OpenAI /responses validates tool function schemas strictly:
- object types must have "properties" (at minimum {})
- "additionalProperties": false is required
/chat/completions is lenient and accepts schemas without these fields,
but /responses rejects them with "object schema missing properties" /
"invalid_function_parameters".
Add normalize_object_schema() which recursively walks the JSON Schema
tree and fills in missing "properties"/{} and "additionalProperties":false
on every object-type node. Existing values are not overwritten.
Call it in openai_tool_definition() before building the request payload
so both /chat/completions and /responses receive strict-validator-safe
schemas.
Add unit tests covering:
- bare object schema gets both fields injected
- nested object schemas are normalised recursively
- existing additionalProperties is not overwritten
Fixes the live repro where gpt-5.4 via OpenAI compat accepted connection
and routing but rejected every tool call with schema validation errors.
Closes ROADMAP #33.
web_search_extracts_and_filters_results set CLAWD_WEB_SEARCH_BASE_URL
without holding env_lock(), while the sibling test
web_search_handles_generic_links_and_invalid_base_url always held it.
Under parallel test execution the two tests interleave set_var/remove_var
calls, pointing the search client at the wrong mock server port and
causing assertion failures.
Fix: add env_lock() guard at the top of web_search_extracts_and_filters_results,
matching the serialization pattern already used by every other env-mutating
test in this module.
Root cause of CI flake on run 24127551802.
Identified and fixed during dogfood session.
Add rust/crates/rusty-claude-cli/build.rs that:
- Captures git rev-parse --short HEAD at build time → GIT_SHA env
- Reads Cargo's TARGET env var → TARGET env
- Derives BUILD_DATE from SOURCE_DATE_EPOCH / BUILD_DATE env or
the current date via `date +%Y-%m-%d` fallback
- Registers rerun-if-changed on .git/HEAD and .git/refs so the SHA
stays fresh across commits
Update main.rs DEFAULT_DATE to pick up BUILD_DATE from option_env!()
instead of the hardcoded 2026-03-31 static string.
Before: `claw --version` always showed Git SHA: unknown, Target: unknown,
Build date: 2026-03-31 in local builds.
After: e.g. Git SHA: 7f53d82, Target: aarch64-apple-darwin, Build date: 2026-04-08
Generated by droid (Kimi K2.5 Turbo) via acpx (wrote build.rs),
cleaned up by Jobdori (added BUILD_DATE step, updated main.rs const).
Co-Authored-By: Droid <noreply@factory.ai>
ProviderClient::from_model_with_anthropic_auth was dispatching every
ProviderKind::OpenAi match to OpenAiCompatConfig::openai(), which reads
OPENAI_API_KEY and points at api.openai.com. But DashScope models
(qwen-plus, qwen/qwen3-coder, etc.) also return ProviderKind::OpenAi
from detect_provider_kind because DashScope speaks the OpenAI wire
format. The metadata layer correctly identifies them as needing
DASHSCOPE_API_KEY and the DashScope compatible-mode endpoint, but that
metadata was being ignored at dispatch time.
Result: users running `claw --model qwen-plus` with DASHSCOPE_API_KEY
set would get a "missing OPENAI_API_KEY" error instead of being routed
to DashScope.
Fix: consult providers::metadata_for_model in the OpenAi dispatch arm
and pick dashscope() vs openai() based on metadata.auth_env.
Adds a regression test asserting ProviderClient::from_model("qwen-plus")
builds with the DashScope base URL. Exposes a pub base_url() accessor
on OpenAiCompatClient so the test can verify the routing.
Authored by droid (Kimi K2.5 Turbo) via acpx, cleaned up by Jobdori
(removed unsafe blocks unnecessary under edition 2021, imported
ProviderClient from super, adopted EnvVarGuard pattern from
providers/mod.rs tests).
Co-Authored-By: Droid <noreply@factory.ai>
The CLI entry point (build_runtime_with_plugin_state in main.rs)
was hardcoded to always instantiate AnthropicRuntimeClient with an
AnthropicClient, regardless of what detect_provider_kind(model)
returned. This meant `--model openai/gpt-4` with OPENAI_API_KEY
set and no ANTHROPIC_* vars still failed with "missing Anthropic
credentials" because the CLI never dispatched to the OpenAI-compat
backend that already exists in the api crate.
Root cause: AnthropicRuntimeClient.client was typed as
AnthropicClient (concrete) rather than ApiProviderClient (enum).
The api crate already had a ProviderClient enum with Anthropic /
Xai / OpenAi variants that dispatches correctly via
detect_provider_kind, plus a unified MessageStream enum that wraps
both anthropic::MessageStream and openai_compat::MessageStream
with the same next_event() -> StreamEvent interface. The CLI just
wasn't using it.
Changes (1 file, +59 -7):
- Import api::ProviderClient as ApiProviderClient
- Change AnthropicRuntimeClient.client from AnthropicClient to
ApiProviderClient
- In AnthropicRuntimeClient::new(), dispatch based on
detect_provider_kind(&resolved_model):
* Anthropic: build AnthropicClient directly with
resolve_cli_auth_source() + api::read_base_url() +
PromptCache (preserves ANTHROPIC_BASE_URL override for mock
test harness and the session-scoped prompt cache)
* xAI / OpenAi: delegate to
ApiProviderClient::from_model_with_anthropic_auth which routes
to OpenAiCompatClient::from_env with the matching config
(reads OPENAI_API_KEY/XAI_API_KEY/DASHSCOPE_API_KEY and their
BASE_URL overrides internally)
- Change push_prompt_cache_record to take &ApiProviderClient
(ProviderClient::take_last_prompt_cache_record returns None for
non-Anthropic variants, so the helper is a no-op on
OpenAI-compat providers without extra branching)
What this unlocks for users:
claw --model openai/gpt-4.1-mini prompt 'hello' # OpenAI
claw --model grok-3 prompt 'hello' # xAI
claw --model qwen-plus prompt 'hello' # DashScope
OPENAI_BASE_URL=https://openrouter.ai/api/v1 \
claw --model openai/anthropic/claude-sonnet-4 prompt 'hello' # OpenRouter
All previously broken, now routed correctly by prefix.
