diff --git a/README.md b/README.md
index 2f0a2cb23..89986d335 100644
--- a/README.md
+++ b/README.md
@@ -402,7 +402,7 @@ 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 (v0.105)** — eleven 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 (v0.106)** — eleven 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 |
 |---|---|
@@ -427,7 +427,7 @@ Plus resources at `pad://workspaces`, `pad://workspace/{ws}/dashboard`,
 and `pad://_meta/version`.
 
 **Stability contract.** The catalog is versioned
-(`tool_surface_version: "0.105"`) and advertised in the initialize handshake and at
+(`tool_surface_version: "0.106"`) 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/docs/mcp.md b/docs/mcp.md
index ea50f83ed..ec26f56ea 100644
--- a/docs/mcp.md
+++ b/docs/mcp.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` (the constant in `internal/mcp/version.go` is the current value) — the cmdhelp CLI help-tree contract. Bump when CLI flag/arg schemas change incompatibly.
-- `ToolSurfaceVersion` (the constant in `internal/mcp/version.go` is the current value; this list is its changelog, newest first) — the MCP tool catalog contract. Bump when tool names, action enums, or parameter shapes change incompatibly. **v0.105** (BUG-4070) applies v0.104's rule on stdio to every top-level parameter declared `"number"`, before the value becomes CLI text. A string used to reach the CLI verbatim: an int flag parses base 0, so `"010"` was 8, `"0x10"` 16, `"1_000"` 1000 and `"+5"` 5, and `pad_chat` delete's positional `seq` parses base 10, so `"010"` was 10. Now a string is accepted only as a plain decimal integer with no leading zero, bounded |x| < 2^53, and forwarded unchanged; every other string is refused with `validation_failed` naming the parameter. A JSON number used to be formatted and forwarded whatever its size; now one that is not whole, or of magnitude 2^53 or more (which the decoder may already have rounded), is refused the same way, as remote has since v0.103. For a string or a JSON number, stdio now accepts and refuses what remote does. Other types keep their path: `intParam` (`pad_item` list and history `limit`) reads `null` as absent, so the default applies (v0.104), and refuses a bool, an array or an object; everywhere else the CLI's own parse refuses all of them; the nested `pad_item.patch` `edits[].line_hint` is BUG-4082. Behaviour only; the schemas are unchanged, as for v0.103 and v0.104. **v0.104** (BUG-4065) stops reading a numeric parameter's non-number value as absent. A string, a bool, an object or an array used to be dropped, so the default applied, and a string `expected_seq` made a content write unguarded. Now only `null` is absent. A string is accepted when it is a plain decimal integer with no leading zero (an optional `-`, then `0` or digits not starting with `0`), parsed exactly and bounded like a JSON number (|x| < 2^53): `"10"` is 10, and `"123"` is a guarded write. Every other string (`"010"`, `"1.0"`, `"1e3"`, `" 10"`, `"+10"`, `""`) and every other type is refused with `validation_failed` naming the parameter; `"010"` is refused because stdio's CLI flags read it as octal 8. An empty string or `false` is refused, not skipped as absent. It covers the v0.103 doors, including every numeric key on a query-string door (item backlinks, item search, item context's `budget`, project activity, project standup and changelog), where a bool, an object or `"abc"` used to reach the server's `Atoi` and silently become its default, plus `pad_item.update`'s and `pad_item.patch`'s `expected_seq`, `pad_item.patch`'s `edits[].line_hint`, `pad_item.link-pr`'s `pr_number` (a `json.Number` is read exactly; 2^53 itself is now refused), the `sort_order` of `pad_collection` and `pad_role` update (which used to reach the server's decode as a 400), and `pad_chat`'s `since`, `limit`, `reply_to`, `seq` and `to` (2^53 now bounds a float64; `json.Number` `"1e6"` is accepted; a present `null` is still refused there, as before, with the same message). Non-numeric query keys are still forwarded verbatim. The parameters are declared `number`, so the bump is owed by behaviour, as for v0.103. **v0.103** (BUG-4061) refuses a numeric parameter that is not a whole int64, with `validation_failed` naming it, where it used to be silently changed: a fraction truncated (`limit: 1.5` read as 1, and `pad_item.list`'s `limit: 0.5` as the default), a value outside int64 converted to an implementation-defined one, and a `json.Number` that did not parse was dropped as absent. It covers `limit`, `offset` and `days` on every door that reads them locally, `pad_item.list`'s and `pad_item.history`'s `limit`, every query-string door the remote dispatcher builds with `buildQuery` (item backlinks, item context's `budget`, project activity, item search, project standup and changelog), whose server parsers used to read a forwarded `1.5` as absent and use their default, and `expected_seq` (range and `json.Number`; fractions were already refused). A whole `json.Number` written with an exponent (`1e6`) is accepted, and is parsed exactly. A number decoded as float64 with magnitude 2^53 or more is refused, because the decoder may already have rounded it (2^53 is the rounded image of 2^53+1; the largest accepted is 2^53-1). A `json.Number` keeps the full int64 range. These parameters are declared `number`, so the refused inputs were valid under the advertised shape: the bump is owed by behaviour, not by a schema change. A zero or absent `limit` still means the default. **v0.102** (TASK-4042) adds the global `pad_chat` tool with `list | inbox | show | send | delete | read` actions on both local stdio and remote HTTP transports; agent chat is excluded from ChatGPT. Targets are `C<n>`, `<n>`, or `@<name>` (send ensures an unknown DM). Show marks through the highest returned message only when the page reaches back to the last read message (minimum returned seq <= read_seq+1); a gap or empty page marks nothing, and `no_mark` skips marking. Remote `mark` reports success (`marked:true`, `read_seq`), gaps (`marked:false`, `reason:"gap"`, `read_seq`, `first_unshown`, `last_unshown`), empty pages (`marked:false`, `reason:"empty"`, `read_seq`), or follow-up errors (`marked:false`, `error`); it is omitted with `no_mark`. Replying marks through `reply_to`; a follow-up mark failure preserves the successful show/send result, with a CLI stderr warning. Limits are 1..200. Existing descriptions were reworded and detail moved to **Tool description detail (moved for the prompt budget)** below; no rule, caveat, refusal or ref was dropped. Messages, including owner-authored messages, are information by default; MCP cannot enable direction. Remote chat without a declared agent name returns a structured `agent_name_required` error. This is additive: no existing tool, action