feat(model): add top p generation setting

docs/features/model-top-p-settings/plan.md

@@ -0,0 +1,38 @@
+# Implementation Plan
+
+## Approach
+
+Implement `topP` as an optional generation setting, mirroring the existing session generation settings pipeline while avoiding a forced default.
+
+## Affected Interfaces
+
+- `src/shared/types/agent-interface.d.ts`: add optional `topP` to `SessionGenerationSettings`.
+- `src/shared/contracts/common.ts`: add optional `topP` to route schemas.
+- `src/shared/utils/generationSettingsValidation.ts`: validate `topP` as a finite number in `[0.1, 1]`.
+- `src/main/presenter/sqlitePresenter/tables/deepchatSessions.ts`: add `top_p` storage and migration.
+- `src/main/presenter/agentRuntimePresenter/index.ts`: sanitize, persist, and pass `topP` through runtime model config.
+- `src/main/presenter/llmProviderPresenter/aiSdk/runtime.ts`: include `topP` in AI SDK `generateText` and `streamText` calls and request traces when defined.
+- `src/renderer/src/stores/ui/draft.ts`: carry draft `topP` overrides for new sessions.
+- `src/renderer/src/components/chat/ChatStatusBar.vue`: show and persist the compact `topP` control.
+- i18n `chat.json` and `settings.json` files: add `topP` label, hover description, and validation.
+- `topP` number inputs use min `0.1`, max `1`, and step `0.1` so values align with common AI SDK/provider constraints.
+
+## Data Flow
+
+1. User edits `topP` in ChatStatusBar.
+2. Draft sessions store it in Pinia; active sessions call `sessions.updateGenerationSettings`.
+3. Main process validates and stores `topP` as part of session generation settings.
+4. Agent runtime adds `topP` to runtime `ModelConfig`.
+5. AI SDK runtime includes `topP` only when defined.
+
+## Compatibility
+
+- Existing databases migrate by adding nullable `top_p`.
+- Existing sessions return no `topP` unless previously set.
+- Requests without `topP` preserve current behavior.
+
+## Test Strategy
+
+- Run formatting and i18n generation required by repository guidelines.
+- Run lint to catch type/schema/template issues.
+- Prefer focused type/lint validation over provider integration tests because this is a pass-through parameter.

docs/features/model-top-p-settings/spec.md

@@ -0,0 +1,36 @@
+# Model Top P Settings
+
+## User Need
+
+Users need to adjust `top_p` for chat models because many upstream model APIs support nucleus sampling and expose it as a generation parameter.
+
+## Goal
+
+Add an optional per-session `topP` generation setting for text chat requests and pass it through to AI SDK text generation when the user explicitly sets it.
+
+## Acceptance Criteria
+
+- Users can set `topP` from the chat model advanced settings panel for regular text chat models.
+- `topP` accepts values greater than or equal to 0.1 and less than or equal to 1.
+- The Top P UI uses the plain label "Top P" and moves explanatory copy into a hover help icon.
+- Existing conversations and new sessions continue to work when no `topP` is set.
+- `topP` persists with DeepChat session generation settings and survives app restart.
+- Text `generateText` and streaming requests pass `topP` to AI SDK only when it is defined.
+- Existing Voice.ai TTS `topP` configuration remains independent.
+
+## Constraints
+
+- Follow current typed route/contracts and presenter boundaries.
+- Use `topP` internally and let SDK/provider layers map provider payload details.
+- Do not default-send `topP: 1`; omit the parameter when unset to preserve provider defaults.
+- Use i18n keys for all user-facing strings.
+- SQLite schema migration must be backward compatible.
+
+## Non-Goals
+
+- Provider-specific `top_p` compatibility matrices.
+- Building a full Provider DB `top_p` capability matrix.
+
+## Open Questions
+
+- None.

docs/features/model-top-p-settings/tasks.md

@@ -0,0 +1,10 @@
+# Tasks
+
+- [x] Create SDD artifacts for optional model `topP` setting.
+- [x] Add shared types, contracts, and validation support for `topP`.
+- [x] Add SQLite session persistence and migration for `topP`.
+- [x] Propagate `topP` through runtime model config and AI SDK calls.
+- [x] Add renderer draft state and advanced settings UI for `topP`.
+- [x] Add i18n strings for `topP` controls and validation.
+- [x] Refine Top P UI to use a help tooltip and `[0.1, 1]` number input range.
+- [x] Run `pnpm run format`, `pnpm run i18n`, and `pnpm run lint`.

