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 | |
|---|---|---|---|
|
|
70ba9405d6 |
49
ROADMAP.md
49
ROADMAP.md
@@ -6429,46 +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.
|
||||
|
||||
686. **`doctor --help --output-format json` now returns parseable JSON on current main, but it is still message-only (`{kind, command, topic, message}`) and does not expose the diagnostic check schema, local-only/no-provider contract, or expected output fields (`checks[]`, check names, levels/statuses), so wrappers cannot discover how to consume the primary preflight surface without scraping prose or running the command first** — dogfooded 2026-05-24 for the 22:30 Clawhip nudge at message `1508235675546419210`, reproduced on a freshly rebuilt current `origin/main` binary (`git_sha f8e1bb726`) from `/tmp/cc-probe-main-2130`. Active claw-code sessions: none.
|
||||
682. **Unsupported native-agent mutation verbs (`claw agents add/remove/enable`) return generic help JSON with `exit=0` instead of a typed unsupported/not-implemented error, so automation can treat a failed staffing/control-plane mutation as success** — dogfooded 2026-05-24 for the 20:30 Clawhip nudge at message `1508205480818774086`, reproduced on local `./rust/target/debug/claw` `git_sha 003b739d` (origin/main `f8e1bb72`) in a clean isolated env. This was found by carrying forward #681's “help + unexpected + exit 0” stealth-success pattern from `mcp` to sibling local route helpers. Number intentionally follows #681 and avoids Jobdori-announced #680.
|
||||
|
||||
Reproduction:
|
||||
|
||||
```bash
|
||||
$ env -i HOME=/tmp/iso41/home PATH=/usr/bin:/bin TERM=dumb \
|
||||
claw doctor --help --output-format json
|
||||
$ env -i HOME=/tmp/iso30/home PATH=/usr/bin:/bin TERM=dumb \
|
||||
claw agents add demo -- /bin/echo hi --output-format json
|
||||
{
|
||||
"command": "doctor",
|
||||
"kind": "help",
|
||||
"message": "Doctor\n Usage claw doctor [--output-format <format>]\n Purpose diagnose local auth, config, workspace, sandbox, and build metadata\n Output local-only health report; no provider request or session resume required\n Formats text (default), json\n Related /doctor · claw --resume latest /doctor",
|
||||
"topic": "doctor"
|
||||
"action": "help",
|
||||
"kind": "agents",
|
||||
"unexpected": "add demo -- /bin/echo hi",
|
||||
"usage": {
|
||||
"direct_cli": "claw agents [list|help]",
|
||||
"slash_command": "/agents [list|help]",
|
||||
"sources": [".claw/agents", "~/.claw/agents", "$CLAW_CONFIG_HOME/agents"]
|
||||
}
|
||||
}
|
||||
# exit 0, stderr empty, no agent created/registered
|
||||
```
|
||||
|
||||
The help object is valid JSON, but all actionable metadata is trapped in `message`. There are no structured `usage`, `purpose`, `formats`, `related`, `local_only`, `requires_credentials:false`, `requires_provider_request:false`, `output_fields`, `check_names`, `status_values`, or `failure_contract` fields.
|
||||
|
||||
Contrast with the actual doctor JSON surface (same command family):
|
||||
Same shape for:
|
||||
|
||||
```bash
|
||||
$ claw doctor --output-format json
|
||||
{
|
||||
"kind": "doctor",
|
||||
"status": "...",
|
||||
"checks": [
|
||||
{"name":"auth", ...},
|
||||
{"name":"config", ...},
|
||||
{"name":"install_source", ...},
|
||||
{"name":"workspace", ...},
|
||||
{"name":"sandbox", ...},
|
||||
{"name":"system", ...}
|
||||
],
|
||||
...
|
||||
}
|
||||
claw agents remove demo --output-format json
|
||||
claw agents enable demo --output-format json
|
||||
```
|
||||
|
||||
And contrast with `export --help --output-format json` on the same rebuilt binary, which already exposes structured `usage`, `purpose`, `formats`, `related`, `defaults`, and `options[]`. The doctor help surface therefore satisfies JSON validity but not schema discoverability for the most important local preflight command.
|
||||
All return `exit=0`, `kind:"agents"`, `action:"help"`, `unexpected:"<verb ...>"` and no stderr. The supported contract in the returned help object is only `list|help`, so these mutation verbs are unsupported by contract, but the command-level outcome is success.
|
||||
|
||||
**Why distinct from existing items:** #357 originally covered `doctor --help --output-format json` returning plain text. Current main no longer reproduces that exact failure: it returns JSON. #686 covers the next-layer contract gap: JSON is message-only and does not describe the doctor schema. #325 is the broad top-level help prose-wrapper problem; #684 and #685 are command-specific schema-depth gaps for `init` and `version`. This entry is doctor-specific because `doctor` is the primary automation preflight and its check schema is what claws branch on before running work. It also complements #100/#102/#107 style doctor-coverage gaps: before adding checks, help should expose which checks and status vocabulary are available.
