Cycle #30 dogfood found a testing gap: OPT_OUT surfaces were classified
in code but their REJECTION behavior was never regression-tested.
## The Gap
OPT_OUT_AUDIT.md declares 12 surfaces as intentionally exempt from
--output-format. The test suite had:
- ✅ test_clawable_surface_has_output_format (CLAWABLE must accept)
- ✅ test_every_registered_command_is_classified (no orphans)
- ❌ Nothing verifying OPT_OUT surfaces REJECT --output-format
If a developer accidentally added --output-format to 'summary' (one of
the 12 OPT_OUT surfaces), no test would catch the silent promotion.
The classification was governed, but the rejection behavior was NOT.
## What Changed
Added TestOptOutSurfaceRejection to test_cli_parity_audit.py with 14 tests:
1. **12 parametrized tests** — one per OPT_OUT surface, verifying each
rejects --output-format with an argparse error.
2. **test_opt_out_set_matches_audit_document** — verifies OPT_OUT_SURFACES
constant matches the declared 12 surfaces in OPT_OUT_AUDIT.md.
3. **test_opt_out_count_matches_declared** — sanity check that the count
stays at 12 as documented.
## Symmetry Achieved
Before: only CLAWABLE acceptance tested
CLAWABLE accepts --output-format ✅
OPT_OUT behavior: untested
After: full parity coverage
CLAWABLE accepts --output-format ✅
OPT_OUT rejects --output-format ✅
Audit doc ↔ constant kept in sync ✅
This completes the parity enforcement loop: every new surface is
explicitly IN or OUT, and BOTH directions are regression-locked.
## Promotion Path Preserved
When a real OPT_OUT surface gains genuine demand (per OPT_OUT_DEMAND_LOG.md):
1. Move from OPT_OUT_SURFACES to CLAWABLE_SURFACES
2. Update OPT_OUT_AUDIT.md with promotion rationale
3. Remove from this test's expected rejections
4. Tests pass (rejection test no longer runs; acceptance test now required)
Graceful promotion; no accidental drift.
## Test Count
- 222 → 236 passing (+14, zero regressions)
- 12 parametrized + 2 metadata = 14 new tests
## Discipline Check
Per cycle #24 calibration:
- Red-state bug? ✗ (no broken behavior)
- Real friction? ✓ (testing gap discovered by dogfood)
- Evidence-backed? ✓ (systematic probe revealed missing coverage)
This is the cycle #27 taxonomy (structural / quality / cross-channel /
text-vs-JSON divergence) extending into classification: not just 'is the
envelope right?' but 'is the OPPOSITE-OF-envelope right?'
Future cycles can apply the same principle to other classifications:
every governed non-goal deserves regression tests that lock its
non-goal-ness.
Classification:
- Real friction: ✓ (cycle #30 dogfood)
- Evidence-backed: ✓ (gap discovered by systematic surface audit)
- Same-cycle fix: ✓ (maintainership discipline)
Source: Jobdori cycle #30 proactive dogfood — probed all 26 subcommands
with --output-format json and noticed OPT_OUT rejection pattern was
unverified by any dedicated test.
Cycle #29 dogfood found a real pinpoint: cross-mode exit code divergence.
## The Pinpoint
Dogfooding the CLI revealed that unknown subcommand errors return different
exit codes depending on output mode:
$ python3 -m src.main nonexistent-cmd # exit 2
$ python3 -m src.main nonexistent-cmd --output-format json # exit 1
ERROR_HANDLING.md documented the exit-code contract (1=parse, 2=timeout)
but did NOT explicitly state the contract applies only to JSON mode. Text
mode follows argparse defaults (exit 2 for any parse error), which
violates the documented contract when interpreted generally.
A claw using text mode with 'claw nonexistent' would see exit 2 and
misclassify as timeout per the docs. Real protocol contract gap, not
implementation bug.
## Classification
This is a DOCUMENTATION gap, not a behavior bug:
- Text mode follows argparse convention (reasonable for humans)
- JSON mode normalizes to documented contract (reasonable for claws)
- The divergence is intentional; only the docs were silent about it
Fix = document the divergence explicitly + lock it with tests.
NOT fix = change text mode exit code to 1 (would break argparse
conventions and confuse human users).
## Documentation Changes
ERROR_HANDLING.md:
1. Added IMPORTANT callout in Quick Reference section:
'The exit code contract applies ONLY when --output-format json is
explicitly set. Text mode follows argparse conventions.'
2. New 'Text mode vs JSON mode exit codes' table showing exact divergence:
- Unknown subcommand: text=2, json=1
- Missing required arg: text=2, json=1
- Session not found: text=1, json=1 (app-level, identical)
- Success: text=0, json=0 (identical)
- Timeout: text=2, json=2 (identical, #161)
3. Practical rule: 'always pass --output-format json'
## Tests Added (5)
TestTextVsJsonModeDivergence in test_cross_channel_consistency.py:
1. test_unknown_command_text_mode_exits_2 — text mode argparse default
2. test_unknown_command_json_mode_exits_1 — JSON mode contract normalized
3. test_missing_required_arg_text_mode_exits_2 — same for missing args
4. test_missing_required_arg_json_mode_exits_1 — same normalization
5. test_success_path_identical_in_both_modes — success exit identical
These tests LOCK the expected divergence so:
- Documentation stays aligned with implementation
- Future changes (either direction) are caught as intentional
- Claws trust the docs
## Test Status
- 217 → 222 tests passing (+5)
- Zero regressions
## Discipline
This cycle follows the cycle #28 template exactly:
- Dogfood probe revealed real friction (test said exit=2, docs said exit=1)
- Minimal fix shape (documentation clarification, not code change)
- Regression guard via tests
- Evidence-backed, not speculative
Relationship to #181:
- #181 fixed env.exit_code != process exit (WITHIN JSON mode)
- #29 clarifies exit code contract scope (ONLY JSON mode)
- Both establish: exit codes are deterministic, but only when --output-format json
---
Classification (per cycle #24 calibration):
- Red-state bug? ✗ (behavior was reasonable, docs were incomplete)
- Real friction? ✓ (docs/code divergence revealed by dogfood)
- Evidence-backed? ✓ (test suite probed both modes, found the gap)
Source: Jobdori cycle #29 proactive dogfood — in response to Clawhip nudge
for pinpoint hunting. Found that text-mode errors return exit 2 but
ERROR_HANDLING.md implied exit 1 was the parse-error contract universally.
Cycle #28 closes the low-hanging metadata protocol gap identified in #180.
## The Gap
Pinpoint #180 (filed cycle #24) documented a metadata protocol gap:
- `--help` works (argparse default)
- `--version` does NOT exist
The ROADMAP entry deferred implementation pending demand. Cycle #28 dogfood
probe found this during routine invariant audit (attempt to call `--version`
as part of comprehensive CLI surface coverage). This is concrete evidence of
real friction, not speculative gap-filling.
## Implementation
Added `--version` flag to argparse in `build_parser()`:
```python
parser.add_argument('--version', action='version', version='claw-code 1.0.0 (Python harness)')
```
Simple one-liner. Follows Python argparse conventions (built-in action='version').
## Tests Added (3)
TestMetadataFlags in test_exec_route_bootstrap_output_format.py:
1. test_version_flag_returns_version_text — `claw --version` prints version
2. test_help_flag_returns_help_text — `claw --help` still works
3. test_help_still_works_after_version_added — Both -h and --help work
Regression guard on the original help surface.
## Test Status
- 214 → 217 tests passing (+3)
- Zero regressions
- Full suite green
## Discipline
This cycle exemplifies the cycle #24 calibration:
- #180 was filed as 'deferred pending demand'
- Cycle #28 dogfood found actual friction (proactive test coverage gap)
- Evidence = concrete ('--version not found during invariant audit')
- Action = minimal implementation + regression tests
- No speculation, no feature creep, no implementation before evidence
Not 'we imagined someone might want this.' Instead: 'we tried to call it
during routine maintenance, got ENOENT, fixed it.'
## Related
- #180 (cycle #24): Metadata protocol gap filed
- Cycle #27: Cross-channel consistency audit established framework
- Cycle #28 invariant audit: Discovered actual friction, triggered fix
---
Classification (per cycle #24 calibration):
- Red-state bug? ✗ (not a malfunction, just an absence)
- Real friction? ✓ (audit probe could not call the flag, had to special-case)
- Evidence-backed? ✓ (proactive test coverage revealed the gap)
Source: Jobdori cycle #28 dogfood — invariant audit attempting comprehensive
CLI surface coverage found that --version was unsupported.
Cycle #27 ships a new test class systematizing the three-layer protocol
invariant framework.
## Context
After cycles #20–#26, the protocol has three distinct invariant classes:
1. **Structural compliance** (#178): Does the envelope exist?
2. **Quality compliance** (#179): Is stderr silent + error message truthful?
3. **Cross-channel consistency** (#181 + NEW): Do multiple channels agree?
#181 revealed a critical gap: the second test class was incomplete.
Envelopes could be structurally valid, quality-compliant, but still
lie about their own state (envelope.exit_code != actual exit).
## New Test Class
TestCrossChannelConsistency in test_cross_channel_consistency.py captures
the third invariant layer with 5 dedicated tests:
1. envelope.command ↔ dispatched subcommand
2. envelope.output_format ↔ --output-format flag
3. envelope.timestamp ↔ actual wall clock (recent, <5s)
4. envelope.exit_code ↔ process exit code (cycle #26/#181 regression guard)
5. envelope boolean fields (found/handled/deleted) ↔ error block presence
Each test specifically targets cross-channel truth, not structure or quality.
## Why Separate Test Classes Matter
A command can fail all three ways independently:
| Failure mode | Exit/Crash | Test class | Example |
|---|---|---|---|
| Structural | stderr noise | TestParseErrorEnvelope | argparse leaks to stderr |
| Quality | correct shape, wrong message | TestParseErrorStderrHygiene | error instead of real message |
| Cross-channel | truthy field, lie about state | TestCrossChannelConsistency | exit_code: 0 but exit 1 |
#181 was invisible to the first two classes. A claw passing all structure/
quality tests could still be misled. The third class catches that.
## Audit Results (Cycle #27)
All 5 tests pass — no drift detected in any channel pair:
- ✅ Envelope command always matches dispatch
- ✅ Envelope output_format always matches flag
- ✅ Envelope timestamp always recent (<5s)
- ✅ Envelope exit_code always matches process exit (post-#181 guard)
- ✅ Boolean fields consistent with error block presence
The systematic audit proved the fix from #181 holds, and identified
no new cross-channel gaps.
## Test Impact
- 209 → 214 tests passing (+5)
- Zero regressions
- New invariant class now has dedicated test suite
- Future cross-channel bugs will be caught by this class
## Related
- #178 (#20): Parser-front-door structural contract
- #179 (#20): Stderr hygiene + real error message quality
- #181 (#26): Envelope exit_code must match process exit
- #182-N: Future cross-channel contract violations will be caught
by TestCrossChannelConsistency
This test class is evergreen — as new fields/channels are added to the
protocol, invariants for those channels should be added here, not mixed
with other test classes. Keeping invariant classes separate makes
regression attribution instant (e.g., 'TestCrossChannelConsistency failed'
= 'some truth channel disagreed').
Classification (per cycle #24 calibration):
- Red-state bug: ✗ (audit is green)
- Real friction: ✓ (structured audit of documented invariants)
- Proof of equilibrium: ✓ (systematic verification, no gaps found)
Source: Jobdori cycle #27 proactive invariant audit — following gaebal
guidance to probe documented invariants, not speculative gaps.
Cycle #26 dogfood found a real red-state bug in the JSON envelope contract.
## The Bug
exec-command and exec-tool not-found cases return exit code 1 from the
process, but the envelope reports exit_code: 0 (the default from
wrap_json_envelope). This is a protocol violation.
Repro (before fix):
$ claw exec-command unknown-cmd test --output-format json > out.json
$ echo $?
1
$ jq '.exit_code' out.json
0 # WRONG — envelope lies about exit code
Claws reading the envelope's exit_code field get misinformation. A claw
implementing the canonical ERROR_HANDLING.md pattern (check exit_code,
then classify by error.kind) would incorrectly treat failures as
successes when dispatching on the envelope alone.
