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
+1
-1
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"name": "hermes-web-ui",
|
"name": "hermes-web-ui",
|
||||||
"version": "0.5.2",
|
"version": "0.5.3",
|
||||||
"description": "Self-hosted AI chat dashboard for Hermes Agent — multi-model (Claude, GPT, Gemini, DeepSeek) web UI with Telegram, Discord, Slack, WhatsApp integration",
|
"description": "Self-hosted AI chat dashboard for Hermes Agent — multi-model (Claude, GPT, Gemini, DeepSeek) web UI with Telegram, Discord, Slack, WhatsApp integration",
|
||||||
"repository": {
|
"repository": {
|
||||||
"type": "git",
|
"type": "git",
|
||||||
|
|||||||
@@ -134,12 +134,16 @@ export function startRunViaSocket(
|
|||||||
// All event handlers share the same cleanup logic
|
// All event handlers share the same cleanup logic
|
||||||
const handleEvent = (event: RunEvent) => {
|
const handleEvent = (event: RunEvent) => {
|
||||||
if (closed) return
|
if (closed) return
|
||||||
|
try {
|
||||||
onEvent(event)
|
onEvent(event)
|
||||||
|
} finally {
|
||||||
if (event.event === 'run.completed' || event.event === 'run.failed') {
|
if (event.event === 'run.completed' || event.event === 'run.failed') {
|
||||||
|
console.log('[startRunViaSocket] Run completed/failed, calling cleanup and onDone', event.event)
|
||||||
cleanup()
|
cleanup()
|
||||||
onDone()
|
onDone()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
function onRunStarted(data: RunEvent) {
|
function onRunStarted(data: RunEvent) {
|
||||||
handleEvent(data)
|
handleEvent(data)
|
||||||
|
|||||||
@@ -119,8 +119,9 @@ onBeforeUnmount(() => {
|
|||||||
const thinkingDurationMs = computed<number | null>(() => {
|
const thinkingDurationMs = computed<number | null>(() => {
|
||||||
const ob = chatStore.getThinkingObservation(props.message.id);
|
const ob = chatStore.getThinkingObservation(props.message.id);
|
||||||
if (!ob?.startedAt) return null;
|
if (!ob?.startedAt) return null;
|
||||||
const end = ob.endedAt ?? (props.message.isStreaming ? nowTick.value : ob.startedAt);
|
const startedAt = ob.startedAt!; // Non-null assertion after check
|
||||||
return Math.max(0, end - ob.startedAt);
|
const end = ob?.endedAt ?? (props.message.isStreaming ? nowTick.value : startedAt);
|
||||||
|
return Math.max(0, end - startedAt);
|
||||||
});
|
});
|
||||||
|
|
||||||
function formatDuration(ms: number): string {
|
function formatDuration(ms: number): string {
|
||||||
@@ -762,6 +763,7 @@ const renderedToolResult = computed(() => {
|
|||||||
padding: 0 4px;
|
padding: 0 4px;
|
||||||
border-radius: 3px;
|
border-radius: 3px;
|
||||||
line-height: 14px;
|
line-height: 14px;
|
||||||
|
margin-left: 4px;
|
||||||
}
|
}
|
||||||
|
|
||||||
.tool-details {
|
.tool-details {
|
||||||
|
|||||||
@@ -18,6 +18,14 @@ function formatTokens(n: number): string {
|
|||||||
return String(n)
|
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 ${secs}s`
|
||||||
|
}
|
||||||
|
|
||||||
const displayMessages = computed(() =>
|
const displayMessages = computed(() =>
|
||||||
chatStore.messages.filter((m) => m.role !== "tool"),
|
chatStore.messages.filter((m) => m.role !== "tool"),
|
||||||
);
|
);
|
||||||
@@ -198,13 +206,52 @@ watch(currentToolCalls, () => {
|
|||||||
<span v-if="tc.toolPreview" class="tool-call-preview">{{
|
<span v-if="tc.toolPreview" class="tool-call-preview">{{
|
||||||
tc.toolPreview
|
tc.toolPreview
|
||||||
}}</span>
|
}}</span>
|
||||||
|
<span
|
||||||
|
v-if="tc.toolDuration && tc.toolStatus !== 'running'"
|
||||||
|
class="tool-call-duration"
|
||||||
|
:title="$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
|
<span
|
||||||
v-if="tc.toolStatus === 'running'"
|
v-if="tc.toolStatus === 'running'"
|
||||||
class="tool-call-spinner"
|
class="tool-call-spinner"
|
||||||
></span>
|
></span>
|
||||||
<span v-if="tc.toolStatus === 'error'" class="tool-call-error">{{
|
<svg
|
||||||
t("chat.error")
|
v-if="tc.toolStatus === 'error'"
|
||||||
}}</span>
|
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>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
@@ -334,13 +381,30 @@ watch(currentToolCalls, () => {
|
|||||||
flex-shrink: 0;
|
flex-shrink: 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
.tool-call-error {
|
.tool-call-error-icon {
|
||||||
font-size: 9px;
|
color: #ff4d4f;
|
||||||
color: $error;
|
flex-shrink: 0;
|
||||||
background: rgba($error, 0.08);
|
margin-left: 6px;
|
||||||
padding: 0 4px;
|
display: flex;
|
||||||
border-radius: 3px;
|
align-items: center;
|
||||||
line-height: 14px;
|
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 {
|
@keyframes spin {
|
||||||
|
|||||||
@@ -5,6 +5,29 @@ export interface ChangelogEntry {
|
|||||||
}
|
}
|
||||||
|
|
||||||
export const changelog: 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',
|
version: '0.5.1',
|
||||||
date: '2026-04-29',
|
date: '2026-04-29',
|
||||||
|
|||||||
@@ -131,7 +131,7 @@ export default {
|
|||||||
arguments: 'Argumente',
|
arguments: 'Argumente',
|
||||||
result: 'Ergebnis',
|
result: 'Ergebnis',
|
||||||
truncated: '... (abgeschnitten)',
|
truncated: '... (abgeschnitten)',
|
||||||
thinkingLabel: 'Denkprozess',
|
executionDuration: 'Execution time', thinkingLabel: 'Denkprozess',
|
||||||
thinkingInProgress: 'Denkt…',
|
thinkingInProgress: 'Denkt…',
|
||||||
thinkingShow: 'Denkprozess anzeigen',
|
thinkingShow: 'Denkprozess anzeigen',
|
||||||
thinkingHide: 'Denkprozess ausblenden',
|
thinkingHide: 'Denkprozess ausblenden',
|
||||||
@@ -563,6 +563,17 @@ jobTriggered: 'Job ausgelost',
|
|||||||
|
|
||||||
// Anderungsprotokoll
|
// Anderungsprotokoll
|
||||||
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_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_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.)',
|
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
|
||||||
|
|||||||
@@ -154,6 +154,7 @@ export default {
|
|||||||
arguments: 'Arguments',
|
arguments: 'Arguments',
|
||||||
result: 'Result',
|
result: 'Result',
|
||||||
truncated: '... (truncated)',
|
truncated: '... (truncated)',
|
||||||
|
executionDuration: 'Execution time',
|
||||||
thinkingLabel: 'Thinking',
|
thinkingLabel: 'Thinking',
|
||||||
thinkingInProgress: 'Thinking…',
|
thinkingInProgress: 'Thinking…',
|
||||||
thinkingShow: 'Show thinking',
|
thinkingShow: 'Show thinking',
|
||||||
@@ -727,6 +728,17 @@ export default {
|
|||||||
|
|
||||||
// Changelog
|
// Changelog
|
||||||
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_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_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.)',
|
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
|
||||||
|
|||||||
@@ -131,7 +131,7 @@ export default {
|
|||||||
arguments: 'Argumentos',
|
arguments: 'Argumentos',
|
||||||
result: 'Resultado',
|
result: 'Resultado',
|
||||||
truncated: '... (truncado)',
|
truncated: '... (truncado)',
|
||||||
thinkingLabel: 'Pensamiento',
|
executionDuration: 'Execution time', thinkingLabel: 'Pensamiento',
|
||||||
thinkingInProgress: 'Pensando…',
|
thinkingInProgress: 'Pensando…',
|
||||||
thinkingShow: 'Mostrar pensamiento',
|
thinkingShow: 'Mostrar pensamiento',
|
||||||
thinkingHide: 'Ocultar pensamiento',
|
thinkingHide: 'Ocultar pensamiento',
|
||||||
@@ -563,6 +563,17 @@ jobTriggered: 'Job ejecutado',
|
|||||||
|
|
||||||
// Registro de cambios
|
// Registro de cambios
|
||||||
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_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_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.)',
|
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
|
||||||
|
|||||||
@@ -131,7 +131,7 @@ export default {
|
|||||||
arguments: 'Arguments',
|
arguments: 'Arguments',
|
||||||
result: 'Resultat',
|
result: 'Resultat',
|
||||||
truncated: '... (tronque)',
|
truncated: '... (tronque)',
|
||||||
thinkingLabel: 'Raisonnement',
|
executionDuration: 'Execution time', thinkingLabel: 'Raisonnement',
|
||||||
thinkingInProgress: 'En réflexion…',
|
thinkingInProgress: 'En réflexion…',
|
||||||
thinkingShow: 'Afficher le raisonnement',
|
thinkingShow: 'Afficher le raisonnement',
|
||||||
thinkingHide: 'Masquer le raisonnement',
|
thinkingHide: 'Masquer le raisonnement',
|
||||||
@@ -563,6 +563,17 @@ jobTriggered: 'Job declenche',
|
|||||||
|
|
||||||
// Journal des modifications
|
// Journal des modifications
|
||||||
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_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_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.)',
|
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
|
||||||
|
|||||||
@@ -131,7 +131,7 @@ export default {
|
|||||||
arguments: '引数',
|
arguments: '引数',
|
||||||
result: '結果',
|
result: '結果',
|
||||||
truncated: '... (省略)',
|
truncated: '... (省略)',
|
||||||
thinkingLabel: '思考過程',
|
executionDuration: 'Execution time', thinkingLabel: '思考過程',
|
||||||
thinkingInProgress: '思考中…',
|
thinkingInProgress: '思考中…',
|
||||||
thinkingShow: '思考過程を表示',
|
thinkingShow: '思考過程を表示',
|
||||||
thinkingHide: '思考過程を隠す',
|
thinkingHide: '思考過程を隠す',
|
||||||
@@ -563,6 +563,17 @@ export default {
|
|||||||
|
|
||||||
// 更新履歴
|
// 更新履歴
|
||||||
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_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_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.)',
|
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
|
||||||
|
|||||||
@@ -131,7 +131,7 @@ export default {
|
|||||||
arguments: '인수',
|
arguments: '인수',
|
||||||
result: '결과',
|
result: '결과',
|
||||||
truncated: '... (잘림)',
|
truncated: '... (잘림)',
|
||||||
thinkingLabel: '사고 과정',
|
executionDuration: 'Execution time', thinkingLabel: '사고 과정',
|
||||||
thinkingInProgress: '사고 중…',
|
thinkingInProgress: '사고 중…',
|
||||||
thinkingShow: '사고 과정 펼치기',
|
thinkingShow: '사고 과정 펼치기',
|
||||||
thinkingHide: '사고 과정 접기',
|
thinkingHide: '사고 과정 접기',
|
||||||
@@ -563,6 +563,17 @@ export default {
|
|||||||
|
|
||||||
// 변경 이력
|
// 변경 이력
|
||||||
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_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_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.)',
|
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
|
||||||
|
|||||||
@@ -131,7 +131,7 @@ export default {
|
|||||||
arguments: 'Argumentos',
|
arguments: 'Argumentos',
|
||||||
result: 'Resultado',
|
result: 'Resultado',
|
||||||
truncated: '... (truncado)',
|
truncated: '... (truncado)',
|
||||||
thinkingLabel: 'Raciocínio',
|
executionDuration: 'Execution time', thinkingLabel: 'Raciocínio',
|
||||||
thinkingInProgress: 'Pensando…',
|
thinkingInProgress: 'Pensando…',
|
||||||
thinkingShow: 'Mostrar raciocínio',
|
thinkingShow: 'Mostrar raciocínio',
|
||||||
thinkingHide: 'Ocultar raciocínio',
|
thinkingHide: 'Ocultar raciocínio',
|
||||||
@@ -563,6 +563,17 @@ jobTriggered: 'Job acionado',
|
|||||||
|
|
||||||
// Registro de alteracoes
|
// Registro de alteracoes
|
||||||
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_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_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.)',
|
new_0_5_1_3: 'Smart cleanup of exclusive platform credentials on profile clone (Telegram, Discord, Slack, etc.)',
|
||||||
|
|||||||
@@ -154,6 +154,7 @@ export default {
|
|||||||
arguments: '参数',
|
arguments: '参数',
|
||||||
result: '结果',
|
result: '结果',
|
||||||
truncated: '... (已截断)',
|
truncated: '... (已截断)',
|
||||||
|
executionDuration: '执行时长',
|
||||||
thinkingLabel: '思考过程',
|
thinkingLabel: '思考过程',
|
||||||
thinkingInProgress: '思考中…',
|
thinkingInProgress: '思考中…',
|
||||||
thinkingShow: '展开思考过程',
|
thinkingShow: '展开思考过程',
|
||||||
@@ -729,6 +730,17 @@ export default {
|
|||||||
|
|
||||||
// 更新日志
|
// 更新日志
|
||||||
changelog: {
|
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_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_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）',
|
new_0_5_1_3: 'Profile 克隆时智能清理独占平台凭据（Telegram、Discord、Slack 等）',
|
||||||
|
|||||||
@@ -26,6 +26,7 @@ export interface Message {
|
|||||||
toolArgs?: string
|
toolArgs?: string
|
||||||
toolResult?: string
|
toolResult?: string
|
||||||
toolStatus?: 'running' | 'done' | 'error'
|
toolStatus?: 'running' | 'done' | 'error'
|
||||||
|
toolDuration?: number // 工具执行时长（秒）
|
||||||
isStreaming?: boolean
|
isStreaming?: boolean
|
||||||
attachments?: Attachment[]
|
attachments?: Attachment[]
|
||||||
// 思考/推理文本。两条来源：
|
// 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
|
// Helper to clean up this session's stream state
|
||||||
const cleanup = () => {
|
const cleanup = () => {
|
||||||
|
console.log('[sendMessage] cleanup called, deleting stream state for sid:', sid)
|
||||||
streamStates.value.delete(sid)
|
streamStates.value.delete(sid)
|
||||||
serverWorking.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.