or parameter changes. **v0.101** (TASK-4035) adds the read-only `pad_project.action=catch-up` (additive, on the v0.28 grounds): the caller's own catch-up digest from `GET /workspaces/{ws}/catch-up` (no params), on both transports, plus a read-only ChatGPT `catch_up`. It never marks caught up: `PUT /me/seen` stays web-only (ruling 380aa793), so `pad_project` keeps its read-only annotation. Some existing tool descriptions were reworded to fewer bytes to pay for it; no rule, caveat, refusal or ref was dropped. **v0.100** (BUG-3864) makes a refused call name its cause on BOTH transports: `permission_denied` gains `details.reason` (`role`, `token_scope`, `no_access`, `workspace_not_authorized`) when the server names the gate, with a hint per reason saying what to do next (a read-only API token is told to create a "Read and write" one). With no reason, the hint leads with the server's message and claims no cause; it used to say "Insufficient role" for every 403. An unverified Cloud email is the new code `email_not_verified`, the server's own, where remote said `permission_denied`. Stdio gets both from a structured marker the CLI root writes for a 403 coded `forbidden`, `permission_denied` or `email_not_verified`; before it, the token-scope and unverified-email refusals said `server_error` there. BEHAVIOR bump on the v0.45 grounds; no name, enum or param shape changed. **v0.99** (BUG-3790) bounds `pad_item` `starred` the same way: at most 300 items, most recently starred first, with `has_more: true` and the truncation note when more exist. It never pages. Both transports ask for one row past the cap (remote `GET /starred?limit=301`, stdio `pad item starred --limit 301`, a new CLI flag; without `--limit` the CLI walks every page). Starred used to return everything. Additive, on the v0.53 grounds. **v0.98** (BUG-3704) makes `pad_item` `list` say when it is truncated: it asks for one row past its limit and, when that row comes back, returns `limit` rows with `has_more: true` on the structured result and a second text block telling the agent to narrow the filters or raise `limit` (max 300). It never pages for the agent. A list that fits is unchanged. Additive, on the v0.53 grounds. **v0.97** (TASK-3613) adds an optional `worker_id` to `pad_item` (`claim`, `release`) and `pad_project` (`next`, `ready`): a lease is now held under a worker id plus the account, the holder label is display only, a claim answers with the caller's `worker_id`, and passing it back resumes the lease from another connection (see **Leases** above). `lease_held` details gain `worker` (the short id). The remote default holder label is the bare client name. ADDITIVE bump on the v0.53 grounds. **v0.96** (PLAN-3598 slice (c)) adds `pad_item.action=context` (`ref`; optional `intent`, `role`, `budget`), read-only, which returns one brief for working an item: the body of `GET /items/{ref}/context`, with the item and its seq, its parent chain with parsed acceptance criteria, the conventions whose trigger matches the intent (plus the always-on ones), matching playbooks, deps, decisions, links, conflicts, and what was omitted for size. New codes are `unknown_intent` (400, with `details.valid_intents`) and `unknown_role` (400). Both transports (`pad item context <ref> [--intent] [--role] [--budget]`). ADDITIVE bump on the v0.53 grounds. **v0.95** (TASK-3611) adds `pad_item.action=link-pr` (`ref`, `pr_number`, `pr_url`; optional `pr_title`, `pr_state`, `pr_branch`, `pr_repo`), which links a pull request from metadata the agent supplies, fetching nothing from GitHub, through the typed `github_pr` member; and `action=unlink-pr` (`ref`), which removes the link and refuses an item with none, as `pad github unlink` does. Both transports (`pad github link <ref> --pr-number N --pr-url U ...`, new flags). ADDITIVE bump on the v0.53 grounds. **v0.94** (TASK-3611) adds `pad_item.action=reminders` (`ref`), which lists an item's reminders with their ids (armed, fired, acknowledged), and `action=unremind` (`reminder_id`), which disarms one, on both transports. Listing is read-only; disarming needs edit permission on the item, as on the CLI. Re-arm stays CLI-only (`pad item remind --rearm`). ADDITIVE bump on the v0.53 grounds. **v0.93** (TASK-3611) makes `pad_item.action=create` and `update` over the local stdio transport WRITE a `fields` value that is an object or array, which they used to refuse (BUG-2850): the stdio door passes those keys, and every other non-string value (numbers and booleans, which `--field key=value` delivered as text unless the schema typed them), to the CLI as one `--fields-json` object (a new additive flag on `pad item create` / `update`), keeping their JSON types, as the remote door sends them. Any other action still refuses one. ADDITIVE bump on the v0.53 grounds. **v0.92** (TASK-3585) adds `op_key` to `pad_item.action=comment`, `note` and `decide`: retrying the same request with the same key answers the comment or entry the first attempt made instead of appending again, recorded in the write's own transaction. On the item-update route a key is accepted only with an append (and `source`); any other member alongside it is refused 400. `idempotency_target_gone` (410: the item or comment the key wrote has since been deleted) is now a structured code on both transports, with its own hint; at 0.91 it reached MCP as a generic error. No name, enum or param moved. ADDITIVE bump on the v0.53 grounds. **v0.91** (TASK-3585) adds `op_key` to `pad_item.action=create`: retrying the same create with the same key answers the item the first attempt created (as it stands now) instead of creating a second one; the answer is recorded in the create's own transaction. A key reused for a different create is refused `idempotency_key_reused`; one still in flight answers `idempotency_in_flight` (both codes already existed, and are structured on both transports for any route). A replay whose item has since been deleted answers HTTP 410 `idempotency_target_gone`, which at 0.91 reached MCP as a generic error. No name, enum or param moved. ADDITIVE bump on the v0.53 grounds. **v0.90** (TASK-3585) adds `pad_item.action=patch` `op_key`, an idempotency key: the same request retried with the same key returns its first answer instead of applying again; new codes `idempotency_key_reused` (422), `idempotency_in_flight` (409) and `patch_outcome_unknown` (409, with `seq` and the diff since). ADDITIVE bump on the v0.53 grounds. **v0.89** (PLAN-3578 step 3) adds `pad_item.action=patch` `undo` (a `patch_id`), which inverts that patch, anchored on the text around each edit as it landed, refusing when that text has changed since, and the code `patch_not_found` (404). ADDITIVE bump on the v0.53 grounds. **v0.88** (PLAN-3578 step 2) makes `pad_item.action=patch` on an item open in a browser editor APPLY (the editor applies it as a narrowed replace of its live document; the answer adds `content_state: "applied_pending_flush"`) where it was refused `patch_room_open`, and adds the code `patch_unstable_roundtrip`. `patch_room_open` now means only an older editor holds the item. BEHAVIOR bump on the v0.84 grounds. **v0.87** (PLAN-3578 step 1) adds `pad_item.action=patch {ref, edits:[{old, new, line_hint?