Verification:
- cargo build --release -p rusty-claude-cli: clean
- cargo test --release -p rusty-claude-cli: 182 tests, 0 failures
(including compact_output tests that exercise the Anthropic mock)
- cargo fmt --all: clean
- cargo clippy --workspace: warnings-only (pre-existing)
- cargo test --release --workspace: all crates green except one
pre-existing race in runtime::config::tests (passes in isolation)
Source: live users nicma (1491342350960562277) and Jengro
(1491345009021030533) in #claw-code on 2026-04-08.
Two live users in #claw-code on 2026-04-08 hit adjacent auth confusion:
varleg set OPENAI_API_KEY for OpenRouter but prefix routing didn't
activate without openai/ model prefix, and stanley078852 put sk-ant-*
in ANTHROPIC_AUTH_TOKEN (Bearer path) instead of ANTHROPIC_API_KEY
(x-api-key path) and got 401 Invalid bearer token.
Changes:
1. ApiError::MissingCredentials gained optional hint field (error.rs)
2. anthropic_missing_credentials_hint() sniffs OPENAI/XAI/DASHSCOPE
env vars and suggests prefix routing when present (providers/mod.rs)
3. All 4 Anthropic auth paths wire the hint helper (anthropic.rs)
4. 401 + sk-ant-* in bearer token detected and hint appended
5. 'Which env var goes where' section added to USAGE.md
Tests: unit tests for all three improvements (no HTTP calls needed).
Workspace: all tests green, fmt clean, clippy warnings-only.
Source: live users varleg + stanley078852 in #claw-code 2026-04-08.
Co-authored-by: gaebal-gajae <gaebal-gajae@layofflabs.com>
Two bugs found in the plugin hook test harness that together caused
Linux CI to fail on 'hooks::tests::collects_and_runs_hooks_from_enabled_plugins'
with 'Broken pipe (os error 32)'. Three reproductions plus one rerun
failure on main today: 24120271422, 24120538408, 24121392171.
Root cause 1 (chmod, defense-in-depth): write_hook_plugin writes
pre.sh/post.sh/failure.sh via fs::write without setting the execute
bit. While the runtime hook runner invokes hooks via 'sh <path>' (so
the script file does not strictly need +x), missing exec perms can
cause subtle fork/exec races on Linux in edge cases.
Root cause 2 (the actual CI failure): output_with_stdin unconditionally
propagated write_all errors on the child's stdin pipe, including
BrokenPipe. A hook script that runs to completion in microseconds
(e.g. a one-line printf) can exit and close its stdin before the parent
finishes writing the JSON payload. Linux pipes surface this as EPIPE
immediately; macOS pipes happen to buffer the small payload, so the
race only shows on ubuntu CI runners. The parent's write_all raised
BrokenPipe, which output_with_stdin returned as Err, which run_command
classified as 'failed to start', making the test assertion fail.
Fix: (a) make_executable helper sets mode 0o755 via PermissionsExt on
each generated hook script, with a #[cfg(unix)] gate and a no-op
#[cfg(not(unix))] branch. (b) output_with_stdin now matches the
write_all result and swallows BrokenPipe specifically (the child still
ran; wait_with_output still captures stdout/stderr/exit code), while
propagating all other write errors. (c) New regression guard
generated_hook_scripts_are_executable under #[cfg(unix)] asserts each
generated .sh file has at least one execute bit set.
Surgical scope per gaebal-gajae's direction: chmod + pipe tolerance +
regression guard only. The deeper plugin-test sealing pass for ROADMAP
#25 + #27 stays in gaebal-gajae's OMX lane.
Verification:
- cargo test --release -p plugins → 35 passing, 0 failing
- cargo fmt -p plugins → clean
- cargo clippy -p plugins -- -D warnings → clean
Co-authored-by: gaebal-gajae <gaebal-gajae@layofflabs.com>
- compact flag: was parsed then discarded (`compact: _`) instead of
passed to `run_turn_with_output` — hardcoded `false` meant --compact
never took effect
- piped stdin vs permission prompter: `read_piped_stdin()` consumed all
stdin before `CliPermissionPrompter::decide()` could read interactive
approval answers; now only consumes stdin as prompt context when
permission mode is `DangerFullAccess` (fully unattended)
- session resolver: `resolve_managed_session_path` and
`list_managed_sessions` now fall back to the pre-isolation flat
`.claw/sessions/` layout so legacy sessions remain accessible
- help assertion: match on stable prefix after `/session delete` was
added in batch 5
- prompt shorthand: fix copy-paste that changed expected prompt from
"help me debug" to "$help overview"
- mock parity harness: filter captured requests to `/v1/messages` path
only, excluding count_tokens preflight calls added by `be561bf`
All 6 failures were pre-existing but masked because `client_integration`
always failed first (fixed in 8c6dfe5).
