +} + +// remoteMCPCaller reports the remote MCP caller a request carries, if any. +func remoteMCPCaller(r *http.Request) (RemoteMCPCaller, bool) { + c, ok := r.Context().Value(ctxRemoteMCPCaller).(RemoteMCPCaller) + return c, ok +} + // ChatGPTDoorVersionsContent is the U1b guarantee the ChatGPT catalog's // update_item description makes: a content write through the ChatGPT door // is versioned first (handleUpdateItem, isChatGPTSurface). The ChatGPT diff --git a/internal/server/handlers_documents.go b/internal/server/handlers_documents.go index f942972e8..302f29dfd 100644 --- a/internal/server/handlers_documents.go +++ b/internal/server/handlers_documents.go @@ -368,9 +368,13 @@ func actorFromRequest(r *http.Request) (actor, source string) { actor = "user" source = "web" - // If an agent name header is present, mark as agent + // If an agent name header is present, mark as agent. A remote MCP call + // is an agent write whether or not its client declared a name + // (BUG-2772): an app acting for the user, never the user typing. if agentNameFromRequest(r) != "" { actor = "agent" + } else if _, ok := remoteMCPCaller(r); ok { + actor = "agent" } // Determine source from auth method. Two signals — both mean diff --git a/internal/server/handlers_item_lease.go b/internal/server/handlers_item_lease.go index aaa55c82f..b985021d0 100644 --- a/internal/server/handlers_item_lease.go +++ b/internal/server/handlers_item_lease.go @@ -154,8 +154,10 @@ func (s *Server) resolveLeaseRequest(w http.ResponseWriter, r *http.Request) (it // defaultLeaseHolder is the holder a claim or release names when the caller // passes none, and the identity `pad project next` / `ready` compare leases -// against (TASK-1809): the request's agent name (X-Pad-Agent, which the CLI -// sets from the session registry), else the account's email, else its id. +// against (TASK-1809): for a remote MCP call, its client name plus a short +// session id (BUG-2772); else the request's agent name (X-Pad-Agent, which +// the CLI sets from the session registry); else the account's email, else its +// id. // // The agent name comes first because several agents commonly share ONE // account. With the email default, a second agent's claim matched the first @@ -164,6 +166,13 @@ func (s *Server) resolveLeaseRequest(w http.ResponseWriter, r *http.Request) (it // is still bound to the authenticated account (BUG-3341), so it can only // split the caller's own claims, never reach into another account's. func defaultLeaseHolder(r *http.Request, user *models.User) string { + // A remote MCP caller holds by its declared client name plus a short id + // from its MCP session (BUG-2772, lead ruling): two connections of one + // client, both "claude-code", must not silently share a lease. Ahead of + // X-Pad-Agent, which carries only the name. + if c, ok := remoteMCPCaller(r); ok && c.LeaseHolder != "" { + return c.LeaseHolder + } if name := agentNameFromRequest(r); name != "" { return name }