|
// 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) {
|
if (toolMsgs.length > 0) {
|
||||||
const last = toolMsgs[toolMsgs.length - 1]
|
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
|
break
|
||||||
@@ -790,9 +799,29 @@ export const useChatStore = defineStore('chat', () => {
|
|||||||
// stream). If we never produced assistant text but the gateway
|
// stream). If we never produced assistant text but the gateway
|
||||||
// reports a non-empty output, fall back to rendering it as a
|
// reports a non-empty output, fall back to rendering it as a
|
||||||
// single assistant message so the user actually sees the reply.
|
// single assistant message so the user actually sees the reply.
|
||||||
|
|
||||||
|
// 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 =
|
const finalOutput =
|
||||||
typeof evt.output === 'string' ? evt.output : ''
|
typeof evt.output === 'string' ? evt.output : ''
|
||||||
const finalOutputTrimmed = finalOutput.trim()
|
finalOutputTrimmed = finalOutput.trim()
|
||||||
if (!runProducedAssistantText && finalOutputTrimmed !== '') {
|
if (!runProducedAssistantText && finalOutputTrimmed !== '') {
|
||||||
addMessage(sid, {
|
addMessage(sid, {
|
||||||
id: uid(),
|
id: uid(),
|
||||||
@@ -802,6 +831,7 @@ export const useChatStore = defineStore('chat', () => {
|
|||||||
})
|
})
|
||||||
runProducedAssistantText = true
|
runProducedAssistantText = true
|
||||||
}
|
}
|
||||||
|
}
|
||||||
// Workaround for upstream hermes-agent bug: when the agent
|
// Workaround for upstream hermes-agent bug: when the agent
|
||||||
// layer silently swallows an error (e.g. invalid API key,
|
// layer silently swallows an error (e.g. invalid API key,
|
||||||
// unsupported model), the gateway still emits run.completed
|
// unsupported model), the gateway still emits run.completed
|
||||||
@@ -875,6 +905,7 @@ export const useChatStore = defineStore('chat', () => {
|
|||||||
},
|
},
|
||||||
// onDone
|
// onDone
|
||||||
() => {
|
() => {
|
||||||
|
console.log('[sendMessage] onDone callback called, cleaning up stream state')
|
||||||
const msgs = getSessionMsgs(sid)
|
const msgs = getSessionMsgs(sid)
|
||||||
const last = msgs[msgs.length - 1]
|
const last = msgs[msgs.length - 1]
|
||||||
if (last?.isStreaming) {
|
if (last?.isStreaming) {
|
||||||
@@ -1076,7 +1107,11 @@ export const useChatStore = defineStore('chat', () => {
|
|||||||
const msgs = getSessionMsgs(sid)
|
const msgs = getSessionMsgs(sid)
|
||||||
const toolMsgs = msgs.filter(m => m.role === 'tool' && m.toolStatus === 'running')
|
const toolMsgs = msgs.filter(m => m.role === 'tool' && m.toolStatus === 'running')
|
||||||
if (toolMsgs.length > 0) {
|
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
|
break
|
||||||
@@ -1096,8 +1131,27 @@ export const useChatStore = defineStore('chat', () => {
|
|||||||
target.outputTokens = (evt as any).outputTokens
|
target.outputTokens = (evt as any).outputTokens
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
// 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 : ''
|
const finalOutput = typeof evt.output === 'string' ? evt.output : ''
|
||||||
const finalOutputTrimmed = finalOutput.trim()
|
finalOutputTrimmed = finalOutput.trim()
|
||||||
if (!runProducedAssistantText && finalOutputTrimmed !== '') {
|
if (!runProducedAssistantText && finalOutputTrimmed !== '') {
|
||||||
addMessage(sid, {
|
addMessage(sid, {
|
||||||
id: uid(),
|
id: uid(),
|
||||||
@@ -1106,6 +1160,7 @@ export const useChatStore = defineStore('chat', () => {
|
|||||||
timestamp: Date.now(),
|
timestamp: Date.now(),
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
|
}
|
||||||
const swallowedError = !runProducedAssistantText && !runHadToolActivity && finalOutputTrimmed === ''
|
const swallowedError = !runProducedAssistantText && !runHadToolActivity && finalOutputTrimmed === ''
|
||||||
if (swallowedError) {
|
if (swallowedError) {
|
||||||
addMessage(sid, {
|
addMessage(sid, {
|
||||||
|
|||||||
@@ -261,9 +261,9 @@ onMounted(async () => {
|
|||||||
|
|
||||||
.log-message {
|
.log-message {
|
||||||
color: $text-secondary;
|
color: $text-secondary;
|
||||||
overflow: hidden;
|
overflow: visible;
|
||||||
text-overflow: ellipsis;
|
white-space: normal;
|
||||||
white-space: nowrap;
|
word-break: break-word;
|
||||||
min-width: 0;
|
min-width: 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -17,7 +17,6 @@ export async function create(ctx: any) {
|
|||||||
const { name, base_url, api_key, model, context_length, providerKey } = ctx.request.body as {
|
const { name, base_url, api_key, model, context_length, providerKey } = ctx.request.body as {
|
||||||
name: string; base_url: string; api_key: string; model: string; context_length?: number; providerKey?: string | null
|
name: string; base_url: string; api_key: string; model: string; context_length?: number; providerKey?: string | null
|
||||||
}
|
}
|
||||||
console.log(name, base_url, api_key, model, providerKey)
|
|
||||||
if (!name || !base_url || !model) {
|
if (!name || !base_url || !model) {
|
||||||
ctx.status = 400; ctx.body = { error: 'Missing name, base_url, or model' }; return
|
ctx.status = 400; ctx.body = { error: 'Missing name, base_url, or model' }; return
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -402,3 +402,43 @@ export async function usageStats(ctx: any) {
|
|||||||
daily_usage: [...dayMap.values()],
|
daily_usage: [...dayMap.values()],
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
export async function getConversationMessagesPaginated(ctx: any) {
|
||||||
|
const offset = ctx.query.offset ? parseInt(ctx.query.offset as string, 10) : 0
|
||||||
|
const limit = ctx.query.limit ? parseInt(ctx.query.limit as string, 10) : 50
|
||||||
|
|
||||||
|
if (useLocalSessionStore()) {
|
||||||
|
const { getSessionDetailPaginated } = await import('../../db/hermes/session-store')
|
||||||
|
const result = getSessionDetailPaginated(ctx.params.id, offset, limit)
|
||||||
|
|
||||||
|
if (!result) {
|
||||||
|
ctx.status = 404
|
||||||
|
ctx.body = { error: 'Conversation not found' }
|
||||||
|
return
|
||||||
|
}
|
||||||
|
|
||||||
|
ctx.body = {
|
||||||
|
session: {
|
||||||
|
id: result.session.id,
|
||||||
|
source: result.session.source,
|
||||||
|
model: result.session.model,
|
||||||
|
title: result.session.title,
|
||||||
|
started_at: result.session.started_at,
|
||||||
|
ended_at: result.session.ended_at,
|
||||||
|
last_active: result.session.last_active,
|
||||||
|
message_count: result.session.message_count,
|
||||||
|
input_tokens: result.session.input_tokens,
|
||||||
|
output_tokens: result.session.output_tokens,
|
||||||
|
},
|
||||||
|
messages: result.messages,
|
||||||
|
total: result.total,
|
||||||
|
offset: result.offset,
|
||||||
|
limit: result.limit,
|
||||||
|
hasMore: result.hasMore,
|
||||||
|
}
|
||||||
|
return
|
||||||
|
}
|
||||||
|
|
||||||
|
ctx.status = 404
|
||||||
|
ctx.body = { error: 'Conversation not found' }
|
||||||
|
}
|
||||||
|
|||||||
@@ -300,6 +300,15 @@ export function searchSessions(profile: string, query: string, limit = 20): Herm
|
|||||||
})
|
})
|
||||||
}
|
}
|
||||||
|
|
||||||
|
export interface PaginatedSessionDetailResult {
|
||||||
|
session: HermesSessionRow
|
||||||
|
messages: HermesMessageRow[]
|
||||||
|
total: number
|
||||||
|
offset: number
|
||||||
|
limit: number
|
||||||
|
hasMore: boolean
|
||||||
|
}
|
||||||
|
|
||||||
export function getSessionDetail(id: string): HermesSessionDetailRow | null {
|
export function getSessionDetail(id: string): HermesSessionDetailRow | null {
|
||||||
if (!isSqliteAvailable()) return null
|
if (!isSqliteAvailable()) return null
|
||||||
const db = getDb()!
|
const db = getDb()!
|
||||||
@@ -411,6 +420,45 @@ export function updateSessionStats(id: string): void {
|
|||||||
).run(id, id, id)
|
).run(id, id, id)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
export function getSessionDetailPaginated(
|
||||||
|
id: string,
|
||||||
|
offset = 0,
|
||||||
|
limit = 500,
|
||||||
|
): PaginatedSessionDetailResult | null {
|
||||||
|
if (!isSqliteAvailable()) {
|
||||||
|
return null
|
||||||
|
}
|
||||||
|
|
||||||
|
const db = getDb()!
