Commit Graph
5113 Commits
Author SHA1 Message Date
Sammsai f3e67fc0aa 笔记模块重构与升级 2026-08-20 20:41:12 +08:00
陈大猫 afc02116a8 Merge pull request #3096 from binaricat/codex/fix-3090-sftp-search-shortcut
fix(sftp): open filter with search shortcut
2026-08-20 17:01:59 +08:00
陈大猫 66310a1172 Merge pull request #3097 from binaricat/codex/fix-3088-autocomplete-history-refresh
fix(terminal): refresh history suggestions as input changes
2026-08-20 16:55:45 +08:00
bincxz 399657247d fix(sftp): preserve terminal search focus 2026-08-20 16:44:07 +08:00
bincxz d5bd69ff90 test(terminal): cover shorter path history replacements 2026-08-20 16:39:32 +08:00
bincxz 60ea41523a fix(sftp): handle search from editable controls 2026-08-20 16:36:43 +08:00
bincxz 78d50b78da fix(terminal): preserve matching path history rows 2026-08-20 16:34:12 +08:00
陈大猫 31e75e114e Merge pull request #3093 from binaricat/codex/fix-3082-split-shortcuts
[Bug] Align horizontal and vertical split shortcuts
2026-08-20 16:24:32 +08:00
bincxz e882ec01f7 test(terminal): cover fuzzy history deletion 2026-08-20 16:15:58 +08:00
bincxz 6f470b3142 test(sftp): verify search shortcut passthrough 2026-08-20 16:14:45 +08:00
bincxz d8d14253d6 fix(terminal): keep autocomplete history aligned with input 2026-08-20 16:12:01 +08:00
bincxz 5245ebbaa0 fix(sftp): open filter with search shortcut 2026-08-20 16:08:41 +08:00
bincxz 9c63b40ddf test(terminal): stabilize split menu coverage 2026-08-20 15:52:52 +08:00
bincxz 490554d6a6 fix(terminal): align split menu icons 2026-08-20 15:49:18 +08:00
bincxz f7a8e1557b fix(terminal): align split menu shortcuts 2026-08-20 15:38:15 +08:00
陈大猫 bd8f7ee7a6 Merge pull request #3080 from binaricat/feat/ai-sidebar-provider-model-thinking
feat(ai): unify sidebar provider, model, and thinking pickers
2026-08-20 12:19:45 +08:00
bincxz 71f6f51707 Merge remote-tracking branch 'origin/main' into feat/ai-sidebar-provider-model-thinking
# Conflicts:
#	components/settings/tabs/ai/ProviderConfigForm.tsx
2026-08-20 11:53:43 +08:00
bincxz 0288d1610a fix(ai): skip no-op AI config updates and simplify permission picker
Avoid rewriting thinking/provider maps when values are unchanged so
mounted AI panels do not re-render. Put permission title and short
description on one line and drop the Cursor CLI parenthetical.
2026-08-20 11:52:29 +08:00
bincxz b701df8822 fix(ai): align Catty thinking levels with vendor capabilities
Stop advertising Gemini 3.7 Flash minimal, GPT-5.x-chat reasoning, and
Claude 4.7+ extended thinking. Map GPT-5 Off to minimal, send adaptive
effort on Claude 4.6+, and keep composer Enter on an exact or custom id.
2026-08-20 11:05:12 +08:00
陈大猫 10d7ff9879 Merge pull request #3084 from DeanCen/fix/3083-ai-request-content-length
fix: send Content-Length for AI request bodies instead of chunked encoding
2026-08-20 10:05:58 +08:00
DeanCen a43ddb6804 fix: send Content-Length for AI request bodies instead of chunked encoding
Node's http.request falls back to Transfer-Encoding: chunked when no
Content-Length header is present. Both AI request paths pass the AI SDK's
headers through unchanged, and those headers carry no content-length (in the
browser fetch computes it), so every AI request body went out chunked.

The body is a fully-buffered string at that point, so its length is known.
Send an explicit Content-Length instead, measured with Buffer.byteLength so
multi-byte system prompts are not truncated.

Chunked request bodies are the less interoperable choice: on the plain-HTTP
path an HTTP proxy has to de-frame and re-serialize them, and some fail on
larger bodies. Xray's HTTP inbound drops the connection once the chunked body
exceeds roughly 8KB. Because Catty's system prompt plus tool definitions is
about 48KB, chat against an http:// provider behind a system HTTP proxy failed
with an opaque "socket hang up" while the connection test kept passing, since
that test issues GET /v1/models with no body and never exercises this path.

Adds three regression tests covering the streaming path, byte-accurate length
for multi-byte bodies, and the non-streaming path.

