feat: add Anthropic format conversion for chat runs and improvements (#347)
* fix: improve chat compression and tool display Context Compression Fixes: - Remove duplicate token calculation in compress() - Simplify compress() to only execute compression, not judge - Add buildConversationHistory() to preserve tool calls in LLM context - Remove unused estimateMessagesTokens() and contextLength parameter - Move all judgment logic to chat-run-socket.ts (uses accurate DB tokens) Tool Call Display Improvements: - Add tool execution duration display (format: 1.272s) - Add success/error status icons with circular backgrounds - Replace text error with SVG icon (X in red circle) - Replace old checkmark with polished green checkmark icon - Add i18n key 'chat.executionDuration' for all locales Bug Fixes: - Fix streaming-indicator stuck by adding try-finally in handleEvent - Add debug logging for compression flow diagnosis - Fix template syntax error in MessageList.vue Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(chat): convert conversation history to Anthropic format before sending to Gateway - Add convertToAnthropicFormat() to transform OpenAI format to Anthropic format - Handle DeepSeek reasoning_content in thinking blocks - Properly convert tool_use and tool_result blocks - Add convertFromAnthropicFormat() for parsing SSE responses - Handle stringified Python arrays in resume messages - Record debug history files for troubleshooting (original vs converted) - Fix tool_call_id validation to prevent empty ID errors - Clean internal Hermes fields (call_id, response_item_id) from tool_calls Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(chat): optimize message parsing and add debug logging - Only check for stringified arrays in assistant messages (performance) - Improve parsing error handling: keep original content on parse failure - Add debug logging for upstream events (reasoning/thinking tracking) - Log run.completed event keys for troubleshooting Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(chat): add message pagination and reasoning sync improvements **Message Pagination:** - Add getSessionDetailPaginated() for paginated message loading - Query with DESC order then reverse in code for optimal performance - Remove listSessionsPaginated() (not needed) **Reasoning Sync:** - Add bidirectional reasoning merge in syncFromHermes - Memory → DB: preserve streamed reasoning from SSE events - DB → Memory: restore reasoning if Hermes Gateway fixes storage - Send resumed event after sync completes with complete messages - Fix reasoning field inconsistency: use unified 'reasoning' field **Message Parsing:** - Only parse stringified arrays for assistant messages (performance) - Improve parse error handling: keep original content on failure - Add debug logging for upstream reasoning/thinking events **Bug Fixes:** - Fix reasoning content display: now works on both SSE and resume - Ensure reasoning is preserved across page refreshes via sync + resumed event Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: increase default pagination limit for messages to 500 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: remove auto-resumed event trigger and clean up debug code - Remove automatic resumed event trigger in syncFromHermes to avoid timing issues - Clean up unused imports (fs, join) - Remove debug history file logging code - Fix socket parameter passing in handleAbort, markCompleted, and syncFromHermes - Change usage emit from room broadcast to socket-only emit - Remove console.log debug statement Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: use reasoning field in convertToAnthropicFormat Change convertToAnthropicFormat to read from reasoning field instead of reasoning_content for consistency with database schema and frontend. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat: parse stringified array content and improve logs - Parse stringified array format in run.completed to extract thinking/text/tool_use - Send parsed content to frontend via parsed_content/parsed_reasoning/parsed_tool_calls - Frontend updates last assistant message with parsed content - Remove ellipsis from log messages, show full content - Add detailed logging for conversion and parsing Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: move finalOutputTrimmed outside else block * fix(chat): handle double-serialized content in resumeSession - Remove outer quotes before parsing stringified array format - Updated changelog for v0.5.2 and v0.5.3 with multilingual support - Fixed message pagination with DESC query + array reverse Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(chat): improve error logging for resume parsing - Add detailed logging for double-serialized content parsing - Log content preview when parsing fails to diagnose issues Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * revert(chat): use simple Python-to-JSON replacement - Revert to simple .replace(/'/g, '"') approach - Parsing failures will keep original content as-is Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
ekko
@@ -26,6 +26,7 @@ export interface Message {
|
||||
toolArgs?: string
|
||||
toolResult?: string
|
||||
toolStatus?: 'running' | 'done' | 'error'
|
||||
toolDuration?: number // 工具执行时长（秒）
|
||||
isStreaming?: boolean
|
||||
attachments?: Attachment[]
|
||||
// 思考/推理文本。两条来源：
|
||||
@@ -615,8 +616,10 @@ export const useChatStore = defineStore('chat', () => {
|
||||
|
||||
// Helper to clean up this session's stream state
|
||||
const cleanup = () => {
|
||||
console.log('[sendMessage] cleanup called, deleting stream state for sid:', sid)
|
||||
streamStates.value.delete(sid)
|
||||
serverWorking.value.delete(sid)
|
||||
console.log('[sendMessage] cleanup done, isStreaming now:', isStreaming.value)
|
||||
}
|
||||
|
||||
// Per-run flags used to detect silently-swallowed errors at run.completed.
|
||||
@@ -765,7 +768,13 @@ export const useChatStore = defineStore('chat', () => {
|
||||
)
|
||||
if (toolMsgs.length > 0) {
|
||||
const last = toolMsgs[toolMsgs.length - 1]
|
||||
updateMessage(sid, last.id, { toolStatus: 'done' })
|
||||
// Check if tool errored
|
||||
const hasError = (evt as any).error === true
|
||||
const duration = (evt as any).duration
|
||||
updateMessage(sid, last.id, {
|
||||
toolStatus: hasError ? 'error' : 'done',
|
||||
toolDuration: duration,
|
||||
})
|
||||
}
|
||||
|
||||
break
|
||||
@@ -790,17 +799,38 @@ export const useChatStore = defineStore('chat', () => {
|
||||
// stream). If we never produced assistant text but the gateway
|
||||
// reports a non-empty output, fall back to rendering it as a
|
||||
// single assistant message so the user actually sees the reply.