}], expected_seq?}`: exact-text edits to the body (each `old` occurs exactly once, applied in order, all or nothing) answered with `{seq, patch_id, version_id, rebased, intervening?, diff}`. A moved `expected_seq` is applied over and reported, never refused. Refusals write nothing: `patch_anchor_missing`, `patch_anchor_ambiguous` (`details.lines`), `patch_room_open`. `get` gains `lines` for numbered body lines with `seq`. ADDITIVE bump on the v0.38 grounds. **v0.86** (PLAN-3555 phase 1) adds `pad_item.action=update` `replace` (bool): the deliberate overwrite of content with no version token, refused with `expected_seq` / `expected_updated_at` or without `content`. A content write with neither carries `warnings.unguarded_content_write: true`, and a later release refuses it. A seq `update_conflict` on a content write gains `details.content_write`, `changed_at` and `changed_by_kind`, a message naming both seqs that says not to resend the body, and the same "re-read and merge, do not resend" hint on both transports. ADDITIVE bump on the v0.53 grounds. **v0.85** (BUG-3544) makes `pad_workspace.action=invite` on an instance with no account yet (the setup window, reachable over local stdio) answer 409 `setup_required` ("This Pad instance must be initialized with pad auth setup") and write nothing, where it answered 500 (`server_error`) from the invitation's inviter foreign key. BEHAVIOR bump on the v0.58 / v0.45 grounds. **v0.84** (BUG-3542) makes a `pad_item` content update answer 409 `content_not_applied` with `details.apply_reason: "unconfirmed_edits"` when a browser tab holding the item open still has typing the server has not stored; token or not, other fields land and the content does not. Wait, re-read and resend; `overwrite_pending_edits: true` is the only override. BEHAVIOR bump on the v0.39 / v0.43 grounds. **v0.83** (TASK-3539) makes `pad_collection` create and update REFUSE a `schema` in which a field has no key, two fields share a key, or a select field lists an empty option or the same option twice, with 400 `validation_error` naming it (`field key "status" is defined more than once`). BEHAVIOR bump on the v0.43 / v0.48 grounds: a write door refuses a call it used to accept. Write-only: a schema already stored with a repeat still reads, and an update that sends no schema still applies. **v0.82** (PLAN-3535 PR 2) makes the items of a REFERENCE collection (`tracks_work: false`) stop counting as open work on every agent surface: `pad_project` next / ready / stale / standup / changelog, the dashboard and bootstrap dashboard, item progress, the `open_children` close guard and the attention decision set leave them out, and a report with no `collections` leaves the collection out as it already did a system one. Sidebar counts, item lists, search and links are unchanged; a collection without the key counts as work. BEHAVIOR bump on the v0.49 grounds. **v0.81** (PLAN-3535 PR 1) adds a `tracks_work` boolean to `pad_collection` create and update: false makes the collection REFERENCE material whose items stop counting toward parent progress, close blocking, Insights and open-work counts (applied by the follow-up PRs). On update it sets that one settings key server-side and leaves the rest alone; omitted, create picks work iff the done field can finish and update leaves it unchanged. ADDITIVE. **v0.80** (BUG-3533) makes `pad_item.action=import` work over remote `/mcp`: it answered `validation_failed` "artifact is required" on every call, because the catalog action dropped `artifact` from the input the HTTP dispatcher reads. Stdio is unchanged. ADDITIVE bump. **v0.79** (TASK-2863) lets a read-only grant (`read` / `pad:read`) run a playbook: `pad_playbook.action=run` stores nothing, and was refused only because it is a POST. It is the one POST a read grant may make (an exact-path allowlist); `match` and every write stay refused. BEHAVIOR bump, additive in effect. **v0.78** (TASK-2308) answers a remote `/mcp` WRITE action from an OAuth connection that can only read (`pad:read`), in a `tools/call` request of up to 1 MiB, with HTTP 403 and a `WWW-Authenticate` `error="insufficient_scope"` challenge naming `scope="pad:read pad:write"` and the metadata document, before dispatch, where it got a `permission_denied` tool result; that challenge is what lets a client re-authorize with the wider grant. Every such call was already refused, so nothing that worked is refused now. A read-scoped PAT keeps the tool error (it cannot re-authorize), as does a larger request, and the ChatGPT mount keeps its own challenge. The 401 challenge also names `scope`. BEHAVIOR bump. **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>" (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=<uuid>` 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 <tmpfile>`. 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` (the constant in `internal/mcp/version.go` is the current value; this list is its changelog, newest first) — the MCP tool catalog contract. Bump when tool names, action enums, or parameter shapes change incompatibly. **v0.106** (BUG-4082) gives each edit's `line_hint` in stdio's `pad_item.patch` remote's rule (v0.104), through the one helper both transports now call. stdio used to forward `edits` to the CLI unread, so its JSON decode refused a string hint that remote coerces (`"5"` is now 5 on stdio too), and took 2^53 or more, which the decoder may already have rounded, as a line number. Now a hint that is not a whole number below 2^53 (a fraction, `"010"`, a bool, an object) is refused on stdio with remote's `validation_failed`, naming the edit (`(in edits[1])`); `null` is absent, and an edit that is not an object keeps its path. Remote is unchanged. Behaviour only; the schemas are unchanged. **v0.105** (BUG-4070) applies v0.104's rule on stdio to every top-level parameter declared `"number"`, before the value becomes CLI text. A string used to reach the CLI verbatim: an int flag parses base 0, so `"010"` was 8, `"0x10"` 16, `"1_000"` 1000 and `"+5"` 5, and `pad_chat` delete's positional `seq` parses base 10, so `"010"` was 10. Now a string is accepted only as a plain decimal integer with no leading zero, bounded |x| < 2^53, and forwarded unchanged; every other string is refused with `validation_failed` naming the parameter. A JSON number used to be formatted and forwarded whatever its size; now