Addresses chatgpt-codex review: the previous full serde_json::to_string
included internal-only fields (allowed_callers, defer_loading,
input_examples, cache_control) that are never sent to the chat API.
This caused spurious drift detection when those fields changed.
- New tool_to_api_json() helper mirrors tool_to_chat() serialization:
only type, name, description, parameters, strict
- Doc comment fixed: 'sorted by name' → 'sorted lexicographically
by JSON text' (greptile review)
Phase 1.5 — upgrade PrefixFingerprint::compute() to hash the full tool
JSON serialization (name + description + schema) instead of just tool
names. This catches schema/description drift in addition to name changes.
- Serialize each tool via serde_json::to_string, sort by name, join
- New test: fingerprint_detects_schema_change_not_just_name_change
- All 21 prefix_cache tests pass
- Aligned with prompt_zones.rs tool_catalog_digest approach
Treat a missing tui.status_items field as None even when the [tui]
table exists, preserving the documented default footer behavior.
Add a regression test for configs that define [tui] without status_items.
with_agent_tools() unconditionally registered web_search/fetch_url/web.run
(via with_web_tools) and apply_patch (via with_patch_tools), but tool_setup.rs
conditionally registered them again based on Feature::WebSearch and
Feature::ApplyPatch flags. This caused double registration (overwritten
with a warning log on the second insert).
Changes:
- Remove with_web_tools() and with_patch_tools() from with_agent_tools()
- Move finance tool out of with_web_tools() into its own with_finance_tool()
(finance is market data, not web search — it should not be gated behind
the web-search feature flag)
- Add with_finance_tool() to with_agent_tools() so finance stays always
available
- Update tests: new test for with_finance_tool(), updated web_tools test
to verify finance is no longer in the web group
- Fix false 'Turn stalled' during long active turns with running tools.
Add turn_last_activity_at tracking and active-tool awareness to
reconcile_turn_liveness(). Three new tests cover the fix.
- Remove Qwen 3.7 Max OpenRouter preset from registry, picker, docs,
and tests. Qwen 3.7 Max is a hosted model; the preset will return
when an open-weight Qwen 3.7 release ships. MiniMax M3 remains as
a full 1M-context multimodal route.
- Sync root CHANGELOG to crates/tui/CHANGELOG for crates.io packaging.
Update docs/CONFIGURATION.md, docs/PROVIDERS.md, and README to
reflect the Qwen 3.7 removal. Regenerate web facts timestamp.
All dead_code in prompt_zones.rs is intentional — these types are
scaffolding awaiting future integration. Pre-existing schema_migration
warnings remain as-is.
Narrower slice per Hmbown's review: typed zone structs as foundation
without wiring into the request path. Future phases will integrate
AppendLog/TurnScratch/ThreeZoneRequest into turn_loop.
- prompt_zones.rs (663 lines, 16 tests): PinnedPrefix / FrozenPrefix /
PrefixDrift (ready), AppendLog / TurnScratch / ThreeZoneRequest
(scaffolding, #[allow(dead_code)])
- FrozenPrefix: full tool JSON hash (name+desc+schema), raw-text
fast-path in verify(), cache_control preserved in build_messages()
- /cache zones subcommand with three-zone status display
- merge_compaction_summary: zone affiliation doc comment
- No turn_loop/session changes — engine continues using
PrefixStabilityManager / MessageRequest as before
Clear stale busy state and retry/title animations on local cancel.\n\nLocal verification:\n- cargo test -p codewhale-tui\n- codewhale doctor\n- codewhale --provider deepseek --model deepseek-v4-pro exec "Reply with exactly: OK"
* fix(web_search): add timeout floor and retry for Volcengine provider
Volcengine's Responses API pipeline (web search + model inference +
JSON generation) can exceed the default 15 s timeout on complex
queries, causing ~50% of requests to fail with transport errors.
Changes:
- Enforce a 60 s minimum timeout for the Volcengine provider
- Separate connect_timeout (15 s) from total request timeout
- Retry transient transport errors up to 3 times (1 s / 2 s backoff)
- Add TCP keepalive, HTTP/2 keepalive, and User-Agent headers
matching the patterns used in client.rs
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix: raise Volcengine timeout floor to 90 s
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix: correct stale comment — floor is 90 s, not 60 s
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(web_search): tighten Volcengine retry semantics
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Hunter B <hmbown@gmail.com>
* refactor(palette): remove unused backward-compat aliases and add module docs
- Remove DEEPSEEK_AQUA_RGB, DEEPSEEK_NAVY_RGB, DEEPSEEK_AQUA, DEEPSEEK_NAVY
(unused backward-compatible aliases with no references in production code)
- Add module-level doc comment explaining the three-layer palette organization:
RGB tuples, semantic Color constants, and backward-compat aliases
- Note that some constants are kept for design-system completeness
* fix: remove deprecated color audit test (DEEPSEEK_AQUA no longer exists)
* fix: remove unused import in palette_audit test
---------
Co-authored-by: Hu Qiantao <huqiantao@HudeMacBook-Air.local>
* fix: use effective_model_for_budget instead of raw model in compaction_config
When model is set to 'auto', self.model holds the literal string 'auto',
which gets passed to the API as the model name in compaction requests.