|
||||||
|
|
||||||
|
// Get session info
|
||||||
|
const sessionRow = db.prepare(`SELECT * FROM ${SESSIONS_TABLE} WHERE id = ?`).get(id) as Record<string, unknown> | undefined
|
||||||
|
if (!sessionRow) return null
|
||||||
|
|
||||||
|
// Get total message count
|
||||||
|
const countResult = db.prepare(
|
||||||
|
`SELECT COUNT(*) as total FROM ${MESSAGES_TABLE} WHERE session_id = ?`,
|
||||||
|
).get(id) as { total: number } | undefined
|
||||||
|
const total = countResult?.total || 0
|
||||||
|
|
||||||
|
// Get paginated messages (newest first from DB, then reverse)
|
||||||
|
const msgRows = db.prepare(
|
||||||
|
`SELECT * FROM ${MESSAGES_TABLE} WHERE session_id = ? ORDER BY timestamp DESC, id DESC LIMIT ? OFFSET ?`,
|
||||||
|
).all(id, limit, offset) as Record<string, unknown>[]
|
||||||
|
|
||||||
|
const session = mapSessionRow(sessionRow)
|
||||||
|
const messages = msgRows.map(mapMessageRow).reverse() // Reverse to show oldest first
|
||||||
|
|
||||||
|
return {
|
||||||
|
session,
|
||||||
|
messages,
|
||||||
|
total,
|
||||||
|
offset,
|
||||||
|
limit,
|
||||||
|
hasMore: offset + messages.length < total,
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
// --- Session store mode ---
|
// --- Session store mode ---
|
||||||
|
|
||||||
import { config } from '../../config'
|
import { config } from '../../config'
|
||||||
|
|||||||
@@ -696,13 +696,14 @@ export async function getSessionDetailFromDbWithProfile(sessionId: string, profi
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
export async function listSessionSummaries(source?: string, limit = 2000): Promise<HermesSessionRow[]> {
|
export async function listSessionSummaries(source?: string, limit = 2000, profile?: string): Promise<HermesSessionRow[]> {
|
||||||
if (!SQLITE_AVAILABLE) {
|
if (!SQLITE_AVAILABLE) {
|
||||||
throw new Error(`node:sqlite requires Node >= 22.5, current: ${process.versions.node}`)
|
throw new Error(`node:sqlite requires Node >= 22.5, current: ${process.versions.node}`)
|
||||||
}
|
}
|
||||||
|
|
||||||
const { DatabaseSync } = await import('node:sqlite')
|
const { DatabaseSync } = await import('node:sqlite')
|
||||||
const db = new DatabaseSync(sessionDbPath(), { open: true, readOnly: true })
|
const dbPath = profile ? `${getProfileDir(profile)}/state.db` : sessionDbPath()
|
||||||
|
const db = new DatabaseSync(dbPath, { open: true, readOnly: true })
|
||||||
|
|
||||||
try {
|
try {
|
||||||
const clauses = ["s.parent_session_id IS NULL", "s.source != 'tool'", "s.id NOT LIKE 'compress_%'"]
|
const clauses = ["s.parent_session_id IS NULL", "s.source != 'tool'", "s.id NOT LIKE 'compress_%'"]
|
||||||
|
|||||||
@@ -33,11 +33,15 @@ export function getDb(): DatabaseSync | null {
|
|||||||
mkdirSync(DB_DIR, { recursive: true })
|
mkdirSync(DB_DIR, { recursive: true })
|
||||||
_db = new DatabaseSync(DB_PATH)
|
_db = new DatabaseSync(DB_PATH)
|
||||||
// Use WAL mode for better concurrency and WSL compatibility
|
// Use WAL mode for better concurrency and WSL compatibility
|
||||||
|
if (isDev) {
|
||||||
|
_db.exec('PRAGMA journal_mode=DELETE')
|
||||||
|
} else {
|
||||||
_db.exec('PRAGMA journal_mode=WAL')
|
_db.exec('PRAGMA journal_mode=WAL')
|
||||||
_db.exec('PRAGMA synchronous=NORMAL')
|
_db.exec('PRAGMA synchronous=NORMAL')
|
||||||
_db.exec('PRAGMA busy_timeout=5000')
|
_db.exec('PRAGMA busy_timeout=5000')
|
||||||
_db.exec('PRAGMA foreign_keys=ON')
|
_db.exec('PRAGMA foreign_keys=ON')
|
||||||
}
|
}
|
||||||
|
}
|
||||||
return _db
|
return _db
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -31,6 +31,7 @@ export interface ChatMessage {
|
|||||||
tool_calls?: Array<{ id: string; type: string; function: { name: string; arguments: string } }>
|
tool_calls?: Array<{ id: string; type: string; function: { name: string; arguments: string } }>
|
||||||
tool_call_id?: string
|
tool_call_id?: string
|
||||||
name?: string
|
name?: string
|
||||||
|
reasoning_content?: string | null
|
||||||
}
|
}
|
||||||
|
|
||||||
export interface CompressionConfig {
|
export interface CompressionConfig {
|
||||||
@@ -94,10 +95,6 @@ export function countTokensForModel(text: string, model: string): number {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
function estimateMessagesTokens(messages: ChatMessage[]): number {
|
|
||||||
return messages.reduce((sum, m) => sum + countTokens(m.content), 0)
|
|
||||||
}
|
|
||||||
|
|
||||||
// ─── Prompts ────────────────────────────────────────────
|
// ─── Prompts ────────────────────────────────────────────
|
||||||
|
|
||||||
export const SUMMARY_PREFIX = `[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted
|
export const SUMMARY_PREFIX = `[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted
|
||||||
@@ -250,6 +247,43 @@ function serializeForSummary(messages: ChatMessage[]): string {
|
|||||||
return parts.join('\n\n')
|
return parts.join('\n\n')
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Convert messages to conversation history format for LLM API.
|
||||||
|
* Tool calls are converted to text format within assistant messages.
|
||||||
|
*/
|
||||||
|
function buildConversationHistory(messages: ChatMessage[]): Array<{ role: string; content: string }> {
|
||||||
|
const result: Array<{ role: string; content: string }> = []
|
||||||
|
|
||||||
|
for (const msg of messages) {
|
||||||
|
if (msg.role === 'tool') {
|
||||||
|
// Convert tool result to text and append to previous assistant message
|
||||||
|
const toolText = `[Tool result: ${msg.name || 'unknown'}]\n${(msg.content || '').slice(0, 500)}${msg.content && msg.content.length > 500 ? '...' : ''}`
|
||||||
|
// Find the last assistant message and append to it
|
||||||
|
const lastAssistant = result.findLast(m => m.role === 'assistant')
|
||||||
|
if (lastAssistant) {
|
||||||
|
lastAssistant.content += `\n\n${toolText}`
|
||||||
|
} else {
|
||||||
|
// Fallback: create an assistant message
|
||||||
|
result.push({ role: 'assistant', content: toolText })
|
||||||
|
}
|
||||||
|
} else if (msg.role === 'assistant' && msg.tool_calls?.length) {
|
||||||
|
// Include tool calls in assistant message
|
||||||
|
const toolsInfo = msg.tool_calls.map(tc => {
|
||||||
|
let args = tc.function.arguments
|
||||||
|
if (args.length > 1000) args = args.slice(0, 1000) + '...'
|
||||||
|
return `[Calling tool: ${tc.function.name} with arguments: ${args}]`
|
||||||
|
}).join('\n')
|
||||||
|
const content = msg.content ? `${msg.content}\n\n${toolsInfo}` : toolsInfo
|
||||||
|
result.push({ role: msg.role, content })
|
||||||
|
} else if (msg.role === 'user' || msg.role === 'assistant' || msg.role === 'system') {
|
||||||
|
result.push({ role: msg.role, content: msg.content || '' })
|
||||||
|
}
|
||||||
|
// Skip other roles
|
||||||
|
}
|
||||||
|
|
||||||
|
return result
|
||||||
|
}
|
||||||
|
|
||||||
function pruneOldToolResults(messages: ChatMessage[], keepRecentCount: number): ChatMessage[] {
|
function pruneOldToolResults(messages: ChatMessage[], keepRecentCount: number): ChatMessage[] {
|
||||||
if (messages.length <= keepRecentCount) return messages
|
if (messages.length <= keepRecentCount) return messages
|
||||||
|
|
||||||
@@ -337,7 +371,7 @@ async function callSummarizer(
|
|||||||
if (parsed.event === 'run.completed') {
|
if (parsed.event === 'run.completed') {
|
||||||
clearTimeout(timer)
|
clearTimeout(timer)
|
||||||
source.close()
|
source.close()
|
||||||
deleteCompressSession(sessionId, profile).catch(() => {})
|
deleteCompressSession(sessionId, profile).catch(() => { })
|
||||||
const output = parsed.output
|
const output = parsed.output
|
||||||
if (!output || typeof output !== 'string' || output.trim() === '') {
|
if (!output || typeof output !== 'string' || output.trim() === '') {
|
||||||
reject(new Error('Empty summarization response'))
|
reject(new Error('Empty summarization response'))
|
||||||
@@ -347,7 +381,7 @@ async function callSummarizer(
|
|||||||
} else if (parsed.event === 'run.failed') {
|
} else if (parsed.event === 'run.failed') {
|
||||||
clearTimeout(timer)
|
clearTimeout(timer)
|
||||||
source.close()
|
source.close()
|
||||||
deleteCompressSession(sessionId, profile).catch(() => {})
|
deleteCompressSession(sessionId, profile).catch(() => { })
|
||||||
reject(new Error(parsed.error || 'Summarization run failed'))
|
reject(new Error(parsed.error || 'Summarization run failed'))
|
||||||
}
|
}
|
||||||
} catch { /* ignore parse errors */ }
|
} catch { /* ignore parse errors */ }
|
||||||
@@ -356,7 +390,7 @@ async function callSummarizer(
|
|||||||
source.onerror = () => {
|
source.onerror = () => {
|
||||||
clearTimeout(timer)
|
clearTimeout(timer)
|
||||||
source.close()
|
source.close()
|
||||||
deleteCompressSession(sessionId, profile).catch(() => {})
|
deleteCompressSession(sessionId, profile).catch(() => { })
|
||||||
reject(new Error('Summarization SSE connection error'))
|
reject(new Error('Summarization SSE connection error'))
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
@@ -402,11 +436,8 @@ export class ChatContextCompressor {
|
|||||||
upstream: string,
|
upstream: string,
|
||||||
apiKey: string | undefined,
|
apiKey: string | undefined,
|
||||||
sessionId?: string,
|
sessionId?: string,
|
||||||
contextLength?: number,
|
|
||||||
profile?: string,
|
profile?: string,
|
||||||
): Promise<CompressedResult> {
|
): Promise<CompressedResult> {
|
||||||
const cl = contextLength || 200_000
|
|
||||||
const triggerTokens = Math.floor(cl / 2)
|
|
||||||
const total = messages.length
|
const total = messages.length
|
||||||
|
|
||||||
const makeMeta = (opts: Partial<CompressedResult['meta']> = {}): CompressedResult['meta'] => ({
|
const makeMeta = (opts: Partial<CompressedResult['meta']> = {}): CompressedResult['meta'] => ({
|
||||||
@@ -419,60 +450,27 @@ export class ChatContextCompressor {
|
|||||||
...opts,
|
...opts,
|
||||||
})
|
})
|
||||||
|
|
||||||
// ── Step 1: Check snapshot first ─────────────────────
|
// Check if we have a previous compression snapshot
|
||||||
const snapshot = sessionId ? getCompressionSnapshot(sessionId) : null
|
const snapshot = sessionId ? getCompressionSnapshot(sessionId) : null
|
||||||
|
|
||||||
if (snapshot) {
|
if (snapshot) {
|
||||||
const { summary: previousSummary, lastMessageIndex } = snapshot
|
// Has snapshot → incremental compress (merge old summary with new messages)
|
||||||
const newMessages = messages.slice(lastMessageIndex + 1)
|
|
||||||
const summaryTokens = countTokens(SUMMARY_PREFIX + previousSummary)
|
|
||||||
const newTokens = estimateMessagesTokens(newMessages)
|
|
||||||
const assembledTokens = summaryTokens + newTokens
|
|
||||||
|
|
||||||
logger.info(
|
logger.info(
|
||||||
'[context-compressor] session=%s: snapshot at %d, %d new messages, assembled ~%d tokens (threshold %d)',
|
'[context-compressor] session=%s: incremental compress with snapshot at index %d',
|
||||||
sessionId, lastMessageIndex, newMessages.length, assembledTokens, triggerTokens,
|
sessionId, snapshot.lastMessageIndex,
|
||||||
)
|
)
|
||||||
|
|
||||||
// Under threshold → return summary + new messages, no LLM call
|
|
||||||
if (assembledTokens <= triggerTokens) {
|
|
||||||
const result: ChatMessage[] = [
|
|
||||||
{ role: 'system', content: SUMMARY_PREFIX + '\n\n' + previousSummary },