one that is not whole, or of magnitude 2^53 or more (which the decoder may already have rounded), is refused the same way, as remote has since v0.103. For a string or a JSON number, stdio now accepts and refuses what remote does. Other types keep their path: `intParam` (`pad_item` list and history `limit`) reads `null` as absent, so the default applies (v0.104), and refuses a bool, an array or an object; everywhere else the CLI's own parse refuses all of them; the nested `pad_item.patch` `edits[].line_hint` is BUG-4082. Behaviour only; the schemas are unchanged, as for v0.103 and v0.104. **v0.104** (BUG-4065) stops reading a numeric parameter's non-number value as absent. A string, a bool, an object or an array used to be dropped, so the default applied, and a string `expected_seq` made a content write unguarded. Now only `null` is absent. A string is accepted when it is a plain decimal integer with no leading zero (an optional `-`, then `0` or digits not starting with `0`), parsed exactly and bounded like a JSON number (|x| < 2^53): `"10"` is 10, and `"123"` is a guarded write. Every other string (`"010"`, `"1.0"`, `"1e3"`, `" 10"`, `"+10"`, `""`) and every other type is refused with `validation_failed` naming the parameter; `"010"` is refused because stdio's CLI flags read it as octal 8. An empty string or `false` is refused, not skipped as absent. It covers the v0.103 doors, including every numeric key on a query-string door (item backlinks, item search, item context's `budget`, project activity, project standup and changelog), where a bool, an object or `"abc"` used to reach the server's `Atoi` and silently become its default, plus `pad_item.update`'s and `pad_item.patch`'s `expected_seq`, `pad_item.patch`'s `edits[].line_hint`, `pad_item.link-pr`'s `pr_number` (a `json.Number` is read exactly; 2^53 itself is now refused), the `sort_order` of `pad_collection` and `pad_role` update (which used to reach the server's decode as a 400), and `pad_chat`'s `since`, `limit`, `reply_to`, `seq` and `to` (2^53 now bounds a float64; `json.Number` `"1e6"` is accepted; a present `null` is still refused there, as before, with the same message). Non-numeric query keys are still forwarded verbatim. The parameters are declared `number`, so the bump is owed by behaviour, as for v0.103. **v0.103** (BUG-4061) refuses a numeric parameter that is not a whole int64, with `validation_failed` naming it, where it used to be silently changed: a fraction truncated (`limit: 1.5` read as 1, and `pad_item.list`'s `limit: 0.5` as the default), a value outside int64 converted to an implementation-defined one, and a `json.Number` that did not parse was dropped as absent. It covers `limit`, `offset` and `days` on every door that reads them locally, `pad_item.list`'s and `pad_item.history`'s `limit`, every query-string door the remote dispatcher builds with `buildQuery` (item backlinks, item context's `budget`, project activity, item search, project standup and changelog), whose server parsers used to read a forwarded `1.5` as absent and use their default, and `expected_seq` (range and `json.Number`; fractions were already refused). A whole `json.Number` written with an exponent (`1e6`) is accepted, and is parsed exactly. A number decoded as float64 with magnitude 2^53 or more is refused, because the decoder may already have rounded it (2^53 is the rounded image of 2^53+1; the largest accepted is 2^53-1). A `json.Number` keeps the full int64 range. These parameters are declared `number`, so the refused inputs were valid under the advertised shape: the bump is owed by behaviour, not by a schema change. A zero or absent `limit` still means the default. **v0.102** (TASK-4042) adds the global `pad_chat` tool with `list | inbox | show | send | delete | read` actions on both local stdio and remote HTTP transports; agent chat is excluded from ChatGPT. Targets are `C<n>`, `<n>`, or `@<name>` (send ensures an unknown DM). Show marks through the highest returned message only when the page reaches back to the last read message (minimum returned seq <= read_seq+1); a gap or empty page marks nothing, and `no_mark` skips marking. Remote `mark` reports success (`marked:true`, `read_seq`), gaps (`marked:false`, `reason:"gap"`, `read_seq`, `first_unshown`, `last_unshown`), empty pages (`marked:false`, `reason:"empty"`, `read_seq`), or follow-up errors (`marked:false`, `error`); it is omitted with `no_mark`. Replying marks through `reply_to`; a follow-up mark failure preserves the successful show/send result, with a CLI stderr warning. Limits are 1..200. Existing descriptions were reworded and detail moved to **Tool description detail (moved for the prompt budget)** below; no rule, caveat, refusal or ref was dropped. Messages, including owner-authored messages, are information by default; MCP cannot enable direction. Remote chat without a declared agent name returns a structured `agent_name_required` error. This is additive: no existing tool, action or parameter changes. **v0.101** (TASK-4035) adds the read-only `pad_project.action=catch-up` (additive, on the v0.28 grounds): the caller's own catch-up digest from `GET /workspaces/{ws}/catch-up` (no params), on both transports, plus a read-only ChatGPT `catch_up`. It never marks caught up: `PUT /me/seen` stays web-only (ruling 380aa793), so `pad_project` keeps its read-only annotation. Some existing tool descriptions were reworded to fewer bytes to pay for it; no rule, caveat, refusal or ref was dropped. **v0.100** (BUG-3864) makes a refused call name its cause on BOTH transports: `permission_denied` gains `details.reason` (`role`, `token_scope`, `no_access`, `workspace_not_authorized`) when the server names the gate, with a hint per reason saying what to do next (a read-only API token is told to create a "Read and write" one). With no reason, the hint leads with the server's message and claims no cause; it used to say "Insufficient role" for every 403. An unverified Cloud email is the new code `email_not_verified`, the server's own, where remote said `permission_denied`. Stdio gets both from a structured marker the CLI root writes for a 403 coded `forbidden`, `permission_denied` or `email_not_verified`; before it, the token-scope and unverified-email refusals said `server_error` there. BEHAVIOR bump on the v0.45 grounds; no name, enum or param shape changed. **v0.99** (BUG-3790) bounds `pad_item` `starred` the same way: at most 300 items, most recently starred first, with `has_more: true` and the truncation note when more exist. It never pages. Both transports ask for one row past the cap (remote `GET /starred?limit=301`, stdio `pad item starred --limit 301`, a new CLI flag; without `--limit` the CLI walks every page). Starred used to return everything. Additive, on the v0.53 grounds. **v0.98** (BUG-3704) makes `pad_item` `list` say when it is truncated: it asks for one row past its limit and, when that row comes back, returns `limit` rows with `has_more: true` on the structured result and a second text block telling the agent to narrow the filters or raise `limit` (max 300). It never pages for the agent. A list that fits is unchanged. Additive, on the v0.53 grounds. **v0.97** (TASK-3613) adds an optional `worker_id` to `pad_item` (`claim`, `release`) and `pad_project` (`next`, `ready`): a lease is now held under a worker id plus the account, the holder label is display only, a claim answers with the caller's `worker_id`, and passing it back resumes the lease from another connection (see **Leases** above). `lease_held` details gain `worker` (the short id). The remote default holder label is the bare client name. ADDITIVE bump on the v0.53 grounds. **v0.96** (PLAN-3598 slice (c)) adds `pad_item.action=context` (`ref`; optional `intent`, `role`, `budget`), read-only, which returns one brief for working an item: the body of `GET /items/{ref}/context`, with the item and its seq, its parent chain with parsed acceptance criteria, the conventions whose trigger matches the intent (plus the always-on ones), matching playbooks, deps, decisions, links, conflicts, and what was omitted for size. New codes are `unknown_intent` (400, with `details.valid_intents`) and `unknown_role` (400). Both transports (`pad item context <ref> [--intent] [--role] [--budget]`). ADDITIVE bump on the v0.53 grounds. **v0.95** (TASK-3611) adds `pad_item.action=link-pr` (`ref`, `pr_number`, `pr_url`; optional `pr_title`, `pr_state`, `pr_branch`, `pr_repo`), which links a pull request from metadata the agent supplies, fetching nothing from GitHub, through the typed `github_pr` member; and `action=unlink-pr` (`ref`), which removes the link and refuses an item with none, as `pad github unlink` does. Both transports (`pad github link <ref> --pr-number N --pr-url U ...`, new flags). ADDITIVE bump on the v0.53 grounds. **v0.94** (TASK-3611) adds `pad_item.action=reminders` (`ref`), which lists an item's reminders with their ids (armed, fired, acknowledged), and `action=unremind` (`reminder_id`), which disarms one, on both transports. Listing is read-only; disarming needs edit permission on the item, as on the CLI. Re-arm stays CLI-only (`pad item remind --rearm`). ADDITIVE bump on the v0.53 grounds. **v0.93** (TASK-3611) makes `pad_item.action=create` and `update` over the local stdio transport WRITE a `fields` value that is an object or array, which they used to refuse (BUG-2850): the stdio door passes those keys, and every other non-string value (numbers and booleans, which `--field key=value` delivered as text unless the schema typed them), to the CLI as one `--fields-json` object (a new additive flag on `pad item create` / `update`), keeping their JSON types, as the remote door sends them. Any other action still refuses one. ADDITIVE bump on the v0.53 grounds. **v0.92** (TASK-3585) adds `op_key` to `pad_item.action=comment`, `note` and `decide`: retrying the same request with the same key answers the comment or entry the first attempt made instead of appending again, recorded in the write's own transaction. On the item-update route a key is accepted only with an append (and `source`); any other member alongside it is refused 400. `idempotency_target_gone` (410: the item or comment the key wrote has since been deleted) is now a structured code on both transports, with its own hint; at 0.91 it reached MCP as a generic error. No name, enum or param moved. ADDITIVE bump on the v0.53 grounds. **v0.91** (TASK-3585) adds `op_key` to `pad_item.action=create`: retrying the same create with the same key answers the item the first attempt created (as it stands now) instead of creating a second one; the answer is recorded in the create's own transaction. A key reused for a different create is refused `idempotency_key_reused`; one still in flight answers `idempotency_in_flight` (both codes already existed, and are structured on both transports for any route). A replay whose item has since been deleted answers HTTP 410 `idempotency_target_gone`, which at 0.91 reached MCP as a generic error. No name, enum or param moved. ADDITIVE bump on the v0.53 grounds. **v0.90** (TASK-3585) adds `pad_item.action=patch` `op_key`, an idempotency key: the same request retried with the same key returns its first answer instead of applying again; new codes `idempotency_key_reused` (422), `idempotency_in_flight` (409) and `patch_outcome_unknown` (409, with `seq` and the diff since). ADDITIVE bump on the v0.53 grounds. **v0.89** (PLAN-3578 step 3) adds `pad_item.action=patch` `undo` (a `patch_id`), which inverts that patch, anchored on the text around each edit as it landed, refusing when that text has changed since, and the code `patch_not_found` (404). ADDITIVE bump on the v0.53 grounds. **v0.88** (PLAN-3578 step 2) makes `pad_item.action=patch` on an item open in a browser editor APPLY (the editor applies it as a narrowed replace of its live document; the answer adds `content_state: "applied_pending_flush"`) where it was refused `patch_room_open`, and adds the code `patch_unstable_roundtrip`. `patch_room_open` now means only an older editor holds the item. BEHAVIOR bump on the v0.84 grounds. **v0.87** (PLAN-3578 step 1) adds `pad_item.action=patch {ref, edits:[{old, new, line_hint?}], expected_seq?}`: exact-text edits to the body (each `old` occurs exactly once, applied in order, all or nothing) answered with `{seq, patch_id, version_id, rebased, intervening?, diff}`. A moved `expected_seq` is applied over and reported, never refused. Refusals write nothing: `patch_anchor_missing`, `patch_anchor_ambiguous` (`details.lines`), `patch_room_open`. `get` gains `lines` for numbered body lines with `seq`. ADDITIVE bump on the v0.38 grounds. **v0.86** (PLAN-3555 phase 1) adds `pad_item.action=update` `replace` (bool): the deliberate overwrite of content with no version token, refused with `expected_seq` / `expected_updated_at` or without `content`. A content write with neither carries `warnings.unguarded_content_write: true`, and a later release refuses it. A seq `update_conflict` on a content write gains `details.content_write`, `changed_at` and `changed_by_kind`, a message naming both seqs that says not to resend the body, and the same "re-read and merge, do not resend" hint on both transports. ADDITIVE bump on the v0.53 grounds. **v0.85** (BUG-3544) makes `pad_workspace.action=invite` on an instance with no account yet (the setup window, reachable over local stdio) answer 409 `setup_required` ("This Pad instance must be initialized with pad auth setup") and write nothing, where it answered 500 (`server_error`) from the invitation's inviter foreign key. BEHAVIOR bump on