admin/Hermes-ui
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add Anthropic format conversion for chat runs and improvements (#347)

Browse Source 
* 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
2026-04-30 16:40:37 +08:00
committed by GitHub
parent 2e87cb910c
commit cd14bb1963
25 changed files with 1097 additions and 437 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/client/src/api/hermes/chat.ts
+8 -4
View File
@@ -134,10 +134,14 @@ export function startRunViaSocket(
// All event handlers share the same cleanup logic
const handleEvent = (event: RunEvent) => {
if (closed) return
onEvent(event)
if (event.event === 'run.completed' || event.event === 'run.failed') {
cleanup()
onDone()
try {
onEvent(event)
} finally {
if (event.event === 'run.completed' || event.event === 'run.failed') {
console.log('[startRunViaSocket] Run completed/failed, calling cleanup and onDone', event.event)
cleanup()
onDone()
}
}
}
packages/client/src/components/hermes/chat/MessageItem.vue
+4 -2
View File
@@ -119,8 +119,9 @@ onBeforeUnmount(() => {
const thinkingDurationMs = computed<number | null>(() => {
const ob = chatStore.getThinkingObservation(props.message.id);
if (!ob?.startedAt) return null;
const end = ob.endedAt ?? (props.message.isStreaming ? nowTick.value : ob.startedAt);
return Math.max(0, end - ob.startedAt);
const startedAt = ob.startedAt!; // Non-null assertion after check
const end = ob?.endedAt ?? (props.message.isStreaming ? nowTick.value : startedAt);
return Math.max(0, end - startedAt);
});
function formatDuration(ms: number): string {
@@ -762,6 +763,7 @@ const renderedToolResult = computed(() => {
padding: 0 4px;
border-radius: 3px;
line-height: 14px;
margin-left: 4px;
}
.tool-details {
packages/client/src/components/hermes/chat/MessageList.vue
+74 -10
View File
@@ -18,6 +18,14 @@ function formatTokens(n: number): string {
return String(n)
}
function formatToolDuration(seconds: number): string {
if (seconds < 1) return `${Math.round(seconds * 1000)}ms`
if (seconds < 60) return `${Math.round(seconds * 10) / 10}s`
const mins = Math.floor(seconds / 60)
const secs = Math.round(seconds % 60)
return `${mins}m ${secs}s`
}
const displayMessages = computed(() =>
chatStore.messages.filter((m) => m.role !== "tool"),
);
@@ -198,13 +206,52 @@ watch(currentToolCalls, () => {
<span v-if="tc.toolPreview" class="tool-call-preview">{{
tc.toolPreview
}}</span>
<span
v-if="tc.toolDuration && tc.toolStatus !== 'running'"
class="tool-call-duration"
:title="$t('chat.executionDuration')"
>{{ formatToolDuration(tc.toolDuration) }}</span
>
<svg
v-if="tc.toolStatus === 'done'"
width="16"
height="16"
viewBox="0 0 24 24"
fill="none"
class="tool-call-success-icon"
>
<circle cx="12" cy="12" r="10" fill="currentColor" fill-opacity="0.15"/>
<path
d="M8 12L11 15L16 9"
stroke="currentColor"
stroke-width="2"
stroke-linecap="round"
stroke-linejoin="round"
fill="none"
/>
</svg>
<span
v-if="tc.toolStatus === 'running'"
class="tool-call-spinner"
></span>
<span v-if="tc.toolStatus === 'error'" class="tool-call-error">{{
t("chat.error")
}}</span>
<svg
v-if="tc.toolStatus === 'error'"
width="16"
height="16"
viewBox="0 0 24 24"
fill="none"
class="tool-call-error-icon"
>
<circle cx="12" cy="12" r="10" fill="currentColor" fill-opacity="0.15"/>
<path
d="M15 9L9 15M9 9L15 15"
stroke="currentColor"
stroke-width="2"
stroke-linecap="round"
stroke-linejoin="round"
fill="none"
/>
</svg>
</div>
</div>
</div>
@@ -334,13 +381,30 @@ watch(currentToolCalls, () => {
flex-shrink: 0;
}
.tool-call-error {
font-size: 9px;
color: $error;
background: rgba($error, 0.08);
padding: 0 4px;
border-radius: 3px;
line-height: 14px;
.tool-call-error-icon {
color: #ff4d4f;
flex-shrink: 0;
margin-left: 6px;
display: flex;
align-items: center;
justify-content: center;
}
.tool-call-duration {
font-size: 10px;
color: $text-muted;
font-family: $font-code;
margin-left: 4px;
flex-shrink: 0;
}
.tool-call-success-icon {
color: #52c41a;
flex-shrink: 0;
margin-left: 6px;
display: flex;
align-items: center;
justify-content: center;
}
@keyframes spin {
packages/client/src/data/changelog.ts