|
|
||||||
...newMessages,
|
|
||||||
]
|
|
||||||
return {
|
|
||||||
messages: result,
|
|
||||||
meta: makeMeta({
|
|
||||||
compressed: true,
|
|
||||||
llmCompressed: false,
|
|
||||||
summaryTokenEstimate: summaryTokens,
|
|
||||||
verbatimCount: newMessages.length,
|
|
||||||
compressedStartIndex: lastMessageIndex,
|
|
||||||
}),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Over threshold → incremental LLM compress
|
|
||||||
return this.incrementalCompress(
|
return this.incrementalCompress(
|
||||||
messages, snapshot, upstream, apiKey, sessionId!, makeMeta(), profile,
|
messages, snapshot, upstream, apiKey, sessionId!, makeMeta(), profile,
|
||||||
)
|
)
|
||||||
}
|
} else {
|
||||||
|
// No snapshot → full compress (compress all messages)
|
||||||
// ── Step 2: No snapshot — check all messages ──────────
|
|
||||||
const totalTokens = estimateMessagesTokens(messages)
|
|
||||||
|
|
||||||
logger.info(
|
logger.info(
|
||||||
'[context-compressor] session=%s: no snapshot, %d messages, ~%d tokens (threshold %d)',
|
'[context-compressor] session=%s: full compress %d messages',
|
||||||
sessionId, total, totalTokens, triggerTokens,
|
sessionId, total,
|
||||||
)
|
)
|
||||||
|
|
||||||
if (totalTokens <= triggerTokens) {
|
|
||||||
return { messages, meta: makeMeta() }
|
|
||||||
}
|
|
||||||
|
|
||||||
// Over threshold → full LLM compress
|
|
||||||
return this.fullCompress(messages, upstream, apiKey, sessionId!, makeMeta(), profile)
|
return this.fullCompress(messages, upstream, apiKey, sessionId!, makeMeta(), profile)
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
private async incrementalCompress(
|
private async incrementalCompress(
|
||||||
messages: ChatMessage[],
|
messages: ChatMessage[],
|
||||||
@@ -503,9 +501,7 @@ export class ChatContextCompressor {
|
|||||||
try {
|
try {
|
||||||
const contentToSummarize = serializeForSummary(toCompress)
|
const contentToSummarize = serializeForSummary(toCompress)
|
||||||
const prompt = buildIncrementalPrompt(previousSummary, contentToSummarize, this.config.summaryBudget)
|
const prompt = buildIncrementalPrompt(previousSummary, contentToSummarize, this.config.summaryBudget)
|
||||||
const history = toCompress
|
const history = buildConversationHistory(toCompress)
|
||||||
.filter(m => m.role === 'user' || m.role === 'assistant')
|
|
||||||
.map(m => ({ role: m.role, content: m.content }))
|
|
||||||
|
|
||||||
const t0 = Date.now()
|
const t0 = Date.now()
|
||||||
summary = await callSummarizer(upstream, apiKey, prompt, history, this.config.summarizationTimeoutMs, previousSummary, profile)
|
summary = await callSummarizer(upstream, apiKey, prompt, history, this.config.summarizationTimeoutMs, previousSummary, profile)
|
||||||
@@ -565,9 +561,7 @@ export class ChatContextCompressor {
|
|||||||
|
|
||||||
const contentToSummarize = serializeForSummary(toCompress)
|
const contentToSummarize = serializeForSummary(toCompress)
|
||||||
const prompt = buildFullPrompt(contentToSummarize, this.config.summaryBudget)
|
const prompt = buildFullPrompt(contentToSummarize, this.config.summaryBudget)
|
||||||
const history = toCompress
|
const history = buildConversationHistory(toCompress)
|
||||||
.filter(m => m.role === 'user' || m.role === 'assistant')
|
|
||||||
.map(m => ({ role: m.role, content: m.content }))
|
|
||||||
|
|
||||||
let summary: string | null = null
|
let summary: string | null = null
|
||||||
try {
|
try {
|
||||||
|
|||||||
@@ -5,6 +5,7 @@ export const sessionRoutes = new Router()
|
|||||||
|
|
||||||
sessionRoutes.get('/api/hermes/sessions/conversations', ctrl.listConversations)
|
sessionRoutes.get('/api/hermes/sessions/conversations', ctrl.listConversations)
|
||||||
sessionRoutes.get('/api/hermes/sessions/conversations/:id/messages', ctrl.getConversationMessages)
|
sessionRoutes.get('/api/hermes/sessions/conversations/:id/messages', ctrl.getConversationMessages)
|
||||||
|
sessionRoutes.get('/api/hermes/sessions/conversations/:id/messages/paginated', ctrl.getConversationMessagesPaginated)
|
||||||
sessionRoutes.get('/api/hermes/sessions', ctrl.list)
|
sessionRoutes.get('/api/hermes/sessions', ctrl.list)
|
||||||
sessionRoutes.get('/api/hermes/search/sessions', ctrl.search)
|
sessionRoutes.get('/api/hermes/search/sessions', ctrl.search)
|
||||||
sessionRoutes.get('/api/hermes/sessions/search', ctrl.search)
|
sessionRoutes.get('/api/hermes/sessions/search', ctrl.search)
|
||||||
|
|||||||
@@ -15,6 +15,7 @@ import { updateUsage } from '../../db/hermes/usage-store'
|
|||||||
import {
|
import {
|
||||||
getSession,
|
getSession,
|
||||||
getSessionDetail,
|
getSessionDetail,
|
||||||
|
getSessionDetailPaginated,
|
||||||
createSession,
|
createSession,
|
||||||
addMessage,
|
addMessage,
|
||||||
updateSessionStats,
|
updateSessionStats,
|
||||||
@@ -29,6 +30,98 @@ import { logger } from '../logger'
|
|||||||
|
|
||||||
const compressor = new ChatContextCompressor()
|
const compressor = new ChatContextCompressor()
|
||||||
|
|
||||||
|
// --- Helper: Convert OpenAI format to Anthropic format ---
|
||||||
|
function convertToAnthropicFormat(messages: any[]): any[] {
|
||||||
|
const result: any[] = []
|
||||||
|
|
||||||
|
for (const m of messages) {
|
||||||
|
const role = m.role
|
||||||
|
const content = m.content || ''
|
||||||
|
|
||||||
|
if (role === 'assistant') {
|
||||||
|
const blocks: any[] = []
|
||||||
|
|
||||||
|
// Add thinking block if reasoning_content exists
|
||||||
|
if (m.reasoning) {
|
||||||
|
blocks.push({ type: 'thinking', thinking: m.reasoning })
|
||||||
|
}
|
||||||
|
|
||||||
|
// Add text content
|
||||||
|
if (content) {
|
||||||
|
if (typeof content === 'string') {
|
||||||
|
blocks.push({ type: 'text', text: content })
|
||||||
|
} else if (Array.isArray(content)) {
|
||||||
|
blocks.push(...content)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Add tool_use blocks
|
||||||
|
if (m.tool_calls && Array.isArray(m.tool_calls)) {
|
||||||
|
for (const tc of m.tool_calls) {
|
||||||
|
if (tc.id && tc.function) {
|
||||||
|
let args = tc.function.arguments || '{}'
|
||||||
|
try {
|
||||||
|
args = typeof args === 'string' ? JSON.parse(args) : args
|
||||||
|
} catch {
|
||||||
|
args = {}
|
||||||
|
}
|
||||||
|
blocks.push({
|
||||||
|
type: 'tool_use',
|
||||||
|
id: tc.id,
|
||||||
|
name: tc.function.name,
|
||||||
|
input: args
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Handle empty content
|
||||||
|
if (blocks.length === 0) {
|
||||||
|
blocks.push({ type: 'text', text: '' })
|
||||||
|
}
|
||||||
|
|
||||||
|
result.push({ role: 'assistant', content: blocks })
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
|
||||||
|
if (role === 'tool') {
|
||||||
|
// Convert tool message to tool_result in user message
|
||||||
|
const toolContent = content || '(no output)'
|
||||||
|
const toolResult = {
|
||||||
|
type: 'tool_result',
|
||||||
|
tool_use_id: m.tool_call_id || '',
|
||||||
|
content: typeof toolContent === 'string' ? toolContent : JSON.stringify(toolContent)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Merge with previous user message if it ends with tool_result
|
||||||
|
if (
|
||||||
|
result.length > 0 &&
|
||||||
|
result[result.length - 1].role === 'user' &&
|
||||||
|
Array.isArray(result[result.length - 1].content) &&
|
||||||
|
result[result.length - 1].content.length > 0 &&
|
||||||
|
result[result.length - 1].content[result[result.length - 1].content.length - 1].type === 'tool_result'
|
||||||
|
) {
|
||||||
|
result[result.length - 1].content.push(toolResult)
|
||||||
|
} else {
|
||||||
|
result.push({ role: 'user', content: [toolResult] })
|
||||||
|
}
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
|
||||||
|
// Regular user message
|
||||||
|
if (role === 'user') {
|
||||||
|
if (typeof content === 'string') {
|
||||||
|
result.push({ role: 'user', content: content || '(empty message)' })
|
||||||
|
} else if (Array.isArray(content)) {
|
||||||
|
result.push({ role: 'user', content })
|
||||||
|
}
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return result
|
||||||
|
}
|
||||||
|
|
||||||
// --- Session state tracking ---
|
// --- Session state tracking ---
|
||||||
|
|
||||||
interface SessionMessage {
|
interface SessionMessage {
|
||||||
@@ -113,14 +206,21 @@ export class ChatRunSocket {
|
|||||||
const sid = data.session_id
|
const sid = data.session_id
|
||||||
const room = `session:${sid}`
|
const room = `session:${sid}`
|
||||||
socket.join(room)
|
socket.join(room)
|
||||||
|
this.resumeSession(socket, sid)
|
||||||
|
})
|
||||||
|
|
||||||
|
socket.on('abort', (data: { session_id?: string }) => {
|
||||||
|
if (data.session_id) {
|
||||||
|
this.handleAbort(socket, data.session_id)
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
private async resumeSession(socket: Socket, sid: string) {
|
||||||
let state = this.sessionMap.get(sid)
|
let state = this.sessionMap.get(sid)
|
||||||
|
|
||||||
// Not in memory — load from DB
|
|
||||||
if (!state) {
|
|
||||||
try {
|
try {
|
||||||
const detail = useLocalSessionStore()
|
const detail = useLocalSessionStore()
|
||||||
? getSessionDetail(sid)
|
? getSessionDetailPaginated(sid)
|
||||||
: await getSessionDetailFromDb(sid)
|
: await getSessionDetailFromDb(sid)
|
||||||
const messages = detail?.messages?.length
|
const messages = detail?.messages?.length
|
||||||
? detail.messages
|
? detail.messages
|
||||||
@@ -131,31 +231,129 @@ export class ChatRunSocket {
|
|||||||
session_id: sid,
|
session_id: sid,
|
||||||
role: m.role,
|
role: m.role,
|
||||||
content: m.content || '',
|
content: m.content || '',
|
||||||
|
reasoning: m.reasoning || '',
|
||||||
timestamp: m.timestamp,
|
timestamp: m.timestamp,
|
||||||
}
|
}
|
||||||
if (m.tool_calls?.length) msg.tool_calls = m.tool_calls
|
// Convert Anthropic format content to OpenAI format
|
||||||
|
// Check if content is a stringified array (Hermes Gateway behavior) - only for assistant messages
|
||||||
|
if (m.role === 'assistant' && typeof m.content === 'string') {
|
||||||
|
// Handle double-serialized content: "[{'type': 'text', ...}]" -> "[{'type': 'text', ...}]"
|
||||||
|
let contentToParse = m.content
|
||||||
|
const trimmed = m.content.trim()
|
||||||
|
if (trimmed.startsWith('"') && trimmed.endsWith('"') && trimmed.length >= 2) {
|
||||||
|
contentToParse = trimmed.slice(1, -1)
|
||||||
|
logger.info('[chat-run-socket] resume message %s: double-serialized, removed outer quotes', m.id)
|
||||||
|
}
|
||||||
|
|
||||||
|
if (contentToParse.startsWith('[') && contentToParse.endsWith(']')) {
|
||||||
|
try {
|
||||||
|
// Parse stringified Python-like array to JSON
|
||||||
|
const parsedContent = JSON.parse(
|
||||||
|
contentToParse
|
||||||
|
.replace(/'/g, '"') // Python single quotes to JSON double quotes
|
||||||
|
.replace(/True/g, 'true')
|
||||||
|
.replace(/False/g, 'false')
|
||||||
|
.replace(/None/g, 'null')
|
||||||
|
)
|
||||||
|
if (Array.isArray(parsedContent)) {
|
||||||
|
const textBlocks: string[] = []
|
||||||
|
const toolCalls: any[] = []
|
||||||
|
let reasoningContent: string | null = null
|
||||||
|
|
||||||
|
for (const block of parsedContent) {
|
||||||
|
if (block.type === 'thinking') {
|
||||||
|
reasoningContent = block.thinking