the v0.58 / v0.45 grounds. **v0.84** (BUG-3542) makes a `pad_item` content update answer 409 `content_not_applied` with `details.apply_reason: "unconfirmed_edits"` when a browser tab holding the item open still has typing the server has not stored; token or not, other fields land and the content does not. Wait, re-read and resend; `overwrite_pending_edits: true` is the only override. BEHAVIOR bump on the v0.39 / v0.43 grounds. **v0.83** (TASK-3539) makes `pad_collection` create and update REFUSE a `schema` in which a field has no key, two fields share a key, or a select field lists an empty option or the same option twice, with 400 `validation_error` naming it (`field key "status" is defined more than once`). BEHAVIOR bump on the v0.43 / v0.48 grounds: a write door refuses a call it used to accept. Write-only: a schema already stored with a repeat still reads, and an update that sends no schema still applies. **v0.82** (PLAN-3535 PR 2) makes the items of a REFERENCE collection (`tracks_work: false`) stop counting as open work on every agent surface: `pad_project` next / ready / stale / standup / changelog, the dashboard and bootstrap dashboard, item progress, the `open_children` close guard and the attention decision set leave them out, and a report with no `collections` leaves the collection out as it already did a system one. Sidebar counts, item lists, search and links are unchanged; a collection without the key counts as work. BEHAVIOR bump on the v0.49 grounds. **v0.81** (PLAN-3535 PR 1) adds a `tracks_work` boolean to `pad_collection` create and update: false makes the collection REFERENCE material whose items stop counting toward parent progress, close blocking, Insights and open-work counts (applied by the follow-up PRs). On update it sets that one settings key server-side and leaves the rest alone; omitted, create picks work iff the done field can finish and update leaves it unchanged. ADDITIVE. **v0.80** (BUG-3533) makes `pad_item.action=import` work over remote `/mcp`: it answered `validation_failed` "artifact is required" on every call, because the catalog action dropped `artifact` from the input the HTTP dispatcher reads. Stdio is unchanged. ADDITIVE bump. **v0.79** (TASK-2863) lets a read-only grant (`read` / `pad:read`) run a playbook: `pad_playbook.action=run` stores nothing, and was refused only because it is a POST. It is the one POST a read grant may make (an exact-path allowlist); `match` and every write stay refused. BEHAVIOR bump, additive in effect. **v0.78** (TASK-2308) answers a remote `/mcp` WRITE action from an OAuth connection that can only read (`pad:read`), in a `tools/call` request of up to 1 MiB, with HTTP 403 and a `WWW-Authenticate` `error="insufficient_scope"` challenge naming `scope="pad:read pad:write"` and the metadata document, before dispatch, where it got a `permission_denied` tool result; that challenge is what lets a client re-authorize with the wider grant. Every such call was already refused, so nothing that worked is refused now. A read-scoped PAT keeps the tool error (it cannot re-authorize), as does a larger request, and the ChatGPT mount keeps its own challenge. The 401 challenge also names `scope`. BEHAVIOR bump. **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>" (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=<uuid>` 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 <tmpfile>`. 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.
 
diff --git a/internal/mcp/bug4082_line_hint_test.go b/internal/mcp/bug4082_line_hint_test.go
new file mode 100644
index 000000000..2548451b2
--- /dev/null
+++ b/internal/mcp/bug4082_line_hint_test.go
@@ -0,0 +1,160 @@
+package mcp
+
+import (
+	"context"
+	"encoding/json"
+	"reflect"
+	"strings"
+	"testing"
+)
+
+// BUG-4082: pad_item patch's edits[].line_hint gets one rule on both
+// transports. Remote's mapItemPatch had it inline (BUG-4065); stdio forwarded
+// edits to the CLI unread, so a string hint was refused there where remote
+// coerced it, and 2^53 or more reached bodypatch as a line number. Both now
+// call editsWithLineHints. Lead ruling 86931478: C1, one table drives both
+// transports, so a change to the helper turns both red and stdio == remote is
+// pinned, not asserted; C2, neither transport modifies the caller's map.
+
+// bug4082Cases is the shared table. edits is the JSON the caller sends; want
+// is the edits JSON each transport must forward (after a decode and re-encode,
+// so key order and number spelling do not matter); refuse, when set, is the
+// refusal both must give instead, with nothing forwarded.
+var bug4082Cases = []struct {
+	name, edits, want, refuse string
+}{
+	{"string hint coerced", `[{"old":"a","new":"b","line_hint":"5"}]`, `[{"line_hint":5,"new":"b","old":"a"}]`, ""},
+	{"number hint kept", `[{"old":"a","new":"b","line_hint":5}]`, `[{"line_hint":5,"new":"b","old":"a"}]`, ""},
+	{"null hint absent", `[{"old":"a","new":"b","line_hint":null}]`, `[{"line_hint":null,"new":"b","old":"a"}]`, ""},
+	{"no hint", `[{"old":"a","new":"b"}]`, `[{"new":"b","old":"a"}]`, ""},
+	{"largest safe hint", `[{"old":"a","new":"b","line_hint":9007199254740991}]`, `[{"line_hint":9007199254740991,"new":"b","old":"a"}]`, ""},
+	{"non-object edit left alone", `["x",{"old":"a","new":"b","line_hint":"2"}]`, `["x",{"line_hint":2,"new":"b","old":"a"}]`, ""},
+	{"leading zero", `[{"old":"a","new":"b","line_hint":"010"}]`, "", `line_hint must be a whole number, got the string \"010\" (in edits[0])`},
+	{"fraction", `[{"old":"a","new":"b","line_hint":1.5}]`, "", "line_hint must be a whole number, got 1.5 (in edits[0])"},
+	{"2^53", `[{"old":"a","new":"b","line_hint":9007199254740992}]`, "", "line_hint is beyond the exact integer range of a JSON number, got 9.007199254740992e+15 (in edits[0])"},
+	{"bool", `[{"old":"a","new":"b","line_hint":true}]`, "", "line_hint must be a number, got a boolean (in edits[0])"},
+	{"object", `[{"old":"a","new":"b","line_hint":{}}]`, "", "line_hint must be a number, got an object (in edits[0])"},
+	{"second edit names its index", `[{"old":"a","new":"b","line_hint":1},{"old":"c","new":"d","line_hint":"0x10"}]`, "", "(in edits[1])"},
+}
+
+func canonicalJSON(t *testing.T, s string) string {
+	t.Helper()
+	var v any
+	if err := json.Unmarshal([]byte(s), &v); err != nil {
+		t.Fatalf("decode %s: %v", s, err)
+	}
+	b, err := json.Marshal(v)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return string(b)
+}
+
+func bug4082Input(t *testing.T, edits string) map[string]any {
+	t.Helper()
+	var in map[string]any
+	if err := json.Unmarshal([]byte(`{"workspace":"docapp","ref":"TASK-1","edits":`+edits+`}`), &in); err != nil {
+		t.Fatal(err)
+	}
+	return in
+}
+
+// remoteLineHints runs the remote mapper and returns the forwarded edits JSON
+// or the refusal text.