Workspace: 810+ tests passing, 0 failing.
CI has been red since be561bf ('Use Anthropic count tokens for preflight')
because that commit replaced the free-function preflight_message_request
(byte-estimate guard) with an instance method that silently returns Ok on
any count_tokens failure:
let counted_input_tokens = match self.count_tokens(request).await {
Ok(count) => count,
Err(_) => return Ok(()), // <-- silent bypass
};
Two consequences:
1. client_integration::send_message_blocks_oversized_requests_before_the_http_call
has been FAILING on every CI run since be561bf. The mock server in that
test only has one HTTP response queued (a bare '{}' to satisfy the main
request), so the count_tokens POST parses into an empty body that fails
to deserialize into CountTokensResponse -> Err -> silent bypass -> the
oversized 600k-char request proceeds to the mock instead of being
rejected with ContextWindowExceeded as the test expects.
2. In production, any third-party Anthropic-compatible gateway that doesn't
implement /v1/messages/count_tokens (OpenRouter, Cloudflare AI Gateway,
etc.) would silently disable the preflight guard entirely, letting
oversized requests hit the upstream only to fail there with a provider-
side context-window error. This is exactly the 'opaque failure surface'
ROADMAP #22 asked us to avoid.
Fix: call the free-function super::preflight_message_request(request)? as
the first step in the instance method, before any network round-trip. This
guarantees the byte-estimate guard always fires, whether or not the remote
count_tokens endpoint is reachable. The count_tokens refinement still runs
afterward when available for more precise token counting, but it is now
strictly additive — it can only catch more cases, never silently skip the
guard.
Test results:
- cargo test -p api --lib: 89 passed, 0 failed
- cargo test --release -p api (all test binaries): 118 passed, 0 failed
- cargo test --release -p api --test client_integration \
send_message_blocks_oversized_requests_before_the_http_call: passes
- cargo fmt --check: clean
This unblocks the Rust CI workflow which has been red on every push since
be561bf landed.
Users in Discord #clawcode-get-help (web3g) asked for Qwen 3.6 Plus via
native Alibaba DashScope API instead of OpenRouter, which has stricter
rate limits. This commit adds first-class routing for qwen/ and bare
qwen- prefixed model names.
Changes:
- DEFAULT_DASHSCOPE_BASE_URL constant: /compatible-mode/v1 endpoint
- OpenAiCompatConfig::dashscope() factory mirroring openai()/xai()
- DASHSCOPE_ENV_VARS + credential_env_vars() wiring
- metadata_for_model: qwen/ and qwen- prefix routes to DashScope with
auth_env=DASHSCOPE_API_KEY, reuses ProviderKind::OpenAi because
DashScope speaks the OpenAI REST shape
- is_reasoning_model: detect qwen-qwq, qwq-*, and *-thinking variants
so tuning params (temperature, top_p, etc.) get stripped before
payload assembly (same pattern as o1/o3/grok-3-mini)
Tests added:
- providers::tests::qwen_prefix_routes_to_dashscope_not_anthropic
- openai_compat::tests::qwen_reasoning_variants_are_detected
89 api lib tests passing, 0 failing. cargo fmt --check: clean.
Closes the user-reported gap: 'use Qwen 3.6 Plus via Alibaba API
directly, not OpenRouter' without needing OPENAI_BASE_URL override
or unsetting ANTHROPIC_API_KEY.
build_runtime_runs_plugin_lifecycle_init_and_shutdown was the only test
that set/removed ANTHROPIC_API_KEY without holding the env_lock mutex.
Under parallel workspace execution, other tests racing on the same env
var could wipe the key mid-construction, causing a flaky credential error.
Root cause: process-wide env vars are shared mutable state. All other
tests that touch ANTHROPIC_API_KEY already use env_lock(). This test
was the only holdout.
Fix: add let _guard = env_lock(); at the top of the test.
openai_compat_integration.rs and client_integration.rs had MessageRequest
constructions without the new tuning param fields (temperature, top_p,
frequency_penalty, presence_penalty, stop) added in c667d47.
Added ..Default::default() to all 4 sites. cargo fmt applied.
This was the root cause of CI red on main (E0063 compile error in
integration tests, not caught by --lib tests).
renders_help_from_shared_specs hardcoded the exact /session usage string,
which broke when /session delete was added in batch 5. Relaxed to check
for /session presence instead of exact subcommand list.
Pre-existing test brittleness (not caused by recent commits).
687 workspace lib tests passing, 0 failing.
MessageRequest now carries OpenAI-compatible tuning params (c667d47), but
the Anthropic API does not support frequency_penalty or presence_penalty,
and uses 'stop_sequences' instead of 'stop'. Without this fix, setting
these params with a Claude model would produce 400 errors.
Changes to strip_unsupported_beta_body_fields:
- Remove frequency_penalty and presence_penalty from Anthropic request body
- Convert stop → stop_sequences (only when non-empty)
- temperature and top_p are preserved (Anthropic supports both)
Tests added:
- strip_removes_openai_only_fields_and_converts_stop
- strip_does_not_add_empty_stop_sequences
87 api lib tests passing, 0 failing.
cargo check --workspace: clean.
Reasoning models reject temperature, top_p, frequency_penalty, and
presence_penalty with 400 errors. Instead of letting these flow through
and returning cryptic provider errors, strip them silently at the
request-builder boundary.
is_reasoning_model() classifies: o1*, o3*, o4*, grok-3-mini.
stop sequences are preserved (safe for all providers).
