feat: improve AI chat - system prompt, tool output, context window display (#17769)

⚠️ **AI-generated PR — not ready for review** ⚠️

cc @FelixMalfait

---

## Changes

### System prompt improvements
- Explicit skill-before-tools workflow to prevent the model from calling
tools without loading the matching skill first
- Data efficiency guidance (default small limits, use filters)
- Pluralized `load_skill` → `load_skills` for consistency with
`load_tools`

### Token usage reduction
- Output serialization layer: strips null/undefined/empty values from
tool results
- Lowered default `find_*` limit from 100 → 10, max from 1000 → 100

### System object tool generation
- System objects (calendar events, messages, etc.) now generate AI tools
- Only workflow-related and favorite-related objects are excluded

### Context window display fix
- **Bug**: UI compared cumulative tokens (sum of all turns) against
single-request context window → showed 100% after a few turns
- **Fix**: Track `conversationSize` (last step's `inputTokens`) which
represents the actual conversation history size sent to the model
- New `conversationSize` column on thread entity with migration

### Workspace AI instructions
- Support for custom workspace-level AI instructions

---------

Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>

packages/twenty-front/src/generated/graphql.ts

@@ -21,6 +21,19 @@ export type Scalars = {
   Upload: any;
 };
 
+export type AiSystemPromptPreview = {
+  __typename?: 'AISystemPromptPreview';
+  estimatedTokenCount: Scalars['Int'];
+  sections: Array<AiSystemPromptSection>;
+};
+
+export type AiSystemPromptSection = {
+  __typename?: 'AISystemPromptSection';
+  content: Scalars['String'];
+  estimatedTokenCount: Scalars['Int'];
+  title: Scalars['String'];
+};
+
 export type ActivateWorkspaceInput = {
   displayName?: InputMaybe<Scalars['String']>;
 };
@@ -76,12 +89,13 @@ export type Agent = {
 export type AgentChatThread = {
   __typename?: 'AgentChatThread';
   contextWindowTokens?: Maybe<Scalars['Int']>;
+  conversationSize: Scalars['Int'];
   createdAt: Scalars['DateTime'];
   id: Scalars['UUID'];
   title?: Maybe<Scalars['String']>;
-  totalInputCredits: Scalars['Int'];
+  totalInputCredits: Scalars['Float'];
   totalInputTokens: Scalars['Int'];
-  totalOutputCredits: Scalars['Int'];
+  totalOutputCredits: Scalars['Float'];
   totalOutputTokens: Scalars['Int'];
   updatedAt: Scalars['DateTime'];
 };
@@ -2039,6 +2053,7 @@ export enum MessageChannelVisibility {
 
 export enum ModelProvider {
   ANTHROPIC = 'ANTHROPIC',
+  GROQ = 'GROQ',
   NONE = 'NONE',
   OPENAI = 'OPENAI',
   OPENAI_COMPATIBLE = 'OPENAI_COMPATIBLE',
@@ -4759,6 +4774,7 @@ export type UpdateWorkflowVersionStepInput = {
 };
 
 export type UpdateWorkspaceInput = {
+  aiAdditionalInstructions?: InputMaybe<Scalars['String']>;
   allowImpersonation?: InputMaybe<Scalars['Boolean']>;
   customDomain?: InputMaybe<Scalars['String']>;
   defaultRoleId?: InputMaybe<Scalars['UUID']>;
@@ -5146,6 +5162,7 @@ export type WorkflowVersionStepChanges = {
 export type Workspace = {
   __typename?: 'Workspace';
   activationStatus: WorkspaceActivationStatus;
+  aiAdditionalInstructions?: Maybe<Scalars['String']>;
   allowImpersonation: Scalars['Boolean'];
   billingEntitlements: Array<BillingEntitlement>;
   billingSubscriptions: Array<BillingSubscription>;