mirror of
https://github.com/instructkr/claw-code.git
synced 2026-06-06 09:52:43 -04:00
Compare commits
1 Commits
docs/roadm
...
docs/roadm
| Author | SHA1 | Date | |
|---|---|---|---|
|
5c46d69961 |
47
ROADMAP.md
47
ROADMAP.md
@@ -6429,38 +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.
|
||||
|
||||
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.
|
||||
692. **`dump-manifests --help --output-format json` is now correctly intercepted as help on current main, but the JSON help is message-only (`{kind, command, topic, message}`) and does not expose the manifest source contract (`--manifests-dir`, required upstream files, output schema, missing-manifest context fields, local/auth behavior); claws cannot discover how to preflight or repair manifest extraction without parsing prose or intentionally hitting `missing_manifests`** — dogfooded 2026-05-25 for the 01:30 Clawhip nudge at message `1508280974243266740`, reproduced on a freshly rebuilt current `origin/main` binary (`git_sha f8e1bb726`) from `/tmp/cc-probe-main-2130`. Active claw-code sessions: none.
|
||||
|
||||
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"}
|
||||
$ env -i HOME=/tmp/iso47/home PATH=/usr/bin:/bin TERM=dumb \
|
||||
claw dump-manifests --help --output-format json
|
||||
{
|
||||
"command": "dump-manifests",
|
||||
"kind": "help",
|
||||
"message": "Dump Manifests\n Usage claw dump-manifests [--manifests-dir <path>] [--output-format <format>]\n Purpose emit every skill/agent/tool manifest the resolver would load for the current cwd\n Options --manifests-dir scopes discovery to a specific directory\n Formats text (default), json\n Related claw skills · claw agents · claw doctor",
|
||||
"topic": "dump-manifests"
|
||||
}
|
||||
```
|
||||
|
||||
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`.
|
||||
On the same binary and environment, the primary command immediately needs structured repair context:
|
||||
|
||||
**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"
|
||||
```bash
|
||||
$ env -i HOME=/tmp/iso47/home PATH=/usr/bin:/bin TERM=dumb \
|
||||
claw dump-manifests --output-format json
|
||||
{
|
||||
"error": "Manifest source files are missing.",
|
||||
"exit_code": 1,
|
||||
"hint": "repo root: /tmp/cc-probe-main-2130\n missing: src/commands.ts, src/tools.ts, src/entrypoints/cli.tsx\n Hint: set CLAUDE_CODE_UPSTREAM=/path/to/upstream or pass `claw dump-manifests --manifests-dir /path/to/upstream`.",
|
||||
"kind": "missing_manifests",
|
||||
"type": "error"
|
||||
}
|
||||
```
|
||||
|
||||
but `classify_error_kind()` has no branch for it, so every invalid reasoning-effort parse error becomes `kind:"unknown"`.
|
||||
Help does not expose structured `options[]`, `output_fields`, `required_source_files`, `source_resolution_order`, `environment_overrides` (e.g. `CLAUDE_CODE_UPSTREAM`), `error_kinds` / `missing_manifests.context` fields, `local_only`, `requires_credentials:false`, `requires_provider_request:false`, or `mutates_workspace:false`.
|
||||
|
||||
**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 distinct from existing items:** #141 covered old parser behavior where `dump-manifests --help` errored as an unknown option. Current main fixed that: it now returns a help object. #20/typed-error-envelope work covers the general desire for structured error context such as `missing_manifests.context`. #692 is narrower: the help JSON for `dump-manifests` does not describe the manifest-source inputs and the error/output schema before callers run the command. #327/#328 cover MCP/agent source-root mismatches; this is the manifest dumper source contract itself.
|
||||
|
||||
**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.
|
||||
**Why this matters:** `dump-manifests` is a resolver/debugging preflight for skills, agents, and tools. It often runs in installed binaries where upstream TypeScript source files are absent, so the normal failure is `missing_manifests`. A claw should be able to read help JSON and learn the required files, env override, `--manifests-dir` semantics, output fields, and possible `missing_manifests` shape before deciding whether to run or how to repair. Today the repair recipe is only in a human `hint` string after failure.
|
||||
|
||||
**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.
|
||||
**Required fix shape:** (a) Extend `dump-manifests --help --output-format json` with structured fields: `usage:"claw dump-manifests [--manifests-dir <path>] [--output-format <format>]"`, `formats:["text","json"]`, `related:["claw skills","claw agents","claw doctor"]`, `local_only:true`, `requires_credentials:false`, `requires_provider_request:false`, `mutates_workspace:false`, `options:[{name:"--manifests-dir", value_name:"PATH", type:"directory", required:false, default:"repo root or CLAUDE_CODE_UPSTREAM", validation:["exists","is_directory"]},{name:"--output-format", values:["text","json"]}]`, `required_source_files:["src/commands.ts","src/tools.ts","src/entrypoints/cli.tsx"]`, `environment_overrides:["CLAUDE_CODE_UPSTREAM"]`, `output_fields:[...]`, and `error_kinds:["missing_manifests","missing_manifest_dir",...]`. (b) Add structured `missing_manifests_context` metadata in help documenting `repo_root`, `missing[]`, and `repair_options[]`. (c) Derive required files and env names from the same resolver used by the command. (d) Keep `message` as human summary only. **Acceptance check:** `claw dump-manifests --help --output-format json | jq -e '.command=="dump-manifests" and .local_only==true and .requires_credentials==false and ([.options[].name] | index("--manifests-dir")) and ([.required_source_files[]] | index("src/commands.ts")) and ([.environment_overrides[]] | index("CLAUDE_CODE_UPSTREAM"))'` should pass; currently those structured fields are absent. Source: gaebal-gajae dogfood for the 2026-05-25 01:30 Clawhip nudge.
|
||||
|
||||
Reference in New Issue
Block a user