## Root Cause
main.py lines 687–739 (exec-command + exec-tool handlers):
- Return statement: 'return 0 if result.handled else 1' (correct)
- Envelope wrap: 'wrap_json_envelope(envelope, args.command)'
(uses default exit_code=0, IGNORES the return value)
The envelope wrap was called BEFORE the return value was computed, so
the exit_code field was never synchronized with the actual exit code.
## The Fix
Compute exit_code ONCE at the top:
exit_code = 0 if result.handled else 1
Pass it explicitly to wrap_json_envelope:
wrap_json_envelope(envelope, args.command, exit_code=exit_code)
Return the same value:
return exit_code
This ensures the envelope's exit_code field is always truth — the SAME
value the process returns.
## Tests Added (3)
TestEnvelopeExitCodeMatchesProcessExit in test_exec_route_bootstrap_output_format.py:
1. test_exec_command_not_found_envelope_exit_matches:
Verifies exec-command unknown-cmd returns exit 1 in both envelope
and process.
2. test_exec_tool_not_found_envelope_exit_matches:
Same for exec-tool.
3. test_all_commands_exit_code_invariant:
Audit across 4 known non-zero cases (show-command, show-tool,
exec-command, exec-tool not-found). Guards against the same bug
in other surfaces.
## Impact
- 206 → 209 passing tests (+3)
- Zero regressions
- Protocol contract now truthful: envelope.exit_code == process exit
- Claws using the one-handler pattern from ERROR_HANDLING.md now get
correct information
## Related
- ERROR_HANDLING.md (cycle #22): Documented exit_code as machine-readable
contract field
- #178/#179 (cycles #19/#20): Closed parser-front-door contract
- This closes a gap in the WORK PROTOCOL contract — envelope values must
match reality, not just be structurally present.
Classification (per cycle #24 calibration):
- Red-state bug: ✓ (contract violation, claws get misinformation)
- Real friction: ✓ (discovered via dogfood, not speculative)
- Fix ships same-cycle: ✓ (discipline per maintainership mode)
Source: Jobdori cycle #26 dogfood — ran multiple edge-case probes, noticed
exec-command envelope showed exit_code: 0 while process exited 1.
Investigated wrap_json_envelope default behavior, confirmed bug, fixed
and tested in same cycle.
Cycle #25 ships navigation improvements connecting USAGE (setup/interactive)
to ERROR_HANDLING.md (subprocess/orchestration patterns).
Before: USAGE.md had JSON scripting mention but no link to error-handling guide.
New users reading USAGE would see JSON is available, but wouldn't discover
the error-handling pattern without accidentally finding ERROR_HANDLING.md.
After: Two strategic cross-links:
1. Top-level tip box: "Building orchestration code? See ERROR_HANDLING.md"
2. JSON scripting section expanded with examples + link to unified pattern
Changes to USAGE.md:
- Added TIP callout near top linking to ERROR_HANDLING.md
- Expanded "JSON output for scripting" section:
- Explains what the envelope contains (exit_code, command, timestamp, fields)
- Added 3 command examples (prompt, load-session, turn-loop)
- Added callout for dispatchers/orchestrators pointing to ERROR_HANDLING pattern
Impact: Operators reading USAGE for "how do I call claw from scripts?" now
immediately see the canonical answer (ERROR_HANDLING.md) instead of having
to reverse-engineer it from code examples.
No code changes. Pure navigation/documentation.
Continues the documentation-governance pattern: the work protocol (14 clawable
commands) has a consumption guide (ERROR_HANDLING.md), and that guide is now
reachable from the main entry point (USAGE.md + README.md top nav).
Cycle #24 dogfood discovery.
Running proactive edge-case dogfood on the JSON contract, hit a real pinpoint:
--help and --version are outside the parser-front-door contract.
The gap:
1. "claw --help --output-format json" returns text (not envelope)
2. "claw bootstrap --help --output-format json" returns text (not envelope)
3. "claw --version" doesn't exist at all
Why it matters:
- Claws can't programmatically discover the CLI surface
- Version checking requires side-effectful commands
- Natural follow-up gap to #178/#179 parser-front-door work
Discoverability scenarios:
- Orchestrator checking whether a new command (e.g., turn-loop) is available
- Version compat check before dispatching work
- Enumerating available commands for routing decisions
Filed as Pinpoint #180 in ROADMAP.md with:
- Gap description + 3-case repro
- Impact analysis (version compat, surface enumeration, governance)
- Root cause (argparse default HelpAction prints text + exits)
- Fix shape (3 stages, ~40 lines total)
- Stage A: --version + JSON envelope version metadata
- Stage B: --help JSON routing via custom HelpAction
- Stage C: optional 'schema-info' command for pre-dispatch discovery
- Acceptance criteria (4 cases, including backward compat)
- Priority: Medium (not red-state, but real discoverability gap)
Status: **Filed, implementation deferred.**
Following maintainership equilibrium: pinpoints stay documented but don't
force code changes. If external demand arrives (claw author building a
dispatcher, orchestrator doing version checks), the fix can ship in one
cycle using the shape already documented.
No code changes this cycle. Pure ROADMAP filing.
Continues the maintainership pattern: find friction, document it, defer
until evidence-backed demand arrives.
Source: Jobdori proactive dogfood at 2026-04-22 20:58 KST.
Cycle #23 ships a documentation discoverability fix.
After #22 shipping ERROR_HANDLING.md, the next natural step is making it
discoverable from the project's entry point (README.md).
Before: README top navigation linked to USAGE, PARITY, ROADMAP, Rust workspace.
ERROR_HANDLING.md was buried in CLAUDE.md references.
After: ERROR_HANDLING.md is now in the top navigation (right after USAGE,
before Rust workspace). Also added SCHEMAS.md mention in repository shape.
This signals that:
1. Error handling is a first-class concern (not an afterthought)
2. The Python harness documentation (SCHEMAS.md, ERROR_HANDLING.md, CLAUDE.md)
is part of the official docs, not just dogfood artifacts
3. New users/claws can discover the error-handling pattern at entry point
Impact: Operators building orchestration code will immediately see
'Error Handling' link in navigation, shortening the path to understanding
how to consume the protocol reliably.
No code changes. No test changes. Pure navigation/discoverability.
Cycle #22 ships documentation that operationalizes cycles #178–#179.
Problem context:
After #178 (parse-error envelope) and #179 (stderr hygiene + real error message),
claws can now build a unified error handler for all 14 clawable commands.
But there was no guide on how to actually do that. Operators had the pieces;
they didn't have the pattern.
This file changes that.
New file: ERROR_HANDLING.md
- Quick reference: exit codes + envelope shapes (0=success, 1=error, 2=timeout)
- One-handler pattern: ~80 lines of Python showing how to parse error.kind,
check retryable, and decide recovery strategy
- Four practical recovery patterns:
- Retry on transient errors (filesystem, timeout)
- Reuse session after timeout (if cancel_observed=true)
- Validate command syntax before dispatch (dry-run --help)
- Log errors for observability
- Error kinds enumeration (parse, session_not_found, filesystem, runtime, timeout)
- Common mistakes to avoid (6 patterns with BAD vs GOOD examples)
- Testing your error handler (unit test examples)
Operational impact:
Orchestration code now has a canonical pattern. Claws can:
- Copy-paste the run_claw_command() function (works for all commands)
- Classify errors uniformly (no special cases per command)
- Decide recovery deterministically (error.kind + retryable + cancel_observed)
- Log/monitor/escalate with confidence
Related cycles:
- #178: Parse-error envelope (commands now emit structured JSON on invalid argv)
- #179: Stderr hygiene + real message (JSON mode silences argparse, carries actual error)
- #164 Stage B: cancel_observed field (callers know if session is safe for reuse)
Updated CLAUDE.md:
- Added ERROR_HANDLING.md to 'Related docs' section
- Now documents the one-handler pattern as a guideline
No code changes. No test changes. Pure documentation.
This completes the documentation trail from protocol (SCHEMAS.md) →
governance (OPT_OUT_AUDIT.md, OPT_OUT_DEMAND_LOG.md) → practice (ERROR_HANDLING.md).
Cycle #21 ships governance infrastructure, not implementation. Maintainership
mode means sometimes the right deliverable is a decision framework, not code.
Problem context:
OPT_OUT_AUDIT.md (cycle #18 bonus) established 'demand-backed audit' as the
next step. But without a structured way to record demand signals, 'demand-backed'
was just a slogan — the next audit cycle would have no evidence to work from.
This commit creates the evidentiary base:
New file: OPT_OUT_DEMAND_LOG.md
- Per-surface entries for all 12 OPT_OUT commands (Groups A/B/C)
- Current state: 0 signals across all surfaces (consistent with audit prediction)
- Signal entry template with required fields:
- Source (who/what)
- Use case (concrete orchestration problem)
- Markdown-alternative-checked (why existing output insufficient)
- Date
- Promotion thresholds:
- 2+ independent signals for same surface → file promotion pinpoint
- 1 signal + existing stable schema → file pinpoint for discussion
- 0 signals → stays OPT_OUT (rationale preserved)
Decision framework for cycle #22 (audit close):
- If 0 signals total: move to PERMANENTLY_OPT_OUT, close audit
- If 1-2 signals: file individual promotion pinpoints with evidence
- If 3+ signals: reopen audit, question classification itself
Updated files:
- OPT_OUT_AUDIT.md: Added demand log reference in Related section
- CLAUDE.md: Added prerequisites for promotions (must have logged signals),
added 'File a demand signal' workflow section
Philosophy:
'Prevent speculative expansion' — schema bloat protection discipline.
Every new CLAWABLE surface is a maintenance tax. Evidence requirement keeps
the protocol lean. OPT_OUT surfaces are intentionally not-clawable until
proven otherwise by external demand.
Operational impact:
Next cycles can now:
1. Watch for real claws hitting OPT_OUT surface limits
2. Log signals in structured format (no ad-hoc filing)
3. Run audit at cycle #22 with actual data, not speculation
No code changes. No test changes. Pure governance infrastructure.
Related: #18 cycle (OPT_OUT_AUDIT.md), maintainership phase transition.
Dogfood discovered #178 had two residual gaps:
1. Stderr pollution: argparse usage + error text still leaked to stderr even in
JSON mode (envelope was correct on stdout, but stderr noise broke the
'machine-first protocol' contract — claws capturing both streams got dual output)
2. Generic error message: envelope carried 'invalid command or argument (argparse
rejection)' instead of argparse's actual text like 'the following arguments
are required: session_id' or 'invalid choice: typo (choose from ...)'
Before #179:
$ claw load-session --output-format json
[stdout] {"error": {"message": "invalid command or argument (argparse rejection)"}}
[stderr] usage: main.py load-session [-h] ...
main.py load-session: error: the following arguments are required: session_id
[exit 1]
After #179:
$ claw load-session --output-format json
[stdout] {"error": {"message": "the following arguments are required: session_id"}}
[stderr] (empty)
[exit 1]
Implementation:
- New _ArgparseError exception class captures argparse's real message
- main() monkey-patches parser.error (+ all subparser.error) in JSON mode to raise
_ArgparseError instead of print-to-stderr + sys.exit(2)
- _emit_parse_error_envelope() now receives the real message verbatim
- Text mode path unchanged: still uses original argparse print+exit behavior
Contract:
- JSON mode: stdout carries envelope with argparse's actual error; stderr silent
- Text mode: unchanged — argparse usage to stderr, exit 2
- Parse errors still error.kind='parse', retryable=false
Test additions (5 new, 14 total in test_parse_error_envelope.py):
- TestParseErrorStderrHygiene (5):
- test_json_mode_stderr_is_silent_on_unknown_command
- test_json_mode_stderr_is_silent_on_missing_arg
- test_json_mode_envelope_carries_real_argparse_message
- test_json_mode_envelope_carries_invalid_choice_details (verifies valid-choices list)
- test_text_mode_stderr_preserved_on_unknown_command (backward compat)
Operational impact:
Claws capturing both stdout and stderr no longer get garbled output. The envelope
message now carries discoverability info (valid command list, missing-arg name)
that claws can use for retry/recovery without probing the CLI a second time.
Test results: 201 → 206 passing, 3 skipped unchanged, zero regression.
Pinpoint discovered via dogfood at 2026-04-22 20:30 KST (cycle #20).
Filed explicit decision criteria for the 12 OPT_OUT surfaces (commands that do
not support --output-format json) documented in test_cli_parity_audit.py.
Categorized by rationale:
- Group A (4): Rich-Markdown reports (summary, manifest, parity-audit, setup-report)
Markdown-as-output is intentional; JSON would be information loss.
