docs(roadmap): add #681 — unsupported mcp mutation verbs return help with exit 0

ROADMAP.md

@@ -6429,18 +6429,42 @@ Original filing (2026-04-18): the session emitted `SessionStart hook (completed)
 
 450. **`prompt` emits `kind:"missing_credentials"` JSON on STDERR (not stdout), leaving stdout at 0 bytes — automation pattern `output=$(claw prompt hello --output-format json)` captures nothing on auth-absent failure; `doctor` correctly surfaces `auth.status:"warn"` with `api_key_present:false` but exposes no `prompt_ready:false` field that automation can check before invoking `prompt`** — dogfooded 2026-05-16 by Jobdori on `a35ee9a0` in response to Clawhip pinpoint nudge at `1505208225321062521`. Exact reproduction (isolated env, no creds, fresh git repo, HEAD `a35ee9a0`): `timeout 5 env -i HOME=$ISOLATED_HOME PATH=$PATH CLAW_CONFIG_HOME=$PROBE/.claw-cfg claw prompt hello --output-format json > stdout.txt 2> stderr.txt` → stdout = **0 bytes**, stderr = 195 bytes containing `{"error":"missing Anthropic credentials…","exit_code":1,"hint":null,"kind":"missing_credentials","type":"error"}`, exit code 1. Confirms Gaebal's `1505208553793781792` pinpoint that `prompt` timeout + zero bytes was the prior state — HEAD `a35ee9a0` now correctly exits 1 with `kind:"missing_credentials"` **but the envelope is still routed to stderr** (issue #447 class, same class as prior entries #422, #435). **Contrast with `doctor`:** `claw doctor --output-format json 2>/dev/null` succeeds to stdout with `checks[auth].status:"warn"`, `api_key_present:false`, `auth_token_present:false` — but the auth check has no `prompt_ready:false` field. Automation that gates on `doctor` before invoking `prompt` must re-derive readiness from `api_key_present && auth_token_present` — there is no single canonical boolean. **Three compound problems:** (a) **stdout-empty on `--output-format json` failure**: same class as #447; `prompt`'s error envelope goes to stderr, not stdout. The canonical automation idiom `if ! result=$(claw prompt "q" --output-format json); then echo "$result" | jq .kind; fi` sees `$result=""` on failure — the jq call gets nothing. All `--output-format json` error paths must route JSON to stdout per #447 contract; (b) **`doctor` missing `prompt_ready` field**: `doctor --output-format json` already knows auth is absent (`api_key_present:false`) but surfaces no derived `prompt_ready:bool` or `prompt_blocked_reason:string` field. Automation must infer readiness from `api_key_present || auth_token_present || legacy_*_present` — a 5-field OR across legacy fields that is fragile as auth mechanisms evolve. A single `prompt_ready:false` (with `prompt_blocked_reason:"auth_missing"`) inside the `auth` check would give downstream a stable contract; (c) **`claw prompt` with no auth does no preflight and fires straight at the API**: the preflight check that `doctor` runs (auth discovery) is not reused by `prompt` to emit a fast typed error before attempting the network call. Both Gaebal's pinpoint (prompt hanging silently on older HEAD) and the current behavior (prompt hitting auth gate after a brief API attempt) stem from the same root: prompt does not short-circuit at the point where `doctor` already knows auth is absent. If `doctor` can emit `kind:"doctor"` with `auth.status:"warn"` in ~20ms without a network call, `prompt` should emit `kind:"missing_credentials"` in the same window and output it to stdout. **Required fix shape:** (a) `prompt --output-format json` must write the `kind:"missing_credentials"` JSON envelope to **stdout**, not stderr — same fix as #447 for all error envelopes; (b) add `prompt_ready:bool` and `prompt_blocked_reason:string|null` to the `auth` check in `doctor --output-format json`; derive it as `api_key_present || auth_token_present || legacy_saved_oauth_present`; (c) `prompt` must run the credential preflight check (same codepath as doctor's auth check) before attempting any API call and emit `{"kind":"missing_credentials","prompt_blocked_reason":"auth_missing"}` on **stdout** with exit 1 if the check fails; (d) `--output-format json` stdout routing fix must cover: `prompt`, `session list` (cross-ref #449), `skills uninstall` (cross-ref #431), `resume` (cross-ref #435), `acp serve` (cross-ref #443) — the full `kind:"missing_credentials"` class; (e) regression test: `claw prompt hello --output-format json` with no creds writes JSON to stdout (0 bytes stderr), exits 1, `kind:"missing_credentials"`, in under 200ms (no network attempt). **Why this matters:** `prompt` is the primary consumer entry point. Auth-absent failure routing to stderr breaks every automation wrapper that captures `$(claw prompt ... --output-format json)`. The `doctor` preflight metadata gap means auth-readiness checks require parsing 5 legacy fields instead of reading one boolean. Cross-references #447 (all JSON error envelopes on stderr), #449 (session list hits auth gate), #431 (skills uninstall hits auth gate), #357 (auth gate on local ops cluster), #422 (exit-code parity). Source: Jobdori live dogfood, `a35ee9a0`, 2026-05-16.
