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

ROADMAP.md

@@ -6422,3 +6422,49 @@ Original filing (2026-04-18): the session emitted `SessionStart hook (completed)
 
 448. **`sandbox --output-format json` has contradictory state flags — `enabled:true, supported:false, active:false, filesystem_active:true, allowed_mounts:[]`: claim that sandbox is "enabled" while OS doesn't support namespace isolation and `allowed_mounts:[]` is empty contradicts `filesystem_active:true filesystem_mode:"workspace-only"`** — dogfooded 2026-05-11 by Jobdori on `7244a82b` in response to Clawhip pinpoint nudge at `1503403842920779917` (using fresh-current-main runner at `/tmp/claw-dog-1430` per gajae's 14:00 protocol switch). Reproduction: `claw sandbox --output-format json` on macOS (where `unshare` is unavailable) returns `{"active":false,"active_namespace":false,"active_network":false,"allowed_mounts":[],"enabled":true,"fallback_reason":"namespace isolation unavailable (requires Linux with \`unshare\`)","filesystem_active":true,"filesystem_mode":"workspace-only","in_container":false,"kind":"sandbox","markers":[],"requested_namespace":true,"requested_network":false,"supported":false}`. **Three contradictions in the same envelope:** (a) `enabled:true` AND `supported:false`: what does "enabled" mean if the OS doesn't support sandboxing? Read literally, sandbox is *enabled but unsupported* — semantic nonsense. The likely intent is "user requested sandbox in config" but the field name `enabled` says "is ON". A better name would be `requested:true` or `config_intent:true`, with `enabled` reserved for the actually-active state. (b) `filesystem_active:true, filesystem_mode:"workspace-only"` AND `allowed_mounts:[]`: if the filesystem fence is active in workspace-only mode, the workspace directory itself MUST be an allowed mount. An empty `allowed_mounts:[]` array combined with `filesystem_active:true` means either (i) the fence is being misreported (it's not really active), (ii) the workspace is implicit and `allowed_mounts` only lists *additional* mounts, or (iii) the fence has no allowed paths and nothing is readable — all three are inconsistent with the user-facing summary. (c) `active:false` AND `filesystem_active:true`: the top-level `active` field is a single boolean summary, but it disagrees with `filesystem_active:true` (one component is active). Either `active` is "all components active" (then it should be `false` when any component is off) or "any component active" (then it should be `true` when filesystem is). The current value is `false` despite filesystem being active. **Sibling: no `claw sandbox --help`**: `claw sandbox status` and `claw sandbox --help` go to LLM-prompt fallback or hang (gajae confirmed at 13:00 that `sandbox status` returns typed `cli_parse` but `sandbox --help` is bounded — schema is non-uniform across help paths). **Required fix shape:** (a) rename `enabled` to `requested` or `config_intent` to disambiguate from "currently active"; (b) make `allowed_mounts` explicitly include the workspace when filesystem_mode is "workspace-only" (`allowed_mounts:[{path:"<cwd>",writable:true,reason:"workspace_root"}]`); (c) document the `active` aggregate semantics: pick either "all" or "any" composition rule and document the choice; (d) add `active_components:["filesystem"]` array as a richer alternative to the single boolean — surfaces exactly which sandbox subsystems are live; (e) regression test: when `filesystem_mode == "workspace-only"`, `allowed_mounts` MUST contain the cwd and `active` must agree with the documented composition rule. **Why this matters:** sandbox is the trust surface — automation that checks `sandbox.active == true` before running a risky LLM prompt sees `false` (no namespace, no network) and assumes no isolation, but `filesystem_active:true` means there IS partial isolation. The mixed signal forces consumers to OR all `*_active` fields together. Cross-references #428 (default permission_mode=danger-full-access — paired with sandbox-not-active means zero isolation), #444 (no broad-cwd guard — sandbox is the only safety net and its status is unclear). Source: Jobdori live dogfood, `7244a82b`, 2026-05-11.
 
+
+449. **`claw session list --output-format json` routes through `CliAction::ResumeSession` and hits the auth gate, returning `kind:"missing_credentials"` — but `session list` is a pure local filesystem read that requires no API credentials; by contrast, `claw session` (without `list`) correctly short-circuits with `kind:"unknown"` + "is a slash command" message without touching the auth gate** — dogfooded 2026-05-12 by Jobdori on `8f55870d` in response to Clawhip pinpoint nudge at `1503638404842131456`. Reproduction (no creds, isolated env): `env -i HOME=$HOME PATH=$PATH claw session list --output-format json` → `{"error":"missing Anthropic credentials...","kind":"missing_credentials"}` exit 1. `env -i HOME=$HOME PATH=$PATH claw session --output-format json` → `{"error":"`claw session` is a slash command...","kind":"unknown"}` exit 1 (no auth check). Root cause: the parser routes `session list` via `parse_resume_session_args` treating `list` as a session-path token, producing `CliAction::ResumeSession { session_path: "list", commands: [] }`. `resume_session()` then calls `LiveCli::new()` which instantiates the Anthropic client and fires the credentials guard. The `SlashCommand::Session { action: Some("list") }` special-case path in `run_resume_command()` (line 3654 comment: "`/session list` can be served from the sessions directory without a live session") is only reachable after auth passes — the no-creds guard fires before the slash-command dispatch loop. **Asymmetry:** the internal code already knows `session list` is credential-free (the comment at line 3654 says so), but the CLI entrypoint forces creds before the command ever reaches that branch. **Sibling: `session list` with no sessions returns `kind:"session_load_failed"` (from `--resume latest` fallback) rather than `{"kind":"session_list","sessions":[],"session_details":[]}` — the empty-sessions case is misrouted to the resume-failure path instead of a list-success with zero entries.** **Required fix shape:** (a) add a dedicated `CliAction::SessionList { output_format }` variant dispatched when `claw session list` is parsed — do not route through `ResumeSession`; (b) implement `run_session_list(output_format)` as a credentials-free function that calls `list_managed_sessions()` directly (same logic as the slash-command special-case at line 3659); (c) ensure empty sessions returns `{"kind":"session_list","sessions":[],"session_details":[],"active":null}` with exit 0, not a `session_load_failed` error; (d) add the same fix for sibling local-only commands that currently hit the auth gate: `session delete <id>`, `session export <id>`; (e) regression test: `claw session list --output-format json` with no credentials returns `kind:"session_list"` exit 0. **Why this matters:** session list is the canonical inventory surface for automation pipelines — `claw session list --output-format json | jq '.session_details[] | .id'` is the idiomatic way to enumerate sessions for replay, export, or resume. Requiring API credentials to read a local directory listing breaks offline use, CI environments with no API key configured, and any scripting that runs before credential setup. Cross-references #357 (session list requires creds — this is the same bug surfaced by that entry; #449 provides the root-cause path trace), #369 (session help/fork require creds), #427 (resume --help hits auth gate), #431 (skills uninstall requires creds). Source: Jobdori live dogfood, `8f55870d`, 2026-05-12.
+
+
+
+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.
+
+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.
+
+    Reproduction:
+
+    ```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.