+func remoteLineHints(t *testing.T, edits string) (forwarded, refusal string) {
+	t.Helper()
+	_, _, body, err := mapItemPatch(bug4082Input(t, edits))
+	if err != nil {
+		return "", err.Error()
+	}
+	var b map[string]json.RawMessage
+	if err := json.Unmarshal(body, &b); err != nil {
+		t.Fatalf("remote body %s: %v", body, err)
+	}
+	return canonicalJSON(t, string(b["edits"])), ""
+}
+
+// stdioLineHints runs the stdio fan-out handler and returns the --edits JSON
+// forwarded to the CLI or the refusal text.
+func stdioLineHints(t *testing.T, edits string) (forwarded, refusal string) {
+	t.Helper()
+	in := bug4082Input(t, edits)
+	in["action"] = "patch"
+	d := &fakeDispatcher{}
+	env := ActionEnv{Doc: liveCmdhelpDoc(t), Workspace: NewWorkspaceState("docapp"), Dispatcher: d}
+	res, err := makeFanOutHandler(padItemTool, env)(context.Background(), callToolRequest(in))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if res != nil && res.IsError {
+		if d.gotPath != nil {
+			t.Fatalf("refused but dispatched: %v", d.gotArgs)
+		}
+		return "", textOf(res)
+	}
+	for i := 0; i+1 < len(d.gotArgs); i++ {
+		if d.gotArgs[i] == "--edits" {
+			return canonicalJSON(t, d.gotArgs[i+1]), ""
+		}
+	}
+	t.Fatalf("no --edits forwarded: %v", d.gotArgs)
+	return "", ""
+}
+
+func TestBUG4082_LineHintSameOnBothTransports(t *testing.T) {
+	for _, tc := range bug4082Cases {
+		t.Run(tc.name, func(t *testing.T) {
+			rFwd, rRef := remoteLineHints(t, tc.edits)
+			sFwd, sRef := stdioLineHints(t, tc.edits)
+			if tc.refuse != "" {
+				// The JSON envelope escapes quotes, so compare stdio against the
+				// escaped form of remote's error text.
+				escaped, _ := json.Marshal(rRef)
+				if !strings.Contains(rRef, strings.ReplaceAll(tc.refuse, `\"`, `"`)) {
+					t.Errorf("remote: want refusal containing %q, got %q (forwarded %s)", tc.refuse, rRef, rFwd)
+				}
+				if !strings.Contains(sRef, string(ErrValidationFailed)) ||
+					!strings.Contains(sRef, "item patch: "+strings.Trim(string(escaped), `"`)) {
+					t.Errorf("stdio: want validation_failed with remote's message %q, got %q (forwarded %s)", rRef, sRef, sFwd)
+				}
+				return
+			}
+			want := canonicalJSON(t, tc.want)
+			if rRef != "" || rFwd != want {
+				t.Errorf("remote: want edits %s, got %s (refusal %q)", want, rFwd, rRef)
+			}
+			if sRef != "" || sFwd != want {
+				t.Errorf("stdio: want edits %s, got %s (refusal %q)", want, sFwd, sRef)
+			}
+		})
+	}
+}
+
+// C2: neither transport modifies the caller's map, its edits slice or an
+// edit in it, on a coerced hint or on a refusal.
+func TestBUG4082_CallerMapUnmodified(t *testing.T) {
+	for _, edits := range []string{
+		`[{"old":"a","new":"b","line_hint":"5"},"x"]`,
+		`[{"old":"a","new":"b","line_hint":2},{"old":"c","new":"d","line_hint":"010"}]`,
+	} {
+		t.Run("remote "+edits, func(t *testing.T) {
+			in, before := bug4082Input(t, edits), bug4082Input(t, edits)
+			_, _, _, _ = mapItemPatch(in)
+			if !reflect.DeepEqual(in, before) {
+				t.Fatalf("caller's map modified: %v, was %v", in, before)
+			}
+		})
+		t.Run("stdio "+edits, func(t *testing.T) {
+			in, before := bug4082Input(t, edits), bug4082Input(t, edits)
+			in["action"], before["action"] = "patch", "patch"
+			env := ActionEnv{Doc: liveCmdhelpDoc(t), Workspace: NewWorkspaceState("docapp"), Dispatcher: &fakeDispatcher{}}
+			req := callToolRequest(in)
+			if _, err := makeFanOutHandler(padItemTool, env)(context.Background(), req); err != nil {
+				t.Fatal(err)
+			}
+			if !reflect.DeepEqual(in, before) {
+				t.Fatalf("caller's map modified: %v, was %v", in, before)
+			}
+		})
+	}
+}
diff --git a/internal/mcp/catalog_item.go b/internal/mcp/catalog_item.go
index 33d046b87..fe1c3648a 100644
--- a/internal/mcp/catalog_item.go
+++ b/internal/mcp/catalog_item.go
@@ -62,7 +62,8 @@ var padItemTool = ToolDef{
 		"get":    actionItemGet,
 
 		// PLAN-3578: content-anchored body edits, answered with the diff.
-		"patch": passThrough([]string{"item", "patch"}),
+		// CUSTOM (BUG-4082) so each edit's line_hint gets remote's rule.