Unlikely promotions (remain OPT_OUT long-term).
- Group B (3): List filters with --query/--limit (subsystems, commands, tools)
Query layer already exists; users have escape hatch.
Remain OPT_OUT (promotion effort >> value).
- Group C (5): Simulation/debug surfaces (remote-mode, ssh-mode, teleport-mode,
direct-connect-mode, deep-link-mode)
Intentionally non-production; JSON output doesn't add value.
Remain OPT_OUT (simulation tools, not orchestration endpoints).
Audit workflow documented:
1. Survey: Check if external claws actually request JSON versions
2. Cost estimate: Schema + tests for each surface
3. Value estimate: Real demand vs hypothetical
4. Decision: CLAWABLE, remain OPT_OUT, or new pinpoint
Promotion criteria locked (only if clear use case + schema simple + demand exists).
Outcome prediction: All 12 likely remain OPT_OUT (documented rationale per group).
Timeline: Survey period (cycles #19–#21), final decision (cycle #22).
Related pinpoints: #175 (summary/manifest JSON parallel?), #176 (--query-json?),
#177 (mode simulators ever CLAWABLE?).
This closes the documentation loop from cycles #173–#174 (protocol closure →
field evolution → reframe). Now governance rules are explicit for future work.
#164 Stage B requires exposing whether cancellation was observed at the
turn-result level. This commit adds the infrastructure field:
Changes:
- TurnResult.cancel_observed: bool = False (query_engine.py)
- _build_timeout_result() accepts cancel_observed parameter (runtime.py)
- Two timeout paths now pass cancel_event.is_set() to signal observation (runtime.py)
- bootstrap command includes cancel_observed in turn JSON (main.py)
- SCHEMAS.md documents Turn Result Fields with cancel_observed contract
Usage:
When a turn timeout occurs, cancel_observed=true indicates that the
engine observed the cancellation event being set. This allows callers
to distinguish:
- timeout with no cancel → infrastructure/network stall
- timeout with cancel observed → cooperative cancellation was triggered
Backward compat:
- Existing TurnResult construction without cancel_observed defaults to False
- bootstrap JSON output still validates per SCHEMAS.md (new field is always present)
Test results: 182 passing, 3 skipped, zero regression.
Related: #161 (wall-clock timeout), #164 (cancellation observability protocol)
ROADMAP continues #164 with Stage C (test coverage for cancellation + turn envelope).
Adds parametrised test suite validating that clawable-surface commands'
JSON output matches their declared envelope contracts per SCHEMAS.md.
Two phases:
Phase 1 (this commit): Consistency baseline.
- Collect ENVELOPE_CONTRACTS registry mapping each command to its
required and optional fields
- TestJsonEnvelopeConsistency: parametrised test iterates over 13
commands, invokes with --output-format json, validates that
actual JSON envelope contains all required fields
- test_envelope_field_value_types: spot-check types (int, str, list)
for consistency
Phase 2 (future #173): Common field wrapping.
- Once wrap_json_envelope() is applied, all commands will emit
timestamp, command, exit_code, output_format, schema_version
- Currently skipped via @pytest.mark.skip, these tests will activate
automatically when wrapping is implemented:
TestJsonEnvelopeCommonFieldPrep::test_all_envelopes_include_timestamp
TestJsonEnvelopeCommonFieldPrep::test_all_envelopes_include_command
TestJsonEnvelopeCommonFieldPrep::test_all_envelopes_include_exit_code_and_schema_version
Why this matters:
- #172 documented the JSON contract; this test validates it
- Currently detects when actual output diverges from SCHEMAS.md
(e.g. list-sessions emits 'count', not 'sessions_count')
- As #173 wraps commands, test suite auto-validates new common fields
- Prevents regression: accidental field removal breaks the test suite
Current status: 11 passed (consistency), 6 skipped (awaiting #173)
Full suite: 168 → 179 passing, zero regression.
Closes ROADMAP #173 prep (framework for common field validation).
Actual field wrapping remains for next cycle.
Stops manual parity inspection from being a human-noticed concern. When
a developer adds a new subcommand to the claw-code CLI, this test suite
enforces explicit classification:
- CLAWABLE_SURFACES: MUST accept --output-format {text,json}
- OPT_OUT_SURFACES: explicitly exempt with documented rationale
A new command that forgets to opt into one of these two sets FAILS
loudly with TestCommandClassificationCoverage::test_every_registered_
command_is_classified. No silent drift possible.
Technique: argparse introspection at test time walks the _actions tree,
discovers every registered subcommand, and compares against the declared
classification sets. Contract is enforced machine-first instead of
depending on human review.
Three test classes covering three invariants:
TestClawableSurfaceParity (14 tests):
- test_all_clawable_surfaces_accept_output_format: every member of
CLAWABLE_SURFACES has --output-format flag registered
- test_clawable_surface_output_format_choices (parametrised over 13
commands): each must accept exactly {text, json} and default to 'text'
for backward compat
TestCommandClassificationCoverage (3 tests):
- test_every_registered_command_is_classified: any new subcommand
must be explicitly added to CLAWABLE_SURFACES or OPT_OUT_SURFACES
- test_no_command_in_both_sets: sanity check for classification conflicts
- test_all_classified_commands_actually_exist: no phantom commands
(catches stale entries after a command is removed)
TestJsonOutputContractEndToEnd (10 tests):
- test_command_emits_parseable_json (parametrised over 10 clawable
commands): actual subprocess invocation with --output-format json
produces valid parseable JSON on stdout
Classification:
CLAWABLE_SURFACES (13):
Session lifecycle: list-sessions, delete-session, load-session,
flush-transcript
Inspect: show-command, show-tool
Execution: exec-command, exec-tool, route, bootstrap
Diagnostic inventory: command-graph, tool-pool, bootstrap-graph
OPT_OUT_SURFACES (12):
Rich-Markdown reports (future JSON schema): summary, manifest,
parity-audit, setup-report
List filter commands: subsystems, commands, tools
Turn-loop: structured_output is future work
Simulation/debug: remote-mode, ssh-mode, teleport-mode,
direct-connect-mode, deep-link-mode
Full suite: 141 → 168 passing (+27), zero regression.
Closes ROADMAP #171.
Why this matters:
Before: parity was human-monitored; every new command was a drift
risk. The CLUSTER 3 sweep required manually auditing every
subcommand and landing fixes as separate pinpoints.
After: parity is machine-enforced. If a future developer adds a new
command without --output-format, the test suite blocks it
immediately with a concrete error message pointing at the
missing flag.
This is the first step in Gaebal-gajae's identified upper-level work:
operationalised parity instead of aspirational parity.
Related clusters:
- Clawability principle: machine-first protocol enforcement
- Test-first regression guard: extends TestTripletParityConsistency
(#160/#165) and TestFullFamilyParity (#166) from per-cluster
parity to cross-surface parity
Final diagnostic surface in the JSON parity sweep: bootstrap-graph
(the runtime bootstrap/prefetch visualization) now supports --output-format.
Concrete addition:
- bootstrap-graph: --output-format {text,json}
JSON envelope:
{stages: [str], note: 'bootstrap-graph is markdown-only in this version'}
Envelope explanation: bootstrap-graph's Markdown output is rich and
textual; raw JSON embedding maintains the markdown format (split into
lines array) rather than attempting lossy structural extraction that
would lose information. This is an honest limitation in this cycle;
full JSON schema can be added in a future audit if claws require
structured bootstrap data (dependency graphs, prefetch timing, etc.).
Backward compatibility:
- Default is 'text' (Markdown unchanged)
Closes ROADMAP #170.
Related: #167, #168, #169. Diagnostic/inventory surface family is now
uniformly JSON-capable. Summary, manifest, parity-audit, setup-report,
command-graph, tool-pool, bootstrap-graph all accept --output-format.
Extends the diagnostic surface audit with the two inventory-structure
commands: command-graph (command family segmentation) and tool-pool
(assembled tool inventory). Both now expose their underlying rich
datastructures via JSON envelope.
Concrete additions:
- command-graph: --output-format {text,json}
- tool-pool: --output-format {text,json}
JSON envelope shapes:
command-graph:
{builtins_count, plugin_like_count, skill_like_count, total_count,
builtins: [{name, source_hint}],
plugin_like: [{name, source_hint}],
skill_like: [{name, source_hint}]}
tool-pool:
{simple_mode, include_mcp, tool_count,
tools: [{name, source_hint}]}
Backward compatibility:
- Default is 'text' (Markdown unchanged)
- Text output byte-identical to pre-#169
Tests (4 new, test_command_graph_tool_pool_output_format.py):
- TestCommandGraphOutputFormat (2): JSON structure + text compat
- TestToolPoolOutputFormat (2): JSON structure + text compat
Full suite: 137 → 141 passing, zero regression.
Closes ROADMAP #169.
Why this matters:
Claws auditing the codebase can now ask 'what commands exist' and
'what tools exist' and get structured, parseable answers instead of
regex-parsing Markdown headers and counting list items.
Related clusters:
- Diagnostic surfaces (#169 adds to #167/#168 work-verb parity)
- Inventory introspection (command-graph + tool-pool are the two
foundational 'what do we have?' queries)
Closes the inspect-capability parity gap: show-command and show-tool were
the only discovery/inspection CLI commands lacking --output-format support,
making them outliers in the ecosystem that already had unified JSON
contracts across list-sessions, load-session, delete-session, and
flush-transcript (#160/#165/#166).
Concrete additions:
- show-command: --output-format {text,json}
- show-tool: --output-format {text,json}
JSON envelope shape (found case):
{name, found: true, source_hint, responsibility}
JSON envelope shape (not-found case):
{name, found: false, error: {kind:'command_not_found'|'tool_not_found',
message, retryable: false}}
Exit codes:
0 = success
1 = not found
Backward compatibility:
- Default (no --output-format) is 'text' (unchanged)
- Text output byte-identical to pre-#167 (three newline-separated lines)
Tests (10 new, test_show_command_tool_output_format.py):
- TestShowCommandOutputFormat (5): found + not-found in JSON; text mode
backward compat; text is default
- TestShowToolOutputFormat (3): found + not-found in JSON; text mode
backward compat
- TestShowCommandToolFormatParity (2): both accept same flag choices;
consistent JSON envelope shape
Full suite: 114 → 124 passing, zero regression.
Closes ROADMAP #167.
Why this matters:
Before: Claws calling show-command/show-tool had to parse human-readable
prose output via regex, with no structured error signal.
After: Same envelope contract as load-session and friends: JSON-first,
typed errors, machine-parseable.
Related clusters:
- Session-lifecycle CLI parity family (#160, #165, #166, #167)
- Machine-readable error contracts (same vein as #162 atomicity + #164
cancellation state-safety: structured boundaries for orchestration)
Closes the #161 follow-up gap identified in review: wall-clock timeout
bounded caller-facing wait but did not cancel the underlying provider
thread, which could silently mutate mutable_messages / transcript_store /
permission_denials / total_usage after the caller had already observed
stop_reason='timeout'. A ghost turn committed post-deadline would poison
any session that got persisted afterwards.
Stage A scope (this commit): runtime + engine layer cooperative cancel.
Engine layer (src/query_engine.py):
- submit_message now accepts cancel_event: threading.Event | None = None
- Two safe checkpoints:
1. Entry (before max_turns / budget projection) — earliest possible return
2. Post-budget (after output synthesis, before mutation) — catches cancel
that arrives while output was being computed
- Both checkpoints return stop_reason='cancelled' with state UNCHANGED
(mutable_messages, transcript_store, permission_denials, total_usage
all preserved exactly as on entry)
- cancel_event=None preserves legacy behaviour with zero overhead (no
checkpoint checks at all)
Runtime layer (src/runtime.py):
- run_turn_loop creates one cancel_event per invocation when a deadline
is in play (and None otherwise, preserving legacy fast path)
- Passes the same event to every submit_message call across turns, so a
late cancel on turn N-1 affects turn N
- On timeout (either pre-call or mid-call), runtime explicitly calls
cancel_event.set() before future.cancel() + synthesizing the timeout
TurnResult. This upgrades #161's best-effort future.cancel() (which
only cancels not-yet-started futures) to cooperative mid-flight cancel.
