Conversation
Add a safe, validated API for modifying DeepChat application settings via natural language. Settings changes are controlled by a dedicated 'deepchat-settings' skill to ensure tools are only available when contextually relevant. Key features: - Skill-gated tool injection: settings tools only appear when deepchat-settings skill is active - Safe settings apply API with Zod validation and strict allowlist - Support for toggles (sound, copy COT, chat mode) and enums (language, theme, font size) - Defense-in-depth: runtime skill verification before applying changes - Deep-linked settings navigation for unsupported/complex settings - Comprehensive test coverage for validation, mapping, and skill gating Changes: - Add ChatSettingsToolHandler with validated apply/open methods - Integrate with AgentToolManager for tool definition gating - Create deepchat-settings built-in skill with clear activation rules - Add shared types for requests/responses (chatSettings.ts) - Implement settings window navigation with SECTION_ALIASES - Add unit tests for handler and integration tests for tool gating - Translate spec documents (plan.md, spec.md, tasks.md) to Chinese - Fix type errors in getCurrentValue and OPEN_SECTION_VALUES
…rvice Remove chatMode setting from the allowlist as it requires conversation-scoped updates that are better handled separately. Add permission checking for settings window opening to provide user control over settings navigation. Key changes: - Remove setChatMode tool and related schemas from ChatSettingsToolHandler - Add SettingsPermissionService for managing tool approvals (one-time and session) - Add permission check for deepchat_settings_open tool - Update PermissionHandler to handle settings permission grants - Add rememberable flag to permission request structure - Update AgentToolManager to consume approvals before opening settings - Add settingsPermissionService to main presenter index - Clear settings approvals when conversation ends - Update spec documents to reflect removed chatMode feature - Remove chatMode-related tests and types This ensures settings window opening requires explicit user approval and provides a cleaner separation of concerns for chat mode management.
Contributor
📝 WalkthroughWalkthroughAdds conversational chat-settings control: new DeepChat skill (deepchat-settings), tool definitions/handler, permission service, types, presenter plumbing to propagate conversationId, UI event for navigating settings, and tests. Validated main-process API, skill gating, and session-scoped approvals are implemented. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Agent
participant ToolHandler as ChatSettingsToolHandler
participant Config as ConfigPresenter
participant Perm as SettingsPermissionService
participant UI as SettingsUI
User->>Agent: Ask to change setting (e.g., enable sound)
Agent->>ToolHandler: callChatSettingsTool(toggle, payload)
ToolHandler->>ToolHandler: Validate skill active & input
ToolHandler->>Config: apply setting change
Config-->>ToolHandler: applied (previousValue, timestamp)
ToolHandler-->>Agent: success result
Agent->>User: Confirm applied
alt Open settings flow
User->>Agent: Ask to open settings (section)
Agent->>ToolHandler: callChatSettingsTool(open, {section})
ToolHandler->>Perm: consumeApproval(conversationId, toolName)
Perm-->>ToolHandler: approved / not approved
alt approved
ToolHandler->>UI: send NAVIGATE event with route
UI-->>User: Settings opened at section
else not approved
ToolHandler-->>Agent: return permissionRequest
Agent->>User: Request approval
end
end
Estimated Code Review Effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly Related PRs
Suggested Labels
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@src/main/presenter/agentPresenter/acp/agentToolManager.ts`:
- Around line 300-325: The fallback that merges requiredSettingsTools into
allowedTools when hasNonOpenSettingsTool is false (calculating
effectiveAllowedTools) needs an explicit comment explaining its intent or else
change to respect allowedTools as-is; update the block around the
hasNonOpenSettingsTool check (variables/functions: allowedTools,
requiredSettingsTools, CHAT_SETTINGS_TOOL_NAMES, effectiveAllowedTools,
buildChatSettingsToolDefinitions,
presenter.skillPresenter.getActiveSkillsAllowedTools) to either add a brief
comment describing why we add all requiredSettingsTools when only "open" is
allowed (e.g., to ensure UI/settings completeness) or remove the merge and use
allowedTools directly so skill metadata is never expanded silently. Ensure the
comment clearly states the design choice and any security/UX rationale.
