mirror of
https://github.com/instructkr/claw-code.git
synced 2026-11-10 00:00:00 +08:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Yeachan-Heo
|
b66c4fedf9 |
+39
-42
@@ -6429,55 +6429,52 @@ 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.
|
||||
|
||||
464. **`--output-format` value parsing is strict-equal-only on `"text"`/`"json"` with five compounding gaps in `CliOutputFormat::parse` (`main.rs:600-611`): (1) **case-hostile** — `JSON`/`Json` rejected even though every UNIX enum-flag convention accepts both; (2) **whitespace-hostile** — `'json '` and `' json'` rejected, a known shell-interpolation footgun; (3) **no "Did you mean?" suggestion** for obvious near-matches like `JSON`/`json5`/`Json`; (4) **error format is always text-mode prose** — even when the operator is explicitly requesting JSON output (`--output-format=xml` → user clearly wanted machine-readable, gets text-prose error to stderr, chicken-and-egg bootstrap problem); (5) **classifier orphan** — the sentinel `"unsupported value for --output-format: ..."` is not registered in `classify_error_kind` so JSON-mode invocations would land with `kind: "unknown"` if it could ever reach that path. This is the second confirmed instance of the `#37×#77 classifier-orphan pattern` documented in #463 — features added without taxonomy registration silently degrade envelope quality** — dogfooded 2026-05-24 for the 14:30 Clawhip pinpoint nudge at message `1508114879985356992`, reproduced on local `./rust/target/debug/claw` `git_sha 003b739d` (origin/main `f8e1bb72`). Live matrix from clean isolated env (`env -i HOME=/tmp/iso21/home PATH=/usr/bin:/bin TERM=dumb`):
|
||||
459. **Memory file discovery is hardcoded to literal `CLAUDE.md` / `CLAUDE.local.md` / `.claw/CLAUDE.md` / `.claw/instructions.md` with no case-folding and no cross-tool aliases — `claw.md`, `CLAW.md`, `AGENTS.md` (the cross-tool industry standard used by Codex, OpenAI Agents, GitHub Copilot Agents), `claude.md` (lowercase), `CLAUDE.MD` (uppercase ext), `.claude/CLAUDE.md` (the Claude Code documented subdir location), `GEMINI.md`, and `memory.md` are all invisible, AND `status --output-format json` exposes only an opaque `memory_file_count: N` integer with no `memory_files: [{path, source}]` structured field, so a claw cannot tell WHICH files were picked up or WHY their memory file is being ignored** — dogfooded 2026-05-24 for the 10:00 Clawhip pinpoint nudge at message `1508046936177901639`, reproduced on local `./rust/target/debug/claw` `git_sha 003b739d` (origin/main `f8e1bb72`). Discovery matrix in a clean isolated env (`HOME=/tmp/iso10/home`, fresh `/tmp/iso10/proj` git-init, `claw status --output-format json | jq .workspace.memory_file_count` after creating each file in turn):
|
||||
|
||||
```bash
|
||||
$ for fmt in "xml" "JSON" "Json" "" "json5" "yaml" "json " " json" "JSON-LD"; do
|
||||
printf -- '--- --output-format=%q ---\n' "$fmt"
|
||||
claw --output-format "$fmt" status </dev/null 2>&1
|
||||
echo "exit=$?"
|
||||
done
|
||||
```
|
||||
|
||||
Every one of those 9 inputs produces identical-shape text-mode stderr prose:
|
||||
|
||||
```
|
||||
[error-kind: unknown]
|
||||
error: unsupported value for --output-format: <VALUE> (expected text or json)
|
||||
|
||||
Run `claw --help` for usage.
|
||||
```
|
||||
|
||||
Note `[error-kind: unknown]` literally leaks into the user-facing prose — a fragment of the classifier debug output, not a friendly hint. The same `[error-kind: unknown]` prefix shows up on `claw login` per #463 — confirming the orphan-sentinel pattern crosses surfaces.
