docs(roadmap): add #470 — reasoning-effort accepted by diagnostics but invisible; invalid parser kind unknown

ROADMAP.md

@@ -6422,3 +6422,45 @@ 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.
+
+470. **`--reasoning-effort` is accepted by local diagnostic subcommands (`status`, `doctor`, `version`, etc.) even though it is a prompt/API-request knob, then disappears from every diagnostic JSON surface; valid values (`low|medium|high`) parse and exit 0 on `status` / `doctor` with no `reasoning_effort` field, no `ignored_flags` warning, and no indication that the flag will only affect future prompt turns. Invalid values have their own strict parser (`LOW`, `Low`, `low `, ` low`, empty, `extreme`, `1`) but that error sentinel is another `classify_error_kind` orphan (`kind:"unknown"`, `hint:null`), repeating the #463/#464 pattern on a third flag-value parser** — dogfooded 2026-05-24 for the 19:30 Clawhip nudge at message `1508190377130197222`, reproduced on local `./rust/target/debug/claw` `git_sha 003b739d` (origin/main `f8e1bb72`) in a clean isolated env.
+
+    Reproduction:
+
+    ```bash
+    $ claw --output-format json --reasoning-effort high status | jq 'keys'
+    ["allowed_tools","config_load_error","kind","model","model_raw","model_source","permission_mode","sandbox","status","usage","workspace"]
+    # no reasoning_effort, no ignored_flags, no active_request_options
+
+    $ claw --output-format json --reasoning-effort high doctor | jq '.checks[].name'
+    "auth" "config" "install_source" "workspace" "sandbox" "system"
+    # no reasoning/model/request-options check carrying reasoning_effort
+
+    $ claw --output-format json --reasoning-effort LOW status
+    {"error":"invalid value for --reasoning-effort: 'LOW'; must be low, medium, or high","hint":null,"kind":"unknown","type":"error"}
+
+    $ claw --output-format json --reasoning-effort 'low ' status
+    {"error":"invalid value for --reasoning-effort: 'low '; must be low, medium, or high","hint":null,"kind":"unknown","type":"error"}
+    ```
+
+    Valid matrix: `low`, `medium`, `high` all exit 0 on `status` and `doctor` but are invisible. Invalid matrix: `LOW`, `Low`, `low `, ` low`, empty string, `extreme`, `1` all exit 1 with `kind:"unknown"` and `hint:null`.
+
+    **Root cause traced:** `rust/crates/rusty-claude-cli/src/main.rs:712-731` validates `--reasoning-effort` as a global flag and stores `reasoning_effort = Some(value)`, but the local diagnostic renderers never receive or serialize it. `status_json_value()` around `main.rs:5688-5714` exposes model, permission mode, allowed tools, workspace, sandbox, config load error, and usage — not request options. `doctor` builds fixed checks (`auth`, `config`, `install_source`, `workspace`, `sandbox`, `system`) and has no request-options check. The invalid-value error string is:
+
+    ```rust
+    "invalid value for --reasoning-effort: '{value}'; must be low, medium, or high"
+    ```
+
+    but `classify_error_kind()` has no branch for it, so every invalid reasoning-effort parse error becomes `kind:"unknown"`.
+
+    **Why distinct from existing items:** ROADMAP #98 covers `--compact` silently ignored outside prompt/text output. This entry covers `--reasoning-effort`, a different prompt/API knob with different parser and provider semantics. ROADMAP #464 covers invalid `--output-format` enum parsing; this entry covers `--reasoning-effort` enum parsing plus valid-value invisibility. ROADMAP #468 covers duplicate global flags; this entry covers single valid flag accepted by diagnostic subcommands with no visible effect. ROADMAP #34/#35 cover OpenAI-compat reasoning-effort transport support; this entry is about CLI diagnostic surfaces accepting the knob without exposing whether it is active. No existing entry documents `--reasoning-effort high status` being a successful no-op/invisible state.
+
+    **Why this matters:** (1) **Prompt/API knobs on diagnostic commands are misleading.** A launcher may run `claw --reasoning-effort high status` to verify a lane is configured for high reasoning; status says ok but never confirms the knob. (2) **Automation cannot audit request options.** `status` is the lightweight preflight surface; if reasoning effort affects cost/latency/model behavior, claws need to know its active value before prompt execution. (3) **Same enum-parser quality gap repeats.** `LOW` and trailing whitespace are common wrapper/env-file outputs; the parser rejects them with `kind:"unknown"` instead of `kind:"invalid_reasoning_effort"`, no suggestion, no trim/case handling. (4) **Silent successful no-op and loud unknown invalid are both bad.** Valid values disappear; invalid values are misclassified. Together they make the knob hard to reason about programmatically. (5) **Regression tests are too shallow.** Existing tests around `rejects_invalid_reasoning_effort_value` assert the substring exists, and `accepts_valid_reasoning_effort_values` asserts parse state only. They do not assert JSON envelope kind/hint, diagnostic-surface visibility, or prompt-vs-diagnostic applicability.
+
+    **Required fix shape:** (a) Decide contract: either reject prompt/API-only knobs (`--reasoning-effort`, maybe future `--max-output-tokens`) on local diagnostic subcommands with a structured `unsupported_flag_for_subcommand` error, or expose them in `status`/`doctor` as `request_options.reasoning_effort` / `active_request_options`. (b) If accepted, add `reasoning_effort` to `status --output-format json` and a `request_options` doctor check so preflight can verify it. (c) Register `invalid_reasoning_effort` in `classify_error_kind` and split a real `hint` field (valid values: `low`, `medium`, `high`). (d) Normalize or suggest common variants: trim whitespace, lower-case `LOW`/`Low`, or produce `Did you mean: low?`. (e) Add regression coverage for valid visibility on `status`/`doctor`, invalid-value JSON kind/hint, and prompt-path preservation. **Acceptance check:** `claw --output-format json --reasoning-effort high status | jq -e '.request_options.reasoning_effort == "high" or .ignored_flags[]?.flag == "--reasoning-effort"'` should pass; current output has neither. `claw --output-format json --reasoning-effort LOW status 2>&1 | jq -e '.kind == "invalid_reasoning_effort"'` should pass; current kind is `unknown`. Source: gaebal-gajae dogfood for the 2026-05-24 19:30 Clawhip nudge. Number intentionally skips #469 because Jobdori publicly reported a local #469 (`/compact` slash divergence) not yet pushed; this avoids collision.