🧹 Nitpick comments (6)
test/main/presenter/agentPresenter/agentToolManagerSettings.test.ts (1)
1-83: LGTM!The test file provides good coverage of the DeepChat settings tool gating behavior in
AgentToolManager. The two test cases effectively verify:
- Tools are excluded when the skill is inactive
- Only explicitly allowed tools are included when the skill is active
Consider adding additional test cases for broader coverage:
- When all settings tools are in the allowed list
- When
chatModeis not'agent'(tools should not be included)- When
conversationIdis not provided💡 Example additional test case
it('does not include settings tools when chatMode is not agent', async () => { ;(presenter.skillPresenter.getActiveSkills as any).mockResolvedValue([CHAT_SETTINGS_SKILL_NAME]) ;(presenter.skillPresenter.getActiveSkillsAllowedTools as any).mockResolvedValue([ CHAT_SETTINGS_TOOL_NAMES.toggle ]) const manager = new AgentToolManager({ yoBrowserPresenter, agentWorkspacePath: null, configPresenter }) const defs = await manager.getAllToolDefinitions({ chatMode: 'chat', supportsVision: false, agentWorkspacePath: null, conversationId: 'conv-1' }) const names = defs.map((def) => def.function.name) expect(names).not.toContain(CHAT_SETTINGS_TOOL_NAMES.toggle) })src/main/presenter/mcpPresenter/index.ts (1)
648-659: Normalizerequiredto an array to keep schemas valid.Defensive defaults look good; consider guarding against non-array
requiredfrom malformed tool definitions to avoid downstream schema validation issues.♻️ Suggested guard for non-array
required- required: toolParameters?.required ?? [] + required: Array.isArray(toolParameters?.required) ? toolParameters?.required : []Also applies to: 677-677
docs/specs/chat-settings-control/plan.md (1)
96-96: Minor grammar nit in Chinese text.Per static analysis, the adverb form should use "地" instead of "的" when modifying a verb: "精确地说明" instead of "精确的说明".
📝 Suggested fix
-- 提供精确的说明告诉用户在哪里更改。 +- 提供精确地说明告诉用户在哪里更改。src/main/presenter/agentPresenter/acp/chatSettingsTools.ts (1)
349-358: Redundant guard check inopenmethod.The
guardreturned fromensureSkillActiveis alwaysnull(skill active) or an object withok: false. The checkguard && !guard.okis redundant since ifguardis truthy, it will always haveok: false.♻️ Simplify guard check
async open(raw: unknown, conversationId?: string): Promise<OpenChatSettingsResult> { const guard = await this.ensureSkillActive(conversationId) - if (guard && !guard.ok) { + if (guard) { return { ok: false, errorCode: 'skill_inactive', message: guard.message, details: guard.details } }src/main/presenter/agentPresenter/acp/agentToolManager.ts (1)
960-968: Consider usingObject.valuesfor maintainability.The
isChatSettingsToolcheck explicitly lists all tool names. Using the constant ensures consistency.♻️ Use CHAT_SETTINGS_TOOL_NAMES for consistency
private isChatSettingsTool(toolName: string): boolean { - return ( - toolName === CHAT_SETTINGS_TOOL_NAMES.toggle || - toolName === CHAT_SETTINGS_TOOL_NAMES.setLanguage || - toolName === CHAT_SETTINGS_TOOL_NAMES.setTheme || - toolName === CHAT_SETTINGS_TOOL_NAMES.setFontSize || - toolName === CHAT_SETTINGS_TOOL_NAMES.open - ) + return Object.values(CHAT_SETTINGS_TOOL_NAMES).includes(toolName as any) }src/shared/types/chatSettings.ts (1)
40-42: Consider constraininglevelinSetFontSizeRequest.The implementation in
