Commit Graph

877 Commits

Author SHA1 Message Date
YeonGyu-Kim
dedad14ae4 fix(#706): skills show <name> returns error+exit1 when skill not found; classify_error_kind covers skill_not_found from prose message 2026-05-26 00:04:39 +09:00
YeonGyu-Kim
f84799c8ef fix: auto_compact runs before every iteration break, including terminal no-tool turns; closes #3106 2026-05-25 23:59:04 +09:00
YeonGyu-Kim
732007da8e fix(#705): add estimated_cost_usd_num (float) to usage JSON alongside string field; doc entry filed 2026-05-25 23:33:14 +09:00
YeonGyu-Kim
8f809d9a9e fix(#704): DiagnosticCheck.json_value now emits stable snake_case id field; doctor checks addressable without scraping name prose 2026-05-25 23:04:06 +09:00
YeonGyu-Kim
1a6f54b970 fix(#703): plugins list JSON now has summary:{total,enabled,disabled,load_failures}; drop reload_runtime/target from list response in both top-level and resume paths 2026-05-25 22:34:20 +09:00
YeonGyu-Kim
1555785294 Merge pull request #3104 from Yeachan-Heo/fix/issue-702-allowed-tools-ci
Stabilize allowedTools rejection contract in CI
2026-05-25 22:03:40 +09:00
YeonGyu-Kim
2f9429cbf0 fix: slash-command guard errors now emit error_kind:interactive_only instead of unknown; covers memory, permissions, review, and any bare_slash_command_guidance path 2026-05-25 22:02:30 +09:00
Yeachan-Heo
4daefc7bd5 Stabilize allowedTools rejection contract in CI
Serialize the allowedTools rejection tests with the existing environment/current-directory test guards so full parallel cargo test runs cannot observe a transient project config or cwd from another test while building the tool registry.\n\nConstraint: Post-merge Rust build workflow run 26399647443 failed only in the full cargo test job while the focused test passed locally.\nRejected: Changing allowedTools parser output | the product contract remains correct and focused reproduction preserves the expected unsupported-tool error.\nConfidence: high\nScope-risk: narrow\nDirective: Keep this as test isolation only; do not bundle inventory provenance or ROADMAP work into this follow-up.\nTested: cargo test --manifest-path rust/Cargo.toml -p rusty-claude-cli tests::rejects_unknown_allowed_tools -- --exact --nocapture; cargo test --verbose -p rusty-claude-cli --bin claw; cargo test --verbose; cargo fmt --check; cargo check --workspace --locked; cargo build --workspace --locked\nNot-tested: GitHub Actions rerun before opening PR
2026-05-25 12:55:53 +00:00
YeonGyu-Kim
5bca9ef039 Merge pull request #3103 from Yeachan-Heo/fix/issue-702-inventory-provenance
Fix #702 inventory provenance schema
2026-05-25 21:10:18 +09:00
YeonGyu-Kim
b8eca2a68e fix(#349): plugins unknown action emits status:error + error_kind:unknown_plugins_action + exit 1 instead of status:ok with prose 2026-05-25 21:08:14 +09:00
Yeachan-Heo
566992c331 Unify inventory provenance for generic parsers
Expose a stable source object on agent and skill inventory entries with the same id/label/detail_label keys while preserving skill origin for compatibility.\n\nConstraint: ROADMAP #702 scope only; keep existing skills origin field for compatibility.\nRejected: Rename agent source to origin | would break existing agents consumers and still require per-resource branching during migration.\nConfidence: high\nScope-risk: narrow\nDirective: Future inventory resources should expose provenance through source.id, source.label, and source.detail_label.\nTested: cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo test --manifest-path rust/Cargo.toml -p commands renders_skills_reports_as_json -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p rusty-claude-cli --test output_format_contract -- --nocapture; cargo build --manifest-path rust/Cargo.toml --workspace --locked; git diff --check\nNot-tested: full cargo test --manifest-path rust/Cargo.toml --workspace
2026-05-25 12:05:50 +00:00
YeonGyu-Kim
36b36267ec fix(#458): add status:ok to config JSON envelope; unknown section now emits status:error + error_kind:unsupported_config_section 2026-05-25 20:33:36 +09:00
YeonGyu-Kim
ee24ff2d83 Merge pull request #3102 from Yeachan-Heo/fix/issue-696-compact-nontty
Fix compact non-TTY hang
2026-05-25 19:41:27 +09:00
Yeachan-Heo
9e6f753640 Fail closed for compact without an interactive session
Route bare compact invocations to a typed interactive-only error before prompt/provider startup so non-TTY JSON probes terminate predictably. Keep the existing resume-session /compact path as the supported automation surface.\n\nConstraint: ROADMAP pinpoint #696 requires no spinner/hang for closed stdin and --output-format json.\nRejected: Broad help-schema rewrites | #699/#700/#701 are outside this PR scope.\nConfidence: high\nScope-risk: narrow\nDirective: Do not route bare slash-command names through the prompt fallback when they require a session.\nTested: cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo test --manifest-path rust/Cargo.toml -p rusty-claude-cli --test compact_output compact_subcommand_ -- --nocapture; cargo build --manifest-path rust/Cargo.toml --workspace; cargo build --manifest-path rust/Cargo.toml --workspace --locked; timeout probes for compact JSON/text with stdin closed.\nNot-tested: Full workspace test suite.