Stop reason taxonomy after Stage A:
'completed' — turn committed, state mutated exactly once
'max_budget_reached' — overflow, state unchanged (#162)
'max_turns_reached' — capacity exceeded, state unchanged
'cancelled' — cancel_event observed, state unchanged (#164 Stage A)
'timeout' — synthesised by runtime, not engine (#161)
The 'cancelled' vs 'timeout' split matters:
- 'timeout' is the runtime's best-effort signal to the caller: deadline hit
- 'cancelled' is the engine's confirmation: cancel was observed + honoured
If the provider call wedges entirely (never reaches a checkpoint), the
caller still sees 'timeout' and the thread is leaked — but any NEXT
submit_message call on the same engine observes the event at entry and
returns 'cancelled' immediately, preventing ghost-turn accumulation.
This is the honest cooperative limit in Python threading land; true
preemption requires async-native provider IO (future work, not Stage A).
Tests (29 new tests, tests/test_submit_message_cancellation.py + tests/
test_run_turn_loop_cancellation.py):
Engine-layer (12 tests):
- TestCancellationBeforeCall (5): pre-set event returns 'cancelled' immediately;
mutable_messages, transcript_store, usage, permission_denials all preserved
- TestCancellationAfterBudgetCheck (1): cancel set mid-call (after projection,
before commit) still honoured; output synthesised but state untouched
- TestCancellationAfterCommit (2): post-commit cancel not observable (honest
limit) BUT next call on same engine observes it + returns 'cancelled'
- TestLegacyCallersUnchanged (3): cancel_event=None preserves #162 atomicity
+ max_turns contract with zero behaviour change
- TestCancellationVsOtherStopReasons (2): cancel precedes max_turns check;
cancel does not retroactively override a completed turn
Runtime-layer (5 tests):
- TestTimeoutPropagatesCancelEvent (3): submit_message receives a real Event
object when deadline is set; None in legacy mode; timeout actually calls
event.set() so in-flight threads observe at their next checkpoint
- TestCancelEventSharedAcrossTurns (1): same event object passed to every
turn (object identity check) — late cancel on turn N-1 must affect turn N
Regression: 3 existing timeout test mocks updated to accept cancel_event
kwarg (mocks that previously had signature (prompt, commands, tools, denials)
now have (prompt, commands, tools, denials, cancel_event=None) since runtime
passes cancel_event positionally on the timeout path).
Full suite: 97 → 114 passing, zero regression.
Closes ROADMAP #164 Stage A.
What's explicitly NOT in Stage A:
- Preemptive cancellation of wedged provider IO (requires asyncio-native
provider path; larger refactor)
- Timeout on the legacy unbounded run_turn_loop path (by design: legacy
callers opt out of cancellation entirely)
- CLI exposure of 'cancelled' as a distinct exit code (currently 'cancelled'
maps to the same stop_reason != 'completed' break condition as others;
CLI surface for cancel is a separate pinpoint if warranted)
Every 'claw flush-transcript' call without --directory writes to
.port_sessions/<uuid>.json in CWD. Without a gitignore entry, every
dogfood run leaves dozens of untracked files in the repo, masking real
changes in 'git status' output.
Now that #160/#166 ship structured session lifecycle commands and
deterministic --session-id, this directory is purely transient by
default — belongs in .gitignore.
#159: multi-turn sessions had a silent security asymmetry: denied_tools
were always empty in run_turn_loop, even though bootstrap_session inferred
them from the routed matches. Result: any tool gated as 'destructive'
(bash-family commands, rm, etc) would silently appear unblocked across all
turns in multi-turn mode, giving a false 'clean' permission picture to any
claw consuming TurnResult.permission_denials.
Fix: compute denied_tools once at loop start via _infer_permission_denials,
then pass the same denials to every submit_message call (both timeout and
legacy unbounded paths). This mirrors the existing bootstrap_session pattern.
Acceptance: run_turn_loop('run bash ls').permission_denials now matches
what bootstrap_session returns — both infer the same denials from the
routed matches. Multi-turn security posture is symmetric.
Tests (tests/test_run_turn_loop_permissions.py, 2 tests):
- test_turn_loop_surfaces_permission_denials_like_bootstrap: Symmetry
check confirming both paths infer identical denials for destructive tools
- test_turn_loop_with_continuation_preserves_denials: Denials inferred at
loop start are passed consistently to all turns; captured via mock and
verified non-empty
Full suite: 82/82 passing, zero regression.
Closes ROADMAP #159.
The #160 session-lifecycle CLI triplet was asymmetric: list-sessions and
delete-session accepted --directory + --output-format and emitted typed
JSON error envelopes, but load-session had neither flag and dumped a raw
Python traceback (including the SessionNotFoundError class name) on a
missing session.
Three concrete impacts this fix closes:
1. Alternate session-store locations (e.g. /tmp/claw-run-XXX/.port_sessions)
were unreachable via load-session; claws had to chdir or monkeypatch
DEFAULT_SESSION_DIR to work around it.
2. Not-found emitted a multi-line Python stack, not a parseable envelope.
Claws deciding retry/escalate/give-up had only exit code 1 to work with.
3. The traceback leaked 'src.session_store.SessionNotFoundError' verbatim,
coupling version-pinned claws to our internal exception class name.
Now all three triplet commands accept the same flag pair and emit the
same JSON error shape:
Success (json mode):
{"session_id": "alpha", "loaded": true, "messages_count": 3,
"input_tokens": 42, "output_tokens": 99}
Not-found:
{"session_id": "missing", "loaded": false,
"error": {"kind": "session_not_found",
"message": "session 'missing' not found in /path",
"directory": "/path", "retryable": false}}
Corrupted file:
{"session_id": "broken", "loaded": false,
"error": {"kind": "session_load_failed",
"message": "...", "directory": "/path",
"retryable": true}}
Exit code contract:
- 0 on successful load
- 1 on not-found (preserves existing $?)
- 1 on OSError/JSONDecodeError (distinct 'kind' in JSON)
Backward compat: legacy 'claw load-session ID' text output unchanged
byte-for-byte. Only new behaviour is the flags and structured error path.
Tests (tests/test_load_session_cli.py, 13 tests):
- TestDirectoryFlagParity (2): --directory works + fallback to CWD/.port_sessions
- TestOutputFormatFlagParity (2): json schema + text-mode backward compat
- TestNotFoundTypedError (2): JSON envelope on not-found; no traceback in
either mode; no internal class name leak
- TestLoadFailedDistinctFromNotFound (1): corrupted file = session_load_failed
with retryable=true, distinct from session_not_found
- TestTripletParityConsistency (6): parametrised over [list, delete, load] *
[--directory, --output-format] — explicit parity guard for future regressions
Full suite: 80/80 passing, zero regression.
Discovered via Jobdori dogfood sweep 2026-04-22 17:44 KST — ran
'claw load-session nonexistent' expecting a clean error, got a Python
traceback. Filed #165 + fixed in same commit.
Closes ROADMAP #165.
#163: run_turn_loop no longer injects f'{prompt} [turn N]' into follow-up
prompts. The suffix was never defined or interpreted anywhere — not by the
engine, not by the system prompt, not by any LLM. It looked like a real
user-typed annotation in the transcript and made replay/analysis fragile.
New behaviour:
- turn 0 submits the original prompt (unchanged)
- turn > 0 submits caller-supplied continuation_prompt if provided, else
the loop stops cleanly — no fabricated user turn
- added continuation_prompt: str | None = None parameter to run_turn_loop
- added --continuation-prompt CLI flag for claws scripting multi-turn loops
- zero '[turn' strings ever appear in mutable_messages or stdout now
Behaviour change for existing callers:
- Before: run_turn_loop(prompt, max_turns=3) submitted 3 turns
('prompt', 'prompt [turn 2]', 'prompt [turn 3]')
- After: run_turn_loop(prompt, max_turns=3) submits 1 turn ('prompt')
- To preserve old multi-turn behaviour, pass continuation_prompt='Continue.'
or any structured follow-up text
One existing timeout test (test_budget_is_cumulative_across_turns) updated
to pass continuation_prompt so the cumulative-budget contract is actually
exercised across turns instead of trivially satisfied by a one-turn loop.
#164 filed: addresses reviewer feedback on #161. The wall-clock timeout
bounds the caller-facing wait, but the underlying submit_message worker
thread keeps running and can mutate engine state after the timeout
TurnResult is returned. A cooperative cancel_event pattern is sketched in
the pinpoint; real asyncio.Task.cancel() support will come once provider
IO is async-native (larger refactor).
Tests (tests/test_run_turn_loop_continuation.py, 8 tests):
- TestNoTurnSuffixInjection (2): zero '[turn' strings in any submitted
prompt, both default and explicit-continuation paths
- TestContinuationDefaultStopsAfterTurnZero (2): default loops run exactly
one turn; engine.submit_message called exactly once despite max_turns=10
- TestExplicitContinuationBehaviour (2): turn 0 = original, turn N = continuation
verbatim; max_turns still respected
- TestCLIContinuationFlag (2): CLI default emits only '## Turn 1';
--continuation-prompt wires through to multi-turn behaviour
Full suite: 67/67 passing.
Closes ROADMAP #163. Files #164.
Previously, QueryEnginePort.submit_message() checked the token budget AFTER
appending the prompt to mutable_messages, transcript_store, and permission_denials,
and AFTER calling compact_messages_if_needed(). On overflow it set
stop_reason='max_budget_reached' but the overflow turn was already committed.
Any caller that persisted the session afterwards wrote the rejected prompt to
disk — the session was silently poisoned even though the TurnResult said the
turn never completed.
Fix:
- Restructure submit_message so the budget check early-returns BEFORE any
mutation of mutable_messages, transcript_store, permission_denials, or
total_usage.
- The returned TurnResult.usage reflects pre-call state (overflow never
advanced the usage counter).
- Normal (in-budget) path unchanged: mutation happens exactly once, at the
end, only on 'completed' results.
This closes the atomicity gap: submit_message is now either 'turn committed'
(stop_reason='completed') or 'turn rejected, state untouched'
(stop_reason in {'max_budget_reached', 'max_turns_reached'}). Callers can
safely retry with a fresh budget or a smaller prompt without worrying about
phantom committed turns from prior rejections.
Tests (tests/test_submit_message_budget.py, 10 tests):
- TestBudgetOverflowDoesNotMutate (5): mutable_messages / transcript /
permission_denials / total_usage / TurnResult.usage all pre-mutation after overflow
- TestOverflowPersistence (2): first-turn overflow persists empty session;
successful-turn-then-overflow persists only the successful turn
- TestEngineUsableAfterOverflow (2): subsequent in-budget call still works
with no residue; repeated overflows don't accumulate hidden state
- TestNormalPathStillCommits (1): regression guard — non-overflow path still
commits mutable_messages/transcript/usage as expected
Full suite: 59/59 passing, zero regression.
Blocker: none. Closes ROADMAP #162.
Previously, run_turn_loop was bounded only by max_turns (turn count). If
engine.submit_message stalled — slow provider, hung network, infinite
stream — the loop blocked indefinitely with no cancellation path. Claws
calling run_turn_loop in CI or orchestration had no reliable way to
enforce a deadline; the loop would hang until OS kill or human intervention.
Fix:
- Add timeout_seconds parameter to run_turn_loop (default None = legacy unbounded).
- When set, each submit_message call runs inside a ThreadPoolExecutor and is
bounded by the remaining wall-clock budget (total across all turns, not per-turn).
- On timeout, synthesize a TurnResult with stop_reason='timeout' carrying the
turn's prompt and routed matches so transcripts preserve orchestration context.
- Exhausted/negative budget short-circuits before calling submit_message.
- Legacy path (timeout_seconds=None) bypasses the executor entirely — zero
overhead for callers that don't opt in.
CLI:
- Added --timeout-seconds flag to 'turn-loop' command.
- Exit code 2 when the loop terminated on timeout (vs 0 for completed),
so shell scripts can distinguish 'done' from 'budget exhausted'.
Tests (tests/test_run_turn_loop_timeout.py, 6 tests):
- Legacy unbounded path unchanged (timeout_seconds=None never emits 'timeout')
- Hung submit_message aborted within budget (0.3s budget, 5s mock hang → exit <1.5s)
- Budget is cumulative across turns (0.6s budget, 0.4s per turn, not per-turn)
- timeout_seconds=0 short-circuits first turn without calling submit_message
- Negative timeout treated as exhausted (guard against caller bugs)
- Timeout TurnResult carries correct prompt, matches, UsageSummary shape
Full suite: 49/49 passing, zero regression.