docs/issues/chat-top-p-tooltip/plan.md

@@ -0,0 +1,22 @@
+# Plan
+
+## Approach
+
+The current nested `Tooltip` is fragile inside the model settings `Popover` and can render beneath or outside the visible stacking context. Replace it with a controlled lightweight hover/focus panel anchored next to the Top P label. This keeps tooltip-style interaction while avoiding portal stacking conflicts.
+
+## Affected Interfaces
+
+- `src/renderer/src/components/chat/ChatStatusBar.vue`
+
+## Data Flow
+
+No data flow changes. The same `chat.advancedSettings.topPDescription` i18n string is displayed.
+
+## Compatibility
+
+No persisted configuration changes. The chat settings Top P clamp behavior remains unchanged.
+
+## Test Strategy
+
+- Static verification of template/script changes.
+- Run project formatting/lint commands if package tooling is available.

docs/issues/chat-top-p-tooltip/spec.md

@@ -0,0 +1,28 @@
+# Chat Top P Tooltip
+
+## User Need
+
+The chat settings panel Top P help icon must show explanatory text reliably. The settings dialog should keep inline description text, while the chat status bar should keep a hover tooltip interaction.
+
+## Goal
+
+Fix the Top P help content in `ChatStatusBar.vue` so it is visible above the settings popover and has a readable width.
+
+## Acceptance Criteria
+
+- Hovering the Top P help icon in the chat settings panel shows the Top P description.
+- The tooltip is not hidden behind the model settings popover.
+- The tooltip content has a readable constrained width for the long description.
+- The settings dialog Top P description remains inline text.
+- The existing Top P range clamp behavior remains aligned between chat and settings pages.
+
+## Constraints
+
+- Keep changes focused to the chat settings Top P help behavior.
+- Preserve existing i18n keys and shadcn/reka UI styling patterns where practical.
+- Do not introduce new dependencies.
+
+## Non-goals
+
+- Redesign the full chat settings panel.
+- Change Top P semantics or persisted data shape.

docs/issues/chat-top-p-tooltip/tasks.md

@@ -0,0 +1,5 @@
+# Tasks
+
+- [x] Inspect current Top P tooltip implementation and popover stacking.
+- [x] Add a layer-safe tooltip-style hover/focus panel for Top P in chat settings.
+- [ ] Verify formatting and report any unavailable validation tooling.

src/main/presenter/agentRuntimePresenter/index.ts

@@ -154,6 +154,11 @@ type PackageJsonManifest = {
   scripts?: Record<string, unknown>
 }
 