2026-05-25 10:37:12 +00:00
YeonGyu-Kim
de2e32c5d4 fix: skills install nonexistent path emits skill_not_found error kind with descriptive message; classify_error_kind adds skill_not_found branch 2026-05-25 19:34:25 +09:00
YeonGyu-Kim
9d1998b3fd test(#458/#700/#701/#702): add status:ok assertions for help/bootstrap-plan/export-help contracts; add diff/export JSON shape tests 2026-05-25 19:07:03 +09:00
YeonGyu-Kim
181b12f0a9 fix: mcp show <nonexistent> now returns status:error + error_kind:server_not_found + exit 1; extend ok:false gate to also check status:error 2026-05-25 18:34:43 +09:00
YeonGyu-Kim
47521cf178 fix(#701): add detail_entries structured key/value to doctor check JSON; booleans/ints emitted as JSON scalars 2026-05-25 18:02:03 +09:00
YeonGyu-Kim
f9e98a2634 fix(#700): add status:ok to all help JSON envelopes; rename session_list kind to sessions with action:list 2026-05-25 17:05:28 +09:00
YeonGyu-Kim
eb7c14c4ae fix(#458): add status:ok to bootstrap-plan JSON envelope; all 12 JSON surfaces now have uniform status field 2026-05-25 16:34:33 +09:00
YeonGyu-Kim
11a6e081a2 fix(#458): add status field to export and diff JSON envelopes 2026-05-25 16:07:16 +09:00
Bellman
16604a111b fix(#458): add status assertions to skills/agents JSON envelope tests
Adds test coverage asserting status:ok in skills list, agents list, skills install, skills help, and agents help JSON envelopes. Status fields themselves were already landed in 0581894b and cc1462a7; this PR adds the regression test assertions that were missing. Duplicate status keys in json! macros are benign (serde_json takes last value) but harmless given all tests pass.
2026-05-25 15:35:40 +09:00
YeonGyu-Kim
cc1462a7f8 fix(#458): add status:ok to skills install JSON envelope (missed in previous sweep) 2026-05-25 15:30:22 +09:00
YeonGyu-Kim
f2a90228fb fix: doctor boot preflight detail shows Some(false) for trust_gate_allowed; use Display instead of Debug 2026-05-25 15:21:15 +09:00
YeonGyu-Kim
0581894b7e fix(#458): add status:ok to agents and skills list JSON envelopes; all 9 subcommands now pass uniform status check 2026-05-25 15:02:25 +09:00
YeonGyu-Kim
5b79413e87 fix(#458): add status field to version/init/system-prompt JSON envelopes; all 9 subcommands now have uniform status field 2026-05-25 14:36:12 +09:00
YeonGyu-Kim
85e736c73f fix: add status field to sandbox JSON envelope (ok/warn/error derived from enabled+active+supported) 2026-05-25 14:34:00 +09:00
YeonGyu-Kim
b64df99134 fix(#698): dedup config deprecation warnings per process; add tempfile dev-dep to runtime crate (fixes pre-existing test compile error) 2026-05-25 14:11:37 +09:00
YeonGyu-Kim
c345ce6d02 fix: mcp/agents/skills help envelopes set ok:false + status:error on unknown subcommand; exit 1 propagates correctly 2026-05-25 13:50:51 +09:00
YeonGyu-Kim
91a0681ae9 fix(#697): agents unknown subcommand exits 1 with typed error; plugins remove aliases uninstall and errors on not-found 2026-05-25 13:39:23 +09:00
Yeachan-Heo
c613e8e676 feat: sweep 2026-05-25 04:36:30 +00:00
YeonGyu-Kim
63a5a87471 fix(#696): exit with typed error when stdin is not a TTY and no prompt piped; fix anthropic/ prefix detection in metadata_for_model 2026-05-25 13:16:12 +09:00