Blocker: none. Closes ROADMAP #161.
- list_sessions(directory=None) -> list[str]: enumerate stored session IDs
- session_exists(session_id, directory=None) -> bool: check existence without FileNotFoundError
- delete_session(session_id, directory=None) -> bool: unlink a session file
- load_session now raises typed SessionNotFoundError (subclass of KeyError) instead of FileNotFoundError
- Claws can now manage session lifecycle without reaching past the module to glob filesystem
Closes ROADMAP #160. Acceptance: claw can call list_sessions(), session_exists(id), delete_session(id) without importing Path or knowing .port_sessions/<id>.json layout.
## Gap
#77 Phase 1 added machine-readable error kind discriminants and #156 extended
them to text-mode output. However, the hint field is still prose derived from
splitting existing error text — not a stable registry-backed remediation
contract.
Downstream claws inspecting the hint field still need to parse human wording
to decide whether to retry, escalate, or terminate.
## Fix Shape
1. Remediation registry: remediation_for(kind, operation) -> Remediation struct
with action (retry/escalate/terminate/configure), target, and stable message
2. Stable hint outputs per error class (no more prose splitting)
3. Golden fixture tests replacing split_error_hint() string hacks
## Source
gaebal-gajae dogfood sweep 2026-04-22 05:30 KST
## Problem
#77 Phase 1 added machine-readable error `kind` discriminants to JSON error
payloads. Text-mode (stderr) errors still emit prose-only output with no
structured classification.
Observability tools (log aggregators, CI error parsers) parsing stderr can't
distinguish error classes without regex-scraping the prose.
## Fix
Added `[error-kind: <class>]` prefix line to all text-mode error output.
The prefix appears before the error prose, making it immediately parseable by
line-based log tools without any substring matching.
**Examples:**
## Impact
- Stderr observers (log aggregators, CI systems) can now parse error class
from the first line without regex or substring scraping
- Same classifier function used for JSON (#77 P1) and text modes
- Text-mode output remains human-readable (error prose unchanged)
- Prefix format follows syslog/structured-logging conventions
## Tests
All 179 rusty-claude-cli tests pass. Verified on 3 different error classes.
Closes ROADMAP #156.
## Problem
All JSON error payloads had the same three-field envelope:
```json
{"type": "error", "error": "<prose with hint baked in>"}
```
Five distinct error classes were indistinguishable at the schema level:
- missing_credentials (no API key)
- missing_worker_state (no state file)
- session_not_found / session_load_failed
- cli_parse (unrecognized args)
- invalid_model_syntax
Downstream claws had to regex-scrape the prose to route failures.
## Fix
1. **Added `classify_error_kind()`** — prefix/keyword classifier that returns a
snake_case discriminant token for 12 known error classes:
`missing_credentials`, `missing_manifests`, `missing_worker_state`,
`session_not_found`, `session_load_failed`, `no_managed_sessions`,
`cli_parse`, `invalid_model_syntax`, `unsupported_command`,
`unsupported_resumed_command`, `confirmation_required`, `api_http_error`,
plus `unknown` fallback.
2. **Added `split_error_hint()`** — splits multi-line error messages into
(short_reason, optional_hint) so the runbook prose stops being stuffed
into the `error` field.
3. **Extended JSON envelope** at 4 emit sites:
- Main error sink (line ~213)
- Session load failure in resume_session
- Stub command (unsupported_command)
- Unknown resumed command (unsupported_resumed_command)
## New JSON shape
```json
{
"type": "error",
"error": "short reason (first line)",
"kind": "missing_credentials",
"hint": "Hint: export ANTHROPIC_API_KEY..."
}
```
`kind` is always present. `hint` is null when no runbook follows.
`error` now carries only the short reason, not the full multi-line prose.
## Tests
Added 2 new regression tests:
- `classify_error_kind_returns_correct_discriminants` — all 9 known classes + fallback
- `split_error_hint_separates_reason_from_runbook` — with and without hints
All 179 rusty-claude-cli tests pass. Full workspace green.
Closes ROADMAP #77 Phase 1.
## Problem
Two session error messages advertised `.claw/sessions/` as the managed-session
location, but the actual on-disk layout is `.claw/sessions/<workspace_fingerprint>/`
where the fingerprint is a 16-char FNV-1a hash of the CWD path.
Users see error messages like:
```
no managed sessions found in .claw/sessions/
```
But the real directory is:
```
.claw/sessions/8497f4bcf995fc19/
```
The error copy was a direct lie — it made workspace-fingerprint partitioning
invisible and left users confused about whether sessions were lost or just in
a different partition.
## Fix
Updated two error formatters to accept the resolved `sessions_root` path
and extract the actual workspace-fingerprint directory:
1. **format_missing_session_reference**: now shows the actual fingerprint dir
and explains that it's a workspace-specific partition
2. **format_no_managed_sessions**: now shows the actual fingerprint dir and
includes a note that sessions from other CWDs are intentionally invisible
Updated all three call sites to pass `&self.sessions_root` to the formatters.
## Examples
**Before:**
```
no managed sessions found in .claw/sessions/
```
**After:**
```
no managed sessions found in .claw/sessions/8497f4bcf995fc19/
Start `claw` to create a session, then rerun with `--resume latest`.
Note: claw partitions sessions per workspace fingerprint; sessions from other CWDs are invisible.
```
```
session not found: nonexistent-id
Hint: managed sessions live in .claw/sessions/8497f4bcf995fc19/ (workspace-specific partition).
Try `latest` for the most recent session or `/session list` in the REPL.
```
## Impact
- Users can now tell from the error message that they're looking in the right
directory (the one their current CWD maps to)
- The workspace-fingerprint partitioning stops being invisible
- Operators understand why sessions from adjacent CWDs don't appear
- Error copy matches the actual on-disk structure
## Tests
All 466 runtime tests pass. Verified on two real workspaces with actual
workspace-fingerprint directories.
Closes ROADMAP #80.
## Problem
Three interactive slash commands are documented in `claw --help` but have no
corresponding section in USAGE.md:
- `/ultraplan [task]` — Run a deep planning prompt with multi-step reasoning
- `/teleport <symbol-or-path>` — Jump to a file or symbol by searching the workspace
- `/bughunter [scope]` — Inspect the codebase for likely bugs
New users see these commands in the help output but don't know:
- What each command does
- How to use it
- When to use it vs. other commands
- What kind of results to expect
## Fix
Added new section "Advanced slash commands (Interactive REPL only)" to USAGE.md
with documentation for all three commands:
1. **`/ultraplan`** — multi-step reasoning for complex tasks
- Example: `/ultraplan refactor the auth module to use async/await`
- Output: structured plan with numbered steps and reasoning
2. **`/teleport`** — navigate to a file or symbol
- Example: `/teleport UserService`, `/teleport src/auth.rs`
- Output: file content with the requested symbol highlighted
3. **`/bughunter`** — scan for likely bugs
- Example: `/bughunter src/handlers`, `/bughunter` (all)
- Output: list of suspicious patterns with explanations
## Impact
Users can now discover these commands and understand when to use them without
having to guess or search external sources. Bridges the gap between `--help`
output and full documentation.
Also filed ROADMAP #155 documenting the gap.
Closes ROADMAP #155.
## Problem
When a user types `claw --model gpt-4` or `--model qwen-plus`, they get:
```
error: invalid model syntax: 'gpt-4'. Expected provider/model (e.g., anthropic/claude-opus-4-6) or known alias
```
USAGE.md documents that "The error message now includes a hint that names the detected env var" — but this hint does not actually exist. The user has to re-read USAGE.md or guess the correct prefix.
## Fix
Enhance `validate_model_syntax` to detect when a model name looks like it belongs to a different provider:
1. **OpenAI models** (starts with `gpt-` or `gpt_`):
```
Did you mean `openai/gpt-4`? (Requires OPENAI_API_KEY env var)
```
2. **Qwen/DashScope models** (starts with `qwen`):
```
Did you mean `qwen/qwen-plus`? (Requires DASHSCOPE_API_KEY env var)
```
3. **Grok/xAI models** (starts with `grok`):
```
Did you mean `xai/grok-3`? (Requires XAI_API_KEY env var)
```
Unrelated invalid models (e.g., `asdfgh`) do not get a spurious hint.
## Verification
- `claw --model gpt-4` → hints `openai/gpt-4` + `OPENAI_API_KEY`
- `claw --model qwen-plus` → hints `qwen/qwen-plus` + `DASHSCOPE_API_KEY`
- `claw --model grok-3` → hints `xai/grok-3` + `XAI_API_KEY`
- `claw --model asdfgh` → generic error (no hint)
## Tests
Added 3 new assertions in `parses_multiple_diagnostic_subcommands`:
- GPT model error hints openai/ prefix and OPENAI_API_KEY
- Qwen model error hints qwen/ prefix and DASHSCOPE_API_KEY
- Unrelated models don't get a spurious hint
All 177 rusty-claude-cli tests pass.
Closes ROADMAP #154.
## Problem
Users frequently ask after building:
- "Where is the claw binary?"
- "Did the build actually work?"
- "Why can't I run \`claw\` from anywhere?"
This happens because \`cargo build\` puts the binary in \`rust/target/debug/claw\`
(or \`rust/target/release/claw\`), and new users don't know:
1. Where to find it
2. How to test it
3. How to add it to PATH (optional but common follow-up)
## Fix
Added new section "Post-build: locate the binary and verify" to README covering:
1. **Binary location table:** debug vs. release, macOS/Linux vs. Windows paths
2. **Verification commands:** Test the binary with \`--help\` and \`doctor\`
3. **Three ways to add to PATH:**
- Symlink (macOS/Linux): \`ln -s ... /usr/local/bin/claw\`
- cargo install: \`cargo install --path . --force\`
- Shell profile update: add rust/target/debug to \$PATH
4. **Troubleshooting:** Common errors ("command not found", "permission denied",
debug vs. release build speed)
## Impact
New users can now:
- Find the binary immediately after build
- Run it and verify with \`claw doctor\`
- Know their options for system-wide access
Also filed ROADMAP #153 documenting the gap.
Closes ROADMAP #153.
## Problem
Users commonly type `claw doctor --json`, `claw status --json`, or
`claw system-prompt --json` expecting JSON output. These fail with
`unrecognized argument \`--json\` for subcommand` with no hint that
`--output-format json` is the correct flag.
## Discovery
Filed as #152 during 21:17 dogfood nudge. The #127 worktree contained
a more comprehensive patch but conflicted with #141 (unified --help).
On re-investigation of main, Bugs 1 and 3 from #127 are already closed
(positional arg rejection works, no double "error:" prefix). Only
Bug 2 (the `--json` hint) remained.
## Fix
Two call sites add the hint:
1. `parse_single_word_command_alias`'s diagnostic-verb suffix path:
when rest[1] == "--json", append "Did you mean \`--output-format json\`?"
2. `parse_system_prompt_options` unknown-option path: same hint when
the option is exactly `--json`.
## Verification
Before:
$ claw doctor --json
error: unrecognized argument `--json` for subcommand `doctor`
Run `claw --help` for usage.
After:
$ claw doctor --json
error: unrecognized argument `--json` for subcommand `doctor`
Did you mean `--output-format json`?
Run `claw --help` for usage.
Covers: `doctor --json`, `status --json`, `sandbox --json`,
`system-prompt --json`, and any other diagnostic verb that routes
through `parse_single_word_command_alias`.
Other unrecognized args (`claw doctor garbage`) correctly don't
trigger the hint.
## Tests
- 2 new assertions in `parses_multiple_diagnostic_subcommands`:
- `claw doctor --json` produces hint
- `claw doctor garbage` does NOT produce hint
- 177 rusty-claude-cli tests pass
- Workspace tests green
Closes ROADMAP #152.
Filed from nudge directive at 21:17 KST. Implementation exists on worktree
`jobdori-127-verb-suffix` but needs rebase due to merge with #141.
Ready for Phase 1 implementation once conflicts resolved.
## Problem
`workspace_fingerprint(path)` hashes the raw path string without
canonicalization. Two equivalent paths (e.g. `/tmp/foo` vs
`/private/tmp/foo` on macOS) produce different fingerprints and
therefore different session stores. #150 fixed the test-side symptom;
this fixes the underlying product contract.