|
||||
|
||||
**Per-input failure-mode breakdown:**
|
||||
|
||||
| Input | Why it's a real bug class |
|
||||
| File | `memory_file_count` |
|
||||
|---|---|
|
||||
| `JSON` | UNIX convention: enum flags are case-insensitive (`curl --request POST`/`post`; `git --color always`/`ALWAYS`; `cargo --color=always`/`Always`). Claw is in a tiny minority of case-hostile parsers. |
|
||||
| `Json` | Same as above; mixed-case is common in TitleCase environments. |
|
||||
| `'json '` / `' json'` | Standard shell-interpolation footgun: `OUTPUT_FORMAT=$(some-cmd)` may include trailing newline; `--output-format "$OUTPUT_FORMAT"` then injects whitespace. `.trim()` is one line of defense. |
|
||||
| `''` | Empty value from unset env var: `--output-format "$UNSET_VAR"`. Specialized error ("empty value supplied for --output-format") would clarify. |
|
||||
| `json5` / `yaml` / `xml` / `JSON-LD` | No "Did you mean: json?" suggestion. Slash commands have this; subcommand parser has this (now); enum-value parser does not. Asymmetric quality. |
|
||||
| `CLAUDE.md` | **1** ✅ |
|
||||
| `CLAUDE.local.md` | **1** ✅ (per source) |
|
||||
| `.claw/CLAUDE.md` | **1** ✅ |
|
||||
| `.claw/instructions.md` | **1** ✅ (per source) |
|
||||
| `claude.md` (lowercase) | 0 ❌ |
|
||||
| `Claude.md` (mixed case) | 0 ❌ |
|
||||
| `CLAUDE.MD` (uppercase ext) | 0 ❌ |
|
||||
| `CLAW.md` (the product's own name) | 0 ❌ |
|
||||
| `claw.md` | 0 ❌ |
|
||||
| `AGENTS.md` (Codex / OpenAI Agents / Copilot Agents standard) | 0 ❌ |
|
||||
| `agents.md` | 0 ❌ |
|
||||
| `AGENT.md` (singular) | 0 ❌ |
|
||||
| `GEMINI.md` (Google's tool convention) | 0 ❌ |
|
||||
| `CONTEXT.md` | 0 ❌ |
|
||||
| `memory.md` | 0 ❌ |
|
||||
| `.claude/CLAUDE.md` (the documented Claude Code subdir location) | 0 ❌ |
|
||||
|
||||
**Root cause traced:** `rust/crates/rusty-claude-cli/src/main.rs:600-611`:
|
||||
**Root cause (traced):** `rust/crates/runtime/src/prompt.rs:203-223`:
|
||||
|
||||
```rust
|
||||
impl CliOutputFormat {
|
||||
fn parse(value: &str) -> Result<Self, String> {
|
||||
match value {
|
||||
"text" => Ok(Self::Text),
|
||||
"json" => Ok(Self::Json),
|
||||
other => Err(format!(
|
||||
"unsupported value for --output-format: {other} (expected text or json)"
|
||||
)),
|
||||
fn discover_instruction_files(cwd: &Path) -> std::io::Result<Vec<ContextFile>> {
|
||||
let mut directories = Vec::new();
|
||||
let mut cursor = Some(cwd);
|
||||
while let Some(dir) = cursor {
|
||||
directories.push(dir.to_path_buf());
|
||||
cursor = dir.parent();
|
||||
}
|
||||
directories.reverse();
|
||||
|
||||
let mut files = Vec::new();
|
||||
for dir in directories {
|
||||
for candidate in [
|
||||
dir.join("CLAUDE.md"),
|
||||
dir.join("CLAUDE.local.md"),
|
||||
dir.join(".claw").join("CLAUDE.md"),
|
||||
dir.join(".claw").join("instructions.md"),
|
||||
] {
|
||||
push_context_file(&mut files, candidate)?;
|
||||
}
|
||||
}
|
||||
Ok(dedupe_instruction_files(files))
|
||||
}
|
||||
```
|
||||
|
||||
Five obvious enrichments missing: (a) `value.trim()` before match; (b) `value.to_lowercase()` before match; (c) levenshtein/prefix near-match suggestion; (d) specialized empty-value branch; (e) explicit `kind` discrimination so downstream classifier doesn't have to substring-match.
|
||||
|
||||
**The chicken-and-egg sub-bug (most severe):** A claw running `claw --output-format json status` to get structured output gets text-prose to stderr when the flag value is invalid. The very flag whose purpose is to request JSON cannot itself produce a JSON error envelope. The minimum fix is: if `--output-format` parsing fails AND any earlier argv contained `--output-format=json` OR `--output-format` with `json` as next arg (i.e., the operator's intent is clearly JSON), THEN emit the parse error as a JSON envelope on stderr instead of text prose. Bootstrap problem solved.