|
||||||
|
} else if (block.type === 'text') {
|
||||||
|
textBlocks.push(block.text)
|
||||||
|
} else if (block.type === 'tool_use') {
|
||||||
|
toolCalls.push({
|
||||||
|
id: block.id,
|
||||||
|
type: 'function',
|
||||||
|
function: {
|
||||||
|
name: block.name,
|
||||||
|
arguments: JSON.stringify(block.input)
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
msg.content = textBlocks.join('') || ''
|
||||||
|
if (toolCalls.length > 0) {
|
||||||
|
msg.tool_calls = toolCalls
|
||||||
|
}
|
||||||
|
if (reasoningContent) {
|
||||||
|
msg.reasoning = reasoningContent
|
||||||
|
}
|
||||||
|
}
|
||||||
|
} catch (e) {
|
||||||
|
// Parsing failed, keep original content
|
||||||
|
msg.content = m.content
|
||||||
|
}
|
||||||
|
}
|
||||||
|
} else if (Array.isArray(m.content)) {
|
||||||
|
const textBlocks: string[] = []
|
||||||
|
const toolCalls: any[] = []
|
||||||
|
let reasoningContent: string | null = null
|
||||||
|
|
||||||
|
for (const block of m.content) {
|
||||||
|
if (block.type === 'thinking') {
|
||||||
|
reasoningContent = block.thinking
|
||||||
|
} else if (block.type === 'text') {
|
||||||
|
textBlocks.push(block.text)
|
||||||
|
} else if (block.type === 'tool_use') {
|
||||||
|
toolCalls.push({
|
||||||
|
id: block.id,
|
||||||
|
type: 'function',
|
||||||
|
function: {
|
||||||
|
name: block.name,
|
||||||
|
arguments: JSON.stringify(block.input)
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
msg.content = textBlocks.join('') || ''
|
||||||
|
if (toolCalls.length > 0) {
|
||||||
|
msg.tool_calls = toolCalls
|
||||||
|
}
|
||||||
|
if (reasoningContent) {
|
||||||
|
msg.reasoning = reasoningContent
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if (m.tool_calls?.length) {
|
||||||
|
// Filter out tool_calls with empty/invalid id and remove internal fields
|
||||||
|
const cleanedToolCalls = m.tool_calls
|
||||||
|
.filter((tc: any) => tc.id && tc.id.length > 0)
|
||||||
|
.map((tc: any) => ({
|
||||||
|
id: tc.id,
|
||||||
|
type: tc.type,
|
||||||
|
function: tc.function
|
||||||
|
}))
|
||||||
|
if (cleanedToolCalls.length > 0) {
|
||||||
|
msg.tool_calls = cleanedToolCalls
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
// For tool messages, ensure tool_call_id exists
|
// For tool messages, ensure tool_call_id exists
|
||||||
if (m.role === 'tool') {
|
if (m.role === 'tool') {
|
||||||
if (m.tool_call_id) {
|
let callId = m.tool_call_id
|
||||||
msg.tool_call_id = m.tool_call_id
|
if (!callId || callId.length === 0) {
|
||||||
} else {
|
|
||||||
// Try to reconstruct tool_call_id from previous assistant message
|
// Try to reconstruct tool_call_id from previous assistant message
|
||||||
const prevMsg = arr[idx - 1]
|
const prevMsg = arr[idx - 1]
|
||||||
if (prevMsg?.role === 'assistant' && prevMsg.tool_calls?.length) {
|
if (prevMsg?.role === 'assistant' && prevMsg.tool_calls?.length) {
|
||||||
// Find matching tool_call by tool_name
|
// Find matching tool_call by tool_name
|
||||||
const tc = prevMsg.tool_calls.find((t: any) => t.function?.name === m.tool_name)
|
const tc = prevMsg.tool_calls.find((t: any) => t.function?.name === m.tool_name)
|
||||||
if (tc?.id) {
|
if (tc?.id) {
|
||||||
msg.tool_call_id = tc.id
|
callId = tc.id
|
||||||
} else {
|
}
|
||||||
// Cannot reconstruct - skip this tool message
|
}
|
||||||
|
}
|
||||||
|
// Skip tool message if no valid tool_call_id
|
||||||
|
if (!callId || callId.length === 0) {
|
||||||
return null
|
return null
|
||||||
}
|
}
|
||||||
} else {
|
msg.tool_call_id = callId
|
||||||
// No previous assistant message with tool_calls - skip
|
|
||||||
return null
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
if (m.tool_name) msg.tool_name = m.tool_name
|
if (m.tool_name) msg.tool_name = m.tool_name
|
||||||
@@ -164,7 +362,6 @@ export class ChatRunSocket {
|
|||||||
})
|
})
|
||||||
.filter(m => m !== null)
|
.filter(m => m !== null)
|
||||||
: []
|
: []
|
||||||
|
|
||||||
// Calculate context tokens — aware of compression snapshot
|
// Calculate context tokens — aware of compression snapshot
|
||||||
let inputTokens: number
|
let inputTokens: number
|
||||||
const snapshot = getCompressionSnapshot(sid)
|
const snapshot = getCompressionSnapshot(sid)
|
||||||
@@ -192,12 +389,105 @@ export class ChatRunSocket {
|
|||||||
state = { messages: [], isWorking: false, events: [] }
|
state = { messages: [], isWorking: false, events: [] }
|
||||||
this.sessionMap.set(sid, state)
|
this.sessionMap.set(sid, state)
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
// Reply with messages, working status + events (if working)
|
// Reply with messages, working status + events (if working)
|
||||||
|
// Convert messages from internal storage format to OpenAI format for client
|
||||||
|
const clientMessages = state.messages.map((m: any) => {
|
||||||
|
const msg: any = { ...m }
|
||||||
|
// Check if content is a stringified array (Hermes Gateway behavior) - only for assistant messages
|
||||||
|
if (m.role === 'assistant' && typeof m.content === 'string') {
|
||||||
|
// Handle double-serialized content: "[{'type': 'text', ...}]"
|
||||||
|
let contentToParse = m.content
|
||||||
|
const trimmed = m.content.trim()
|
||||||
|
if (trimmed.startsWith('"') && trimmed.endsWith('"') && trimmed.length >= 2) {
|
||||||
|
contentToParse = trimmed.slice(1, -1)
|
||||||
|
logger.info('[chat-run-socket] resume message %s: double-serialized, removed outer quotes', m.id)
|
||||||
|
}
|
||||||
|
|
||||||
|
if (contentToParse.trim().startsWith('[') && contentToParse.trim().endsWith(']')) {
|
||||||
|
try {
|
||||||
|
// Parse stringified Python-like array to JSON
|
||||||
|
const parsedContent = JSON.parse(
|
||||||
|
contentToParse
|
||||||
|
.replace(/'/g, '"')
|
||||||
|
.replace(/True/g, 'true')
|
||||||
|
.replace(/False/g, 'false')
|
||||||
|
.replace(/None/g, 'null')
|
||||||
|
)
|
||||||
|
if (Array.isArray(parsedContent)) {
|
||||||
|
const textBlocks: string[] = []
|
||||||
|
const toolCalls: any[] = []
|
||||||
|
let reasoningContent: string | null = null
|
||||||
|
|
||||||
|
for (const block of parsedContent) {
|
||||||
|
if (block.type === 'thinking') {
|
||||||
|
reasoningContent = block.thinking
|
||||||
|
} else if (block.type === 'text') {
|
||||||
|
textBlocks.push(block.text)
|
||||||
|
} else if (block.type === 'tool_use') {
|
||||||
|
toolCalls.push({
|
||||||
|
id: block.id,
|
||||||
|
type: 'function',
|
||||||
|
function: {
|
||||||
|
name: block.name,
|
||||||
|
arguments: JSON.stringify(block.input)
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
msg.content = textBlocks.join('') || ''
|
||||||
|
if (toolCalls.length > 0) {
|
||||||
|
msg.tool_calls = toolCalls
|
||||||
|
}
|
||||||
|
if (reasoningContent) {
|
||||||
|
msg.reasoning = reasoningContent
|
||||||
|
}
|
||||||
|
}
|
||||||
|
} catch (e) {
|
||||||
|
logger.error('[chat-run-socket] resume message %s: failed to parse content, error=%s, content=%s', m.id, (e as Error).message, contentToParse.substring(0, 200))
|
||||||
|
// Parsing failed, keep original content
|
||||||
|
msg.content = m.content
|
||||||
|
}
|
||||||
|
}
|
||||||
|
} else if (Array.isArray(m.content)) {
|
||||||
|
// If content is an array (Anthropic format), convert to OpenAI format
|
||||||
|
const textBlocks: string[] = []
|
||||||
|
const toolCalls: any[] = []
|
||||||
|
let reasoningContent: string | null = null
|
||||||
|
|
||||||
|
for (const block of m.content) {
|
||||||
|
if (block.type === 'thinking') {
|
||||||
|
reasoningContent = block.thinking
|
||||||
|
} else if (block.type === 'text') {
|
||||||
|
textBlocks.push(block.text)
|
||||||
|
} else if (block.type === 'tool_use') {
|
||||||
|
toolCalls.push({
|
||||||
|
id: block.id,
|
||||||
|
type: 'function',
|
||||||
|
function: {
|
||||||
|
name: block.name,
|
||||||
|
arguments: JSON.stringify(block.input)
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
msg.content = textBlocks.join('') || ''
|
||||||
|
if (toolCalls.length > 0) {
|
||||||
|
msg.tool_calls = toolCalls
|
||||||
|
}
|
||||||
|
if (reasoningContent) {
|
||||||
|
msg.reasoning = reasoningContent
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return msg
|
||||||
|
})
|
||||||
|
|
||||||
socket.emit('resumed', {
|
socket.emit('resumed', {
|
||||||
session_id: sid,
|
session_id: sid,
|
||||||
messages: state.messages,
|
messages: clientMessages,
|
||||||
isWorking: state.isWorking,
|
isWorking: state.isWorking,
|
||||||
events: state.isWorking ? state.events : [],
|
events: state.isWorking ? state.events : [],
|
||||||
inputTokens: state.inputTokens,
|
inputTokens: state.inputTokens,
|
||||||
@@ -206,15 +496,7 @@ export class ChatRunSocket {
|
|||||||
|
|
||||||
logger.info('[chat-run-socket] socket %s resumed session %s (working: %s, messages: %d)',
|
logger.info('[chat-run-socket] socket %s resumed session %s (working: %s, messages: %d)',
|
||||||
socket.id, sid, state.isWorking, state.messages.length)
|
socket.id, sid, state.isWorking, state.messages.length)
|
||||||
})
|
|
||||||
|
|
||||||
socket.on('abort', (data: { session_id?: string }) => {
|
|
||||||
if (data.session_id) {
|
|
||||||
this.handleAbort(data.session_id)
|
|
||||||
}
|
}
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
// --- Run handler ---
|
// --- Run handler ---
|
||||||
|
|
||||||
private async handleRun(
|
private async handleRun(
|
||||||
@@ -301,32 +583,46 @@ export class ChatRunSocket {
|
|||||||
tool_calls?: any[]
|
tool_calls?: any[]
|
||||||
tool_call_id?: string
|
tool_call_id?: string
|
||||||
name?: string
|
name?: string
|
||||||
|
reasoning_content?: string | null
|
||||||
}> = (lastUserMsgIndex >= 0
|
}> = (lastUserMsgIndex >= 0
|
||||||
? validMessages.slice(0, validMessages.length - lastUserMsgIndex - 1)
|
? validMessages.slice(0, validMessages.length - lastUserMsgIndex - 1)
|
||||||
: validMessages
|
: validMessages
|
||||||
).map((m, idx, arr) => {
|
).map((m, idx, arr) => {
|
||||||
const msg: any = { role: m.role, content: m.content || '' }
|
const msg: any = { role: m.role, content: m.content || 'empty message' }
|
||||||
if (m.tool_calls?.length) msg.tool_calls = m.tool_calls
|
if (m.reasoning_content) msg.reasoning_content = m.reasoning_content
|
||||||
|
if (m.tool_calls?.length) {
|
||||||
|
// Filter out tool_calls with empty/invalid id and remove internal fields
|
||||||
|
const cleanedToolCalls = m.tool_calls
|
||||||
|
.filter((tc: any) => tc.id && tc.id.length > 0)
|
||||||
|
.map((tc: any) => ({
|
||||||
|
id: tc.id,
|
||||||
|
type: tc.type,
|
||||||
|
function: tc.function
|
||||||
|
}))
|
||||||
|
if (cleanedToolCalls.length > 0) {
|
||||||
|
msg.tool_calls = cleanedToolCalls
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
// For tool messages, ensure tool_call_id exists
|
// For tool messages, ensure tool_call_id exists
|
||||||
if (m.role === 'tool') {
|
if (m.role === 'tool') {
|
||||||
if (m.tool_call_id) {
|
let callId = m.tool_call_id
|
||||||
msg.tool_call_id = m.tool_call_id
|
if (!callId || callId.length === 0) {
|
||||||
} else {
|
|
||||||
// Try to reconstruct tool_call_id from previous assistant message
|
// Try to reconstruct tool_call_id from previous assistant message
|
||||||
const prevMsg = arr[idx - 1]
|
const prevMsg = arr[idx - 1]
