docs(roadmap): add #452 — claw models/list/help/--help falls through to prompt dispatch (prompt misdelivery, sibling of #78)

ROADMAP.md

@@ -6429,33 +6429,4 @@ 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.
 
-683. **Top-level `sandbox --help --output-format json` exits successfully but emits plain text help instead of JSON, so automation cannot discover sandbox isolation semantics without scraping prose** — dogfooded 2026-05-24 for the 21:00 Clawhip nudge at message `1508213026480849056`, reproduced on local `./rust/target/debug/claw` `git_sha 003b739d` (origin/main `f8e1bb72`) in a clean isolated env. This continues the command-help JSON parity audit while avoiding already-filed #356 (`status --help --output-format json`) and #357 (`doctor --help --output-format json`).
-
-    Reproduction:
-
-    ```bash
-    $ env -i HOME=/tmp/iso34/home PATH=/usr/bin:/bin TERM=dumb \
-        claw sandbox --help --output-format json
-    Sandbox
-      Usage            claw sandbox [--output-format <format>]
-      Purpose          inspect the resolved sandbox and isolation state for the current directory
-      Output           namespace, network, filesystem, and fallback details
-      Formats          text (default), json
-      Related          /sandbox · claw status
-    # exit 0, stderr empty, stdout is not JSON
-    ```
-
-    In the same clean environment, the normal command is machine-readable:
-
-    ```bash
-    claw sandbox --output-format json
-    # => {"kind":"sandbox", ...}
-    ```
-
-    And global flag order is not the issue: corrected argv probes confirm both `claw sandbox --output-format json` and `claw --output-format json sandbox` work. The failure is specifically the help path accepting `--output-format json` while rendering text.
-
-    **Why distinct from existing items:** #356 covers `status --help --output-format json` returning plain text. #357 covers `doctor --help --output-format json` returning plain text. #325 covers top-level `help --output-format json` being prose wrapped in JSON. #683 is the sandbox command's own help path: it returns no JSON envelope at all even though `sandbox` is a core preflight/isolation control-plane surface and its non-help JSON command already exists. It is also distinct from #381/cache and #358/#380 cost/tokens hangs: sandbox help returns promptly, but ignores the requested machine format.
-
-    **Why this matters:** (1) Sandbox state gates whether a claw can safely run filesystem/network actions; the help surface is where automation learns the fields and related slash command. (2) Returning plain text with exit 0 after `--output-format json` forces claws to parse human alignment columns or special-case sandbox help. (3) This weakens the preflight contract: `sandbox` itself is machine-readable, but the discovery path for its schema/options is not. (4) The bug likely shares the same help-rendering branch as status/doctor, but sandbox needs its own regression because the command-specific help body and accepted options differ.
-
-    **Required fix shape:** (a) Make `sandbox --help --output-format json` emit valid stdout JSON such as `{kind:"help", command:"sandbox", action:"help", usage:"claw sandbox [--output-format <format>]", purpose:"...", output_fields:[...], formats:["text","json"], related:["/sandbox","claw status"]}`. (b) Preserve the current aligned text only for text/default mode. (c) Add a `format:"json"` or schema/version field so callers can assert the help contract without parsing prose. (d) Add regression coverage proving sandbox help with JSON format parses as JSON and that normal `sandbox --output-format json` remains unchanged. (e) Consider sharing the fix with status/doctor (#356/#357), but keep sandbox covered explicitly to prevent partial help parity. **Acceptance check:** `claw sandbox --help --output-format json | jq -e '.kind == "help" and .command == "sandbox" and (.formats | index("json"))'` should pass; currently `jq` fails immediately because stdout begins with `Sandbox`. Source: gaebal-gajae dogfood for the 2026-05-24 21:00 Clawhip nudge. Coordination note: avoided Jobdori #680/session-sort, #681/#682 help-success mutation cluster, and existing help JSON items #325/#356/#357/#358/#380/#381; filed a fresh sandbox-specific preflight help parity gap.
+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`.