 
-458. **There is no portable success-detection field across `claw <subcommand> --output-format json` envelopes — only `kind` is universal; `status`, `action`, `summary`, `message`, and `report` are present on different subsets, so a claw that writes `if response["status"] == "ok"` silently breaks on 7 of the 9 standard subcommands** — dogfooded 2026-05-24 for the 09:00 Clawhip pinpoint nudge at message `1508031832669814834`, reproduced on local `./rust/target/debug/claw` `git_sha 003b739d` (origin/main `f8e1bb72`). Catalog of top-level fields in successful `--output-format json` envelopes for the nine standard subcommands (clean isolated env, no `.claw.json`, fresh git-init workspace):
+681. **Unsupported `claw mcp` mutation verbs (`add`, `remove`, `delete`, `enable`, `disable`) return a help payload with `exit=0` instead of a typed unsupported/not-implemented error: `claw mcp add demo -- /bin/echo hi --output-format json` emits `{kind:"mcp", action:"help", unexpected:"add demo -- /bin/echo hi", usage:{...}}` on stdout, no stderr, and no file changes. The command clearly did not add anything, but shell/CI sees success; `unexpected` is the only clue, and it is embedded in a help object rather than a `status:"unsupported"` / `kind:"error"` envelope** — dogfooded 2026-05-24 for the 20:00 Clawhip nudge at message `1508197932497899740`, reproduced on local `./rust/target/debug/claw` `git_sha 003b739d` (origin/main `f8e1bb72`) in a clean isolated env. Number intentionally jumps to #681 because Jobdori publicly filed/announced ROADMAP #680 in this channel; avoiding distributed queue collision.
 
-    | Subcommand | `kind` | `status` | `action` | `summary` | `message` | `report` |
-    |---|---|---|---|---|---|---|
-    | `status` | ✅ `"status"` | ✅ `"ok"` | – | – | – | – |
-    | `mcp` | ✅ `"mcp"` | ✅ `"ok"` | ✅ `"list"` | – | – | – |
-    | `skills` | ✅ `"skills"` | – | ✅ `"list"` | ✅ | – | – |
-    | `agents` | ✅ `"agents"` | – | ✅ `"list"` | ✅ | – | – |
-    | `doctor` | ✅ `"doctor"` | – | – | ✅ | ✅ | ✅ |
-    | `sandbox` | ✅ `"sandbox"` | – | – | – | – | – |
-    | `init` | ✅ `"init"` | – | – | – | ✅ | – |
-    | `system-prompt` | ✅ `"system-prompt"` | – | – | – | ✅ | – |
-    | `version` | ✅ `"version"` | – | – | – | ✅ | – |
+    Reproduction:
 
-    **Only `kind` is universal.** Every other top-level discriminator is present on some envelopes and missing on others. A claw orchestrator that does `if json.status == "ok"` works for exactly 2 of 9 subcommands (`status`, `mcp`) and **silently returns `false`/`None` for the other 7 because the field doesn't exist**. A claw that does `if json.action == "list"` works for 3 of 9 (`mcp`, `skills`, `agents`) and breaks for the rest. There is **no single field a claw can read to determine "did this subcommand succeed?"** other than parsing stdout-vs-stderr routing (broken by #447/#450/#340/#341) or checking process exit code (broken by #435/#444). **Why distinct from existing items:** #90/#91/#92/#110/#115/#116/#130 cover **error envelope** shape asymmetry (the `{error, type}` shape vs `{kind, error}` shape); #340/#341/#347/#349/#350 cover specific subcommand envelopes where a not-found/unsupported state is shaped wrong; #121 covers the `doctor` `message`/`report` byte-duplication. **This pinpoint is the cross-subcommand catalog of success envelopes** — the structural fact that no single top-level field is present on every success envelope means **no portable