Tests added:
- reasoning_model_strips_tuning_params: o1-mini strips all 4 params, keeps stop
- grok_3_mini_is_reasoning_model: classification coverage for grok-3-mini, o1,
o3-mini, and negative cases (gpt-4o, grok-3, claude)
85 api lib tests passing, 0 failing.
MessageRequest was missing standard OpenAI-compatible generation tuning
parameters. Callers had no way to control temperature, top_p,
frequency_penalty, presence_penalty, or stop sequences.
Changes:
- Added 5 optional fields to MessageRequest (all Option, None by default)
- Wired into build_chat_completion_request: only included in payload when set
- All existing construction sites updated with ..Default::default()
- MessageRequest now derives Default for ergonomic partial construction
Tests added:
- tuning_params_included_in_payload_when_set: all 5 params flow into JSON
- tuning_params_omitted_from_payload_when_none: absent params stay absent
83 api lib tests passing, 0 failing.
cargo check --workspace: 0 warnings.
metadata_for_model returned None for unknown models like openai/gpt-4.1-mini,
causing detect_provider_kind to fall through to auth-sniffer order. If
ANTHROPIC_API_KEY was set, the model was silently misrouted to Anthropic
and the user got a confusing 'missing Anthropic credentials' error.
Fix: add explicit prefix checks for 'openai/' and 'gpt-' in
metadata_for_model so the model name wins over env-var presence.
Regression test added: openai_namespaced_model_routes_to_openai_not_anthropic
- 'openai/gpt-4.1-mini' routes to OpenAi
- 'gpt-4o' routes to OpenAi
Reported and reproduced by gaebal-gajae against current main.
81 api lib tests passing, 0 failing.
WorkerGet had zero test coverage. WorkerAwaitReady and WorkerSendPrompt
had only one happy-path test each with no error paths.
Added 4 tests:
- worker_get_returns_worker_state: WorkerGet fetches correct worker_id/status/cwd
- worker_get_on_unknown_id_returns_error: unknown id -> 'worker not found'
- worker_await_ready_on_spawning_worker_returns_not_ready: ready=false on spawning worker
- worker_send_prompt_on_non_ready_worker_returns_error: sending prompt before ready fails
94 tool tests passing, 0 failing.
recovery_loop_state_file_reflects_transitions reads the actual state
file after each transition to verify the canonical observability surface
reflects the full stall->resolve->ready progression:
spawning (state file exists, seconds_since_update present)
-> trust_required (is_ready=false, trust_gate_cleared=false in file)
-> spawning (trust_gate_cleared=true after WorkerResolveTrust)
-> ready_for_prompt (is_ready=true after ready screen observe)
This is the end-to-end proof gaebal-gajae called for: clawhip polling
.claw/worker-state.json will see truthful state at every step of the
recovery loop, including the seconds_since_update staleness signal.
90 tool tests passing, 0 failing.
Proves the clawhip restart/recover flow that gaebal-gajae flagged:
1. stall_detect_and_resolve_trust_end_to_end
- Worker created without trusted_roots -> trust_auto_resolve=false
- WorkerObserve with trust-prompt text -> status=trust_required, gate cleared=false
- WorkerResolveTrust -> status=spawning, trust_gate_cleared=true
- WorkerObserve with ready text -> status=ready_for_prompt
Full resolve path verified end-to-end.
2. stall_detect_and_restart_recovery_end_to_end
- Worker stalls at trust_required
- WorkerRestart resets to spawning, trust_gate_cleared=false
Documents the restart-then-re-acquire-trust flow.
Note: seconds_since_update is in .claw/worker-state.json (state file),
not in the Worker tool output struct. Staleness detection via state file
is covered by emit_state_file_writes_worker_status_on_transition in
worker_boot.rs tests.
87 tool tests passing, 0 failing.
Three dead-code warnings eliminated from cargo check:
1. KNOWN_TOP_LEVEL_KEYS / DEPRECATED_TOP_LEVEL_KEYS in config.rs
- Superseded by config_validate::TOP_LEVEL_FIELDS and DEPRECATED_FIELDS
- Were out of date (missing aliases, providerFallbacks, trustedRoots)
- Removed
2. read_git_recent_commits in prompt.rs
- Private function, never called anywhere in the codebase
- Removed
3. workspace_sessions_dir in session.rs
- Public API scaffolded for session isolation (#41)
- Genuinely useful for external consumers (clawhip enumerating sessions)
- Added 2 tests: deterministic path for same CWD, different path for different CWDs
- Annotated with #[allow(dead_code)] since it is external-facing API
cargo check --workspace: 0 warnings remaining
430 runtime tests passing, 0 failing
WorkerRestart and WorkerTerminate had zero test coverage despite being
public tools in the tool spec. Also confirms one design decision worth
noting: restart resets trust_gate_cleared=false, so an allowlisted
worker that gets restarted must re-acquire trust via the normal observe
flow (by design — trust is per-session, not per-CWD).
Tests added:
- worker_terminate_sets_finished_status
- worker_restart_resets_to_spawning (verifies status=spawning,
prompt_in_flight=false, trust_gate_cleared=false)
- worker_terminate_on_unknown_id_returns_error
- worker_restart_on_unknown_id_returns_error
85 tool tests passing, 0 failing.
Previously WorkerCreate passed trusted_roots directly to spawn_worker
with no config-level default. Any batch script omitting the field
stalled all workers at TrustRequired with no recovery path.
