docs(roadmap): add #682 — unsupported agents mutation verbs return help with exit 0

ROADMAP.md

@@ -6429,4 +6429,39 @@ 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.
 
-452. **`claw models`, `claw models list`, `claw models help`, and `claw models --help` are not wired as a `CliAction` at all — every spelling falls through to `CliAction::Prompt` and is sent verbatim to the Anthropic API as a user prompt; with credentials the CLI spins on the LLM "Thinking…" spinner forever, without credentials it errors with `missing_credentials` from the provider path. Direct sibling of #78 (`claw plugins` had the same prompt-misdelivery failure mode) for an additional discovery surface that operators and claws naturally try first when they need a model registry/alias/provider list before invoking `--model <alias> prompt …`** — dogfooded 2026-05-24 for the 05:00 Clawhip pinpoint nudge at message `1507971434704797716`, reproduced on local `./rust/target/debug/claw` `git_sha 003b739d` (origin/main `f8e1bb72`; `models` dispatch is grep-clean across `rust/crates/` — `git grep -nE 'CliAction::Models|"/models"|"models"' rust/` returns 0 hits, while `CliAction::Plugins` is wired at `rust/crates/rusty-claude-cli/src/main.rs:356,891,10153,10158,10167,10180,10193`, so `models` is the analogous unrouted command exactly the way `plugins` was before #78 landed). Repros in a fully clean isolated environment (`HOME=/tmp/iso2/home` with `{"}` settings, fresh `/tmp/iso2/proj` git-init'd workspace, `stdin=/dev/null`): `timeout 8 claw models list` exits `1` with `stderr=490` carrying the **Anthropic provider** `missing_credentials` envelope when `ANTHROPIC_*` env vars are unset, proving the command was dispatched to the LLM rather than handled locally; with `ANTHROPIC_API_KEY` set, every spelling (`models list`, `models`, `models help`, `models --help`) shows the spinner ANSI sequence (`\x1b[38;5;12m⠋ 🦀 Thinking…\x1b[0m`) on stdout and never returns inside the 6–8s bounded budget. **Why this is distinct from #78 / #145 / the help-JSON cluster:** #78 covered `claw plugins` only; #145 added the regression for `Plugins` parsing; #451 covers `models` in `--output-format json` mode where the failure surface is the silent zero-byte JSON deadlock. This pinpoint is the **plain-text prompt-misdelivery path** for `models`, with three behavioral consequences not covered above: (1) operators get the wrong-shaped error (`missing_credentials` for an Anthropic prompt) when they meant to inspect the model registry; (2) with credentials, expensive token burn on a meaningless `"models list"` LLM completion; (3) no slash-command-vs-direct-command parity — there is also no `/models` REPL command, so claws have no recovery path either. **Required fix shape:** (a) add `CliAction::Models { action: ModelsAction }` with `List`, `Show { name }`, `Help` variants wired in `parse_args` next to the existing `CliAction::Plugins` arm, never falling through to `CliAction::Prompt` for any `models*` spelling; (b) implement `models list` to return the resolved provider registry merged from built-ins (`anthropic`, `openai`, `xai`) plus any `modelProviders.*` profiles in settings, with per-model `name`, `provider`, `aliases[]`, `available`, `requires_credentials`, `source`; (c) implement `models --help` / `models help` as a static bounded help renderer (text + JSON envelopes) that does not touch provider runtime; (d) mirror the slash surface (`/models` REPL command) to match the existing `/agents`, `/mcp`, `/skills`, `/config` pattern; (e) add regression coverage in `parses_models_subcommand`-style tests proving every `models*` spelling resolves to `CliAction::Models` (no LLM dispatch), AND that the action returns within a deterministic budget without provider credentials. **Why this matters:** `models list` is the canonical model-registry discovery spelling across competing CLIs (`gh models list`, `openai api models.list`, `codex models`, the Anthropic Console UI). A claw or operator who reaches for it before deciding `--model <alias>` cannot discover what models exist, cannot validate an alias before paying for a prompt, and — worst case — burns provider tokens sending the string `"models list"` to Claude on a credentialed setup. The cost-of-doing-nothing here is real spend, not just opacity, which is why the prompt-misdelivery class deserves its own surface entry beyond #78/#145's `plugins` precedent. Source: gaebal-gajae dogfood follow-up for the 2026-05-24 05:00 Clawhip pinpoint nudge at message `1507971434704797716`.