chatSettingsTools.tsvalidateslevelas one of[0, 1, 2, 3, 4], but this type uses a genericnumber. For stronger type safety, consider using a literal union.♻️ Constrain font size level type
+export type FontSizeLevel = 0 | 1 | 2 | 3 | 4 + export type SetFontSizeRequest = { - level: number + level: FontSizeLevel }
Comment on lines
+300
to
+325
| // 4. DeepChat settings tools (agent mode only, skill gated) | ||
| if (isAgentMode && this.isSkillsEnabled() && context.conversationId) { | ||
| try { | ||
| const activeSkills = await presenter.skillPresenter.getActiveSkills(context.conversationId) | ||
| if (activeSkills.includes(CHAT_SETTINGS_SKILL_NAME)) { | ||
| const allowedTools = await presenter.skillPresenter.getActiveSkillsAllowedTools( | ||
| context.conversationId | ||
| ) | ||
| const requiredSettingsTools = Object.values(CHAT_SETTINGS_TOOL_NAMES) | ||
| const nonOpenSettingsTools = requiredSettingsTools.filter( | ||
| (tool) => tool !== CHAT_SETTINGS_TOOL_NAMES.open | ||
| ) | ||
| const hasNonOpenSettingsTool = nonOpenSettingsTools.some((tool) => | ||
| allowedTools.includes(tool) | ||
| ) | ||
| const effectiveAllowedTools = hasNonOpenSettingsTool | ||
| ? allowedTools | ||
| : Array.from(new Set([...allowedTools, ...requiredSettingsTools])) | ||
|
|
||
| const settingsDefs = buildChatSettingsToolDefinitions(effectiveAllowedTools) | ||
| defs.push(...settingsDefs) | ||
| } | ||
| } catch (error) { | ||
| logger.warn('[AgentToolManager] Failed to load DeepChat settings tools', { error }) | ||
| } | ||
| } |
Contributor
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# First, find the skill definition file
fd -t f "SKILL.md" -p "deepchat-settings" 2>/dev/null || echo "SKILL.md not found in deepchat-settings, searching more broadly..."
find . -type f -name "*SKILL*" -o -name "skill*" | grep -i "deepchat\|settings" | head -20Repository: ThinkInAIXYZ/deepchat
Length of output: 219
🏁 Script executed:
#!/bin/bash
# Let's examine the agentToolManager.ts file around lines 300-325 and the logic context
cat -n src/main/presenter/agentPresenter/acp/agentToolManager.ts | sed -n '300,330p'Repository: ThinkInAIXYZ/deepchat
Length of output: 1547
🏁 Script executed:
#!/bin/bash
# Also check for any constants defining CHAT_SETTINGS_TOOL_NAMES
grep -n "CHAT_SETTINGS_TOOL_NAMES" src/main/presenter/agentPresenter/acp/agentToolManager.ts | head -20Repository: ThinkInAIXYZ/deepchat
Length of output: 855
🏁 Script executed:
#!/bin/bash
# Search for where CHAT_SETTINGS_TOOL_NAMES is defined
rg "CHAT_SETTINGS_TOOL_NAMES\s*=" -A 10 -B 2Repository: ThinkInAIXYZ/deepchat
Length of output: 1212
🏁 Script executed:
#!/bin/bash
# Look for skill definitions and deepchat-settings configuration
find . -type d -name "*skill*" -o -name "*deepchat*" 2>/dev/null | grep -E "skill|deepchat" | head -20Repository: ThinkInAIXYZ/deepchat
Length of output: 408
🏁 Script executed:
#!/bin/bash
cat -n ./resources/skills/deepchat-settings/SKILL.mdRepository: ThinkInAIXYZ/deepchat
Length of output: 3494
🏁 Script executed:
#!/bin/bash
# Also check if there are any comments or documentation about the fallback logic
grep -B 5 -A 5 "allowedTools\|requiredSettingsTools" src/main/presenter/agentPresenter/acp/agentToolManager.ts | head -40Repository: ThinkInAIXYZ/deepchat
Length of output: 1196
🏁 Script executed:
#!/bin/bash
# Check the skillPresenter to understand how getActiveSkillsAllowedTools works
rg "getActiveSkillsAllowedTools" -A 15 src/main/presenter/skillPresenter/Repository: ThinkInAIXYZ/deepchat
