mirror of
https://github.com/instructkr/claude-code.git
synced 2026-05-25 15:06:44 +00:00
Compare commits
1 Commits
docs/roadm
...
docs/roadm
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
e63b0458ed |
39
ROADMAP.md
39
ROADMAP.md
@@ -6429,33 +6429,38 @@ 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`).
|
||||
687. **`status --help --output-format json` is JSON-valid on current main but message-only (`{kind, command, topic, message}`), while actual `status --output-format json` exposes a large preflight schema (`workspace`, `sandbox`, `allowed_tools`, `lane_board`, `model_source`, `usage`, etc.) that help does not describe; wrappers cannot discover status output fields or local/auth semantics without invoking status and reverse-engineering the payload** — dogfooded 2026-05-24 for the 23:00 Clawhip nudge at message `1508243229626204292`, 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
|
||||
$ 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
|
||||
$ env -i HOME=/tmp/iso42/home PATH=/usr/bin:/bin TERM=dumb \
|
||||
claw status --help --output-format json
|
||||
{
|
||||
"command": "status",
|
||||
"kind": "help",
|
||||
"message": "Status\n Usage claw status [--output-format <format>]\n Purpose show the local workspace snapshot without entering the REPL\n Output model, permissions, git state, config files, and sandbox status\n Formats text (default), json\n Related /status · claw --resume latest /status",
|
||||
"topic": "status"
|
||||
}
|
||||
```
|
||||
|
||||
In the same clean environment, the normal command is machine-readable:
|
||||
Actual status JSON on the same binary exposes many structured fields:
|
||||
|
||||
```bash
|
||||
claw sandbox --output-format json
|
||||
# => {"kind":"sandbox", ...}
|
||||
$ claw status --output-format json | jq 'keys'
|
||||
["allowed_tools", "config_load_error", "kind", "lane_board", "model", "model_raw", "model_source", "permission_mode", "sandbox", "status", "usage", "workspace"]
|
||||
|
||||
$ claw status --output-format json | jq '.workspace | keys'
|
||||
["boot_preflight", "branch_freshness", "changed_files", "cwd", "discovered_config_files", "git_branch", "git_state", "loaded_config_files", "memory_file_count", "project_root", "session", "session_id", "session_lifecycle", "staged_files", "unstaged_files", "untracked_files"]
|
||||
|
||||
$ claw status --output-format json | jq '.sandbox | keys'
|
||||
["active", "active_namespace", "active_network", "allowed_mounts", "enabled", "fallback_reason", "filesystem_active", "filesystem_mode", "in_container", "markers", "requested_namespace", "requested_network", "supported"]
|
||||
```
|
||||
|
||||
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.
|
||||
None of this is described as structured help metadata. There is no `output_fields`, `workspace_fields`, `sandbox_fields`, `status_values`, `local_only`, `requires_credentials:false`, `requires_provider_request:false`, `mutates_workspace:false`, or `related` array.
|
||||
|
||||
**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 distinct from existing items:** #356 covered `status --help --output-format json` returning plain text; current main no longer reproduces that exact issue because it returns valid JSON. #687 covers the next-layer schema-depth gap: status help is message-only and does not describe the actual status output schema. #325 is broad top-level help prose-wrapper. #686 is doctor-specific check-schema help. #326/#448 cover specific status/sandbox payload correctness problems; #687 is the discoverability contract for status as a whole.
|
||||
|
||||
**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.
|
||||
**Why this matters:** `status` is the lightweight lane truth surface. Claws use it to decide model/provenance, permission mode, workspace git state, sandbox state, active session lifecycle, and lane board state before choosing work. A wrapper should not need to run status and reverse-engineer keys before it knows whether `workspace.branch_freshness`, `sandbox.filesystem_active`, or `allowed_tools.restricted` exist. Help JSON should declare the output schema and local/auth semantics.
|
||||
|
||||
**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.
|
||||
**Required fix shape:** (a) Extend `status --help --output-format json` with structured fields: `usage:"claw status [--output-format <format>]"`, `formats:["text","json"]`, `related:["/status","claw --resume latest /status"]`, `local_only:true`, `requires_credentials:false`, `requires_provider_request:false`, `mutates_workspace:false`, `output_fields:["kind","status","model","model_raw","model_source","permission_mode","allowed_tools","workspace","sandbox","usage","lane_board","config_load_error"]`, `workspace_fields:[...]`, `sandbox_fields:[...]`, `status_values:["ok","degraded",...]` or equivalent documented vocabulary, and `schema_version`. (b) Keep `message` as human summary only. (c) Derive help schema from the same status renderer structs/registry so newly added status fields do not drift from help. (d) Add regression coverage proving `claw status --help --output-format json | jq '.output_fields'` contains `workspace`, `sandbox`, `allowed_tools`, and that `workspace_fields` contains `branch_freshness` / `session_lifecycle`. **Acceptance check:** `claw status --help --output-format json | jq -e '.command=="status" and .local_only==true and .requires_credentials==false and ([.output_fields[]] | index("workspace") and index("sandbox") and index("allowed_tools")) and ([.workspace_fields[]] | index("branch_freshness"))'` should pass; currently those fields are absent. Source: gaebal-gajae dogfood for the 2026-05-24 23:00 Clawhip nudge.
|
||||
|
||||
Reference in New Issue
Block a user