Now run_worker_create loads RuntimeConfig from the worker CWD before
spawning and merges config.trusted_roots() with per-call overrides.
Per-call overrides still take effect; config provides the default.
Add test: worker_create_merges_config_trusted_roots_without_per_call_override
- writes .claw/settings.json with trustedRoots=[<os-temp-dir>] in a temp worktree
- calls WorkerCreate with no trusted_roots field
- asserts trust_auto_resolve=true (config roots matched the CWD)
81 tool tests passing, 0 failing.
Closes the startup-friction gap filed in ROADMAP (dd97c49).
WorkerCreate required trusted_roots on every call with no config-level
default. Any batch script that omitted the field stalled all workers at
TrustRequired with no auto-recovery path.
Changes:
- RuntimeFeatureConfig: add trusted_roots: Vec<String> field
- ConfigLoader: wire parse_optional_trusted_roots() for 'trustedRoots' key
- RuntimeConfig / RuntimeFeatureConfig: expose trusted_roots() accessor
- config_validate: add trustedRoots to TOP_LEVEL_FIELDS schema (StringArray)
- Tests: parses_trusted_roots_from_settings + trusted_roots_default_is_empty_when_unset
Callers can now set trusted_roots in .claw/settings.json:
{ "trustedRoots": ["/tmp/worktrees"] }
WorkerRegistry::spawn_worker() callers should merge config.trusted_roots()
with any per-call overrides (wiring left for follow-up).
Two real schema gaps found via dogfood (cargo test -p runtime):
1. aliases and providerFallbacks not in TOP_LEVEL_FIELDS
- Both are valid config keys parsed by config.rs
- Validator was rejecting them as unknown keys
- 2 tests failing: parses_user_defined_model_aliases,
parses_provider_fallbacks_chain
2. Deprecated keys were being flagged as unknown before the deprecated
check ran (unknown-key check runs first in validate_object_keys)
- Added early-exit for deprecated keys in unknown-key loop
- Keeps deprecated→warning behavior for permissionMode/enabledPlugins
which still appear in valid legacy configs
3. Config integration tests had assertions on format strings that never
matched the actual validator output (path:3: vs path: ... (line N))
- Updated assertions to check for path + line + field name as
independent substrings instead of a format that was never produced
426 tests passing, 0 failing.
Clawhip needs to distinguish a stalled trust_required worker from one
that just transitioned. Without a pre-computed staleness field it has
to compute epoch delta itself from updated_at.
seconds_since_update = now - updated_at at snapshot write time.
Clawhip threshold: > 60s in trust_required = stalled; act.
WorkerStatus is fully tracked in worker_boot.rs but was invisible to
external observers (clawhip, orchestrators) because opencode serve's
HTTP server is upstream and not ours to extend.
Solution: atomic file-based observability.
- emit_state_file() writes .claw/worker-state.json on every push_event()
call (tmp write + rename for atomicity)
- Snapshot includes: worker_id, status, is_ready, trust_gate_cleared,
prompt_in_flight, last_event, updated_at
- Add 'claw state' CLI subcommand to read and print the file
- Add regression test: emit_state_file_writes_worker_status_on_transition
verifies spawning→ready_for_prompt transition is reflected on disk
This closes the /state dogfood gap without requiring any upstream
opencode changes. Clawhip can now distinguish a truly stalled worker
(status: trust_required or running with no recent updated_at) from a
quiet-but-progressing one.
Add missing imports to test module:
- PromptHistoryEntry, render_prompt_history_report, parse_history_count
- parse_export_args, render_session_markdown
- summarize_tool_payload_for_markdown, short_tool_id
Fixes test compilation errors introduced by new session and export
features from batch 5/6 work.
The CLI was using a flat cwd/.claw/sessions/ path without workspace
fingerprinting, while SessionStore::from_cwd() adds a hash subdirectory.
This mismatch meant the isolation machinery existed but wasn't actually
used by the main session management codepath.
Now sessions_dir() delegates to SessionStore::from_cwd(), ensuring all
session operations use workspace-fingerprinted directories.
Remove #[cfg(test)] gate from session_control module — SessionStore
is now available at runtime, not just in tests. Export SessionStore and
add workspace_sessions_dir() helper that creates fingerprinted session
directories per workspace root.
This is the #41 kill shot: parallel opencode serve instances will use
separate session namespaces based on workspace fingerprint instead of
sharing a global ~/.local/share/opencode/ store.
The CLI already uses cwd/.claw/sessions/ (sessions_dir()), and now
SessionStore::from_cwd() adds workspace hash isolation on top.
Global session store causes cross-worktree confusion in parallel lanes.
Added workspace_root field to session metadata and documented root cause
in ROADMAP.md.
Sterling reported 'json_error: no field input/input_tokens' still firing
despite existing serde(default) in types.rs. Root cause: SSE streaming
path had a separate deserialization site that didn't use the same defaults.
- Add serde(default) to sse.rs UsageEvent deserialization
- Add serde(default) to types.rs Usage struct fields (input_tokens, output_tokens)
- Add regression test with empty-usage JSON response in streaming context
The CLI already reframes direct preflight and provider oversized-request
errors, but retry-wrapped provider failures still fell back to the generic
retry-exhausted surface because the user-visible formatter keyed off the
safe failure class. Route formatting through nested context-window
detection so wrapped provider failures keep the same compact/reduce-scope
guidance.