+23
View File
@@ -5,6 +5,29 @@ export interface ChangelogEntry {
}
export const changelog: ChangelogEntry[] = [
{
version: '0.5.3',
date: '2026-04-30',
changes: [
'changelog.new_0_5_3_1',
'changelog.new_0_5_3_2',
'changelog.new_0_5_3_3',
'changelog.new_0_5_3_4',
'changelog.new_0_5_3_5',
],
},
{
version: '0.5.2',
date: '2026-04-29',
changes: [
'changelog.new_0_5_2_1',
'changelog.new_0_5_2_2',
'changelog.new_0_5_2_3',
'changelog.new_0_5_2_4',
'changelog.new_0_5_2_5',
'changelog.new_0_5_2_6',
],
},
{
version: '0.5.1',
date: '2026-04-29',
packages/client/src/i18n/locales/de.ts
+12 -1
View File
@@ -131,7 +131,7 @@ export default {
arguments: 'Argumente',
result: 'Ergebnis',
truncated: '... (abgeschnitten)',
thinkingLabel: 'Denkprozess',
executionDuration: 'Execution time', thinkingLabel: 'Denkprozess',
thinkingInProgress: 'Denkt…',
thinkingShow: 'Denkprozess anzeigen',
thinkingHide: 'Denkprozess ausblenden',
@@ -563,6 +563,17 @@ jobTriggered: 'Job ausgelost',
// Anderungsprotokoll
changelog: {
new_0_5_3_1: 'Improve reasoning process display with persistence across page refreshes',
new_0_5_3_2: 'Optimize stringified array format parsing to extract thinking/text/tool_calls',
new_0_5_3_3: 'Improve log display by removing ellipsis and showing full content',
new_0_5_3_4: 'Add detailed logging for format conversion and parsing',
new_0_5_3_5: 'Optimize token calculation to accurately include tool results',
new_0_5_2_1: 'Convert conversation history to Anthropic format before sending to Gateway',
new_0_5_2_2: 'Add bidirectional reasoning sync between memory and database',
new_0_5_2_3: 'Add message pagination with DESC query + array reverse for performance',
new_0_5_2_4: 'Clean up debug code and unused imports',
new_0_5_2_5: 'Remove auto-resumed event trigger to avoid timing issues',
new_0_5_2_6: 'Use reasoning field consistently across codebase',
new_0_5_1_1: 'Auto-sync Hermes history sessions on first startup',
new_0_5_1_2: 'Fix session sync failure with old Hermes versions (backward compatible)',
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
packages/client/src/i18n/locales/en.ts
+12
View File
@@ -154,6 +154,7 @@ export default {
arguments: 'Arguments',
result: 'Result',
truncated: '... (truncated)',
executionDuration: 'Execution time',
thinkingLabel: 'Thinking',
thinkingInProgress: 'Thinking…',
thinkingShow: 'Show thinking',
@@ -727,6 +728,17 @@ export default {
// Changelog
changelog: {
new_0_5_3_1: 'Improve reasoning process display with persistence across page refreshes',
new_0_5_3_2: 'Optimize stringified array format parsing to extract thinking/text/tool_calls',
new_0_5_3_3: 'Improve log display by removing ellipsis and showing full content',
new_0_5_3_4: 'Add detailed logging for format conversion and parsing',
new_0_5_3_5: 'Optimize token calculation to accurately include tool results',
new_0_5_2_1: 'Convert conversation history to Anthropic format before sending to Gateway',
new_0_5_2_2: 'Add bidirectional reasoning sync between memory and database',
new_0_5_2_3: 'Add message pagination with DESC query + array reverse for performance',
new_0_5_2_4: 'Clean up debug code and unused imports',
new_0_5_2_5: 'Remove auto-resumed event trigger to avoid timing issues',
new_0_5_2_6: 'Use reasoning field consistently across codebase',
new_0_5_1_1: 'Auto-sync Hermes history sessions on first startup',
new_0_5_1_2: 'Fix session sync failure with old Hermes versions (backward compatible)',
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
packages/client/src/i18n/locales/es.ts
+12 -1
View File
@@ -131,7 +131,7 @@ export default {
arguments: 'Argumentos',
result: 'Resultado',
truncated: '... (truncado)',
thinkingLabel: 'Pensamiento',
executionDuration: 'Execution time', thinkingLabel: 'Pensamiento',
thinkingInProgress: 'Pensando…',
thinkingShow: 'Mostrar pensamiento',
thinkingHide: 'Ocultar pensamiento',
@@ -563,6 +563,17 @@ jobTriggered: 'Job ejecutado',
// Registro de cambios
changelog: {
new_0_5_3_1: 'Improve reasoning process display with persistence across page refreshes',