|
||||
|
||||
**Why distinct from existing items:** Surfaces a different facet of the broader **classifier-orphan / sentinel-not-typed pattern** documented in #463 (login/logout) and #455 (missing_credentials hint shape) and #449 (prompt JSON error routed to stderr). #463 covered the SAME root function (`classify_error_kind`) for a DIFFERENT sentinel ("has been removed"). This entry covers a DIFFERENT sentinel ("unsupported value for --output-format") with the SAME root, plus FOUR additional concerns specific to enum-value parsing (case, whitespace, near-match, empty). #109 covers config-loader warnings flattened to stderr prose (loader-side, not CLI-flag-side). #108 covers subcommand typos with no "Did you mean?" — analogous design pattern but different parser layer (subcommand name vs flag-value). **None** of these existing entries document the `CliOutputFormat::parse` strict-match-with-five-gaps surface. **Why this matters:** (1) **CI/automation reliability** — every CI step that constructs `--output-format $VAR` with VAR from another tool's output (Make, Justfile, shell completion, env file) is one trailing-newline or one casing mismatch away from text-prose-to-stderr instead of structured JSON. (2) **Bootstrap chicken-and-egg** is the worst flavor: the flag exists specifically to enable machine parsing, and the flag's own error path bypasses that machine parsing. (3) **Cross-surface asymmetry erodes trust** — slash commands suggest, subcommand parser now suggests (per #108 fix), but flag-enum parser doesn't. A claw learning the CLI grammar by trial-and-error gets contradictory teaching about the quality of suggestions. (4) **Same classifier-orphan pattern as #463** — `[error-kind: unknown]` text leakage proves the classifier-string roundtrip is happening even on simple flag-parse failures. The taxonomy gap from #77 is structurally chronic; per-instance fixes alone won't resolve it. (5) **Discovery method itself is a signal** — a 30-second hypothesis sweep covering 9 inputs caught 5 distinct bug classes. Strict-match parsers without trim+case+near-match+empty handling have a high latent-bug density per LoC. The classifier should ship as a typed result with structured envelope from day one. **Required fix shape:** (a) **`CliOutputFormat::parse` enrichments:** trim input; lowercase before match; explicit empty-value branch with specialized error; levenshtein-based "Did you mean?" suggestion (reuse the slash-command suggester from `commands::resolve_skill_invocation` or the subcommand suggester being added for #108). (b) **Bootstrap fix:** when `--output-format` parsing fails AND the operator's argv contains the literal token `json` adjacent to `--output-format`, emit the parse error as a JSON envelope to stderr so JSON-requesting consumers can decode it. (c) **Classifier registration:** add `"output_format_invalid"` to `classify_error_kind`, keyed on `"unsupported value for --output-format"`. (d) **Strip `[error-kind: ...]` debug prefix from text-mode user-facing output** — it's classifier internals leaking into the UX (also fixes #463's same complaint). (e) **Regression coverage in `output_format_contract.rs`:** parameterized test asserting 9 invalid inputs each produce the expected enriched behavior (case-normalized acceptance, trimmed acceptance, near-match suggestion, empty-value error, JSON-envelope bootstrap output when intent is JSON). **Acceptance check (one-liner):** `claw --output-format JSON status 2>&1 | jq -e '.kind == "output_format_invalid"'` should print `true` for the bootstrap-fix path; `claw --output-format JSON status; echo $?` should exit 0 after the case-normalization fix; `claw --output-format json5 status 2>&1 | grep -q "Did you mean: json"` should pass after the suggester fix. Source: gaebal-gajae dogfood for the 2026-05-24 14:30 Clawhip pinpoint nudge at message `1508114879985356992`. Pre-grep gate filtered 9 hypotheses → 2 fresh (W=`--output-format` value handling, Y=base URL validation); W selected because failures reproduce in credential-free path with multiple distinct sub-issues. Y deferred to a future tick because it requires actual HTTP-send path to surface failure, and the BASE_URL pinpoint is more about the `status`/`doctor` envelope failing to surface "configured to talk to malformed URL" warnings — different fix shape, different code path. Coordination note: Jobdori took #469 (`/compact` slash divergence) this tick and acknowledged F (CLAW_CONFIG_HOME validation, 5-mode silent failure surfaced in #463 tick) as "next confirmed but unfiled," so F is intentionally NOT covered here to avoid duplicate filing.