|
||||
**Root cause shape:** the agents command parser shares the same “unknown tail becomes help with `unexpected`” pattern as MCP. It preserves the unrecognized verb in a decorative help field but does not set an error status, code, nonzero exit, or structured `unsupported_action` metadata. The result is neither a successful mutation nor a machine-classifiable failure.
|
||||
|
||||
**Why this matters:** `doctor` is the command operators and claws run when setup is broken. A wrapper should be able to learn from help, without running health checks yet, that `doctor` is local-only, credential-free, produces `checks[]`, and uses check/status levels suitable for gating. Today it must scrape prose or run `doctor` and reverse-engineer the response. That makes preflight adapters brittle and hides schema changes from automation.
|
||||
**Why distinct from existing items:** ROADMAP #328 covers agent source-root/provenance mismatch. #329 covers resume-safe slash `/agents` flattening structured inventory to prose. #346 covers natural `agents show <name>` detail inspection collapsing to help-success. This entry covers unsupported *mutation/control-plane verbs* (`add/remove/enable`) returning success, which matters for setup/staffing automation and not just detail lookup. #681 covers the same failure class for `mcp`; #682 documents the native-agent subsystem's separate route and required regression coverage.
|
||||
|
||||
**Required fix shape:** (a) Extend `doctor --help --output-format json` with structured fields such as `usage:"claw doctor [--output-format <format>]"`, `purpose`, `formats:["text","json"]`, `related:["/doctor","claw --resume latest /doctor"]`, `local_only:true`, `requires_credentials:false`, `requires_provider_request:false`, `mutates_workspace:false`, `output_fields:["kind","status","checks","message"]`, `check_names:["auth","config","install_source","workspace","sandbox","system"]` (or a versioned stable/default list), `status_values:["ok","warn","fail"]`, and optional `schema_version`. (b) Keep `message` as human summary only. (c) Add regression coverage proving `claw doctor --help --output-format json | jq '.output_fields'` includes `checks`, and that `.requires_credentials == false`. (d) When new doctor checks land, update the help schema from the same registry/source used to build the report so help/check output cannot drift. **Acceptance check:** `claw doctor --help --output-format json | jq -e '.command=="doctor" and .local_only==true and .requires_credentials==false and ([.output_fields[]] | index("checks")) and ([.status_values[]] | index("warn"))'` should pass; currently those structured fields are absent. Source: gaebal-gajae dogfood for the 2026-05-24 22:30 Clawhip nudge.
|
||||
**Why this matters:** (1) **Automation false success.** A bootstrap script can run `claw agents add reviewer ...` and continue because exit code is 0, even though no agent exists. (2) **Staffing state becomes unverifiable.** Native-agent availability controls delegation; a failed add/enable/remove must not look like successful help. (3) **Mutation verbs are natural expectations.** Users will try `agents add/remove/enable` after seeing agent inventory, and the CLI should fail closed if those mutations are intentionally unsupported. (4) **`unexpected` is not an error contract.** Claws should not have to infer failure from an optional field inside an otherwise successful help object. (5) **The bug is reusable.** #681 proved the pattern in MCP; this sibling route shows the parser/helper abstraction likely needs a shared unsupported-subaction contract across local route helpers.
|
||||
|
||||
**Required fix shape:** (a) Unsupported agents sub-actions should return a typed JSON error or explicit non-ok status such as `{type:"error", kind:"unsupported_agents_action", requested_action:"add", supported_actions:["list","help"], hint:"Native-agent mutation commands are not implemented; add agent files under a documented agents root or use ..."}` and exit non-zero. (b) Keep help fallback only for explicit `agents help` / `agents --help`; attempted mutations must not be reported as successful help. (c) If `add/remove/enable` are planned features, return `not_implemented` with nonzero exit and no file writes until the write-target/source-layer semantics exist. (d) Add parser/output tests for `agents add`, `agents remove`, and `agents enable` proving they are distinguishable from successful help and successful list. (e) Consider a shared helper for local route families (`agents`, `mcp`, maybe `skills`/`plugins`) so `unexpected` can never be the sole machine signal for unsupported actions. **Acceptance check:** `claw agents add demo -- /bin/echo hi --output-format json >/tmp/out 2>/tmp/err; test $? -ne 0 && jq -e '.kind == "unsupported_agents_action" and .requested_action == "add"' /tmp/err` should pass; currently exit is 0 and stdout is a help object. Source: gaebal-gajae dogfood for the 2026-05-24 20:30 Clawhip nudge. Coordination note: avoided Jobdori #680/session-sort, F/CLAW_CONFIG_HOME, already-covered MCP items, and prior agent items #328/#329/#346; targeted mutation semantics after route-sibling probe.
|
||||
|
||||
Reference in New Issue
Block a user