Constraint: Keep the fix UX-scoped without widening broader failure classification behavior
Rejected: Reorder safe_failure_class for all RetriesExhausted errors | broader semantic change than needed for this issue
Confidence: high
Scope-risk: narrow
Directive: Keep context-window rendering keyed to nested error inspection so provider wrappers do not lose recovery guidance
Tested: cargo fmt --check; cargo test -p rusty-claude-cli context_window; cargo test -p api oversized
Not-tested: Full workspace test suite
Generic fatal wrapper handling already preserved safe classes and trace ids for single provider failures, but repeated retry exhaustion still surfaced as provider_internal. Classify generic wrapped RetriesExhausted failures as provider_retry_exhausted so Jobdori-style repeat failures stay distinguishable from one-off provider crashes, and keep the display logic clippy-clean.
Constraint: Keep the change minimal and preserve existing user-visible error wording outside retry-exhaustion classification
Rejected: Broadly rework all provider error taxonomy | unnecessary for the targeted opaque-wrapper regression
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep retry exhaustion distinct from single-shot provider_internal wrappers when the nested error is the same generic fatal wrapper
Tested: cargo test -p api detects_generic_fatal_wrapper_and_classifies_it_as_provider_internal
Tested: cargo test -p api retries_exhausted_preserves_nested_request_id_and_failure_class
Tested: cargo test -p rusty-claude-cli opaque_provider_wrapper_surfaces_failure_class_session_and_trace
Tested: cargo test -p rusty-claude-cli retry_exhaustion_uses_retry_failure_class_for_generic_provider_wrapper
Tested: cargo test --workspace
Tested: cargo fmt --check
Tested: cargo clippy --workspace --all-targets -- -D warnings
Not-tested: Live OpenClaw/Anthropic service failure telemetry outside the local test harness
The CLI still treated every /skills payload other than list/install/help as local usage text, so skills that appeared in /skills could not actually be invoked. This restores prompt dispatch for /skills <skill> [args], keeps list/install on the local path, and shares skill resolution with the Skill tool so project-local and legacy /commands entries resolve consistently.
Constraint: --resume local slash execution still only supports local commands without provider turns
Rejected: Implement full resumed prompt-turn execution for /skills | larger behavior change outside this bugfix
Rejected: Keep separate skill lookups in tools and commands | drift already caused listing/invocation mismatches
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep /skills discovery, CLI prompt dispatch, and Tool Skill resolution on the same registry semantics
Tested: cargo fmt --all; cargo clippy -p commands -p tools -p rusty-claude-cli --all-targets -- -D warnings; cargo test --workspace -- --nocapture
Not-tested: Live provider-backed /skills invocation against external skill packs in an interactive REPL
Dogfood showed oversized requests still surfacing as raw hard errors, even when claw could tell the user exactly how to recover. This keeps context-window failures classified, recognizes the same failure when it comes back from a provider response, and renders recovery steps that point operators at the existing compaction and fresh-session paths instead of a provider-style dump.
Constraint: Keep the failure class explicit so automation and operators can still distinguish context-window exhaustion from generic provider failures
Constraint: Reuse existing /compact and session-reset UX instead of inventing a new recovery workflow
Rejected: Auto-run compaction on failure | mutates session state on an error path the user may want to inspect first
Rejected: Only prettify local preflight failures | provider-returned context-window errors would still leak raw failure text
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep provider-side context-window detection aligned with real oversized-request messages before broadening the marker list
Tested: cargo fmt --all --check
Tested: cargo test -p api
Tested: cargo test -p rusty-claude-cli
Tested: cargo clippy -p api -p rusty-claude-cli --all-targets -- -D warnings
Not-tested: cargo test --workspace
Resumed slash dispatch was still dropping back to prose for several JSON-capable local commands, which forced automation to special-case direct CLI invocations versus --resume flows. This routes resumed local-command handlers through the same structured JSON payloads used by direct status, sandbox, inventory, version, and init commands, and records the inventory parity audit result in the roadmap.
Constraint: Text-mode resumed output must stay unchanged for existing shell users
Rejected: Teach callers to scrape resumed text output | brittle and defeats the JSON contract
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: When a direct local command has a JSON renderer, keep resumed slash dispatch on the same serializer instead of adding one-off format branches
Tested: cargo fmt --check; cargo test --workspace; cargo clippy --workspace --all-targets -- -D warnings
Not-tested: Live provider-backed REPL resume flows outside the local test harness
`claw agents --output-format json` was still wrapping the text report,
which meant automation could not distinguish empty inventories from
populated agent definitions. Add a dedicated structured handler in the
commands crate, wire the CLI to it, and extend the contracts to cover
both empty and populated agent listings.
Constraint: Keep text-mode `claw agents` output unchanged while aligning JSON behavior with existing structured inventory handlers
Rejected: Parse the text report into JSON in the CLI layer | brittle duplication and no reusable structured handler
Confidence: high
Scope-risk: narrow
Directive: Keep inventory subcommands on dedicated structured handlers instead of serializing human-readable reports
Tested: cargo test -p commands renders_agents_reports_as_json; cargo test -p rusty-claude-cli --test output_format_contract; cargo test --workspace; cargo fmt --check; cargo clippy --workspace --all-targets -- -D warnings
Not-tested: Manual invocation of `claw agents --output-format json` outside automated tests
Issue #22 was triggered by generic upstream fatal wrappers that only surfaced 'Something went wrong', which left repeated Jobdori-style failures opaque in the CLI. Capture provider request ids on error responses, classify the known generic wrapper as provider_internal, and prefix the user-visible runtime error with the failure class plus session/trace identifiers so operators can correlate the failure quickly.