|
||||
Four hardcoded literal `PathBuf::join` calls. No case-folding, no extension variants, no cross-tool alias table, no `.claude/CLAUDE.md` (the official Claude Code documented subdir at `https://docs.anthropic.com/en/docs/claude-code/memory`). The ancestor-walk logic IS present (good — `cursor = dir.parent()`), but it walks looking for these four exact names only. **Status JSON drops the path list:** `rust/crates/rusty-claude-cli/src/main.rs` builds `StatusContext { …, memory_file_count: project_context.instruction_files.len(), … }` (taking only the count), then serializes that field as `workspace.memory_file_count` in the JSON envelope. The original `Vec<ContextFile>` with full paths and content is **discarded before reaching the JSON envelope**. **Why distinct from existing items:** ROADMAP mentions `AGENTS.md` 5 times (#215, #216, #225, #231, etc.) but **only as a config-mutation target** ("installer changes AGENTS.md", "AGENTS.md orchestration brain is loaded automatically" — that's the installer/onboarding noise, not the runtime memory loader). Nothing in ROADMAP says "claw-code does not actually read AGENTS.md as a memory file at runtime." #84 covers the dump-manifests `repo root: /Users/...` build-host leak (a different name-identity bug). #1756 mentions ancestor `CLAUDE.md` for worker safety (different concern). No entry documents the discovery name set or the `.claude/CLAUDE.md` blind spot. **Why this matters:** (a) **Cross-tool migration silently breaks.** A user with an existing `AGENTS.md` workflow (Codex, OpenAI Agents, GitHub Copilot Agents — `AGENTS.md` is the de-facto cross-tool standard) installs `claw`, runs it in their existing project, and `status` reports `memory_file_count: 0`. There is **no warning** that `AGENTS.md` was found-but-ignored, no doctor check, no hint. They think claw has no memory of their project rules — claw silently has zero context. (b) **Product-name divergence.** The binary is called `claw`. The discovered file is `CLAUDE.md`. A user typing `CLAW.md` (matching the tool they actually invoked) gets silently zero memory. Same identity-leak pattern as #84 (build-host paths in error messages) — the marketing/binary name diverges from the runtime-effective file name. (c) **Claude Code documented subdir location ignored.** The Claude Code docs at `https://docs.anthropic.com/en/docs/claude-code/memory` document `.claude/CLAUDE.md` as a memory-file location. claw-code (which advertises Claude Code parity throughout `--help` and README) **does not read it**. A user migrating from Claude Code with their memory file at `.claude/CLAUDE.md` gets silently zero memory pickup. (d) **Case-sensitivity is OS-leaky.** On macOS with case-insensitive HFS+/APFS, `claude.md` and `CLAUDE.md` are the same file — discovery happens to work. On Linux/Windows with case-sensitive filesystems, `claude.md` is invisible. Cross-platform users get different memory behavior from the same repo layout. (e) **`memory_file_count: 0` with no `memory_files: []` field means a claw cannot debug "why is my memory not loading?"** without re-implementing the discovery walk itself. (f) The four candidates include `CLAUDE.local.md` and `.claw/instructions.md` — these aren't documented in README or `--help`, and the discovery list itself is a hidden contract. **Required fix shape:** (a) **Extend the discovery name set** to a documented union: `CLAUDE.md`, `CLAUDE.local.md`, `CLAW.md`, `CLAW.local.md`, `AGENTS.md`, `AGENTS.local.md`, plus `.claude/CLAUDE.md` and `.claw/CLAUDE.md`. Optionally allow user-configured extras via `.claw.json` `memory.discoveryNames: ["GEMINI.md", "CONTEXT.md"]`. (b) **Case-fold the comparison** on case-sensitive filesystems — when walking directory entries, match case-insensitively against the discovery name set, so `claude.md` / `CLAUDE.MD` / `Claude.md` all resolve to the same memory file. Document this as the contract. (c) **Expose the full `memory_files[]` array in status JSON**: `workspace.memory_files: [{path: "/abs/CLAUDE.md", source: "project", bytes: 1234}, {path: "/abs/.claw/CLAUDE.md", source: "project_subdir", bytes: 200}]`. Keep `memory_file_count` for back-compat but make the array the source of truth. (d) **Add a `doctor` check `memory_files` that lists discovered files AND files that were skipped because they were in a non-discovered name** (e.g., "found `AGENTS.md` at repo root but not loaded — claw memory discovery uses `CLAUDE.md`; rename or add `memory.discoveryNames` to `.claw.json`"). This turns "silent zero memory" into a visible diagnostic. (e) **Update README and `--help`** to list the discovery name set explicitly. (f) **Regression coverage** for each name in the matrix above, asserting the file is discovered (or, for explicitly-excluded names, that `doctor` produces a "found-but-skipped" hint). **Acceptance check (one-liner):** `for n in CLAUDE.md CLAW.md AGENTS.md .claude/CLAUDE.md; do mkdir -p $(dirname /tmp/cmp/$n); echo test > /tmp/cmpLine truncated
|
||||
Reference in new issue
Block a user