|
||||||
if (prevMsg?.role === 'assistant' && prevMsg.tool_calls?.length) {
|
if (prevMsg?.role === 'assistant' && prevMsg.tool_calls?.length) {
|
||||||
const tc = prevMsg.tool_calls.find((t: any) => t.function?.name === m.tool_name)
|
const tc = prevMsg.tool_calls.find((t: any) => t.function?.name === m.tool_name)
|
||||||
if (tc?.id) {
|
if (tc?.id) {
|
||||||
msg.tool_call_id = tc.id
|
callId = tc.id
|
||||||
} else {
|
|
||||||
return null // Cannot reconstruct
|
|
||||||
}
|
|
||||||
} else {
|
|
||||||
return null // No assistant message to reconstruct from
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
// Skip tool message if no valid tool_call_id
|
||||||
|
if (!callId || callId.length === 0) {
|
||||||
|
return null
|
||||||
|
}
|
||||||
|
msg.tool_call_id = callId
|
||||||
|
}
|
||||||
|
|
||||||
if (m.tool_name) msg.name = m.tool_name
|
if (m.tool_name) msg.name = m.tool_name
|
||||||
return msg
|
return msg
|
||||||
@@ -367,7 +663,7 @@ export class ChatRunSocket {
|
|||||||
|
|
||||||
try {
|
try {
|
||||||
const result = await compressor.compress(
|
const result = await compressor.compress(
|
||||||
history, upstream, apiKey, session_id, contextLength,
|
history, upstream, apiKey, session_id,
|
||||||
)
|
)
|
||||||
const afterTokens = await this.calcAndUpdateUsage(session_id, cState, emit)
|
const afterTokens = await this.calcAndUpdateUsage(session_id, cState, emit)
|
||||||
this.replaceState(session_id, 'compression.completed', {
|
this.replaceState(session_id, 'compression.completed', {
|
||||||
@@ -397,13 +693,29 @@ export class ChatRunSocket {
|
|||||||
compressedStartIndex: result.meta.compressedStartIndex,
|
compressedStartIndex: result.meta.compressedStartIndex,
|
||||||
})
|
})
|
||||||
|
|
||||||
history = result.messages.map(m => ({
|
history = result.messages.map(m => {
|
||||||
|
const msg: any = {
|
||||||
role: m.role,
|
role: m.role,
|
||||||
content: m.content,
|
content: m.content,
|
||||||
tool_calls: m.tool_calls,
|
|
||||||
tool_call_id: m.tool_call_id,
|
tool_call_id: m.tool_call_id,
|
||||||
name: m.name,
|
name: m.name,
|
||||||
|
}
|
||||||
|
if (m.reasoning_content) msg.reasoning_content = m.reasoning_content
|
||||||
|
// Filter tool_calls if present, remove internal fields
|
||||||
|
if (m.tool_calls?.length) {
|
||||||
|
const cleanedToolCalls = m.tool_calls
|
||||||
|
.filter((tc: any) => tc.id && tc.id.length > 0)
|
||||||
|
.map((tc: any) => ({
|
||||||
|
id: tc.id,
|
||||||
|
type: tc.type,
|
||||||
|
function: tc.function
|
||||||
}))
|
}))
|
||||||
|
if (cleanedToolCalls.length > 0) {
|
||||||
|
msg.tool_calls = cleanedToolCalls
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return msg
|
||||||
|
})
|
||||||
// Update usage from DB (snapshot now updated by compressor)
|
// Update usage from DB (snapshot now updated by compressor)
|
||||||
await this.calcAndUpdateUsage(session_id, cState, emit)
|
await this.calcAndUpdateUsage(session_id, cState, emit)
|
||||||
} catch (err: any) {
|
} catch (err: any) {
|
||||||
@@ -457,7 +769,7 @@ export class ChatRunSocket {
|
|||||||
|
|
||||||
try {
|
try {
|
||||||
const result = await compressor.compress(
|
const result = await compressor.compress(
|
||||||
history, upstream, apiKey, session_id, contextLength,
|
history, upstream, apiKey, session_id,
|
||||||
)
|
)
|
||||||
const cState = this.getOrCreateSession(session_id)
|
const cState = this.getOrCreateSession(session_id)
|
||||||
const afterTokens = await this.calcAndUpdateUsage(session_id, cState, emit)
|
const afterTokens = await this.calcAndUpdateUsage(session_id, cState, emit)
|
||||||
@@ -488,13 +800,29 @@ export class ChatRunSocket {
|
|||||||
compressedStartIndex: result.meta.compressedStartIndex,
|
compressedStartIndex: result.meta.compressedStartIndex,
|
||||||
})
|
})
|
||||||
|
|
||||||
history = result.messages.map(m => ({
|
history = result.messages.map(m => {
|
||||||
|
const msg: any = {
|
||||||
role: m.role,
|
role: m.role,
|
||||||
content: m.content,
|
content: m.content,
|
||||||
tool_calls: m.tool_calls,
|
|
||||||
tool_call_id: m.tool_call_id,
|
tool_call_id: m.tool_call_id,
|
||||||
name: m.name,
|
name: m.name,
|
||||||
|
}
|
||||||
|
if (m.reasoning_content) msg.reasoning_content = m.reasoning_content
|
||||||
|
// Filter tool_calls if present, remove internal fields
|
||||||
|
if (m.tool_calls?.length) {
|
||||||
|
const cleanedToolCalls = m.tool_calls
|
||||||
|
.filter((tc: any) => tc.id && tc.id.length > 0)
|
||||||
|
.map((tc: any) => ({
|
||||||
|
id: tc.id,
|
||||||
|
type: tc.type,
|
||||||
|
function: tc.function
|
||||||
}))
|
}))
|
||||||
|
if (cleanedToolCalls.length > 0) {
|
||||||
|
msg.tool_calls = cleanedToolCalls
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return msg
|
||||||
|
})
|
||||||
await this.calcAndUpdateUsage(session_id, cState, emit)
|
await this.calcAndUpdateUsage(session_id, cState, emit)
|
||||||
} catch (err: any) {
|
} catch (err: any) {
|
||||||
this.replaceState(session_id, 'compression.completed', {
|
this.replaceState(session_id, 'compression.completed', {
|
||||||
@@ -535,6 +863,16 @@ export class ChatRunSocket {
|
|||||||
|
|
||||||
const headers: Record<string, string> = { 'Content-Type': 'application/json' }
|
const headers: Record<string, string> = { 'Content-Type': 'application/json' }
|
||||||
if (apiKey) headers['Authorization'] = `Bearer ${apiKey}`
|
if (apiKey) headers['Authorization'] = `Bearer ${apiKey}`
|
||||||
|
|
||||||
|
// Debug: write history to JSON file for analysis (before conversion)
|
||||||
|
|
||||||
|
// Convert conversation_history from OpenAI format to Anthropic format
|
||||||
|
if (body.conversation_history && Array.isArray(body.conversation_history)) {
|
||||||
|
body.conversation_history = convertToAnthropicFormat(body.conversation_history)
|
||||||
|
logger.info('[chat-run-socket] converted conversation_history to Anthropic format for session %s: %d messages, content: %s',
|
||||||
|
session_id || '(new)', body.conversation_history.length, JSON.stringify(body.conversation_history, null, 2))
|
||||||
|
}
|
||||||
|
|
||||||
const res = await fetch(`${upstream}/v1/runs`, {
|
const res = await fetch(`${upstream}/v1/runs`, {
|
||||||
method: 'POST',
|
method: 'POST',
|
||||||
headers,
|
headers,
|
||||||
@@ -589,6 +927,12 @@ export class ChatRunSocket {
|
|||||||
source.onmessage = (event: MessageEvent) => {
|
source.onmessage = (event: MessageEvent) => {
|
||||||
try {
|
try {
|
||||||
const parsed = JSON.parse(event.data as string)
|
const parsed = JSON.parse(event.data as string)
|
||||||
|
// Debug: log all events from upstream
|
||||||
|
if (parsed.event?.includes('reasoning') || parsed.event?.includes('thinking')) {
|
||||||
|
logger.info('[chat-run-socket] upstream event: %s, data: %j', parsed.event, parsed)
|
||||||
|
} else {
|
||||||
|
logger.info('[chat-run-socket] upstream event: %s', parsed.event)
|
||||||
|
}
|
||||||
|
|
||||||
// Track messages into sessionMap
|
// Track messages into sessionMap
|
||||||
if (session_id) {
|
if (session_id) {
|
||||||
@@ -653,9 +997,15 @@ export class ChatRunSocket {
|
|||||||
break
|
break
|
||||||
}
|
}
|
||||||
case 'run.completed': {
|
case 'run.completed': {
|
||||||
|
logger.info('[chat-run-socket] ENTER run.completed case, session_id: %s, messages: %d',
|
||||||
|
session_id, msgs.length)
|
||||||
|
|
||||||
if (last?.role === 'assistant' && last.finish_reason == null) {
|
if (last?.role === 'assistant' && last.finish_reason == null) {
|
||||||
last.finish_reason = parsed.finish_reason || 'stop'
|
last.finish_reason = parsed.finish_reason || 'stop'
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Debug: log run.completed to check if reasoning is included
|
||||||
|
logger.info('[chat-run-socket] run.completed keys: %s', Object.keys(parsed))
|
||||||
// Finalize assistant message — if no content was streamed, use output
|
// Finalize assistant message — if no content was streamed, use output
|
||||||
if (parsed.output && !runProducedAssistantText(msgs)) {
|
if (parsed.output && !runProducedAssistantText(msgs)) {
|
||||||
if (last?.role === 'assistant') {
|
if (last?.role === 'assistant') {
|
||||||
@@ -670,6 +1020,70 @@ export class ChatRunSocket {
|
|||||||
})
|
})
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Parse stringified array content for all assistant messages
|
||||||
|
let parsedCount = 0
|
||||||
|
for (const msg of msgs) {
|
||||||
|
if (msg.role === 'assistant' && typeof msg.content === 'string' &&
|
||||||
|
msg.content.trim().startsWith('[') && msg.content.trim().endsWith(']')) {
|
||||||
|
try {
|
||||||
|
logger.info('[chat-run-socket] parsing array content for message %s, content preview: %s',
|
||||||
|
msg.id, msg.content.slice(0, 100))
|
||||||
|
const parsedContent = JSON.parse(
|
||||||
|
msg.content
|
||||||
|
.replace(/'/g, '"')
|
||||||
|
.replace(/True/g, 'true')
|
||||||
|
.replace(/False/g, 'false')
|
||||||
|
.replace(/None/g, 'null')
|
||||||
|
)
|
||||||
|
if (Array.isArray(parsedContent)) {
|
||||||
|
const textBlocks: string[] = []
|
||||||
|
const toolCalls: any[] = []
|
||||||
|
let reasoningContent: string | null = null
|
||||||
|
|
||||||
|
for (const block of parsedContent) {
|
||||||
|
if (block.type === 'thinking') {
|
||||||
|
reasoningContent = block.thinking
|
||||||
|
} else if (block.type === 'text') {
|
||||||
|
textBlocks.push(block.text)
|
||||||
|
} else if (block.type === 'tool_use') {
|
||||||
|
toolCalls.push({
|
||||||
|
id: block.id,
|
||||||
|
type: 'function',
|
||||||
|
function: {
|
||||||
|
name: block.name,
|
||||||
|
arguments: JSON.stringify(block.input)
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
msg.content = textBlocks.join('') || ''
|
||||||
|
if (toolCalls.length > 0) {
|
||||||
|
msg.tool_calls = toolCalls
|
||||||
|
}
|
||||||
|
if (reasoningContent) {
|
||||||
|
msg.reasoning = reasoningContent
|
||||||
|
}
|
||||||
|
parsedCount++
|
||||||
|
}
|
||||||
|
} catch (e) {
|
||||||
|
logger.error(e, '[chat-run-socket] failed to parse array content for message %s', msg.id)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
logger.info('[chat-run-socket] EXIT run.completed case, parsed %d messages', parsedCount)
|
||||||
|
|
||||||
|
// Attach the last assistant message's parsed content to fix stringified array format
|
||||||
|
const lastAssistantMsg = msgs.filter((m: any) => m.role === 'assistant').pop()
|
||||||
|
if (lastAssistantMsg && parsedCount > 0) {
|
||||||
|
parsed.parsed_content = lastAssistantMsg.content || ''
|
||||||
|
parsed.parsed_tool_calls = lastAssistantMsg.tool_calls || null
|
||||||
|
parsed.parsed_reasoning = lastAssistantMsg.reasoning || null
|
||||||
|
logger.info('[chat-run-socket] attached parsed content to run.completed event for message %s', lastAssistantMsg.id)
|
||||||
|
}
|
||||||
|
|
||||||
break
|
break
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -682,7 +1096,7 @@ export class ChatRunSocket {
|
|||||||
|
|
||||||
if (parsed.event === 'run.completed' || parsed.event === 'run.failed') {
|
if (parsed.event === 'run.completed' || parsed.event === 'run.failed') {
|
||||||
source.close()
|
source.close()
|
||||||
if (session_id) this.markCompleted(session_id, { event: parsed.event, run_id: parsed.run_id })
|