+function normalizeTopP(value: unknown): number | undefined {
+  const numeric = parseFiniteNumericValue(value)
+  return numeric !== undefined && numeric >= 0.1 && numeric <= 1 ? numeric : undefined
+}
+
 function readPackageJsonManifest(workdir: string): PackageJsonManifest | null {
   try {
     const packageJsonPath = path.join(workdir, 'package.json')
@@ -202,6 +207,7 @@ type PersistedSessionGenerationRow = {
   permission_mode: PermissionMode
   system_prompt: string | null
   temperature: number | null
+  top_p: number | null
   context_length: number | null
   max_tokens: number | null
   timeout_ms: number | null
@@ -1237,7 +1243,6 @@ export class AgentRuntimePresenter implements IAgentImplementation {
     if (!state && !dbSession) {
       throw new Error(`Session ${sessionId} not found`)
     }
-
     const providerId = state?.providerId ?? dbSession?.provider_id
     const modelId = state?.modelId ?? dbSession?.model_id
     if (!providerId || !modelId) {
@@ -1987,6 +1992,7 @@ export class AgentRuntimePresenter implements IAgentImplementation {
     const modelConfig: ModelConfig = {
       ...baseModelConfig,
       temperature: generationSettings.temperature,
+      topP: generationSettings.topP,
       contextLength: generationSettings.contextLength,
       maxTokens: capAgentRequestMaxTokens(generationSettings.maxTokens, contextBudgetLength),
       timeout: generationSettings.timeout,
@@ -3328,6 +3334,9 @@ export class AgentRuntimePresenter implements IAgentImplementation {
     if (sessionRow.temperature !== null) {
       patch.temperature = sessionRow.temperature
     }
+    if (sessionRow.top_p !== null) {
+      patch.topP = sessionRow.top_p
+    }
     if (sessionRow.context_length !== null) {
       patch.contextLength = sessionRow.context_length
     }
@@ -3375,6 +3384,9 @@ export class AgentRuntimePresenter implements IAgentImplementation {
     if (Object.prototype.hasOwnProperty.call(requestedPatch, 'temperature')) {
       patch.temperature = sanitized.temperature
     }
+    if (Object.prototype.hasOwnProperty.call(requestedPatch, 'topP')) {
+      patch.topP = sanitized.topP
+    }
     if (Object.prototype.hasOwnProperty.call(requestedPatch, 'contextLength')) {
       patch.contextLength = sanitized.contextLength
     }
@@ -3402,6 +3414,9 @@ export class AgentRuntimePresenter implements IAgentImplementation {
     if (Object.prototype.hasOwnProperty.call(requestedPatch, 'imageGeneration')) {
       patch.imageGeneration = sanitized.imageGeneration
     }
+    if (Object.prototype.hasOwnProperty.call(requestedPatch, 'videoGeneration')) {
+      patch.videoGeneration = sanitized.videoGeneration
+    }
 
     return patch
   }
@@ -3412,6 +3427,7 @@ export class AgentRuntimePresenter implements IAgentImplementation {
     return {
       systemPrompt: settings.systemPrompt,
       temperature: settings.temperature,
+      topP: settings.topP,
       contextLength: settings.contextLength,
       maxTokens: settings.maxTokens,
       timeout: settings.timeout,
@@ -3420,7 +3436,8 @@ export class AgentRuntimePresenter implements IAgentImplementation {
       reasoningVisibility: settings.reasoningVisibility,
       verbosity: settings.verbosity,
       forceInterleavedThinkingCompat: settings.forceInterleavedThinkingCompat,
-      imageGeneration: settings.imageGeneration
+      imageGeneration: settings.imageGeneration,
+      videoGeneration: settings.videoGeneration
     }
   }
 
@@ -3466,6 +3483,7 @@ export class AgentRuntimePresenter implements IAgentImplementation {
         fixedTemperatureKimi?.temperature ??
         parseFiniteNumericValue(modelConfig.temperature) ??
         0.7,
+      topP: normalizeTopP(modelConfig.topP),
       contextLength: contextLengthDefault,
       timeout:
         timeoutDefault >= MODEL_TIMEOUT_MIN_MS && timeoutDefault <= MODEL_TIMEOUT_MAX_MS
@@ -3607,6 +3625,15 @@ export class AgentRuntimePresenter implements IAgentImplementation {
       }
     }
 
+    if (Object.prototype.hasOwnProperty.call(patch, 'topP')) {
+      const normalizedTopP = normalizeTopP(patch.topP)
+      if (normalizedTopP !== undefined) {
+        next.topP = normalizedTopP
+      } else {
+        delete next.topP
+      }
+    }
+
     if (Object.prototype.hasOwnProperty.call(patch, 'timeout')) {
       const error = validateGenerationNumericField('timeout', patch.timeout)
       const numeric = toValidNonNegativeInteger(parseFiniteNumericValue(patch.timeout))