DeepSeek's API rejects 'auto' with HTTP 400 since it's not a recognized
model ID.
effective_model_for_budget() resolves 'auto' to the last effective model
or falls back to DEFAULT_TEXT_MODEL, ensuring compaction always sends a
concrete model name.
* test(tui): cover auto model compaction config
---------
Co-authored-by: codgo <anbiaoren@gie777.com>
Co-authored-by: Hunter B <hmbown@gmail.com>
Prevent inline skill slash completions from opening while editing arguments for an existing slash command.
This keeps `/attach /path/to/image.png` usable without showing skill entries after the path slash, while
preserving inline skill completions in normal message text.
Adds a regression test for `/attach /`.
Hardens the tool override path from #2420 so a broken replacement override cannot silently fall through to the original built-in tool.
Validation:
- git diff --check
- CARGO_TARGET_DIR=/Volumes/VIXinSSD/codewhale-target/fix-plugin-override cargo test -p codewhale-tui tools::registry --all-features
- CARGO_TARGET_DIR=/Volumes/VIXinSSD/codewhale-target/fix-plugin-override cargo test -p codewhale-tui tools::plugin --all-features
Add Volcengine (火山引擎) as a new SearchProvider in web_search tool.
Uses Volcengine's Responses API with `tools: [{type: "web_search"}]`
and strict JSON prompt constraints to extract structured search results.
- Free tier: 20K queries/month per API key
- API key resolution: [search] api_key → VOLCENGINE_API_KEY →
VOLCENGINE_ARK_API_KEY → ARK_API_KEY env vars
- Select via `DEEPSEEK_SEARCH_PROVIDER=volcengine` or
`[search] provider = "volcengine"` in config.toml
Co-authored-by: Cursor <cursoragent@cursor.com>
Harvested from #2391 with thanks to @wplll.
Tracks a cache warmup key across provider, model, base URL, static prefix, tool catalog, project pack, and skills hashes; records base URL and tool catalog from completed turns; reports whether /cache inspect still matches the last warmup key; and computes the warmup key from the actual warmup request sent to the provider.
Validation:
- cargo fmt --all -- --check
- git diff --check
- CARGO_TARGET_DIR=/Volumes/VIXinSSD/codewhale-target/harvest-2391-rebase cargo test -p codewhale-tui warmup_status --all-features
- CARGO_TARGET_DIR=/Volumes/VIXinSSD/codewhale-target/harvest-2391-rebase cargo test -p codewhale-tui cache_inspect --all-features
Harvested from #2390 with thanks to @wplll.
Records the actual tool catalog used by the last model request, reports that catalog in /cache inspect JSON and text output, and includes review hardening for stale catalog clearing, JSON/verbose flag handling, and CJK-aware token estimates.
Validation:
- cargo fmt --all -- --check
- CARGO_TARGET_DIR=/Volumes/VIXinSSD/codewhale-target/harvest-2390 cargo test -p codewhale-tui cache_inspect --all-features
Harvested from #2377 with thanks to @buko.
Threads the parent MCP tool pool into child SubAgentRuntime construction and registers MCP-backed tools for child agents when MCP is enabled, while leaving the broader mention-browser/provider/config work for focused follow-ups.
Validation:
- cargo fmt --all -- --check
- CARGO_TARGET_DIR=/Volumes/VIXinSSD/codewhale-pr2377-target cargo test -p codewhale-tui tools::subagent
- CARGO_TARGET_DIR=/Volumes/VIXinSSD/codewhale-target/harvest-2377-recheck cargo test -p codewhale-tui tools::subagent --all-features
Harvested from #2393 with thanks to @wplll.
Strengthens the tool-result dedup regression coverage by exercising repeated medium-sized outputs that are above the dedup threshold but below the truncation budget.
Harvested from #2392 with thanks to @wplll.
Makes project context pack path ordering deterministic across Unix and Windows-style separators while keeping README/config/source entries prioritized before general directory noise.
Harvested from #2402 with thanks to @axobase001.
Keeps `allow_shell` guidance visible for gated shell tools even when missing-tool suggestions exist, removes the nonexistent task_shell_cancel matcher, and broadens regression coverage.
Partially addresses #2328.
Harvested from #2415 with thanks to @axobase001.
Keeps the denser mobile QR renderer and replaces the fixed binding-warning sleep with health polling plus an explicit timeout failure path, so slow starts fail with the useful cause instead of drifting into misleading assertions.
Follow-up to #2403.
Harvested from #2408 with thanks to @axobase001.
Adds regression coverage proving tty:true shell commands receive a controlling terminal, with a longer wait margin so the test is stable on slower CI hosts.
Partially addresses #2372.
Harvested from #2405 with thanks to @axobase001.\n\nCompacts the statusline token chip to use the short label while preserving the existing token detail and adding focused coverage for the rendered label.\n\nPartially addresses #2309.
Hunter B