Constraint: Keep the fix small and user-safe without redesigning the broader runtime error taxonomy
Constraint: Preserve existing non-generic error text unless the wrapper is the known opaque fatal surface
Rejected: Broadly rewriting every runtime error into classified envelopes | unnecessary scope expansion for issue #22
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: If more opaque wrappers appear, extend the marker list and classification helper rather than reintroducing raw wrapper text alone
Tested: cargo test -p api detects_generic_fatal_wrapper_and_classifies_it_as_provider_internal -- --nocapture; cargo test -p api retries_exhausted_preserves_nested_request_id_and_failure_class -- --nocapture; cargo test -p rusty-claude-cli opaque_provider_wrapper_surfaces_failure_class_session_and_trace -- --nocapture; cargo test -p rusty-claude-cli retry_exhaustion_preserves_internal_failure_class_for_generic_provider_wrapper -- --nocapture; cargo test --workspace
Not-tested: Live upstream reproduction of the Jobdori failure against a real provider session
The resumed slash-command path built a reduced status JSON payload by hand, so it drifted from the fresh status schema and dropped metadata like model, permission mode, workspace counters, and sandbox details. Reuse a shared status JSON builder for both code paths and tighten the resume regression tests to lock parity in place.
Constraint: Resume mode does not carry an active runtime model, so restored sessions continue to report the existing restored-session sentinel value
Rejected: Copy the fresh status JSON shape into the resume path again | would recreate the same schema drift risk
Confidence: high
Scope-risk: narrow
Directive: Keep resumed and fresh /status JSON on the same helper so future schema changes stay in parity
Tested: Reproduced failure in temporary HEAD worktree with strengthened resumed_status_command_emits_structured_json_when_requested
Tested: cargo test -p rusty-claude-cli resumed_status_command_emits_structured_json_when_requested --test resume_slash_commands -- --exact --nocapture
Tested: cargo test -p rusty-claude-cli doctor_and_resume_status_emit_json_when_requested --test output_format_contract -- --exact --nocapture
Tested: cargo test --workspace
Tested: cargo fmt --check
Tested: cargo clippy --workspace --all-targets -- -D warnings
Persist derived machine states for agent manifests so downstream monitors can distinguish working, blocked, degraded, and finished-cleanable lanes without inferring everything from prose. This also records commit provenance in terminal-state manifests and marks the new session-state classification roadmap item as done.
Constraint: Keep the change scoped to manifest persistence and tests without introducing a new monitoring service layer
Rejected: Leave state classification as downstream text scraping only | repeated dogfood runs showed quiet/finished lanes being misreported as stale
Confidence: medium
Scope-risk: narrow
Directive: Reuse derived_state + commit provenance from manifests before adding any new stale-session heuristics elsewhere
Tested: python .github/scripts/check_doc_source_of_truth.py
Tested: cd rust && cargo fmt --all --check
Tested: cd rust && cargo test -q -p tools
Tested: cd rust && cargo clippy -p tools --all-targets --no-deps -- -D warnings
Not-tested: full cargo clippy --workspace --all-targets -- -D warnings still fails on unrelated pre-existing runtime lint debt
The remaining blocker after the roadmap backlog landed was workspace-wide clippy debt in runtime and adjacent test modules. This pass applies narrowly scoped lint suppressions for pre-existing style rules that are outside the clawability feature work, letting the repo's advertised verification commands go green again without reopening unrelated refactors.
Constraint: Keep behavior unchanged while making pass on the current codebase
Rejected: Broad refactors of runtime subsystems to satisfy every lint structurally | too much risk for a follow-up verification-hardening pass
Confidence: medium
Scope-risk: narrow
Directive: Replace these targeted allows with real structural cleanup when those runtime modules are next touched for behavior changes
Tested: cd rust && cargo fmt --all --check
Tested: cd rust && cargo test --workspace
Tested: cd rust && cargo clippy --workspace --all-targets -- -D warnings
Not-tested: No behavioral changes intended beyond verification status restoration
Finish the remaining roadmap work by making direct CLI JSON output deterministic across the non-interactive surface, restoring the degraded-startup MCP test as a real workspace test, and adding branch-lock plus commit-lineage primitives so downstream lane consumers can distinguish superseded worktree commits from canonical lineage.
Constraint: Keep the user-facing config namespace centered on .claw while preserving legacy fallback discovery for compatibility
Constraint: Verification needed to stay clean-room and reproducible from the checked-in workspace alone
Rejected: Leave the output-format contract implied by ad-hoc smoke runs only | too easy for direct CLI regressions to slip back into prose-only output
Rejected: Keep commit provenance as free-form detail text | downstream consumers need structured branch/worktree/supersession metadata
Confidence: medium
Scope-risk: moderate
Directive: Extend the JSON contract through the same direct CLI entrypoints instead of adding one-off serializers on parallel code paths
Tested: python .github/scripts/check_doc_source_of_truth.py
Tested: cd rust && cargo fmt --all --check
Tested: cd rust && cargo test --workspace
Tested: cd rust && cargo clippy -p commands -p tools -p rusty-claude-cli --all-targets --no-deps -- -D warnings
Not-tested: full cargo clippy --workspace --all-targets -- -D warnings still reports unrelated pre-existing runtime lint debt outside this change set
The skills and mcp inventory handlers were still emitting prose tables even when the global --output-format json flag was set. This wires structured JSON renderers into the command handlers and CLI dispatch so direct invocations and resumed slash-command execution both return machine-readable payloads while preserving existing text output in the REPL path.