src/main/presenter/configPresenter/modelConfig.ts

@@ -184,6 +184,7 @@ export class ModelConfigHelper {
       contextLength: resolveModelContextLength(model.limit?.context),
       timeout: DEFAULT_MODEL_TIMEOUT,
       temperature: 0.6,
+      topP: undefined,
       vision: isImageInputSupported(model),
       speechRecognition: false,
       functionCall: resolveModelFunctionCall(model.tool_call),
@@ -488,6 +489,7 @@ export class ModelConfigHelper {
         ...DEFAULT_MODEL_CAPABILITY_FALLBACKS,
         timeout: DEFAULT_MODEL_TIMEOUT,
         temperature: 0.6,
+        topP: undefined,
         type: ModelType.Chat,
         apiEndpoint: ApiEndpointType.Chat,
         endpointType: undefined,
@@ -512,6 +514,7 @@ export class ModelConfigHelper {
         contextLength: storedConfig.contextLength ?? finalConfig.contextLength,
         timeout: storedConfig.timeout ?? finalConfig.timeout,
         temperature: storedConfig.temperature ?? finalConfig.temperature,
+        topP: storedConfig.topP ?? finalConfig.topP,
         vision: storedConfig.vision ?? finalConfig.vision,
         speechRecognition: storedConfig.speechRecognition ?? finalConfig.speechRecognition,
         functionCall: storedConfig.functionCall ?? finalConfig.functionCall,

src/main/presenter/llmProviderPresenter/aiSdk/runtime.ts

@@ -1178,7 +1178,8 @@ export async function runAiSdkGenerateText(
     maxOutputTokens: maxTokens,
     ...(shouldSendTemperature && resolvedTemperature !== undefined
       ? { temperature: resolvedTemperature }
-      : {})
+      : {}),
+    ...(normalizedModelConfig.topP !== undefined ? { topP: normalizedModelConfig.topP } : {})
   }
 
   await context.emitRequestTrace?.(normalizedModelConfig, {
@@ -1195,6 +1196,7 @@ export async function runAiSdkGenerateText(
     ...(shouldSendTemperature && resolvedTemperature !== undefined
       ? { temperature: resolvedTemperature }
       : {}),
+    ...(normalizedModelConfig.topP !== undefined ? { topP: normalizedModelConfig.topP } : {}),
     maxOutputTokens: maxTokens
   })
 
@@ -1380,6 +1382,7 @@ export async function* runAiSdkCoreStream(
     ...(shouldSendTemperature && resolvedTemperature !== undefined
       ? { temperature: resolvedTemperature }
       : {}),
+    ...(normalizedModelConfig.topP !== undefined ? { topP: normalizedModelConfig.topP } : {}),
     tools: tools.map((tool) => tool.function.name)
   }
 
@@ -1398,6 +1401,7 @@ export async function* runAiSdkCoreStream(
     ...(shouldSendTemperature && resolvedTemperature !== undefined
       ? { temperature: resolvedTemperature }
       : {}),
+    ...(normalizedModelConfig.topP !== undefined ? { topP: normalizedModelConfig.topP } : {}),
     maxOutputTokens: maxTokens
   })
 

src/main/presenter/sqlitePresenter/schemaCatalog.ts

@@ -117,6 +117,7 @@ const CATALOG_DEFINITIONS: CatalogDefinition[] = [
     repairableColumns: {
       system_prompt: 'ALTER TABLE deepchat_sessions ADD COLUMN system_prompt TEXT;',
       temperature: 'ALTER TABLE deepchat_sessions ADD COLUMN temperature REAL;',
+      top_p: 'ALTER TABLE deepchat_sessions ADD COLUMN top_p REAL;',
       context_length: 'ALTER TABLE deepchat_sessions ADD COLUMN context_length INTEGER;',
       max_tokens: 'ALTER TABLE deepchat_sessions ADD COLUMN max_tokens INTEGER;',
       thinking_budget: 'ALTER TABLE deepchat_sessions ADD COLUMN thinking_budget INTEGER;',
@@ -131,7 +132,9 @@ const CATALOG_DEFINITIONS: CatalogDefinition[] = [
         'ALTER TABLE deepchat_sessions ADD COLUMN force_interleaved_thinking_compat INTEGER;',
       reasoning_visibility: 'ALTER TABLE deepchat_sessions ADD COLUMN reasoning_visibility TEXT;',
       image_generation_options_json:
-        'ALTER TABLE deepchat_sessions ADD COLUMN image_generation_options_json TEXT;'
+        'ALTER TABLE deepchat_sessions ADD COLUMN image_generation_options_json TEXT;',
+      video_generation_options_json:
+        'ALTER TABLE deepchat_sessions ADD COLUMN video_generation_options_json TEXT;'
     },
     typeCheckedColumns: [
       'summary_cursor_order_seq',