Closes #3083
2026-08-20 00:30:55 +08:00
bincxz 97ef84db06 fix(ai): persist discovered context windows from composer picks
Codex P2: switching to a catalog model dropped context_length, so
Catty budgeted 128k instead of the advertised window. Keep the
metadata on picker models and write it to modelContextWindows.
2026-08-19 23:51:05 +08:00
bincxz 8bce8c15a0 fix(ai): do not display unset thinking as Off
Codex P2: models whose menu includes Off still showed Off for users
with no stored preference, while the request sent no override. Leave
the chip unselected until the user picks a level.
2026-08-19 23:40:09 +08:00
bincxz b7b35afa24 fix(ai): persist explicit Off and omit unset thinking options
Codex P2: missing agentThinkingMap was treated as Off, so GPT-5.1+
got reasoningEffort=none and Gemini 2.5 Flash got thinkingBudget=0
without a user choice. Store Off as an explicit value and leave an
absent preference unset so the provider default is used.
2026-08-19 23:34:28 +08:00
bincxz 958972ffa0 fix(ai): omit Gemini 3 Flash thinking when preference is unset
Codex P2: an empty agentThinkingMap was normalized to Off and then to
minimal, so every Gemini 3 Flash turn overrode the provider default.
Only send thinkingLevel when the user actually picked a level.
2026-08-19 23:29:50 +08:00
bincxz d137662d02 fix(ai): treat gpt-5-chat models as non-reasoning
Codex P2: gpt-5-chat-latest matched the gpt-5 heuristic and received
reasoningEffort, which the OpenAI chat-only variants reject. Exclude
gpt-5-chat* from the thinking chip and request options.
2026-08-19 23:24:35 +08:00
bincxz 10ca915370 fix(ai): include Catty thinking map in settings sync
Codex P2: agentThinkingMap was persisted locally but omitted from
collect/apply sync, so backups and other devices restored provider
and model without the chosen reasoning level.
2026-08-19 23:18:50 +08:00
bincxz 33dc249d74 fix(ai): do not Enter-select custom IDs on external agents
Codex P2: hiding the custom-model row still left Enter falling back
to the typed query, which send-time validation then discarded. Only
use the query as a custom ID when Catty offers that action.
2026-08-19 23:10:34 +08:00
bincxz b490eb3273 fix(ai): keep unset Catty thinking as provider default
Codex P2: opening the composer on Gemini Pro persisted Low for users
who had never chosen a thinking level. Only remap an explicit stale
value; leave an empty preference unset so the request uses the
provider default.
2026-08-19 23:03:56 +08:00
bincxz 55852918c2 fix(ai): sync composer model prefs across retained panels
Codex P2: pinning or recents in one parked ChatInput only updated that
instance. Subscribe every mounted composer so sibling terminals see
the same recent/pinned list without remounting.
2026-08-19 22:57:21 +08:00
bincxz cc85cc7ebe fix(ai): keep Gemini 3.1 Pro medium and drop 3.0 Pro medium
Codex P2: gemini-3.1-pro-preview supports Medium, but Catty rewrote it
to High. Original Gemini 3 Pro still only has Low/High, so omit Medium
instead of silently converting it.
2026-08-19 22:50:29 +08:00
bincxz 6e99c9c1dc fix(ai): drop stale external-agent pinned models
Codex P2: refreshed CLI catalogs still showed saved IDs that the
catalog no longer contains, then send-time validation swapped them.
Only Catty may keep a custom ID that is not in the live list.
2026-08-19 22:45:11 +08:00
bincxz 1dac363d84 fix(ai): discover Catty models from preset Base URL when omitted
Codex P2: a built-in provider with no stored baseURL never listed
live models even though chat still used the preset host. Fall back to
PROVIDER_PRESETS.defaultBaseURL before probing /models.
2026-08-19 22:38:33 +08:00
bincxz 4eddbfab22 fix(ai): hide CLI custom models and count thinking budget once
Codex P2: external-agent pickers advertised a custom ID that send-time
validation ignored. Offer Use custom model only for Catty providers.

Codex P2: the thinking budget was added to both compaction max output
and reservedTokens, so it was subtracted twice. Keep it only on
compaction max output.
2026-08-19 22:29:33 +08:00
bincxz 54d92fb326 fix(ai): reserve Anthropic thinking budget in Catty compaction
Codex P2: medium/high thinking adds 10k/20k to the SDK max_tokens,
but pre-turn/step compaction still reserved only the 4,096 default.
Fold the selected thinking budget into output reserve and compaction
max output without changing the streamed maxTokens field.
2026-08-19 22:24:05 +08:00
bincxz 73a9669bf7 fix(ai): hide Anthropic thinking on models without extended thinking
Codex P2: Claude 3 Haiku still offered Low/Medium/High and would send
an enabled thinking budget. Gate the chip and the provider option on
Claude 3.7 / 4+ model ids. Also memoize Catty thinking levels.
2026-08-19 22:15:34 +08:00
bincxz 5971e03ffe fix(ai): drop stale thinking levels and hide Gemini Pro Off
Codex P2: switching away from Gemini 3 Flash left `minimal` selected
on models that do not advertise it. Persist a valid level for the new
model.