new_0_5_3_2: 'Optimize stringified array format parsing to extract thinking/text/tool_calls',
new_0_5_3_3: 'Improve log display by removing ellipsis and showing full content',
new_0_5_3_4: 'Add detailed logging for format conversion and parsing',
new_0_5_3_5: 'Optimize token calculation to accurately include tool results',
new_0_5_2_1: 'Convert conversation history to Anthropic format before sending to Gateway',
new_0_5_2_2: 'Add bidirectional reasoning sync between memory and database',
new_0_5_2_3: 'Add message pagination with DESC query + array reverse for performance',
new_0_5_2_4: 'Clean up debug code and unused imports',
new_0_5_2_5: 'Remove auto-resumed event trigger to avoid timing issues',
new_0_5_2_6: 'Use reasoning field consistently across codebase',
new_0_5_1_1: 'Auto-sync Hermes history sessions on first startup',
new_0_5_1_2: 'Fix session sync failure with old Hermes versions (backward compatible)',
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
packages/client/src/i18n/locales/fr.ts
+12 -1
View File
@@ -131,7 +131,7 @@ export default {
arguments: 'Arguments',
result: 'Resultat',
truncated: '... (tronque)',
thinkingLabel: 'Raisonnement',
executionDuration: 'Execution time', thinkingLabel: 'Raisonnement',
thinkingInProgress: 'En réflexion…',
thinkingShow: 'Afficher le raisonnement',
thinkingHide: 'Masquer le raisonnement',
@@ -563,6 +563,17 @@ jobTriggered: 'Job declenche',
// Journal des modifications
changelog: {
new_0_5_3_1: 'Improve reasoning process display with persistence across page refreshes',
new_0_5_3_2: 'Optimize stringified array format parsing to extract thinking/text/tool_calls',
new_0_5_3_3: 'Improve log display by removing ellipsis and showing full content',
new_0_5_3_4: 'Add detailed logging for format conversion and parsing',
new_0_5_3_5: 'Optimize token calculation to accurately include tool results',
new_0_5_2_1: 'Convert conversation history to Anthropic format before sending to Gateway',
new_0_5_2_2: 'Add bidirectional reasoning sync between memory and database',
new_0_5_2_3: 'Add message pagination with DESC query + array reverse for performance',
new_0_5_2_4: 'Clean up debug code and unused imports',
new_0_5_2_5: 'Remove auto-resumed event trigger to avoid timing issues',
new_0_5_2_6: 'Use reasoning field consistently across codebase',
new_0_5_1_1: 'Auto-sync Hermes history sessions on first startup',
new_0_5_1_2: 'Fix session sync failure with old Hermes versions (backward compatible)',
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
packages/client/src/i18n/locales/ja.ts
+12 -1
View File
@@ -131,7 +131,7 @@ export default {
arguments: '引数',
result: '結果',
truncated: '... (省略)',
thinkingLabel: '思考過程',
executionDuration: 'Execution time', thinkingLabel: '思考過程',
thinkingInProgress: '思考中…',
thinkingShow: '思考過程を表示',
thinkingHide: '思考過程を隠す',
@@ -563,6 +563,17 @@ export default {
// 更新履歴
changelog: {
new_0_5_3_1: 'Improve reasoning process display with persistence across page refreshes',
new_0_5_3_2: 'Optimize stringified array format parsing to extract thinking/text/tool_calls',
new_0_5_3_3: 'Improve log display by removing ellipsis and showing full content',
new_0_5_3_4: 'Add detailed logging for format conversion and parsing',
new_0_5_3_5: 'Optimize token calculation to accurately include tool results',
new_0_5_2_1: 'Convert conversation history to Anthropic format before sending to Gateway',
new_0_5_2_2: 'Add bidirectional reasoning sync between memory and database',
new_0_5_2_3: 'Add message pagination with DESC query + array reverse for performance',
new_0_5_2_4: 'Clean up debug code and unused imports',
new_0_5_2_5: 'Remove auto-resumed event trigger to avoid timing issues',
new_0_5_2_6: 'Use reasoning field consistently across codebase',
new_0_5_1_1: 'Auto-sync Hermes history sessions on first startup',
new_0_5_1_2: 'Fix session sync failure with old Hermes versions (backward compatible)',
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
packages/client/src/i18n/locales/ko.ts
+12 -1
View File
@@ -131,7 +131,7 @@ export default {
arguments: '인수',
result: '결과',
truncated: '... (잘림)',
thinkingLabel: '사고 과정',