## Discovery path
#150 fix (canonicalize in test) was a workaround. Q's ack on #150
surfaced the deeper gap: the function itself is still fragile for
any caller passing a non-canonical path:
1. Embedded callers with a raw `--data-dir` path
2. Programmatic `SessionStore::from_cwd(user_path)` calls
3. NixOS store paths, Docker bind mounts, case-insensitive normalization
The REPL's default flow happens to work because `env::current_dir()`
returns canonical paths on macOS. But any caller passing a raw path
risks silent session-store divergence.
## Fix
Canonicalize inside `SessionStore::from_cwd()` and `from_data_dir()`
before computing the fingerprint. Kept `workspace_fingerprint()` itself
as a pure function for determinism — canonicalization is the entry
point's responsibility.
```rust
let canonical_cwd = fs::canonicalize(cwd).unwrap_or_else(|_| cwd.to_path_buf());
let sessions_root = canonical_cwd.join(".claw").join("sessions").join(workspace_fingerprint(&canonical_cwd));
```
Falls back to the raw path if canonicalize fails (directory doesn't
exist yet).
## Test-side updates
Three legacy-session tests expected the non-canonical base path to
match the store's workspace_root. Updated them to canonicalize
`base` after creation — same defensive pattern as #150, now
explicit across all three tests.
## Regression test
Added `session_store_from_cwd_canonicalizes_equivalent_paths` that
creates two stores from equivalent paths (raw vs canonical) and
asserts they resolve to the same sessions_dir.
## Verification
- `cargo test -p runtime session_store_` — 9/9 pass
- `cargo test --workspace` — all green, no FAILED markers
- No behavior change for existing users (REPL default flow already
used canonical paths)
## Backward compatibility
Users on macOS who always went through `env::current_dir()`:
no hash change, sessions resume identically.
Users who ever called with a non-canonical path: hash would change,
but those sessions were already broken (couldn't be resumed from a
canonical-path cwd). Net improvement.
Closes ROADMAP #151.
## #150 Fix: resume_latest test flake
**Problem:** `resume_latest_restores_the_most_recent_managed_session` intermittently
fails when run in the workspace suite or multiple times in sequence, but passes in
isolation.
**Root cause:** `workspace_fingerprint(path)` hashes the path string without
canonicalization. On macOS, `/tmp` is a symlink to `/private/tmp`. The test
creates a temp dir via `std::env::temp_dir().join(...)` which returns
`/var/folders/...` (non-canonical). When the subprocess spawns,
`env::current_dir()` returns the canonical path `/private/var/folders/...`.
The two fingerprints differ, so the subprocess looks in
`.claw/sessions/<hash1>` while files are in `.claw/sessions/<hash2>`.
Session discovery fails.
**Fix:** Call `fs::canonicalize(&project_dir)` after creating the directory
to ensure test and subprocess use identical path representations.
**Verification:** 5 consecutive runs of the full test suite — all pass.
Previously: 5/5 failed when run in sequence.
## #246 Filing: Reminder cron outcome ambiguity (control-loop blocker)
The `clawcode-dogfood-cycle-reminder` cron times out repeatedly with no
structured feedback on whether the nudge was delivered, skipped, or died in-flight.
**Phase 1 outcome schema** — add explicit field to cron result:
- `delivered` — nudge posted to Discord
- `timed_out_before_send` — died before posting
- `timed_out_after_send` — posted but cleanup timed out
- `skipped_due_to_active_cycle` — previous cycle active
- `aborted_gateway_draining` — daemon shutdown
Assigned to gaebal-gajae (cron/orchestration domain). Unblocks trustworthy
dogfood cycle observability.
Closes ROADMAP #150. Filed ROADMAP #246.
## Problem
`runtime::config::tests::validates_unknown_top_level_keys_with_line_and_field_name`
intermittently fails during `cargo test --workspace` (witnessed during
#147 and #148 workspace runs) but passes deterministically in isolation.
Example failure from workspace run:
test result: FAILED. 464 passed; 1 failed
## Root cause
`runtime/src/config.rs::tests::temp_dir()` used nanosecond timestamp
alone for namespace isolation:
std::env::temp_dir().join(format!("runtime-config-{nanos}"))
Under parallel test execution on fast machines with coarse clock
resolution, two tests start within the same nanosecond bucket and
collide on the same path. One test's `fs::remove_dir_all(root)` then
races another's in-flight `fs::create_dir_all()`.
Other crates already solved this pattern:
- plugins::tests::temp_dir(label) — label-parameterized
- runtime::git_context::tests::temp_dir(label) — label-parameterized
runtime/src/config.rs was missed.
## Fix
Added process id + monotonically-incrementing atomic counter to the
namespace, making every callsite provably unique regardless of clock
resolution or scheduling:
static COUNTER: AtomicU64 = AtomicU64::new(0);
let pid = std::process::id();
let seq = COUNTER.fetch_add(1, Ordering::Relaxed);
std::env::temp_dir().join(format!("runtime-config-{pid}-{nanos}-{seq}"))
Chose counter+pid over the label-parameterized pattern to avoid
touching all 20 callsites in the same commit (mechanical noise with
no added safety — counter alone is sufficient).
## Verification
Before: one failure per workspace run (config test flake).
After: 5 consecutive `cargo test --workspace` runs — zero config
test failures. Only pre-existing `resume_latest` flake remains
(orthogonal, unrelated to this change).
for i in 1 2 3 4 5; do cargo test --workspace; done
# All 5 runs: config tests green. Only resume_latest flake appears.
cargo test -p runtime
# 465 passed; 0 failed
## ROADMAP.md
Added Pinpoint #149 documenting the gap, root cause, and fix.
Closes ROADMAP #149.
## Scope
Two deltas in one commit:
### #128 closure (docs)
Re-verified on main HEAD `4cb8fa0`: malformed `--model` strings already
rejected at parse time (`validate_model_syntax` in parse_args). All
historical repro cases now produce specific errors:
claw --model '' → error: model string cannot be empty
claw --model 'bad model' → error: invalid model syntax: 'bad model' contains spaces
claw --model 'sonet' → error: invalid model syntax: 'sonet'. Expected provider/model or known alias
claw --model '@invalid' → error: invalid model syntax: '@invalid'. Expected provider/model ...
claw --model 'totally-not-real-xyz' → error: invalid model syntax: ...
claw --model sonnet → ok, resolves to claude-sonnet-4-6
claw --model anthropic/claude-opus-4-6 → ok, passes through
Marked #128 CLOSED in ROADMAP with repro block. Residual provenance gap
split off as #148.
### #148 implementation
**Problem.** After #128 closure, `claw status --output-format json`
still surfaces only the resolved model string. No way for a claw to
distinguish whether `claude-sonnet-4-6` came from `--model sonnet`
(alias resolution) vs `--model claude-sonnet-4-6` (pass-through) vs
`ANTHROPIC_MODEL` env vs `.claw.json` config vs compiled-in default.
Debug forensics had to re-read argv instead of reading a structured
field. Clawhip orchestrators sending `--model` couldn't confirm the
flag was honored vs falling back to default.
**Fix.** Added two fields to status JSON envelope:
- `model_source`: "flag" | "env" | "config" | "default"
- `model_raw`: user's input before alias resolution (null on default)
Text mode appends a `Model source` line under `Model`, showing the
source and raw input (e.g. `Model source flag (raw: sonnet)`).
**Resolution order** (mirrors resolve_repl_model but with source
attribution):
1. If `--model` / `--model=` flag supplied → source: flag, raw: flag value
2. Else if ANTHROPIC_MODEL set → source: env, raw: env value
3. Else if `.claw.json` model key set → source: config, raw: config value
4. Else → source: default, raw: null
## Changes
### rust/crates/rusty-claude-cli/src/main.rs
- Added `ModelSource` enum (Flag/Env/Config/Default) with `as_str()`.
- Added `ModelProvenance` struct (resolved, raw, source) with
three constructors: `default_fallback()`, `from_flag(raw)`, and
`from_env_or_config_or_default(cli_model)`.
- Added `model_flag_raw: Option<String>` field to `CliAction::Status`.
- Parse loop captures raw input in `--model` and `--model=` arms.
- Extended `parse_single_word_command_alias` to thread
`model_flag_raw: Option<&str>` through.
- Extended `print_status_snapshot` signature to accept
`model_flag_raw: Option<&str>`. Resolves provenance at dispatch time
(flag provenance from arg; else probe env/config/default).
- Extended `status_json_value` signature with
`provenance: Option<&ModelProvenance>`. On Some, adds `model_source`
and `model_raw` fields; on None (legacy resume paths), omits them
for backward compat.
- Extended `format_status_report` signature with optional provenance.
On Some, renders `Model source` line after `Model`.
- Updated all existing callers (REPL /status, resume /status, tests)
to pass None (legacy paths don't carry flag provenance).
- Added 2 regression assertions in parse_args test covering both
`--model sonnet` and `--model=...` forms.
### ROADMAP.md
- Marked #128 CLOSED with re-verification block.
- Filed #148 documenting the provenance gap split, fix shape, and
acceptance criteria.
## Live verification
$ claw --model sonnet --output-format json status | jq '{model,model_source,model_raw}'
{"model": "claude-sonnet-4-6", "model_source": "flag", "model_raw": "sonnet"}
$ claw --output-format json status | jq '{model,model_source,model_raw}'
{"model": "claude-opus-4-6", "model_source": "default", "model_raw": null}
$ ANTHROPIC_MODEL=haiku claw --output-format json status | jq '{model,model_source,model_raw}'
{"model": "claude-haiku-4-5-20251213", "model_source": "env", "model_raw": "haiku"}
$ echo '{"model":"claude-opus-4-7"}' > .claw.json && claw --output-format json status | jq '{model,model_source,model_raw}'
{"model": "claude-opus-4-7", "model_source": "config", "model_raw": "claude-opus-4-7"}
$ claw --model sonnet status
Status
Model claude-sonnet-4-6
Model source flag (raw: sonnet)
Permission mode danger-full-access
...
## Tests
- rusty-claude-cli bin: 177 tests pass (2 new assertions for #148)
- Full workspace green except pre-existing resume_latest flake (unrelated)
Closes ROADMAP #128, #148.
## Problem
The `"prompt"` subcommand arm enforced `if prompt.trim().is_empty()`
and returned a specific error. The fallthrough `other` arm in the same
match block — which routes any unrecognized first positional arg to
`CliAction::Prompt` — had no such guard. Result:
$ claw ""
error: missing Anthropic credentials; export ANTHROPIC_AUTH_TOKEN ...
$ claw " "
error: missing Anthropic credentials; ...
$ claw "" ""
error: missing Anthropic credentials; ...
$ claw --output-format json ""
{"error":"missing Anthropic credentials; ...","type":"error"}
An empty prompt should never reach the credentials check. Worse: with
valid credentials, the literal empty string gets sent to Claude as a
user prompt, either burning tokens for nothing or triggering a model-
side refusal. Same prompt-misdelivery family as #145.
## Root cause
In `parse_subcommand()`, the final `other =>` arm in the top-level
match only guards against typos (#108 guard via `looks_like_subcommand_typo`)
and then unconditionally builds `CliAction::Prompt { prompt: rest.join(" ") }`.
An empty/whitespace-only join passes through.
## Changes
### rust/crates/rusty-claude-cli/src/main.rs
Added the same `if joined.trim().is_empty()` guard already used in the
`"prompt"` arm to the fallthrough path. Error message distinguishes it
from the `prompt` subcommand path:
empty prompt: provide a subcommand (run `claw --help`) or a
non-empty prompt string
Runs AFTER the typo guard (so `claw sttaus` still suggests `status`)
and BEFORE CliAction::Prompt construction (so no network call ever
happens for empty inputs).
### Regression tests
Added 4 assertions in the existing parse_args test:
- parse_args([""]) → Err("empty prompt: ...")
- parse_args([" "]) → Err("empty prompt: ...")
- parse_args(["", ""]) → Err("empty prompt: ...")
- parse_args(["sttaus"]) → Err("unknown subcommand: ...") [verifies #108 typo guard still takes precedence]
### ROADMAP.md
Added Pinpoint #147 documenting the gap, verification, root cause,
fix shape, and acceptance. Joins the prompt-misdelivery cluster
alongside #145.
## Live verification
$ claw ""
error: empty prompt: provide a subcommand (run `claw --help`) or a non-empty prompt string
$ claw " "
error: empty prompt: provide a subcommand (run `claw --help`) or a non-empty prompt string
$ claw --output-format json ""
{"error":"empty prompt: provide a subcommand ...","type":"error"}
$ claw prompt "" # unchanged: subcommand-specific error preserved
error: prompt subcommand requires a prompt string
$ claw hello # unchanged: typo guard still fires
error: unknown subcommand: hello.
