docs(roadmap): add #683 — sandbox help ignores json output format

ROADMAP.md

@@ -6429,47 +6429,33 @@ 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.
 
-684. **`init --help --output-format json` returns parseable JSON but keeps the init contract inside a prose `message`, unlike `export` help which exposes structured defaults/options; automation cannot discover which artifacts `init` creates, idempotency semantics, or next-step/recovery fields without scraping aligned text** — dogfooded 2026-05-24 for the 21:30 Clawhip nudge at message `1508220580053389436`, reproduced on a freshly rebuilt current `origin/main` binary (`git_sha f8e1bb726`) from `/tmp/cc-probe-main-2130`, after discarding stale-debug-binary observations from `003b739d`/`e939777f`.
+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/iso38/home PATH=/usr/bin:/bin TERM=dumb \
-        claw init --help --output-format json
-    {
-      "command": "init",
-      "kind": "help",
-      "message": "Init\n  Usage            claw init [--output-format <format>]\n  Purpose          create .claw/, .claw.json, .gitignore, and CLAUDE.md in the current project\n  Output           list of created vs. skipped files (idempotent: safe to re-run)\n  Formats          text (default), json\n  Related          claw status · claw doctor",
-      "topic": "init"
-    }
+    $ 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
     ```
 
-    The command returns valid JSON, but every init-specific contract is embedded in the human `message` string. There are no structured fields for `usage`, `purpose`, `creates`, `idempotent`, `output_shape`, `formats`, `related`, `side_effects`, `requires_confirmation`, or `next_step`.
-
-    Contrast with the same current-main binary's actual init output:
+    In the same clean environment, the normal command is machine-readable:
 
     ```bash
-    $ claw init --output-format json
-    {
-      "kind": "init",
-      "artifacts": [
-        {"name":".claw/", "status":"created"},
-        {"name":".claw.json", "status":"created"},
-        {"name":".gitignore", "status":"created"},
-        {"name":"CLAUDE.md", "status":"created"}
-      ],
-      "created": [".claw/", ".claw.json", ".gitignore", "CLAUDE.md"],
-      "skipped": [],
-      "updated": [],
-      "next_step": "Review and tailor the generated guidance",
-      ...
-    }
+    claw sandbox --output-format json
+    # => {"kind":"sandbox", ...}
     ```
 
-    And contrast with `export --help --output-format json` on the same binary, which already exposes structured fields beyond `message` such as `defaults`, `formats`, `kind`, and `options[]` with `name`, `value`, `description`, aliases, and defaults. The init help surface is therefore a schema-quality outlier among local command help surfaces: parseable JSON exists, but not the machine-readable contract that a claw needs before running a side-effectful initializer.
+    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:** #325 covers top-level `help --output-format json` being prose wrapped in JSON. #356/#357/#683 cover status/doctor/sandbox help returning plain text or command-specific help-format gaps. #358/#380/#381 cover hanging help surfaces. #420 covers `plugins help` mutation-envelope drift. #684 is narrower: current-main `init` help is valid JSON but under-structured for a side-effectful project initializer, while sibling `export` help already demonstrates the richer command-help schema pattern. This is not a stale-binary finding; the binary under test reports `git_sha f8e1bb726` matching `origin/main`.
+    **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:** `init` is side-effectful: it creates `.claw/`, `.claw.json`, `.gitignore`, and `CLAUDE.md`. A wrapper or onboarding claw should be able to discover these writes, idempotency guarantees, and follow-up expectations before executing the command. Today it must scrape the aligned prose in `message`, then separately infer the actual artifact list from a dry-run-less real invocation. That is backwards for safe automation: help should expose side effects before mutation.
+    **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) Extend `init --help --output-format json` with structured fields mirroring its real output and side-effect contract: `usage`, `purpose`, `formats:["text","json"]`, `creates:[{"name":".claw/","kind":"directory"}, ...]`, `idempotent:true`, `mutates_workspace:true`, `requires_confirmation:false`, `output_fields:["artifacts","created","skipped","updated","next_step","project_path"]`, `related:["claw status","claw doctor"]`, and optional `dry_run_available:false` until such a flag exists. (b) Keep `message` as human summary only. (c) Align command-help JSON schemas so side-effectful commands expose side-effect metadata consistently; `export` already proves richer help JSON is acceptable. (d) Add regression coverage proving `claw init --help --output-format json | jq '.creates[]?.name'` contains `.claw/`, `.claw.json`, `.gitignore`, and `CLAUDE.md`, and that it declares `idempotent:true` / `mutates_workspace:true`. **Acceptance check:** `claw init --help --output-format json | jq -e '.command=="init" and .mutates_workspace==true and .idempotent==true and ([.creates[].name] | index(".claw.json")) and ([.output_fields[]] | index("artifacts"))'` should pass; currently `.creates`, `.idempotent`, `.mutates_workspace`, and `.output_fields` are absent. Source: gaebal-gajae dogfood for the 2026-05-24 21:30 Clawhip nudge. Coordination note: avoided #420 after pre-grep showed Jobdori already tracked `plugins help`; avoided stale-binary candidates by rebuilding current `origin/main` before filing.
+    **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.