YeonGyu-Kim
78a0ff615a Merge pull request #3014 from wangguan1995/fix_qwen
Add Qwen model token limits for DashScope compatibility
2026-05-25 12:58:59 +09:00
YeonGyu-Kim
60108dfbf6 fix(test): update client_integration version string 0.1.0 -> 0.1.3 2026-05-25 12:49:37 +09:00
Yeachan-Heo
bd9102f851 fix(api): skip preflight for unknown model limits 2026-05-25 12:49:37 +09:00
YeonGyu-Kim
e7d5d08892 fix: ChunkDelta thinking field in test initializers; fix parse_local_help_action ? operator 2026-05-25 12:49:37 +09:00
YeonGyu-Kim
f003a108e3 fix: remove stale retry_after refs from openai_compat.rs 2026-05-25 12:49:37 +09:00
YeonGyu-Kim
a76dda2b19 chore: cargo fmt --all on fix-683 branch 2026-05-25 12:49:37 +09:00
YeonGyu-Kim
013694476e chore: sync Cargo.lock and openai_compat.rs to main (stash artifact cleanup) 2026-05-25 12:49:37 +09:00
YeonGyu-Kim
3d02baf567 fix(#683): claw skills remove/add/uninstall/delete emits typed error, exit 1
- Add unsupported skills action guard in parse_args for remove/add/uninstall/delete
- Add unsupported_skills_action to classify_error_kind for structured JSON errors
- Fix pre-existing compile errors (stale retry_after field, missing Team variant)
- Add regression test unsupported_skills_actions_return_typed_error_683
2026-05-25 12:49:37 +09:00
YeonGyu-Kim
0423321cb1 fix(test): update compact test to reflect flattened previous-context header 2026-05-25 12:49:34 +09:00
YeonGyu-Kim
06c126ab6b fix(claw-analog): reject backslash paths in validate_rel_path (dotdot bypass on Linux) 2026-05-25 12:41:32 +09:00
YeonGyu-Kim
1f572ff8de fix: add missing config_load_error_kind to test StatusContext initializers; remove stale retry_after refs again 2026-05-25 12:15:57 +09:00
YeonGyu-Kim
03bd461984 fix: ChunkDelta thinking field in tests, remove residual retry_after refs, fix parse_local_help_action return type 2026-05-25 12:09:29 +09:00
YeonGyu-Kim
495e7a015c fix: remove stale retry_after field, Team variant, config_load_error_kind, denied_tools initializer errors
- Remove retry_after: None from ApiError::Api structs in openai_compat.rs (field was removed)
- Remove SlashCommand::Team parse arm (variant was removed from enum)
- Add config_load_error_kind: None to doctor path StatusContext initializer
- Add Thinking arm to all ContentBlock match blocks in trident.rs
- Remove cargo fmt drift across commands, config, compact, tools, trident
2026-05-25 12:01:09 +09:00
YeonGyu-Kim
3364dc4bee chore: fix conflict markers and cargo fmt drift in main (commands, openai_compat, trident, config, tools) 2026-05-25 11:51:44 +09:00
OrbisAI Security
c8b44878c5 fix: CVE-2021-29937 security vulnerability (#3056)
Automated dependency upgrade by OrbisAI Security
2026-05-25 11:27:08 +09:00
gismo212
ae30bf4f04 feat(analog): add claw-analog minimal harness
Adds claw-analog minimal harness for lean, predictable tool execution.
2026-05-25 11:25:28 +09:00
gismo212
a4efdc43d7 feat(rag): add claw-rag-service
Adds claw-rag-service for repository indexing and semantic search.
2026-05-25 11:25:25 +09:00
TheArchitectit
b43a6f2d29 feat: auto-compact and retry on context window errors
Adds automatic compaction and retry when context window is exceeded.
2026-05-25 11:24:44 +09:00