executionDuration: 'Execution time', thinkingLabel: '사고 과정',
thinkingInProgress: '사고 중…',
thinkingShow: '사고 과정 펼치기',
thinkingHide: '사고 과정 접기',
@@ -563,6 +563,17 @@ export default {
// 변경 이력
changelog: {
new_0_5_3_1: 'Improve reasoning process display with persistence across page refreshes',
new_0_5_3_2: 'Optimize stringified array format parsing to extract thinking/text/tool_calls',
new_0_5_3_3: 'Improve log display by removing ellipsis and showing full content',
new_0_5_3_4: 'Add detailed logging for format conversion and parsing',
new_0_5_3_5: 'Optimize token calculation to accurately include tool results',
new_0_5_2_1: 'Convert conversation history to Anthropic format before sending to Gateway',
new_0_5_2_2: 'Add bidirectional reasoning sync between memory and database',
new_0_5_2_3: 'Add message pagination with DESC query + array reverse for performance',
new_0_5_2_4: 'Clean up debug code and unused imports',
new_0_5_2_5: 'Remove auto-resumed event trigger to avoid timing issues',
new_0_5_2_6: 'Use reasoning field consistently across codebase',
new_0_5_1_1: 'Auto-sync Hermes history sessions on first startup',
new_0_5_1_2: 'Fix session sync failure with old Hermes versions (backward compatible)',
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
packages/client/src/i18n/locales/pt.ts
+12 -1
View File
@@ -131,7 +131,7 @@ export default {
arguments: 'Argumentos',
result: 'Resultado',
truncated: '... (truncado)',
thinkingLabel: 'Raciocínio',
executionDuration: 'Execution time', thinkingLabel: 'Raciocínio',
thinkingInProgress: 'Pensando…',
thinkingShow: 'Mostrar raciocínio',
thinkingHide: 'Ocultar raciocínio',
@@ -563,6 +563,17 @@ jobTriggered: 'Job acionado',
// Registro de alteracoes
changelog: {
new_0_5_3_1: 'Improve reasoning process display with persistence across page refreshes',
new_0_5_3_2: 'Optimize stringified array format parsing to extract thinking/text/tool_calls',
new_0_5_3_3: 'Improve log display by removing ellipsis and showing full content',
new_0_5_3_4: 'Add detailed logging for format conversion and parsing',
new_0_5_3_5: 'Optimize token calculation to accurately include tool results',
new_0_5_2_1: 'Convert conversation history to Anthropic format before sending to Gateway',
new_0_5_2_2: 'Add bidirectional reasoning sync between memory and database',
new_0_5_2_3: 'Add message pagination with DESC query + array reverse for performance',
new_0_5_2_4: 'Clean up debug code and unused imports',
new_0_5_2_5: 'Remove auto-resumed event trigger to avoid timing issues',
new_0_5_2_6: 'Use reasoning field consistently across codebase',
new_0_5_1_1: 'Auto-sync Hermes history sessions on first startup',
new_0_5_1_2: 'Fix session sync failure with old Hermes versions (backward compatible)',
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
packages/client/src/i18n/locales/zh.ts
+12
View File
@@ -154,6 +154,7 @@ export default {
arguments: '参数',
result: '结果',
truncated: '... (已截断)',
executionDuration: '执行时长',
thinkingLabel: '思考过程',
thinkingInProgress: '思考中…',
thinkingShow: '展开思考过程',
@@ -729,6 +730,17 @@ export default {
// 更新日志
changelog: {
new_0_5_3_1: '改进思考过程显示，支持页面刷新后持久化',
new_0_5_3_2: '优化字符串化数组格式解析，自动提取思考/文本/工具调用',
new_0_5_3_3: '改进日志显示，移除省略号完整展示日志内容',
new_0_5_3_4: '添加详细的格式转换和解析日志记录',
new_0_5_3_5: '优化 token 计算，准确包含 tool 结果',
new_0_5_2_1: '将对话历史转换为 Anthropic 格式后发送给 Gateway',
new_0_5_2_2: '添加内存和数据库之间的双向思考过程同步',
new_0_5_2_3: '添加消息分页功能（DESC 查询 + 数组反转，性能优化）',
new_0_5_2_4: '清理调试代码和未使用的导入',
new_0_5_2_5: '移除自动 resumed 事件触发，避免时序问题',
new_0_5_2_6: '统一使用 reasoning 字段',
new_0_5_1_1: '首次启动时自动同步 Hermes 历史会话',
new_0_5_1_2: '修复旧版本 Hermes 会话同步失败问题（向后兼容）',
new_0_5_1_3: 'Profile 克隆时智能清理独占平台凭据（Telegram、Discord、Slack 等）',
packages/client/src/stores/hermes/chat.ts
+77 -22
View File
@@ -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) {
packages/client/src/views/hermes/LogsView.vue
+3 -3
View File
@@ -261,9 +261,9 @@ onMounted(async () => {
.log-message {
color: $text-secondary;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
overflow: visible;
white-space: normal;
word-break: break-word;
min-width: 0;
}