if (session_id) this.markCompleted(socket, session_id, { event: parsed.event, run_id: parsed.run_id })
|
||||||
}
|
}
|
||||||
} catch { /* not JSON, skip */ }
|
} catch { /* not JSON, skip */ }
|
||||||
}
|
}
|
||||||
@@ -690,26 +1104,26 @@ export class ChatRunSocket {
|
|||||||
source.onerror = () => {
|
source.onerror = () => {
|
||||||
source.close()
|
source.close()
|
||||||
emit('run.failed', { event: 'run.failed', error: 'EventSource connection lost' })
|
emit('run.failed', { event: 'run.failed', error: 'EventSource connection lost' })
|
||||||
if (session_id) this.markCompleted(session_id, { event: 'run.failed' })
|
if (session_id) this.markCompleted(socket, session_id, { event: 'run.failed' })
|
||||||
}
|
}
|
||||||
} catch (err: any) {
|
} catch (err: any) {
|
||||||
emit('run.failed', { event: 'run.failed', error: err.message })
|
emit('run.failed', { event: 'run.failed', error: err.message })
|
||||||
if (session_id) this.markCompleted(session_id, { event: 'run.failed' })
|
if (session_id) this.markCompleted(socket, session_id, { event: 'run.failed' })
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// --- Abort handler ---
|
// --- Abort handler ---
|
||||||
|
|
||||||
private handleAbort(sessionId: string) {
|
private handleAbort(socket: Socket, sessionId: string) {
|
||||||
const state = this.sessionMap.get(sessionId)
|
const state = this.sessionMap.get(sessionId)
|
||||||
if (state?.isWorking && state.abortController) {
|
if (state?.isWorking && state.abortController) {
|
||||||
state.abortController.abort()
|
state.abortController.abort()
|
||||||
this.markCompleted(sessionId, { event: 'run.failed', run_id: state.runId })
|
this.markCompleted(socket, sessionId, { event: 'run.failed', run_id: state.runId })
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
/** Mark a session run as completed/failed so reconnecting clients get notified */
|
/** Mark a session run as completed/failed so reconnecting clients get notified */
|
||||||
private markCompleted(sessionId: string, _info: { event: string; run_id?: string }) {
|
private markCompleted(socket: Socket, sessionId: string, _info: { event: string; run_id?: string }) {
|
||||||
const state = this.sessionMap.get(sessionId)
|
const state = this.sessionMap.get(sessionId)
|
||||||
if (state) {
|
if (state) {
|
||||||
state.isWorking = false
|
state.isWorking = false
|
||||||
@@ -723,7 +1137,7 @@ export class ChatRunSocket {
|
|||||||
const prof = state.profile
|
const prof = state.profile
|
||||||
state.hermesSessionId = undefined
|
state.hermesSessionId = undefined
|
||||||
state.profile = undefined
|
state.profile = undefined
|
||||||
this.syncFromHermes(sessionId, hermesId, prof)
|
this.syncFromHermes(socket, sessionId, hermesId, prof)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -775,7 +1189,7 @@ export class ChatRunSocket {
|
|||||||
* and write to local DB. This gives us tool results that SSE events don't include.
|
* and write to local DB. This gives us tool results that SSE events don't include.
|
||||||
* After sync, enqueues the ephemeral session for deletion.
|
* After sync, enqueues the ephemeral session for deletion.
|
||||||
*/
|
*/
|
||||||
private syncFromHermes(localSessionId: string, hermesSessionId: string, profile?: string) {
|
private syncFromHermes(socket: Socket, localSessionId: string, hermesSessionId: string, profile?: string) {
|
||||||
getSessionDetailFromDb(hermesSessionId)
|
getSessionDetailFromDb(hermesSessionId)
|
||||||
.then((detail) => {
|
.then((detail) => {
|
||||||
if (!detail || !detail.messages?.length) {
|
if (!detail || !detail.messages?.length) {
|
||||||
@@ -800,6 +1214,40 @@ export class ChatRunSocket {
|
|||||||
}
|
}
|
||||||
|
|
||||||
if (toInsert.length > 0) {
|
if (toInsert.length > 0) {
|
||||||
|
// Get in-memory messages to preserve reasoning that was streamed via SSE
|
||||||
|
const state = this.sessionMap.get(localSessionId)
|
||||||
|
const memoryMessages = state?.messages || []
|
||||||
|
logger.info('[chat-run-socket] syncFromHermes: memory has %d messages, DB has %d messages',
|
||||||
|
memoryMessages.length, toInsert.length)
|
||||||
|
|
||||||
|
// Match messages by order since Hermes DB and memory should have same sequence
|
||||||
|
let memoryIdx = 0
|
||||||
|
let mergedCount = 0
|
||||||
|
for (let i = 0; i < toInsert.length && memoryIdx < memoryMessages.length; i++) {
|
||||||
|
const dbMsg = toInsert[i]
|
||||||
|
// Skip user messages in memory when matching
|
||||||
|
while (memoryIdx < memoryMessages.length && memoryMessages[memoryIdx].role === 'user') {
|
||||||
|
memoryIdx++
|
||||||
|
}
|
||||||
|
if (memoryIdx >= memoryMessages.length) break
|
||||||
|
const memoryMsg = memoryMessages[memoryIdx]
|
||||||
|
// Only merge if roles match
|
||||||
|
if (dbMsg.role === memoryMsg.role) {
|
||||||
|
// Merge reasoning from memory if DB doesn't have it
|
||||||
|
if (!dbMsg.reasoning && memoryMsg.reasoning) {
|
||||||
|
dbMsg.reasoning = memoryMsg.reasoning
|
||||||
|
mergedCount++
|
||||||
|
logger.info('[chat-run-socket] syncFromHermes: merged reasoning from memory to DB for %s message at index %d',
|
||||||
|
dbMsg.role, i)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
memoryIdx++
|
||||||
|
}
|
||||||
|
|
||||||
|
if (mergedCount > 0) {
|
||||||
|
logger.info('[chat-run-socket] syncFromHermes: merged reasoning for %d messages', mergedCount)
|
||||||
|
}
|
||||||
|
|
||||||
for (const msg of toInsert) {
|
for (const msg of toInsert) {
|
||||||
// Resolve tool_name from assistant's tool_calls if missing
|
// Resolve tool_name from assistant's tool_calls if missing
|
||||||
let toolName = msg.tool_name || null
|
let toolName = msg.tool_name || null
|
||||||
@@ -816,7 +1264,7 @@ export class ChatRunSocket {
|
|||||||
timestamp: msg.timestamp || Math.floor(Date.now() / 1000),
|
timestamp: msg.timestamp || Math.floor(Date.now() / 1000),
|
||||||
token_count: msg.token_count || null,
|
token_count: msg.token_count || null,
|
||||||
finish_reason: msg.finish_reason || null,
|
finish_reason: msg.finish_reason || null,
|
||||||
reasoning: msg.reasoning || null,
|
reasoning: msg.reasoning || null, // Now includes merged reasoning
|
||||||
reasoning_details: msg.reasoning_details || null,
|
reasoning_details: msg.reasoning_details || null,
|
||||||
reasoning_content: msg.reasoning_content || null,
|
reasoning_content: msg.reasoning_content || null,
|
||||||
codex_reasoning_items: msg.codex_reasoning_items || null,
|
codex_reasoning_items: msg.codex_reasoning_items || null,
|
||||||
@@ -843,7 +1291,7 @@ export class ChatRunSocket {
|
|||||||
const state = this.sessionMap.get(localSessionId)
|
const state = this.sessionMap.get(localSessionId)
|
||||||
if (state) {
|
if (state) {
|
||||||
const emit = (event: string, payload: any) => {
|
const emit = (event: string, payload: any) => {
|
||||||
this.nsp.to(`session:${localSessionId}`).emit(event, { ...payload, session_id: localSessionId })
|
socket.emit(event, { ...payload, session_id: localSessionId })
|
||||||
}
|
}
|
||||||
this.calcAndUpdateUsage(localSessionId, state, emit)
|
this.calcAndUpdateUsage(localSessionId, state, emit)
|
||||||
}
|
}
|
||||||
@@ -871,6 +1319,7 @@ export class ChatRunSocket {
|
|||||||
} catch { /* best-effort */ }
|
} catch { /* best-effort */ }
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
/** Get or create session state in sessionMap */
|
/** Get or create session state in sessionMap */
|
||||||
private getOrCreateSession(sessionId: string): SessionState {
|
private getOrCreateSession(sessionId: string): SessionState {
|
||||||
let state = this.sessionMap.get(sessionId)
|
let state = this.sessionMap.get(sessionId)
|
||||||
|
|||||||
@@ -2,16 +2,21 @@
|
|||||||
* Sync Hermes sessions from all profiles on startup.
|
* Sync Hermes sessions from all profiles on startup.
|
||||||
* Reads api_server sessions from Hermes state.db and imports into local DB.
|
* Reads api_server sessions from Hermes state.db and imports into local DB.
|
||||||
* Only runs when local DB is empty (first startup).
|
* Only runs when local DB is empty (first startup).
|
||||||
|
*
|
||||||
|
* Uses sessions-db.ts query logic to properly aggregate session chains.
|
||||||
*/
|
*/
|
||||||
import { readdirSync, existsSync } from 'fs'
|
import { readdirSync, existsSync } from 'fs'
|
||||||
import { resolve, join } from 'path'
|
import { resolve, join } from 'path'
|
||||||
import { homedir } from 'os'
|
import { homedir } from 'os'
|
||||||
import { DatabaseSync } from 'node:sqlite'
|
|
||||||
import { randomBytes } from 'crypto'
|
import { randomBytes } from 'crypto'
|
||||||
import { getProfileDir } from './hermes-profile'
|
import { getProfileDir } from './hermes-profile'
|
||||||
import { createSession, addMessage, updateSession, getSession } from '../../db/hermes/session-store'
|
import { createSession, addMessage, updateSession } from '../../db/hermes/session-store'
|
||||||
import { getDb } from '../../db/index'
|
import { getDb } from '../../db/index'
|
||||||
import { logger } from '../logger'
|
import { logger } from '../logger'
|
||||||
|
import { listSessionSummaries as listHermesSessionSummaries } from '../../db/hermes/sessions-db'
|
||||||
|
|
||||||
|
const HERMES_BASE = resolve(homedir(), '.hermes')
|
||||||
|
const PROFILES_DIR = join(HERMES_BASE, 'profiles')
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Generate a UUID v4 without external dependencies
|
* Generate a UUID v4 without external dependencies
|
||||||
@@ -29,45 +34,6 @@ function generateUuid(): string {
|
|||||||
].join('-')
|
].join('-')
|
||||||
}
|
}
|
||||||
|
|
||||||
const HERMES_BASE = resolve(homedir(), '.hermes')
|
|
||||||
const PROFILES_DIR = join(HERMES_BASE, 'profiles')
|
|
||||||
|
|
||||||
interface HermesSessionRow {
|
|
||||||
id: string
|
|
||||||
source: string
|
|
||||||
model: string
|
|
||||||
title: string | null
|
|
||||||
started_at: number
|
|
||||||
ended_at: number | null
|
|
||||||
end_reason: string | null
|
|
||||||
message_count: number
|
|
||||||
tool_call_count: number
|
|
||||||
input_tokens: number
|
|
||||||
output_tokens: number
|
|
||||||
cache_read_tokens: number
|
|
||||||
cache_write_tokens: number
|
|
||||||
reasoning_tokens: number
|
|
||||||
estimated_cost_usd: number
|
|
||||||
last_active: number
|
|
||||||
}
|
|
||||||
|
|
||||||
interface HermesMessageRow {
|
|
||||||
id: number | string
|
|
||||||
session_id: string
|
|
||||||
role: string
|
|
||||||
content: string
|
|
||||||
tool_call_id: string | null
|
|
||||||
tool_calls: any[] | null
|
|
||||||
tool_name: string | null
|
|
||||||
timestamp: number
|
|
||||||
token_count: number | null
|
|
||||||
finish_reason: string | null
|
|
||||||
reasoning: string | null
|
|
||||||
reasoning_details: string | null
|
|
||||||
reasoning_content: string | null
|
|
||||||
codex_reasoning_items: string | null
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Get all available profile names including 'default'
|
* Get all available profile names including 'default'
|
||||||
*/
|
*/
|
||||||
@@ -85,73 +51,25 @@ function getAllProfiles(): string[] {
|
|||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Open Hermes state.db for a specific profile
|
* Sync api_server sessions from a single profile.
