Commit Graph
4 Commits
Author SHA1 Message Date
陈大猫andClaude Opus 4.6 e6166a1de3 feat: AI Provider 高级参数配置 (#532) (#533)
* feat: expose advanced AI model parameters in provider settings (#532)

Add collapsible "Advanced Parameters" section to provider config with
optional max_tokens, temperature, top_p, frequency_penalty, and
presence_penalty fields. Parameters are merged into streamText() calls
only when explicitly set, otherwise provider defaults apply.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: use maxOutputTokens instead of maxTokens for ai@6 SDK

The streamText CallSettings in ai@6 expects maxOutputTokens, not
maxTokens. Without this fix the user's max_tokens setting is silently
ignored.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: allow negative penalty input and clamp params on save

- Use raw string state for penalty fields so typing "-" is not
  discarded before the digit is entered
- Clamp all parameters to valid ranges on save (temperature 0-2,
  topP 0-1, penalties -2 to 2)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: use raw string state for all numeric advanced param inputs

Prevents intermediate text like "0." from being normalized to "0"
during keyboard entry of decimal values for temperature, topP, and
maxTokens fields.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: clamp max_tokens to minimum of 1 after rounding

Prevents Math.round(0.4) = 0 from being persisted and causing
streamText to reject with "maxOutputTokens must be >= 1".

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: reject non-finite max_tokens before persisting

Guard with Number.isFinite to prevent Infinity from being stored
and forwarded to streamText.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 20:26:13 +08:00
陈大猫andClaude Opus 4.6 835a1231a6 feat: add skip TLS verification option for self-hosted AI providers (#369)
* feat: add skip TLS verification option for AI providers

Self-hosted AI endpoints (vLLM, text-generation-webui, etc.) often use
self-signed TLS certificates which Node.js rejects by default, causing
502 Bad Gateway errors. Add a per-provider "Skip TLS certificate
verification" checkbox that sets rejectUnauthorized=false on both
streaming and non-streaming requests.

Ref #294

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: surface real error message instead of generic 502 Bad Gateway

- Pass the actual bridge error message in statusText so Vercel AI SDK
  shows the real cause (e.g. "HTTP is only allowed for localhost",
  "URL host is not in the allowed list", TLS errors)
- Show real error details for 5xx provider errors instead of generic
  "The AI provider returned a server error" message

Previously all connection-level errors were masked as "Bad Gateway"
making it impossible for users to diagnose configuration issues.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: pass server error body details through to the user

- Read HTTP error response body before resolving (was resolving before
  body was read, losing the error detail)
- Parse OpenAI-compatible JSON error format to extract error.message
- Return error Response with body+statusText for non-2xx instead of
  empty stream, so Vercel AI SDK shows the real server error
- Now users see e.g. "502 model not loaded" instead of just "Bad Gateway"

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: widen link modifier key dropdown to prevent text wrapping

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Revert "fix: widen link modifier key dropdown to prevent text wrapping"

This reverts commit 1f75686391.

* fix: apply skipTLSVerify to model listing requests

ModelSelector.aiFetch() didn't pass providerId, so the provider-level
skipTLSVerify was not applied when refreshing/listing models. Add
skipTLSVerify as a direct parameter alongside the provider lookup.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: keep error detail in Response body, not statusText

statusText only accepts single-line Latin-1 — multiline or non-ASCII
error messages from self-hosted gateways would throw TypeError before
the AI SDK could read them. Move detailed error to body instead.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: return JSON error body for AI SDK compatibility, fix FetchBridge type

- Wrap error responses in OpenAI-compatible JSON format so Vercel AI
  SDK's failedResponseHandler extracts the message correctly instead
  of showing a blank error
- Update FetchBridge type to match the expanded aiFetch parameter list

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: add ASCII statusText fallback for non-OpenAI SDK providers

Anthropic/Google SDKs fall back to Response.statusText when they can't
parse the error body. Add safe ASCII statusText alongside the JSON body.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 16:05:09 +08:00
bincxzandClaude Opus 4.6 1816c3d0df fix: resolve eslint warnings in AI chat panel components
- Copy abortControllersRef to variable before cleanup
- Remove unnecessary useMemo deps (activeTabId, workspaces)
- Remove unused Shield import
- Add missing deps (t, isCustom) to useMemo/useCallback

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 23:28:50 +08:00
bincxzandClaude Opus 4.6 a55da77471 refactor: fix security issues, remove dead code, and split monolithic files
Security:
- Fix command injection in 15+ shell interpolation sites with shellQuote()
- Add token-based authentication to MCP TCP server
- Fix heredoc delimiter collision in SFTP write fallbacks
- Add case-insensitive flag to mcpServerBridge command blocklist
- Add exhaustive default case to createModelFromConfig

Architecture:
- Split aiBridge.cjs (1971→1483 lines) into 4 modules:
  shellUtils, codexHelpers, claudeHelpers, ptyExec
- Split SettingsAITab.tsx (1480→520 lines) into 10 sub-components
- Extract shared processCattyStream from AIChatSidePanel.tsx (-168 lines)
- Consolidate duplicate PTY execution logic into shared ptyExec.cjs
- Consolidate duplicate stripAnsi/toUnpackedAsarPath utilities

Code quality:
- Remove ~33 debug console.log statements from production code
- Remove dead code: terminal_read_output stub, checkToolPermission,
  isCommandAllowed, READ_ONLY_TOOLS
- Unify bridge type accessor in useAIState.ts (eliminate 15 unsafe casts)
- Add localStorage session pruning (50 sessions / 200 messages cap)
- Fix ModelSelector onBlur race condition (setTimeout → preventDefault)
- Fix duplicate getShellEnv() calls in Codex helpers
- Remove unused _config param from claudeAgentAdapter
- Type claudeAgentAdapter bridge parameter directly as ClaudeBridge

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 19:45:50 +08:00