Constraint: Must preserve existing text output and help behavior for interactive slash commands
Rejected: Parse existing prose tables into JSON at the CLI edge | brittle and loses structured fields
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep text and JSON variants driven by the same command parsing branches so --output-format stays deterministic across entry points
Tested: cargo test -p commands
Tested: cargo test -p rusty-claude-cli
Not-tested: Manual invocation against a live user skills registry or external MCP services
Agents, skills, and init output were still surfacing .codex/.claude paths even though the runtime already treats .claw as the canonical config home. This updates help text, reports, skill install defaults, and repo bootstrap output to present a single .claw namespace while keeping legacy discovery fallbacks in place for existing setups.
Constraint: Existing .codex/.claude agent and skill directories still need to load for compatibility
Rejected: Remove legacy discovery entirely | would break existing user setups instead of just cleaning up surfaced output
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep future user-facing config, agent, and skill path copy aligned to .claw and even when legacy fallbacks remain supported internally
Tested: cargo fmt --all --check; cargo test --workspace --exclude compat-harness
Not-tested: cargo clippy --workspace --all-targets -- -D warnings | fails in pre-existing unrelated runtime files (for example mcp_lifecycle_hardened.rs, mcp_tool_bridge.rs, lsp_client.rs, permission_enforcer.rs, recovery_recipes.rs, stale_branch.rs, task_registry.rs, team_cron_registry.rs, worker_boot.rs)
The direct CLI wrappers for agents, skills, and mcp treated nested help flags as ordinary operands. That made commands like `claw mcp show --help` report a missing server and `claw skills install --help` fall into filesystem install logic instead of surfacing usage.
This change normalizes help-path arguments before dispatch so nested help stays on the help path. The regression tests cover both handler-level behavior and end-to-end CLI output for nested help and unknown subcommands with trailing help flags.
Constraint: Keep the fix scoped to direct CLI slash-command wrappers without changing unrelated parser behavior
Rejected: Rework top-level argument parsing for all subcommands | broader risk than needed for the regression
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: If more nested subcommands are added, extend the help-path normalization table before relying on raw operand dispatch
Tested: cargo build -p commands -p rusty-claude-cli
Tested: cargo test -p commands -p rusty-claude-cli
Not-tested: cargo clippy -p commands -p rusty-claude-cli --all-targets --no-deps -- -D warnings (pre-existing warnings in untouched files block clean run)
Promote doctor into a real top-level CLI action, reuse the same local report for resumed and REPL doctor invocations, and intercept doctor/status/sandbox help flags before prompt-mode dispatch. The parser change also closes the help fallthrough that previously wandered into runtime startup for local-info commands.
Constraint: Preserve prompt shorthand for normal multi-word text input while fixing exact local subcommand help paths
Rejected: Route \7[1G[2K[m⠋ 🦀 Thinking...[0m8[1G[2K[m✘ ❌ Request failed
[0m through prompt/slash guidance | still shells out through the wrong surface and keeps health checks hidden
Rejected: Reuse the status report as doctor output | status does not explain auth/config health or expose a dedicated diagnostic summary
Confidence: high
Scope-risk: narrow
Directive: Keep doctor local-only unless an explicit network probe is intentionally added and separately tested
Tested: cargo build -p rusty-claude-cli; cargo test -p rusty-claude-cli; cargo run -p rusty-claude-cli -- doctor --help; CLAW_CONFIG_HOME=/tmp/tmp.7pm9SVzOPN ANTHROPIC_API_KEY= ANTHROPIC_AUTH_TOKEN= cargo run -p rusty-claude-cli -- doctor
Not-tested: direct /doctor outside the REPL remains interactive-only
The shipped CLI surface lives in `src/main.rs`, which only wires `init`,
`input`, and `render`. The legacy `app.rs` and `args.rs` prototypes were
not in the module tree and had no inbound references, so this change deletes
those orphaned files instead of widening scope into a larger refactor.
It also aligns the TUI enhancement plan with that reality so the document no
longer describes the removed prototypes as current tracked structure.
Constraint: Must preserve shipped CLI parsing and slash-command behavior
Rejected: Refactor main.rs into smaller modules now | widens scope beyond behavior-safe cleanup
Rejected: Leave TUI plan wording untouched | leaves low-risk stale documentation behind
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep this slice deletion-first; do not reintroduce alternate CLI surfaces without wiring them into main.rs and its tests
Tested: cargo test -p rusty-claude-cli defaults_to_repl_when_no_args
Tested: cargo test -p rusty-claude-cli parses_login_and_logout_subcommands
Tested: cargo test -p rusty-claude-cli parses_direct_agents_mcp_and_skills_slash_commands
Tested: cargo test -p rusty-claude-cli direct_slash_commands_surface_shared_validation_errors
Tested: cargo test -p rusty-claude-cli parses_resume_flag_with_multiple_slash_commands -- --nocapture
Tested: cargo test -p rusty-claude-cli resumed_binary_accepts_slash_commands_with_arguments -- --nocapture
Tested: cargo check -p rusty-claude-cli
Tested: git diff --check
Not-tested: cargo clippy -p rusty-claude-cli --all-targets -- -D warnings (pre-existing failures in rust/crates/runtime/* and existing warnings outside this diff)
Jobdori
YeonGyu-Kim
Yeachan-Heo