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>
This commit is contained in:
@@ -119,8 +119,10 @@ export const useAgentChat = (uiMessages: ExtendedUIMessage[]) => {
|
||||
type UsageMetadata = {
|
||||
inputTokens: number;
|
||||
outputTokens: number;
|
||||
cachedInputTokens: number;
|
||||
inputCredits: number;
|
||||
outputCredits: number;
|
||||
conversationSize: number;
|
||||
};
|
||||
type ModelMetadata = {
|
||||
contextWindowTokens: number;
|
||||
@@ -133,11 +135,17 @@ export const useAgentChat = (uiMessages: ExtendedUIMessage[]) => {
|
||||
|
||||
if (isDefined(usage) && isDefined(model)) {
|
||||
setAgentChatUsage((prev) => ({
|
||||
lastMessage: {
|
||||
inputTokens: usage.inputTokens,
|
||||
outputTokens: usage.outputTokens,
|
||||
cachedInputTokens: usage.cachedInputTokens,
|
||||
inputCredits: usage.inputCredits,
|
||||
outputCredits: usage.outputCredits,
|
||||
},
|
||||
conversationSize: usage.conversationSize,
|
||||
contextWindowTokens: model.contextWindowTokens,
|
||||
inputTokens: (prev?.inputTokens ?? 0) + usage.inputTokens,
|
||||
outputTokens: (prev?.outputTokens ?? 0) + usage.outputTokens,
|
||||
totalTokens:
|
||||
(prev?.totalTokens ?? 0) + usage.inputTokens + usage.outputTokens,
|
||||
contextWindowTokens: model.contextWindowTokens,
|
||||
inputCredits: (prev?.inputCredits ?? 0) + usage.inputCredits,
|
||||
outputCredits: (prev?.outputCredits ?? 0) + usage.outputCredits,
|
||||
}));
|
||||
|
||||
@@ -23,16 +23,17 @@ const setUsageFromThread = (
|
||||
thread: AgentChatThread,
|
||||
setAgentChatUsage: SetterOrUpdater<AgentChatUsageState | null>,
|
||||
) => {
|
||||
const totalTokens = thread.totalInputTokens + thread.totalOutputTokens;
|
||||
const hasUsageData = totalTokens > 0 && isDefined(thread.contextWindowTokens);
|
||||
const hasUsageData =
|
||||
(thread.conversationSize ?? 0) > 0 && isDefined(thread.contextWindowTokens);
|
||||
|
||||
setAgentChatUsage(
|
||||
hasUsageData
|
||||
? {
|
||||
lastMessage: null,
|
||||
conversationSize: thread.conversationSize ?? 0,
|
||||
contextWindowTokens: thread.contextWindowTokens ?? 0,
|
||||
inputTokens: thread.totalInputTokens,
|
||||
outputTokens: thread.totalOutputTokens,
|
||||
totalTokens,
|
||||
contextWindowTokens: thread.contextWindowTokens ?? 0,
|
||||
inputCredits: thread.totalInputCredits,
|
||||
outputCredits: thread.totalOutputCredits,
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user