Did you mean help
$ claw "real prompt here" # unchanged: real prompts still reach API
error: api returned 401 Unauthorized (with dummy key, as expected)
All empty/whitespace-only paths exit 1. No network call. No misleading
credentials error.
## Tests
- rusty-claude-cli bin: 177 tests pass (4 new assertions)
- Full workspace green except pre-existing resume_latest flake (unrelated)
Closes ROADMAP #147.
## Problem
`claw config` and `claw diff` are pure-local read-only introspection
commands (config merges .claw.json + .claw/settings.json from disk; diff
shells out to `git diff --cached` + `git diff`). Neither needs a session
context, yet both rejected direct CLI invocation:
$ claw config
error: `claw config` is a slash command. Use `claw --resume SESSION.jsonl /config` ...
$ claw diff
error: `claw diff` is a slash command. ...
This forced clawing operators to spin up a full session just to inspect
static disk state, and broke natural pipelines like
`claw config --output-format json | jq`.
## Root cause
Sibling of #145: `SlashCommand::Config { section }` and
`SlashCommand::Diff` had working renderers (`render_config_report`,
`render_config_json`, `render_diff_report`, `render_diff_json_for`)
exposed for resume sessions, but the top-level CLI parser in
`parse_subcommand()` had no arms for them. Zero-arg `config`/`diff`
hit `parse_single_word_command_alias`'s fallback to
`bare_slash_command_guidance`, producing the misleading guidance.
## Changes
### rust/crates/rusty-claude-cli/src/main.rs
- Added `CliAction::Config { section, output_format }` and
`CliAction::Diff { output_format }` variants.
- Added `"config"` / `"diff"` arms to the top-level parser in
`parse_subcommand()`. `config` accepts an optional section name
(env|hooks|model|plugins) matching SlashCommand::Config semantics.
`diff` takes no positional args. Both reject extra trailing args
with a clear error.
- Added `"config" | "diff" => None` to
`parse_single_word_command_alias` so bare invocations fall through
to the new parser arms instead of the slash-guidance error.
- Added dispatch in run() that calls existing renderers: text mode uses
`render_config_report` / `render_diff_report`; JSON mode uses
`render_config_json` / `render_diff_json_for` with
`serde_json::to_string_pretty`.
- Added 5 regression assertions in parse_args test covering:
parse_args(["config"]), parse_args(["config", "env"]),
parse_args(["config", "--output-format", "json"]),
parse_args(["diff"]), parse_args(["diff", "--output-format", "json"]).
### ROADMAP.md
Added Pinpoint #146 documenting the gap, verification, root cause,
fix shape, and acceptance. Explicitly notes which other slash commands
(`hooks`, `usage`, `context`, etc.) are NOT candidates because they
are session-state-modifying.
## Live verification
$ claw config # no config files
Config
Working directory /private/tmp/cd-146-verify
Loaded files 0
Merged keys 0
Discovered files
user missing ...
project missing ...
local missing ...
Exit 0.
$ claw config --output-format json
{
"cwd": "...",
"files": [...],
...
}
$ claw diff # no git
Diff
Result no git repository
Detail ...
Exit 0.
$ claw diff --output-format json # inside claw-code
{
"kind": "diff",
"result": "changes",
"staged": "",
"unstaged": "diff --git ..."
}
Exit 0.
## Tests
- rusty-claude-cli bin: 177 tests pass (5 new assertions in parse_args)
- Full workspace green except pre-existing resume_latest flake (unrelated)
## Not changed
`hooks`, `usage`, `context`, `tasks`, `theme`, `voice`, `rename`,
`copy`, `color`, `effort`, `branch`, `rewind`, `ide`, `tag`,
`output-style`, `add-dir` — all session-mutating or interactive-only;
correctly remain slash-only.
Closes ROADMAP #146.
## Problem
`claw plugins` (and `claw plugins list`, `claw plugins --help`,
`claw plugins info <name>`, etc.) fell through the top-level subcommand
match and got routed into the prompt-execution path. Result: a purely
local introspection command triggered an Anthropic API call and surfaced
`missing Anthropic credentials` to the user. With valid credentials, it
would actually send the literal string "plugins" as a user prompt to
Claude, burning tokens for a local query.
$ claw plugins
error: missing Anthropic credentials; export ANTHROPIC_AUTH_TOKEN or ANTHROPIC_API_KEY before calling the Anthropic API
$ ANTHROPIC_API_KEY=dummy claw plugins
⠋ 🦀 Thinking...
✘ ❌ Request failed
error: api returned 401 Unauthorized
Meanwhile siblings (`agents`, `mcp`, `skills`) all worked correctly:
$ claw agents
No agents found.
$ claw mcp
MCP
Working directory ...
Configured servers 0
## Root cause
`CliAction::Plugins` exists, has a working dispatcher
(`LiveCli::print_plugins`), and is produced inside the REPL via
`SlashCommand::Plugins`. But the top-level CLI parser in
`parse_subcommand()` had arms for `agents`, `mcp`, `skills`, `status`,
`doctor`, `init`, `export`, `prompt`, etc., and **no arm for
`plugins`**. The dispatch never ran from the CLI entry point.
## Changes
### rust/crates/rusty-claude-cli/src/main.rs
Added a `"plugins"` arm to the top-level match in `parse_subcommand()`
that produces `CliAction::Plugins { action, target, output_format }`,
following the same positional convention as `mcp` (`action` = first
positional, `target` = second). Rejects >2 positional args with a clear
error.
Added four regression assertions in the existing `parse_args` test:
- `plugins` alone → `CliAction::Plugins { action: None, target: None }`
- `plugins list` → action: Some("list"), target: None
- `plugins enable <name>` → action: Some("enable"), target: Some(...)
- `plugins --output-format json` → action: None, output_format: Json
### ROADMAP.md
Added Pinpoint #145 documenting the gap, verification, root cause,
fix shape, and acceptance.
## Live verification
$ claw plugins # no credentials set
Plugins
example-bundled v0.1.0 disabled
sample-hooks v0.1.0 disabled
$ claw plugins --output-format json # no credentials set
{
"action": "list",
"kind": "plugin",
"message": "Plugins\n example-bundled ...\n sample-hooks ...",
"reload_runtime": false,
"target": null
}
Exit 0 in all modes. No network call. No "missing credentials" error.
## Tests
- rusty-claude-cli bin: 177 tests pass (new plugin assertions included)
- Full workspace green except pre-existing resume_latest flake (unrelated)
Closes ROADMAP #145.
Filing + Phase 1 fix in one commit (sibling of #143).
## Context
With #143 Phase 1 landed (`claw status` degrades), `claw mcp` was the
remaining diagnostic surface that hard-failed on a malformed `.claw.json`.
Same input, same parse error, same partial-success violation. Fresh
dogfood at 18:59 KST caught it on main HEAD `e2a43fc`.
## Changes
### ROADMAP.md
Added Pinpoint #144 documenting the gap and acceptance criteria. Joins
the partial-success / Principle #5 cluster with #143.
### rust/crates/commands/src/lib.rs
`render_mcp_report_for()` + `render_mcp_report_json_for()` now catch the
ConfigError at loader.load() instead of propagating:
- **Text mode** prepends a "Config load error" block (same shape as
#143's status output) before the MCP listing. The listing still renders
with empty servers so the output structure is preserved.
- **JSON mode** adds top-level `status: "ok" | "degraded"` +
`config_load_error: string | null` fields alongside existing fields
(`kind`, `action`, `working_directory`, `configured_servers`,
`servers[]`). On clean runs, `status: "ok"` and
`config_load_error: null`. On parse failure, `status: "degraded"`,
`config_load_error: "..."`, `servers: []`, exit 0.
- Both list and show actions get the same treatment.
### Regression test
`commands::tests::mcp_degrades_gracefully_on_malformed_mcp_config_144`:
- Injects the same malformed .claw.json as #143 (one valid + one broken
mcpServers entry).
- Asserts mcp list returns Ok (not Err).
- Asserts top-level status: "degraded" and config_load_error names the
malformed field path.
- Asserts show action also degrades.
- Asserts clean path returns status: "ok" with config_load_error null.
## Live verification
$ claw mcp --output-format json
{
"action": "list",
"kind": "mcp",
"status": "degraded",
"config_load_error": ".../.claw.json: mcpServers.missing-command: missing string field command",
"working_directory": "/Users/yeongyu/clawd",
"configured_servers": 0,
"servers": []
}
Exit 0.
## Contract alignment after this commit
All three diagnostic surfaces match now:
- `doctor` — degraded envelope with typed check entries ✅
- `status` — degraded envelope with config_load_error ✅ (#143)
- `mcp` — degraded envelope with config_load_error ✅ (this commit)
Phase 2 (typed-error object joining taxonomy §4.44) tracked separately
across all three surfaces.
Full workspace test green except pre-existing resume_latest flake (unrelated).
Closes ROADMAP #144 phase 1.
Previously `claw status` hard-failed on any config parse error, emitting
a bare error string and exiting 1. This took down the entire health
surface for a single malformed MCP entry, even though workspace, git,
model, permission, and sandbox state could all be reported independently.
`claw doctor` already degraded gracefully on the exact same input.
This commit matches `claw status` to that contract.
Changes:
- Add `StatusContext::config_load_error: Option<String>` to capture parse
errors without aborting.
- Rewrite `status_context()` to match on `ConfigLoader::load()`: on Err,
fall back to default `SandboxConfig` for sandbox resolution and record
the parse error, then continue populating workspace/git/memory fields.
- JSON output gains top-level `status: "ok" | "degraded"` marker and a
`config_load_error` string (null on clean runs). All other existing
fields preserved for backward compat.
- Text output prepends a "Config load error" block with Details + Hint
when config failed to parse, then a "Status (degraded)" header on the
main block. Clean runs show the usual "Status" header.
- Doctor path updated to pass the config load error through StatusContext.
Regression test `status_degrades_gracefully_on_malformed_mcp_config_143`:
- Injects a .claw.json with one valid + one malformed mcpServers entry
- Asserts status_context() returns Ok (not Err)
- Asserts config_load_error names the malformed field path
- Asserts workspace/sandbox fields still populated in JSON
- Asserts top-level status is 'degraded'
- Asserts clean config path still returns status: 'ok'
Verified live on /Users/yeongyu/clawd (contains deliberately broken MCP entries):
$ claw status --output-format json
{ "status": "degraded",
"config_load_error": ".../mcpServers.missing-command: missing string field command",
"model": "claude-opus-4-6",
"workspace": {...},
"sandbox": {...},
... }
Phase 2 (typed error object joining #4.44 taxonomy) tracked separately.
Full workspace test green except pre-existing resume_latest flake (unrelated).
Closes ROADMAP #143 phase 1.
Add two missing sections documenting the recently-fixed commands:
- **Initialize a repository**: Shows both text and JSON output modes for
`claw init`. Explains that structured JSON fields (created[], updated[],
skipped[], artifacts[]) allow claws to detect per-artifact state without
substring-matching prose. Documents idempotency.
- **Inspect worker state**: Documents `claw state` and the prerequisite
that a worker must have executed at least once. Includes the helpful error
message and remediation hints (claw or claw prompt <text>) so users
discovering the command for the first time see actionable guidance.
These sections complement the product fixes in #142 (init JSON structure)
and #139 (state error actionability) by documenting the contract from a
user perspective.
Related: ROADMAP #142 (structured init output), #139 (worker-state discoverability).
Previously `claw state` errored with "no worker state file found ... — run a
worker first" but there is no `claw worker` subcommand, so claws had no
discoverable path from the error to a fix.
Changes:
- Rewrite the missing-state error to name the two concrete commands that
produce .claw/worker-state.json:
* `claw` (interactive REPL, writes state on first turn)
* `claw prompt <text>` (one non-interactive turn)
Also tell the user what to rerun: `claw state [--output-format json]`.
- Expand the State --help topic with "Produces state", "Observes state",
and "Exit codes" lines so the worker-state contract is discoverable
before the user hits the error.
- Add regression test state_error_surfaces_actionable_worker_commands_139
asserting the error contains `claw prompt`, REPL mention, and the
rerun path, plus that the help topic documents the producer contract.