success detection is possible** across the catalog without per-subcommand special-casing. It is the meta-pattern that the per-subcommand bugs above are individual instances of. **Trace:** every envelope is emitted from a separate code path with no shared envelope constructor. `status` JSON at `rust/crates/rusty-claude-cli/src/main.rs:5738` emits `"status": "ok"` directly. `mcp` JSON elsewhere emits both `status:"ok"` and `action:"list"`. `skills`/`agents` emit `action:"list"` and `summary` but no `status`. `doctor` JSON at `main.rs:1905-1923` emits `kind`/`message`/`report`/`has_failures`/`summary{ok,warn,fail,total}`/`checks[]` — no `status` field at all, while every `checks[i]` has its own `status`. `sandbox`/`init`/`system-prompt`/`version` each emit different ad-hoc shapes. There is no `EnvelopeBuilder` / `BaseEnvelope` shared struct that guarantees a uniform success/error discriminator across subcommands. **Why it matters:** structured JSON output exists precisely so claws can write generic dispatch logic. With the current catalog: (a) a claw that wants a single "is this OK?" predicate has to memorize 9 different rules — `status == "ok"` for two, `has_failures == false` for `doctor`, no field at all for `sandbox`/`init`/`system-prompt`/`version`. (b) A claw that wants to lift the human-readable summary has to check `message` for 4 commands, `report` for 1 (`doctor`, where `message == report` byte-for-byte per #121), `summary` for 3, and "no human summary at all" for 2. (c) A generic "render any claw JSON response" UI cannot exist — the consumer must implement a per-`kind` template. (d) New subcommands inherit the chaos: when a contributor adds `claw foo --output-format json`, there is no shared envelope they must conform to, so they invent another shape. The 458 entry locks in the cross-envelope catalog before more subcommands ship. **Required fix shape:** (a) **define a single shared `BaseEnvelope` for all `--output-format json` success responses**: `{kind: "<subcommand>", status: "ok"|"warn"|"error", action: "<verb>"|null, summary: "<one-line>", details: <command-specific-payload>}`. The two universal fields are `kind` + `status`; `action` and `summary` are optional-but-encouraged. (b) **Drop ad-hoc `message`/`report` fields** in favor of putting prose in a documented `summary` (one line) + optional `text_render` (full prose, only if a human-text rendering is genuinely needed in JSON mode, with a clear note that machines should not parse it). (c) **`doctor` rollup**: top-level `status` derived from `has_failures` and `summary.warnings` (`"ok"` when both zero, `"warn"` when warnings>0 and failures=0, `"error"` when failures>0); de-duplicate `message`/`report` (per #121). (d) **Regression coverage**: a single contract test that parses every `claw <subcommand> --output-format json` output, asserts `kind` is the subcommand name and `status ∈ {"ok","warn","error"}`, and rejects any envelope that omits either. (e) **Doc the envelope** in a new `docs/json-envelope-contract.md` so new subcommands have a single template to copy from. **Acceptance check (one-liner):** `for c in status mcp skills agents doctor sandbox init system-prompt version; do claw $c --output-format json 2>&1 | jq -e '.kind and (.status | IN("ok","warn","error"))' || echo "FAIL: $c"; done` should print no FAILs. Source: gaebal-gajae dogfood follow-up for the 2026-05-24 09:00 Clawhip pinpoint nudge at message `1508031832669814834`.