Length of output: 1292
🏁 Script executed:
#!/bin/bash
# Search for comments around the fallback logic in the file
grep -B 10 "effectiveAllowedTools" src/main/presenter/agentPresenter/acp/agentToolManager.ts | head -30Repository: ThinkInAIXYZ/deepchat
Length of output: 810
🏁 Script executed:
#!/bin/bash
# Check git blame/history if available to see when this was added
git log -p --all -S "effectiveAllowedTools" -- src/main/presenter/agentPresenter/acp/agentToolManager.ts 2>/dev/null | head -100 || echo "Git history not available"Repository: ThinkInAIXYZ/deepchat
Length of output: 47
🏁 Script executed:
#!/bin/bash
# Search for any documentation or comments about skill tool restrictions
rg "allowedTools.*restrict\|restrict.*allowedTools\|fallback.*tools" -iRepository: ThinkInAIXYZ/deepchat
Length of output: 47
The fallback logic lacks documentation and should clarify its intent.
Lines 315-317 silently add all requiredSettingsTools if no non-open tools appear in allowedTools. With the current SKILL.md listing all 5 tools, this fallback never executes. However, if the skill metadata were restricted (e.g., to only allow deepchat_settings_open), the code would bypass that restriction without explanation.
Either document why this fallback exists or reconsider whether allowedTools should be respected as-is. Add a comment explaining the design intent behind this logic, as it's not self-evident from the code.
🤖 Prompt for AI Agents
In `@src/main/presenter/agentPresenter/acp/agentToolManager.ts` around lines 300 -
325, The fallback that merges requiredSettingsTools into allowedTools when
hasNonOpenSettingsTool is false (calculating effectiveAllowedTools) needs an
explicit comment explaining its intent or else change to respect allowedTools
as-is; update the block around the hasNonOpenSettingsTool check
(variables/functions: allowedTools, requiredSettingsTools,
CHAT_SETTINGS_TOOL_NAMES, effectiveAllowedTools,
buildChatSettingsToolDefinitions,
presenter.skillPresenter.getActiveSkillsAllowedTools) to either add a brief
comment describing why we add all requiredSettingsTools when only "open" is
allowed (e.g., to ensure UI/settings completeness) or remove the merge and use
allowedTools directly so skill metadata is never expanded silently. Ensure the
comment clearly states the design choice and any security/UX rationale.
Contributor
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Fix all issues with AI agents
In `@docs/specs/chat-settings-control/spec.md`:
- Line 20: The line "Use skills to control context:" contains a typographical
error with a double backtick after the inline code token for
`deepchat-settings`; edit the markdown in spec.md to replace the double backtick
sequence following "deepchat-settings" with a single backtick so the inline code
is correctly formatted (locate the occurrence of `deepchat-settings`` and change
it to `deepchat-settings`).
In `@docs/specs/chat-settings-control/tasks.md`:
- Line 21: Replace the unclear abbreviation "best-eff-mn navigation" in the
tasks.md text with a spelled-out phrase; locate the string "best-eff-mn
navigation" and change it to "best-effort navigation" (or "best-effort
navigation (best-eff-mn)" if you want to preserve the shorthand), updating any
related wording nearby such as the sentence "Add 'open settings' helper/tool for
unsupported settings (MCP/prompts, etc.), including best-eff-mn navigation" to
the clarified version.