Verified live:
$ claw state
error: no worker state file found at .claw/worker-state.json
Hint: worker state is written by the interactive REPL or a non-interactive prompt.
Run: claw # start the REPL (writes state on first turn)
Or: claw prompt <text> # run one non-interactive turn
Then rerun: claw state [--output-format json]
JSON mode preserves the full hint inside the error envelope so CI/claws
can match on `claw prompt` without losing the canonical prefix.
Full workspace test green except pre-existing resume_latest flake (unrelated).
Closes ROADMAP #139.
Previously `claw init --output-format json` emitted a valid JSON envelope but
packed the entire human-formatted output into a single `message` string. Claw
scripts had to substring-match human language to tell `created` from `skipped`.
Changes:
- Add InitStatus::json_tag() returning machine-stable "created"|"updated"|"skipped"
(unlike label() which includes the human " (already exists)" suffix).
- Add InitReport::NEXT_STEP constant so claws can read the next-step hint
without grepping the message string.
- Add InitReport::artifacts_with_status() to partition artifacts by state.
- Add InitReport::artifact_json_entries() for the structured artifacts[] array.
- Rewrite run_init + init_json_value to emit first-class fields alongside the
legacy message string (kept for text consumers): project_path, created[],
updated[], skipped[], artifacts[], next_step, message.
- Update the slash-command Init dispatch to use the same structured JSON.
- Add regression test artifacts_with_status_partitions_fresh_and_idempotent_runs
asserting both fresh + idempotent runs produce the right partitioning and
that the machine-stable tag is bare 'skipped' not label()'s phrasing.
Verified output:
- Fresh dir: created[] has 4 entries, skipped[] empty
- Idempotent call: created[] empty, skipped[] has 4 entries
- project_path, next_step as first-class keys
- message preserved verbatim for backward compat
Full workspace test green except pre-existing resume_latest flake (unrelated).
Closes ROADMAP #142.
Previously, `claw <subcommand> --help` had 5 different behaviors:
- 7 subcommands returned subcommand-specific help (correct)
- init/export/state/version silently fell back to global `claw --help`
- system-prompt/dump-manifests errored with `unknown <cmd> option: --help`
- bootstrap-plan printed its phase list instead of help text
Changes:
- Extend LocalHelpTopic enum with Init, State, Export, Version, SystemPrompt,
DumpManifests, BootstrapPlan variants.
- Extend parse_local_help_action() to resolve those 7 subcommands to their
local help topic instead of falling through to the main dispatch.
- Remove init/state/export/version from the explicit wants_help=true matcher
so they reach parse_local_help_action() before being routed to global help.
- Add render_help_topic() entries for the 7 new topics with consistent
Usage/Purpose/Output/Formats/Related structure.
- Add regression test subcommand_help_flag_has_one_contract_across_all_subcommands_141
asserting every documented subcommand + both --help and -h variants resolve
to a HelpTopic with non-empty text that contains a Usage line.
Verification:
- All 14 subcommands now return subcommand-specific help (live dogfood).
- Full workspace test green except pre-existing resume_latest flake.
Closes ROADMAP #141.
Previously this test inherited the cargo test runner's CWD, which could contain
a stale .claw/settings.json with "permissionMode": "acceptEdits" written by
another test. The deprecated-field resolver then silently downgraded the
default permission mode to WorkspaceWrite, breaking the test's assertion.
Fix: wrap the assertion in with_current_dir() + env_lock() so the test runs in
an isolated temp directory with no stale config.
Full workspace test now passes except for pre-existing resume_latest flake
(unrelated to #140, environment-dependent, tracked separately).
Closes ROADMAP #140.
Updated LocalHelpTopic help strings to surface --output-format support:
- Status, Sandbox, Doctor, Acp all now show [--output-format <format>]
- Added 'Formats: text (default), json' line to each
Diagnostic verbs support JSON output but help text didn't advertise it.
Post-#127 fix: help text now matches actual CLI surface.
Verified: cargo build passes, claw doctor --help shows output-format.
Refs: #127
USAGE.md now documents:
- for machine-readable diagnostics
- Note about parse-time rejection of invalid suffix args (post-#127 fix)
Verifies that diagnostic verbs support JSON output for scripting,
and documents the behavior change from #127 (invalid args rejected
at parse time instead of falling through to prompt dispatch).
Refs: #127
Diagnostic verbs (help, version, status, sandbox, doctor, state) now
reject unrecognized suffix arguments at parse time instead of silently
falling through to Prompt dispatch.
Fixes: claw doctor --json (and similar) no longer accepts --json silently
and attempts to send it to the LLM as a prompt. Now properly emits:
'unrecognized argument `--json` for subcommand `doctor`'
Joined parser-level trust gap quintet #108 + #117 + #119 + #122 + #127.
Prevents token burn on rejected arguments.
Verified: cargo build --workspace passes, claw doctor --json errors cleanly.
Refs: #127, ROADMAP
Adds ship provenance detection and emission in execute_bash_async():
- Detects git push to main/master commands
- Captures current branch, HEAD commit, git user as actor
- Emits ship.prepared event with ShipProvenance payload
- Logs to stderr as interim routing (event stream integration pending)
This is the first wired provenance event — schema (§4.44.5) now has
runtime emission at actual git operation boundary.
Verified: cargo build --workspace passes.
Next: wire ship.commits_selected, ship.merged, ship.pushed_main events.
Refs: §4.44.5.1, ROADMAP #4.44.5
#122: doctor invocation now checks stale-base condition
- Calls run_stale_base_preflight(None) in render_doctor_report()
- Emits stale-base warnings to stderr when branch is behind main
- Fixes inconsistency: doctor 'ok' vs prompt 'stale base' warning
#125: git_state field reflects non-git directories
- When !in_git_repo, git_state = 'not in git repo' instead of 'clean'
- Fixes contradiction: in_git_repo: false but git_state: 'clean'
- Applied in both doctor text output and status JSON
Verified: cargo build --workspace passes.
Refs: ROADMAP #122 (dd73962), #125 (debbcbe)
Adds run_stale_base_preflight(None) call to render_doctor_report() so that
claw doctor emits stale-base warnings to stderr when the current branch is
behind main. Previously doctor reported 'ok' even when branch was stale,
creating inconsistency with prompt path warnings.
Fixes silent-state inventory gap: doctor now consistent with prompt/repl
stale-base checking. No behavior change for non-stale branches.
Verified: cargo build --workspace passes, no test failures.
Ref: ROADMAP #122 dogfood filing @ dd73962
Dogfood cycle 2026-04-20 identified that §4.44.5 ship/provenance event schema
is implemented (ShipProvenance struct, ship.* constructors, tests pass) but
actual git push/merge/commit-range operations do not yet emit these events.
Events remain dead code—constructors exist but are never called during real
workflows. This pinpoint tracks the missing wiring: locating actual git
operation call sites in main.rs/tools/lib.rs/worker_boot.rs and intercepting
to emit ship.prepared/commits_selected/merged/pushed_main with real metadata
(source_branch, commit_range, merge_method, actor, pr_number).
Acceptance: at least one real git push emits all 4 events with actual payload
values, claw state JSON surfaces ship provenance.
Ref: dogfood gaebal-gajae @ 1495672954573291571 (15:30 KST)
Adds structured ship provenance surface to eliminate delivery-path opacity:
New lane events:
- ship.prepared — intent to ship established
- ship.commits_selected — commit range locked
- ship.merged — merge completed with provenance
- ship.pushed_main — delivery to main confirmed
ShipProvenance struct carries:
- source_branch, base_commit
- commit_count, commit_range
- merge_method (direct_push/fast_forward/merge_commit/squash_merge/rebase_merge)
- actor, pr_number
Constructor methods added to LaneEvent for all four ship events.
Tests:
- Wire value serialization for ship events
- Round-trip deserialization
- Canonical event name coverage
Runtime: 465 tests pass
ROADMAP updated with IMPLEMENTED status
This closes the gap where 56 commits pushed to main had no structured
provenance trail — now emits first-class events for clawhip consumption.
Added structured delivery-path contract to surface branch → merge → main-push
provenance as first-class events. Filed from the 56-commit 2026-04-20 push
that exposed the gap.
Also fixes: ApiError test compilation — add suggested_action: None to 4 sites
- Line ~8414: opaque_provider_wrapper_surfaces_failure_class_session_and_trace
- Line ~8436: retry_exhaustion_uses_retry_failure_class_for_generic_provider_wrapper
- Line ~8499: provider_context_window_errors_are_reframed_with_same_guidance
- Line ~8533: retry_wrapped_context_window_errors_keep_recovery_guidance
Dogfooded 2026-04-18 on main HEAD debbcbe from /tmp/cdBB2.
Non-git directory:
$ mkdir /tmp/cdBB2 && cd /tmp/cdBB2 # NO git init
$ claw --output-format json status | jq .workspace.git_state
'clean' # should be null — not in a git repo
$ claw --output-format json doctor | jq '.checks[]
| select(.name=="workspace") | {in_git_repo, git_state}'
{"in_git_repo": false, "git_state": "clean"}
# CONTRADICTORY: not in git BUT git is 'clean'
Trace:
main.rs:2550-2554 parse_git_workspace_summary:
let Some(status) = status else {
return summary; // all-zero default when no git
};
All-zero GitWorkspaceSummary → is_clean() (changed_files==0)
→ true → headline() = 'clean'
main.rs:4950 status JSON: git_summary.headline() for git_state
main.rs:1856 doctor workspace: same headline() for git_state
Fix shape (~25 lines):
- Return Option<GitWorkspaceSummary> when status is None
- headline() returns Option<String>: None when no git
- Status JSON: git_state: null when not in git
- Doctor: omit git_state when in_git_repo: false, or set null
- Optional: claw init skip .gitignore in non-git dirs
- Regression: non-git → null, git clean → 'clean',
detached HEAD → 'clean' + 'detached HEAD'
Joins Truth-audit — 'clean' is a lie for non-git dirs.
Adjacent to #89 (claw blind to mid-rebase) — same field,
different missing state.
Joins #100 (status/doctor JSON gaps) — another field whose
value doesn't reflect reality.
Natural bundle: #89 + #100 + #125 — git-state-completeness
triple: rebase/merge invisible (#89) + stale-base unplumbed
(#100) + non-git 'clean' lie (#125). Complete git_state
field failure coverage.
Filed in response to Clawhip pinpoint nudge 1495016073085583442
in #clawcode-building-in-public.
Dogfooded 2026-04-18 on main HEAD bb76ec9 from /tmp/cdAA2.
--model flag has zero validation:
claw --model sonet status → model:'sonet' (typo passthrough)
claw --model '' status → model:'' (empty accepted)
claw --model garbage status → model:'garbage' (any string)
Valid aliases do resolve:
sonnet → claude-sonnet-4-6
opus → claude-opus-4-6
Config aliases also resolve via resolve_model_alias_with_config
But unresolved strings pass through silently. Typo 'sonet'
becomes literal model ID sent to API → fails late with
'model not found' after full context assembly.
Compare:
--reasoning-effort: validates low|medium|high. Has guard.
--permission-mode: validates against known set. Has guard.
--model: no guard. Any string.
--base-commit: no guard (#122). Same pattern.
status JSON:
{model: 'sonet'} — shows resolved name only.
No model_source (flag/config/default).
No model_raw (pre-resolution input).
No model_valid (known to any provider).
Claw can't distinguish typo from exact model from alias.
Trace:
main.rs:470-480 --model parsing:
model = value.clone(); index += 2;
No validation. Raw string stored.
main.rs:1032-1046 resolve_model_alias_with_config:
resolves known aliases. Unknown strings pass through.
main.rs:~4951 status JSON builder:
reports resolved model. No source/raw/valid fields.
Fix shape (~65 lines):
- Reject empty string at parse time
- Warn on unresolved aliases with fuzzy-match suggestion
- Add model_source, model_raw to status JSON
- Add model-validity check to doctor
- Regression per failure mode
Joins #105 (4-surface model disagreement) — model pair:
#105 status ignores config model, doctor mislabels
#124 --model flag unvalidated, no provenance in JSON
Joins #122 (--base-commit zero validation) — unvalidated-flag
pair: same parser pattern, no guards.
Joins Silent-flag/documented-but-unenforced as 17th.
Joins Truth-audit — status model field has no provenance.
Joins Parallel-entry-point asymmetry as 10th.
Filed in response to Clawhip pinpoint nudge 1495000973914144819
in #clawcode-building-in-public.