|
||||
const finalOutput =
|
||||
typeof evt.output === 'string' ? evt.output : ''
|
||||
const finalOutputTrimmed = finalOutput.trim()
|
||||
if (!runProducedAssistantText && finalOutputTrimmed !== '') {
|
||||
addMessage(sid, {
|
||||
id: uid(),
|
||||
role: 'assistant',
|
||||
content: finalOutput,
|
||||
timestamp: Date.now(),
|
||||
})
|
||||
runProducedAssistantText = true
|
||||
|
||||
// Check if backend provided parsed content (from stringified array format)
|
||||
let finalOutputTrimmed = ''
|
||||
if ((evt as any).parsed_content !== undefined) {
|
||||
// Backend has parsed stringified array format, update last assistant message
|
||||
const msgs = getSessionMsgs(sid)
|
||||
const lastAssistant = [...msgs].reverse().find(m => m.role === 'assistant')
|
||||
if (lastAssistant) {
|
||||
updateMessage(sid, lastAssistant.id, {
|
||||
content: (evt as any).parsed_content || '',
|
||||
})
|
||||
if ((evt as any).parsed_reasoning) {
|
||||
updateMessage(sid, lastAssistant.id, {
|
||||
reasoning: (evt as any).parsed_reasoning,
|
||||
})
|
||||
}
|
||||
finalOutputTrimmed = ((evt as any).parsed_content || '').trim()
|
||||
}
|
||||
} else {
|
||||
// Fallback to output field (legacy behavior)
|
||||
const finalOutput =
|
||||
typeof evt.output === 'string' ? evt.output : ''
|
||||
finalOutputTrimmed = finalOutput.trim()
|
||||
if (!runProducedAssistantText && finalOutputTrimmed !== '') {
|
||||
addMessage(sid, {
|
||||
id: uid(),
|
||||
role: 'assistant',
|
||||
content: finalOutput,
|
||||
timestamp: Date.now(),
|
||||
})
|
||||
runProducedAssistantText = true
|
||||
}
|
||||
}
|
||||
// Workaround for upstream hermes-agent bug: when the agent
|
||||
// layer silently swallows an error (e.g. invalid API key,
|
||||
@@ -875,6 +905,7 @@ export const useChatStore = defineStore('chat', () => {
|
||||
},
|
||||
// onDone
|
||||
() => {
|
||||
console.log('[sendMessage] onDone callback called, cleaning up stream state')
|
||||
const msgs = getSessionMsgs(sid)
|
||||
const last = msgs[msgs.length - 1]
|
||||
if (last?.isStreaming) {
|
||||
@@ -1076,7 +1107,11 @@ export const useChatStore = defineStore('chat', () => {
|
||||
const msgs = getSessionMsgs(sid)
|
||||
const toolMsgs = msgs.filter(m => m.role === 'tool' && m.toolStatus === 'running')
|
||||
if (toolMsgs.length > 0) {
|
||||
updateMessage(sid, toolMsgs[toolMsgs.length - 1].id, { toolStatus: 'done' })
|
||||
const hasError = (evt as any).error === true
|
||||
updateMessage(sid, toolMsgs[toolMsgs.length - 1].id, {
|
||||
toolStatus: hasError ? 'error' : 'done',
|
||||
toolDuration: (evt as any).duration,
|
||||
})
|
||||
}
|
||||
|
||||
break
|
||||
@@ -1096,15 +1131,35 @@ export const useChatStore = defineStore('chat', () => {
|
||||
target.outputTokens = (evt as any).outputTokens
|
||||
}
|
||||
}
|
||||
const finalOutput = typeof evt.output === 'string' ? evt.output : ''
|
||||
const finalOutputTrimmed = finalOutput.trim()
|
||||
if (!runProducedAssistantText && finalOutputTrimmed !== '') {
|
||||
addMessage(sid, {
|
||||
id: uid(),
|
||||
role: 'assistant',
|
||||
content: finalOutput,
|
||||
timestamp: Date.now(),
|
||||
})
|
||||
// Check if backend provided parsed content (from stringified array format)
|
||||
let finalOutputTrimmed = ''
|
||||
if ((evt as any).parsed_content !== undefined) {
|
||||
// Backend has parsed stringified array format, update last assistant message
|
||||
const msgs = getSessionMsgs(sid)
|
||||
const lastAssistant = [...msgs].reverse().find(m => m.role === 'assistant')
|
||||
if (lastAssistant) {
|
||||
updateMessage(sid, lastAssistant.id, {
|
||||
content: (evt as any).parsed_content || '',
|
||||
})
|
||||
if ((evt as any).parsed_reasoning) {
|
||||
updateMessage(sid, lastAssistant.id, {
|
||||
reasoning: (evt as any).parsed_reasoning,
|
||||
})
|
||||
}
|
||||
finalOutputTrimmed = ((evt as any).parsed_content || '').trim()
|
||||
}
|
||||
} else {
|
||||
// Fallback to output field (legacy behavior)
|
||||
const finalOutput = typeof evt.output === 'string' ? evt.output : ''
|
||||
finalOutputTrimmed = finalOutput.trim()
|
||||
if (!runProducedAssistantText && finalOutputTrimmed !== '') {
|
||||
addMessage(sid, {
|
||||
id: uid(),
|
||||
role: 'assistant',
|
||||
content: finalOutput,
|
||||
timestamp: Date.now(),
|
||||
})
|
||||
}
|
||||
}
|
||||
const swallowedError = !runProducedAssistantText && !runHadToolActivity && finalOutputTrimmed === ''
|
||||
if (swallowedError) {
|
||||
|
||||
Reference in New Issue
Block a user