+    ```bash
+    $ env -i HOME=/tmp/iso29/home PATH=/usr/bin:/bin TERM=dumb \
+        claw mcp add demo -- /bin/echo hi --output-format json
+    {
+      "action": "help",
+      "kind": "mcp",
+      "unexpected": "add demo -- /bin/echo hi",
+      "usage": {
+        "direct_cli": "claw mcp [list|show <server>|help]",
+        "slash_command": "/mcp [list|show <server>|help]",
+        "sources": [".claw/settings.json", ".claw/settings.local.json"]
+      }
+    }
+    # exit 0, stderr empty, no .claw/settings.json written
+    ```
+
+    Same shape for:
+
+    ```bash
+    claw mcp add demo /bin/echo hi --output-format json
+    claw mcp remove demo --output-format json
+    claw mcp delete demo --output-format json
+    claw mcp disable demo --output-format json
+    claw mcp enable demo --output-format json
+    ```
+
+    All return `exit=0`, `kind:"mcp"`, `action:"help"`, `unexpected:"<verb ...>"` and no stderr. The supported action list in `mcp help --output-format json` is only `list|show <server>|help`, so these mutation verbs are unsupported by contract, but the failure mode is success/help.
+
+    **Root cause shape:** the MCP command parser treats unknown sub-actions as a help-topic request and preserves the raw tail in `unexpected`, but does not convert that branch into a command failure. The help JSON schema has no `status`, `ok`, `error_kind`, `exit_ok`, or `unsupported_action` field, so automation must special-case `action:"help" && unexpected != null` to detect that a requested operation did not run.
+
+    **Why distinct from existing items:** ROADMAP #327 covers `mcp help` source-list mismatch (`.claw.json` omitted while accepted). This entry covers unsupported mutation verbs returning success. ROADMAP #347 covers `mcp show <missing>` returning `status:"ok"` with `found:false`; this entry is broader/different: unsupported *verbs* (`add/remove/enable/disable/delete`) return help with exit 0 and no command-status field. ROADMAP #102/#129 cover MCP server liveness/runtime startup; this is control-plane mutation command semantics. ROADMAP #78 covered `plugins` route falling through to prompt; this is the `mcp` route resolving locally but reporting failed mutation as successful help. No existing entry found for `mcp add/remove` write-target or unsupported mutation verbs.
+
+    **Why this matters:** (1) **Automation false success.** A setup script can run `claw mcp add demo ...` and proceed because exit code is 0, even though no server was added. (2) **Mutation verbs are common user expectation.** MCP CLIs often support `add`/`remove`; users will try them. If not implemented, fail closed with a clear typed error. (3) **No write-target clarity.** Since help claims sources `.claw/settings.json` / `.claw/settings.local.json`, a user may reasonably expect `add` to write one. Returning success/help leaves them guessing. (4) **Machine contract ambiguity.** `unexpected` inside help is not an error field; claws should not have to infer failure from a non-null optional help attribute. (5) **Compounds #327.** The help object shown in the failure path also repeats the stale source-list problem, so the unsupported-action error points at incomplete config-source docs.
+
+    **Required fix shape:** (a) For unsupported MCP sub-actions, return a typed JSON error such as `{type:"error", kind:"unsupported_mcp_action", action:"add", supported_actions:["list","show","help"], hint:"MCP mutation commands are not implemented; edit .claw/settings.json manually or use ..."}` and exit non-zero. (b) Preserve a human help fallback only for explicit `mcp help` / `mcp --help`, not for attempted mutations. (c) If mutation verbs are intended roadmap features, add `not_implemented` status with non-zero exit and no file writes. (d) Add tests for `add/remove/enable/disable/delete` proving they are distinguishable from successful help and successful list/show. (e) When mutation support lands, include explicit write-target/source-layer semantics (`project`, `local`, `user`) instead of guessing. **Acceptance check:** `claw mcp add demo -- /bin/echo hi --output-format json >/tmp/out 2>/tmp/err; test $? -ne 0 && jq -e '.kind == "unsupported_mcp_action" and .action == "add"' /tmp/err` should pass; currently exit is 0 and stdout is a help object. Source: gaebal-gajae dogfood for the 2026-05-24 20:00 Clawhip nudge. Coordination note: avoided Jobdori-claimed #680/session-sort and F/CLAW_CONFIG_HOME; targeted MCP mutation semantics after pre-grep showed common MCP lifecycle gaps already covered.