+		"patch": actionItemPatch,
 		// list is CUSTOM (not passThrough) so a bare agent list stays
 		// bounded: it injects a default limit and clamps an oversized one
 		// before dispatch, mirroring the backlinks default/max. See
@@ -770,6 +771,31 @@ const (
 	mcpItemListMaxLimit     = 300
 )
 
+// actionItemPatch handles pad_item.action=patch on stdio. It gives each edit's
+// line_hint remote's rule (editsWithLineHints, shared with mapItemPatch) and
+// then forwards to `item patch` as passThrough did (BUG-4082). edits used to
+// reach the CLI unread: its JSON decode into an int refused a string hint that
+// remote coerces, and took a JSON number of 2^53 or more, which the decoder
+// may already have rounded, as a line number. A refusal is validation_failed
+// with remote's message. The caller's map is not modified.
+func actionItemPatch(ctx context.Context, input map[string]any, env ActionEnv) (*CallToolResult, error) {
+	edits, isList := input["edits"].([]any)
+	if !isList {
+		return env.Dispatch(ctx, []string{"item", "patch"}, input)
+	}
+	out, err := editsWithLineHints(edits)
+	if err != nil {
+		return validationFailedResult("item patch", err.Error(),
+			"Pass each line_hint as a whole JSON number below 2^53, or a string of decimal digits with no leading zero."), nil
+	}
+	in := make(map[string]any, len(input))
+	for k, v := range input {
+		in[k] = v
+	}
+	in["edits"] = out
+	return env.Dispatch(ctx, []string{"item", "patch"}, in)
+}
+
 // actionItemList handles pad_item.action=list. It forwards to `item list`
 // but first applies a default limit (when the agent didn't ask for one) and
 // clamps an oversized one, so a bare agent list can't dump the whole
diff --git a/internal/mcp/dispatch_http_routes.go b/internal/mcp/dispatch_http_routes.go
index 1e6692343..4b5211a6b 100644
--- a/internal/mcp/dispatch_http_routes.go
+++ b/internal/mcp/dispatch_http_routes.go
@@ -886,31 +886,52 @@ func mapItemPatch(input map[string]any) (string, string, []byte, error) {
 		in["expected_seq"] = seq
 	}
 	if edits, isList := input["edits"].([]any); isList {
-		out := make([]any, len(edits))
-		for i, e := range edits {
-			out[i] = e
-			edit, isObj := e.(map[string]any)
-			if !isObj {
-				continue
-			}
-			hint, present, err := intParam(edit, "line_hint")
-			if err != nil {
-				return "", "", nil, fmt.Errorf("%w (in edits[%d])", err, i)
-			}
-			if present {
-				copied := make(map[string]any, len(edit))
-				for k, v := range edit {
-					copied[k] = v
-				}
-				copied["line_hint"] = hint
-				out[i] = copied
-			}
+		out, err := editsWithLineHints(edits)
+		if err != nil {
+			return "", "", nil, err
 		}
 		in["edits"] = out
 	}
 	return itemPatchRoute(in)
 }
 
+// editsWithLineHints returns a copy of a patch's edits with each object edit's
+// line_hint read through intParam (numericInput's rule) and replaced by its
+// int64. A refusal names the edit, e.g. `line_hint must be a whole number, got
+// the string "010" (in edits[0])`. An edit that is not an object is left as it
+// is, for the server or the CLI to refuse, since its shape is theirs to
+// define; a null line_hint is absent and left as it is. Neither edits nor any
+// edit in it is modified: a changed edit is a copy.
+//
+// Both transports call it (BUG-4082): remote's mapItemPatch, where the loop
+// was inline (BUG-4065), and stdio's patch action, which used to forward edits
+// to the CLI unread, so a string hint was refused there where remote coerced
+// it, and a JSON number of 2^53 or more, already rounded by the decoder,
+// reached bodypatch as a line number.
+func editsWithLineHints(edits []any) ([]any, error) {
+	out := make([]any, len(edits))
+	for i, e := range edits {
+		out[i] = e
+		edit, isObj := e.(map[string]any)
+		if !isObj {
+			continue
+		}
+		hint, present, err := intParam(edit, "line_hint")
+		if err != nil {
+			return nil, fmt.Errorf("%w (in edits[%d])", err, i)
+		}
+		if present {
+			copied := make(map[string]any, len(edit))
+			for k, v := range edit {
+				copied[k] = v
+			}
+			copied["line_hint"] = hint
+			out[i] = copied
+		}
+	}
+	return out, nil
+}
+
 // mapItemClaim dispatches `pad item claim <ref> [--holder] [--ttl]`.
 //
 // POST /api/v1/workspaces/{ws}/items/{ref}/claim with an optional body
diff --git a/internal/mcp/instructions.md b/internal/mcp/instructions.md
index e3e4bd6a8..fe75b59bf 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 (v0.105)
+## Tool surface (v0.106)
 
 Eleven resource × action tools, plus `pad_set_workspace`. Twelve tools total.
 
diff --git a/internal/mcp/version.go b/internal/mcp/version.go
index 7df676903..fafe70622 100644
--- a/internal/mcp/version.go
+++ b/internal/mcp/version.go
@@ -2284,7 +2284,18 @@ const CmdhelpVersion = "0.1"
 // bool, an array or an object; everywhere else the CLI's own parse refuses
 // all of them. The nested pad_item.patch edits[].line_hint is BUG-4082.
 // Behaviour only; the schemas are unchanged, as for v0.103 and v0.104.
-const ToolSurfaceVersion = "0.105"
+//
+// v0.106 — BUG-4082: stdio's pad_item.patch gives each edit's line_hint
+// remote's rule (v0.104), through the one helper both transports now call.
+// stdio used to forward edits to the CLI unread, so its JSON decode refused a
+// string hint that remote coerces ("5" is now 5 on stdio too), and took 2^53
+// or more, which the decoder may already have rounded, as a line number. Now
+// a hint that is not a whole number below 2^53 (a fraction, "010", a bool, an
+// object) is refused on stdio with remote's validation_failed, naming the
+// edit ("(in edits[1])"); null is absent, and an edit that is not an object
+// keeps its path. Remote is unchanged. Behaviour only; the schemas are
+// unchanged.
+const ToolSurfaceVersion = "0.106"
 
 // MetaVersionURI is the canonical URI of the queryable version document.
 // Lives outside the pad://workspace/{ws}/... namespace because it's a