- Line 20: Fix the stray double backtick typo around the identifier
"deepchat-settings" in the tasks text (the line that currently reads
`deepchat-settings``) by replacing the trailing double backtick with a single
backtick so it appears as `deepchat-settings`; also mirror the same correction
in spec.md where the same double-backtick issue occurs.
zhangmo8
added a commit
that referenced
this pull request
Jan 21, 2026
* chore: release v0.5.6-beta.5 * chore: typecheck with tsgo (#1278) * feat: image left align * feat: app settings skills (#1283) * docs: add spec for app-settings * feat: implement chat-driven settings control with skill gating Add a safe, validated API for modifying DeepChat application settings via natural language. Settings changes are controlled by a dedicated 'deepchat-settings' skill to ensure tools are only available when contextually relevant. Key features: - Skill-gated tool injection: settings tools only appear when deepchat-settings skill is active - Safe settings apply API with Zod validation and strict allowlist - Support for toggles (sound, copy COT, chat mode) and enums (language, theme, font size) - Defense-in-depth: runtime skill verification before applying changes - Deep-linked settings navigation for unsupported/complex settings - Comprehensive test coverage for validation, mapping, and skill gating Changes: - Add ChatSettingsToolHandler with validated apply/open methods - Integrate with AgentToolManager for tool definition gating - Create deepchat-settings built-in skill with clear activation rules - Add shared types for requests/responses (chatSettings.ts) - Implement settings window navigation with SECTION_ALIASES - Add unit tests for handler and integration tests for tool gating - Translate spec documents (plan.md, spec.md, tasks.md) to Chinese - Fix type errors in getCurrentValue and OPEN_SECTION_VALUES * refactor: remove chatMode from settings control and add permission service Remove chatMode setting from the allowlist as it requires conversation-scoped updates that are better handled separately. Add permission checking for settings window opening to provide user control over settings navigation. Key changes: - Remove setChatMode tool and related schemas from ChatSettingsToolHandler - Add SettingsPermissionService for managing tool approvals (one-time and session) - Add permission check for deepchat_settings_open tool - Update PermissionHandler to handle settings permission grants - Add rememberable flag to permission request structure - Update AgentToolManager to consume approvals before opening settings - Add settingsPermissionService to main presenter index - Clear settings approvals when conversation ends - Update spec documents to reflect removed chatMode feature - Remove chatMode-related tests and types This ensures settings window opening requires explicit user approval and provides a cleaner separation of concerns for chat mode management. * docs: translate to en * feat: voice ai text to speech * feat: voice ai call phone * Initial plan * perf: optimize message cache and cloning operations - Add reverse index for O(1) thread lookup in messageRuntimeCache - Extract duplicate cloneMessageWithContent to shared utility - Replace JSON.parse/stringify with structuredClone - Filter before cloning in messageTruncator to avoid wasted work Co-authored-by: zhangmo8 <43628500+zhangmo8@users.noreply.github.com> * docs: add comprehensive performance optimization analysis Add detailed optimization analysis document covering: - Implemented optimizations (cache, cloning, filtering) - High priority opportunities (provider consolidation, IPC batching) - Medium/low priority improvements (DB indices, token caching) - Performance metrics and recommendations Co-authored-by: zhangmo8 <43628500+zhangmo8@users.noreply.github.com> * docs: add Chinese optimization summary Add user-friendly Chinese summary of optimization work Co-authored-by: zhangmo8 <43628500+zhangmo8@users.noreply.github.com> --------- Co-authored-by: zerob13 <zerob13@gmail.com> Co-authored-by: xiaomo <wegi866@gmail.com> Co-authored-by: wanna <wanna.w@binarywalk.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: zhangmo8 <43628500+zhangmo8@users.noreply.github.com>
zerob13
added a commit
that referenced
this pull request
Feb 5, 2026