Codex P2: Gemini 3 Pro and 2.5 Pro cannot disable thinking, so Off
was a lie. Those menus only offer low/medium/high.
2026-08-19 22:10:09 +08:00
bincxz 3123c33914 fix(ai): bust model cache on key change and label Gemini minimal
Codex P2: catalog cache ignored API key rotation, so a replaced
credential could keep the previous account's models. Fingerprint the
stored secret in the cache key.

Codex P2: Gemini 3 Flash cannot turn thinking off; Off was sending
thinkingLevel=minimal. Surface Minimal on the chip instead of Off.
2026-08-19 22:02:03 +08:00
bincxz 90e3f121ee fix(ai): send none only on GPT-5.1+ and honor Cursor effort params
Codex P1: o3/o4-mini/gpt-5 reject reasoning_effort=none. Only GPT-5.1+
get that Off mapping; older reasoning models omit the field.

Codex P2: Cursor ModelListItem.parameters.effort.values is the catalog
capability list. Use it when present instead of fabricating fallbacks
or dropping the thinking chip on unknown models.
2026-08-19 21:53:24 +08:00
bincxz be63983693 fix(ai): hide Catty thinking chip on non-reasoning models
Codex P2: OpenAI-style models such as gpt-4o rejected reasoning_effort
when the chip always offered Off/Low/Medium/High. Gate the chip and
the provider option on known reasoning model ids, and send explicit
none when Off is selected on a reasoning model.
2026-08-19 21:45:15 +08:00
bincxz ad16f19268 fix(ai): tighten picker chrome and align provider action buttons
Remove the provider divider and search-field outline in the sidebar
model picker. Size Save/Test/Cancel to the same h-8 box without
changing the global Button styles.
2026-08-19 21:32:18 +08:00
bincxz 77cb55315a fix(ai): keep Ollama Cloud API keys and append /v1
The Ollama preset always rewrote OpenAI-compat keys to the literal
"ollama" dummy. That is correct for local servers with no key, but it
replaced the IPC placeholder used for Cloud, so chat sent
Authorization: Bearer ollama and 401ed. Only fill the dummy when no key
is configured, and normalize a bare ollama.com origin to /v1.
2026-08-19 20:45:58 +08:00
bincxz 54647b2f9a fix(ai): clamp Gemini 3 Pro levels and union Cursor fallbacks
Omit Gemini 3 Pro Off instead of sending unsupported minimal, clamp
medium to high, and merge advertised Cursor efforts with the fallback
table so CLI-listed gpt-5 still gets a thinking chip.
2026-08-19 18:34:26 +08:00
bincxz f3d5e1e88f fix(ai): omit 2.5 Pro Off budget and keep CodeBuddy picker unsuffixed
Gemini 2.5 Pro rejects thinkingBudget 0, so Off omits the config.
Picking a CodeBuddy model without a chip level no longer writes /medium.
2026-08-19 18:25:50 +08:00
bincxz 2f96b86fed fix(ai): keep CodeBuddy settings effort and Gemini 2.5 budgets
Do not rewrite bare CodeBuddy model ids to /medium, fail closed when
Google has no model id, and send Gemini 2.5 thinkingBudget instead of
Gemini 3 thinkingLevel.
2026-08-19 18:11:41 +08:00
bincxz b29f74b925 feat(ai): wire Cursor, CodeBuddy, and Gemini thinking chips
Map Cursor effort variants and CodeBuddy SDK effort onto the shared
sidebar thinking chip, and send Gemini thinkingConfig for Catty
models that look like they support it.
2026-08-19 17:50:16 +08:00
bincxz 3d154ca235 fix(ai): switch providers from a one-line submenu
Keep the composer model menu as a single-column list. Provider
switching now drills in from the header row instead of a left rail.
2026-08-19 17:35:44 +08:00
bincxz 4acf254f72 feat(ai): unify sidebar provider, model, and thinking pickers
Give Catty a two-column provider/model menu in the composer, add search
plus recent/pinned models, and move thinking effort onto its own chip
so Claude, Codex, Grok, and Catty share the same compact controls.

Closes #2137
Closes #2637
Closes #1884
2026-08-19 17:23:06 +08:00
陈大猫 69af65fd02 Merge pull request #3079 from binaricat/feat/3078-openai-responses-api
feat(ai): add optional OpenAI Responses API format
2026-08-19 16:22:18 +08:00
bincxz fdecf652bf feat(ai): add optional OpenAI Responses API format
Closes #3078

OpenAI-compatible providers always used Chat Completions. Some
relays cache poorly on that path. Add a per-provider Responses
opt-in so Catty can call /v1/responses while keeping Chat
Completions as the default.
2026-08-19 16:10:20 +08:00