+682. **Unsupported native-agent mutation verbs (`claw agents add/remove/enable`) return generic help JSON with `exit=0` instead of a typed unsupported/not-implemented error, so automation can treat a failed staffing/control-plane mutation as success** — dogfooded 2026-05-24 for the 20:30 Clawhip nudge at message `1508205480818774086`, reproduced on local `./rust/target/debug/claw` `git_sha 003b739d` (origin/main `f8e1bb72`) in a clean isolated env. This was found by carrying forward #681's “help + unexpected + exit 0” stealth-success pattern from `mcp` to sibling local route helpers. Number intentionally follows #681 and avoids Jobdori-announced #680.
+
+    Reproduction:
+
+    ```bash
+    $ env -i HOME=/tmp/iso30/home PATH=/usr/bin:/bin TERM=dumb \
+        claw agents add demo -- /bin/echo hi --output-format json
+    {
+      "action": "help",
+      "kind": "agents",
+      "unexpected": "add demo -- /bin/echo hi",
+      "usage": {
+        "direct_cli": "claw agents [list|help]",
+        "slash_command": "/agents [list|help]",
+        "sources": [".claw/agents", "~/.claw/agents", "$CLAW_CONFIG_HOME/agents"]
+      }
+    }
+    # exit 0, stderr empty, no agent created/registered
+    ```
+
+    Same shape for:
+
+    ```bash
+    claw agents remove demo --output-format json
+    claw agents enable demo --output-format json
+    ```
+
+    All return `exit=0`, `kind:"agents"`, `action:"help"`, `unexpected:"<verb ...>"` and no stderr. The supported contract in the returned help object is only `list|help`, so these mutation verbs are unsupported by contract, but the command-level outcome is success.
+
+    **Root cause shape:** the agents command parser shares the same “unknown tail becomes help with `unexpected`” pattern as MCP. It preserves the unrecognized verb in a decorative help field but does not set an error status, code, nonzero exit, or structured `unsupported_action` metadata. The result is neither a successful mutation nor a machine-classifiable failure.
+
+    **Why distinct from existing items:** ROADMAP #328 covers agent source-root/provenance mismatch. #329 covers resume-safe slash `/agents` flattening structured inventory to prose. #346 covers natural `agents show <name>` detail inspection collapsing to help-success. This entry covers unsupported *mutation/control-plane verbs* (`add/remove/enable`) returning success, which matters for setup/staffing automation and not just detail lookup. #681 covers the same failure class for `mcp`; #682 documents the native-agent subsystem's separate route and required regression coverage.
+
+    **Why this matters:** (1) **Automation false success.** A bootstrap script can run `claw agents add reviewer ...` and continue because exit code is 0, even though no agent exists. (2) **Staffing state becomes unverifiable.** Native-agent availability controls delegation; a failed add/enable/remove must not look like successful help. (3) **Mutation verbs are natural expectations.** Users will try `agents add/remove/enable` after seeing agent inventory, and the CLI should fail closed if those mutations are intentionally unsupported. (4) **`unexpected` is not an error contract.** Claws should not have to infer failure from an optional field inside an otherwise successful help object. (5) **The bug is reusable.** #681 proved the pattern in MCP; this sibling route shows the parser/helper abstraction likely needs a shared unsupported-subaction contract across local route helpers.
+
+    **Required fix shape:** (a) Unsupported agents sub-actions should return a typed JSON error or explicit non-ok status such as `{type:"error", kind:"unsupported_agents_action", requested_action:"add", supported_actions:["list","help"], hint:"Native-agent mutation commands are not implemented; add agent files under a documented agents root or use ..."}` and exit non-zero. (b) Keep help fallback only for explicit `agents help` / `agents --help`; attempted mutations must not be reported as successful help. (c) If `add/remove/enable` are planned features, return `not_implemented` with nonzero exit and no file writes until the write-target/source-layer semantics exist. (d) Add parser/output tests for `agents add`, `agents remove`, and `agents enable` proving they are distinguishable from successful help and successful list. (e) Consider a shared helper for local route families (`agents`, `mcp`, maybe `skills`/`plugins`) so `unexpected` can never be the sole machine signal for unsupported actions. **Acceptance check:** `claw agents add demo -- /bin/echo hi --output-format json >/tmp/out 2>/tmp/err; test $? -ne 0 && jq -e '.kind == "unsupported_agents_action" and .requested_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 20:30 Clawhip nudge. Coordination note: avoided Jobdori #680/session-sort, F/CLAW_CONFIG_HOME, already-covered MCP items, and prior agent items #328/#329/#346; targeted mutation semantics after route-sibling probe.