* chore: typecheck with tsgo (#1278) * feat: image left align * feat: app settings skills (#1283) * docs: add spec for app-settings * feat: implement chat-driven settings control with skill gating Add a safe, validated API for modifying DeepChat application settings via natural language. Settings changes are controlled by a dedicated 'deepchat-settings' skill to ensure tools are only available when contextually relevant. Key features: - Skill-gated tool injection: settings tools only appear when deepchat-settings skill is active - Safe settings apply API with Zod validation and strict allowlist - Support for toggles (sound, copy COT, chat mode) and enums (language, theme, font size) - Defense-in-depth: runtime skill verification before applying changes - Deep-linked settings navigation for unsupported/complex settings - Comprehensive test coverage for validation, mapping, and skill gating Changes: - Add ChatSettingsToolHandler with validated apply/open methods - Integrate with AgentToolManager for tool definition gating - Create deepchat-settings built-in skill with clear activation rules - Add shared types for requests/responses (chatSettings.ts) - Implement settings window navigation with SECTION_ALIASES - Add unit tests for handler and integration tests for tool gating - Translate spec documents (plan.md, spec.md, tasks.md) to Chinese - Fix type errors in getCurrentValue and OPEN_SECTION_VALUES * refactor: remove chatMode from settings control and add permission service Remove chatMode setting from the allowlist as it requires conversation-scoped updates that are better handled separately. Add permission checking for settings window opening to provide user control over settings navigation. Key changes: - Remove setChatMode tool and related schemas from ChatSettingsToolHandler - Add SettingsPermissionService for managing tool approvals (one-time and session) - Add permission check for deepchat_settings_open tool - Update PermissionHandler to handle settings permission grants - Add rememberable flag to permission request structure - Update AgentToolManager to consume approvals before opening settings - Add settingsPermissionService to main presenter index - Clear settings approvals when conversation ends - Update spec documents to reflect removed chatMode feature - Remove chatMode-related tests and types This ensures settings window opening requires explicit user approval and provides a cleaner separation of concerns for chat mode management. * docs: translate to en * chore: yo browser less context (#1284) * docs: add specs for yo browesr context manager * feat(yo-browser): improve skill description and add yo_browser_cdp_send to offload whitelist * refactor(yobrowser): remove skill gating and make CDP tools always available in agent mode * refactor(yobrowser): add CDP method schema validation with strict enums - Add enum-based validation for cdp_send method (11 common CDP methods) - Add detailed union schemas for each method's parameters with examples - Add normalizeCdpParams method to handle both object and JSON string inputs - Prevent method typos and provide better type safety for CDP interactions * fix(yobrowser): add strict tab ID validation in CDP send handler * chore: update deps * refactor: agent provider simplification (#1286) * docs: add spec for agent provider * refactor(agent): remove BaseAgentProvider layer and simplify provider hierarchy * feat(mcp): implement real Apple Maps search using URL scheme (#1289) * feat: support voice.ai (#1291) * feat: remove custome tiptap (#1295) * feat: settings auto scroll toggle (#1293) * feat: settings auto scroll toggle * feat: i18n support * fix(renderer): remove specific event listeners instead of all * feat: add tooltip for filling default API URL in settings (#1296) * fix: fix model list refresh failed (#1297) * feat: add question tools (#1298) * feat(agent): add question tool flow * feat(mcp): implement real Apple Maps search using URL scheme (#1289) * feat: support voice.ai (#1291) * feat: remove custome tiptap (#1295) * feat: settings auto scroll toggle (#1293) * feat: settings auto scroll toggle * feat: i18n support * fix(renderer): remove specific event listeners instead of all * feat: add tooltip for filling default API URL in settings (#1296) * refactor(question): simplify question request UI to single-choice interface * fix(chat): restore pending question state * fix: review issues --------- Co-authored-by: Qi Jin <jin.qi1@northeastern.edu> Co-authored-by: xiaomo <wegi866@gmail.com> * chore: integrated vue-tsgo (#1299) * chore: integrated vue-tsgo * chore: update recommendation exteion * chore: update * feat: add prompt for ask tool * chore: version to 0.5.7 --------- Co-authored-by: xiaomo <wegi866@gmail.com> Co-authored-by: wanna <wanna.w@binarywalk.com> Co-authored-by: Qi Jin <jin.qi1@northeastern.edu>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
finish #1275
Summary by CodeRabbit
New Features
Documentation
Tests
✏️ Tip: You can customize this high-level summary in your review settings.