|
||||||
|
* Uses sessions-db.ts query logic to properly aggregate session chains.
|
||||||
*/
|
*/
|
||||||
function openHermesStateDb(profile: string): DatabaseSync {
|
async function syncProfileSessions(profile: string): Promise<{
|
||||||
const profileDir = getProfileDir(profile)
|
|
||||||
const dbPath = join(profileDir, 'state.db')
|
|
||||||
|
|
||||||
if (!existsSync(dbPath)) {
|
|
||||||
throw new Error(`Hermes state.db not found for profile '${profile}' at ${dbPath}`)
|
|
||||||
}
|
|
||||||
|
|
||||||
return new DatabaseSync(dbPath, { readOnly: true })
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Sync api_server sessions from a single profile
|
|
||||||
*/
|
|
||||||
function syncProfileSessions(profile: string): {
|
|
||||||
synced: number
|
synced: number
|
||||||
skipped: number
|
|
||||||
errors: string[]
|
errors: string[]
|
||||||
} {
|
}> {
|
||||||
const result = { synced: 0, skipped: 0, errors: [] as string[] }
|
const result = { synced: 0, errors: [] as string[] }
|
||||||
|
|
||||||
try {
|
try {
|
||||||
const db = openHermesStateDb(profile)
|
// Use listSessionSummaries to get aggregated session chains
|
||||||
|
// This returns only root sessions with aggregated stats from the entire chain
|
||||||
|
const summaries = await listHermesSessionSummaries('api_server', 10000, profile)
|
||||||
|
|
||||||
|
logger.info(`[session-sync] profile '${profile}': found ${summaries.length} aggregated session chains`)
|
||||||
|
|
||||||
|
for (const hermesSession of summaries) {
|
||||||
try {
|
try {
|
||||||
// Check if sessions table has estimated_cost_usd column
|
// Generate new session ID for local DB
|
||||||
const tableInfo = db.prepare('PRAGMA table_info(sessions)').all() as Array<{ name: string }>
|
|
||||||
const hasEstimatedCost = tableInfo.some(col => col.name === 'estimated_cost_usd')
|
|
||||||
|
|
||||||
// Build SELECT query - only include estimated_cost_usd if column exists
|
|
||||||
const estimatedCostCol = hasEstimatedCost ? ', COALESCE(estimated_cost_usd, 0) AS estimated_cost_usd' : ', 0 AS estimated_cost_usd'
|
|
||||||
|
|
||||||
// Get all api_server sessions
|
|
||||||
const sessions = db.prepare(`
|
|
||||||
SELECT
|
|
||||||
id,
|
|
||||||
source,
|
|
||||||
COALESCE(model, '') AS model,
|
|
||||||
title,
|
|
||||||
started_at,
|
|
||||||
ended_at,
|
|
||||||
end_reason,
|
|
||||||
message_count,
|
|
||||||
tool_call_count,
|
|
||||||
input_tokens,
|
|
||||||
output_tokens,
|
|
||||||
cache_read_tokens,
|
|
||||||
cache_write_tokens,
|
|
||||||
reasoning_tokens${estimatedCostCol}
|
|
||||||
FROM sessions
|
|
||||||
WHERE source = 'api_server'
|
|
||||||
ORDER BY started_at ASC
|
|
||||||
`).all() as unknown as Omit<HermesSessionRow, 'preview' | 'last_active'>[]
|
|
||||||
|
|
||||||
logger.info(`[session-sync] profile '${profile}': found ${sessions.length} api_server sessions`)
|
|
||||||
for (const hermesSession of sessions) {
|
|
||||||
try {
|
|
||||||
// Check if this Hermes session ID already exists in local DB
|
|
||||||
const existing = getSession(hermesSession.id)
|
|
||||||
if (existing) {
|
|
||||||
result.skipped++
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
|
|
||||||
// Generate new session ID
|
|
||||||
const newSessionId = generateUuid()
|
const newSessionId = generateUuid()
|
||||||
|
|
||||||
// Create session in local DB
|
// Create session in local DB
|
||||||
@@ -162,30 +80,18 @@ function syncProfileSessions(profile: string): {
|
|||||||
title: hermesSession.title || undefined,
|
title: hermesSession.title || undefined,
|
||||||
})
|
})
|
||||||
|
|
||||||
// Get all messages for this session
|
// Get full detail including all messages from the session chain
|
||||||
const messages = db.prepare(`
|
const { getSessionDetailFromDbWithProfile } = await import('../../db/hermes/sessions-db')
|
||||||
SELECT
|
const detail = await getSessionDetailFromDbWithProfile(hermesSession.id, profile)
|
||||||
id,
|
|
||||||
session_id,
|
|
||||||
role,
|
|
||||||
content,
|
|
||||||
tool_call_id,
|
|
||||||
tool_calls,
|
|
||||||
tool_name,
|
|
||||||
timestamp,
|
|
||||||
token_count,
|
|
||||||
finish_reason,
|
|
||||||
reasoning,
|
|
||||||
reasoning_details,
|
|
||||||
reasoning_content,
|
|
||||||
codex_reasoning_items
|
|
||||||
FROM messages
|
|
||||||
WHERE session_id = ?
|
|
||||||
ORDER BY timestamp, id
|
|
||||||
`).all(hermesSession.id) as unknown as HermesMessageRow[]
|
|
||||||
|
|
||||||
// Insert all messages
|
if (!detail || !detail.messages) {
|
||||||
for (const msg of messages) {
|
result.errors.push(`session ${hermesSession.id}: failed to load messages`)
|
||||||
|
logger.warn(`[session-sync] failed to load messages for session ${hermesSession.id}`)
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
|
||||||
|
// Insert all messages from the entire chain
|
||||||
|
for (const msg of detail.messages) {
|
||||||
addMessage({
|
addMessage({
|
||||||
session_id: newSessionId,
|
session_id: newSessionId,
|
||||||
role: msg.role,
|
role: msg.role,
|
||||||
@@ -203,22 +109,7 @@ function syncProfileSessions(profile: string): {
|
|||||||
})
|
})
|
||||||
}
|
}
|
||||||
|
|
||||||
// Generate preview from first user message
|
// Update session with aggregated stats from Hermes
|
||||||
const firstUserMessage = messages.find(m => m.role === 'user' && m.content)
|
|
||||||
let preview = ''
|
|
||||||
if (firstUserMessage && firstUserMessage.content) {
|
|
||||||
// Remove newlines, truncate to 63 chars
|
|
||||||
preview = firstUserMessage.content
|
|
||||||
.replace(/[\n\r]/g, ' ')
|
|
||||||
.trim()
|
|
||||||
.slice(0, 63)
|
|
||||||
}
|
|
||||||
|
|
||||||
// Update session with Hermes data
|
|
||||||
const estimatedCost = typeof hermesSession.estimated_cost_usd === 'number'
|
|
||||||
? hermesSession.estimated_cost_usd
|
|
||||||
: 0
|
|
||||||
|
|
||||||
updateSession(newSessionId, {
|
updateSession(newSessionId, {
|
||||||
started_at: hermesSession.started_at,
|
started_at: hermesSession.started_at,
|
||||||
ended_at: hermesSession.ended_at,
|
ended_at: hermesSession.ended_at,
|
||||||
@@ -228,21 +119,18 @@ function syncProfileSessions(profile: string): {
|
|||||||
cache_read_tokens: hermesSession.cache_read_tokens,
|
cache_read_tokens: hermesSession.cache_read_tokens,
|
||||||
cache_write_tokens: hermesSession.cache_write_tokens,
|
cache_write_tokens: hermesSession.cache_write_tokens,
|
||||||
reasoning_tokens: hermesSession.reasoning_tokens,
|
reasoning_tokens: hermesSession.reasoning_tokens,
|
||||||
estimated_cost_usd: estimatedCost,
|
estimated_cost_usd: hermesSession.estimated_cost_usd,
|
||||||
last_active: hermesSession.started_at, // Use started_at as fallback since last_active doesn't exist in Hermes state.db
|
last_active: hermesSession.last_active,
|
||||||
preview,
|
preview: hermesSession.preview,
|
||||||
})
|
})
|
||||||
|
|
||||||
result.synced++
|
result.synced++
|
||||||
logger.info(`[session-sync] synced Hermes session ${hermesSession.id} -> ${newSessionId} (${messages.length} messages)`)
|
logger.info(`[session-sync] synced Hermes session ${hermesSession.id} -> ${newSessionId} (${detail.messages.length} messages, thread_session_count=${detail.thread_session_count})`)
|
||||||
} catch (err: any) {
|
} catch (err: any) {
|
||||||
result.errors.push(`session ${hermesSession.id}: ${err.message}`)
|
result.errors.push(`session ${hermesSession.id}: ${err.message}`)
|
||||||
logger.warn(err, `[session-sync] failed to sync session ${hermesSession.id}`)
|
logger.warn(err, `[session-sync] failed to sync session ${hermesSession.id}`)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
} finally {
|
|
||||||
db.close()
|
|
||||||
}
|
|
||||||
} catch (err: any) {
|
} catch (err: any) {
|
||||||
if (!err.message.includes('state.db not found')) {
|
if (!err.message.includes('state.db not found')) {
|
||||||
result.errors.push(err.message)
|
result.errors.push(err.message)
|
||||||
@@ -257,7 +145,7 @@ function syncProfileSessions(profile: string): {
|
|||||||
* Main entry point: sync all profiles on startup
|
* Main entry point: sync all profiles on startup
|
||||||
* Only runs if local DB is empty (first startup or after DB reset)
|
* Only runs if local DB is empty (first startup or after DB reset)
|
||||||
*/
|
*/
|
||||||
export function syncAllHermesSessionsOnStartup(): void {
|
export async function syncAllHermesSessionsOnStartup(): Promise<void> {
|
||||||
// Check if local DB has any sessions - only sync if completely empty
|
// Check if local DB has any sessions - only sync if completely empty
|
||||||
const db = getDb()
|
const db = getDb()
|
||||||
if (!db) {
|
if (!db) {
|
||||||
@@ -279,13 +167,11 @@ export function syncAllHermesSessionsOnStartup(): void {
|
|||||||
logger.info(`[session-sync] found ${profiles.length} profiles: ${profiles.join(', ')}`)
|
logger.info(`[session-sync] found ${profiles.length} profiles: ${profiles.join(', ')}`)
|
||||||
|
|
||||||
let totalSynced = 0
|
let totalSynced = 0
|
||||||
let totalSkipped = 0
|
|
||||||
let totalErrors = 0
|
let totalErrors = 0
|
||||||
|
|
||||||
for (const profile of profiles) {
|
for (const profile of profiles) {
|
||||||
const result = syncProfileSessions(profile)
|
const result = await syncProfileSessions(profile)
|
||||||
totalSynced += result.synced
|
totalSynced += result.synced
|
||||||
totalSkipped += result.skipped
|
|
||||||
totalErrors += result.errors.length
|
totalErrors += result.errors.length
|
||||||
|
|
||||||
if (result.errors.length > 0) {
|
if (result.errors.length > 0) {
|
||||||
@@ -299,5 +185,5 @@ export function syncAllHermesSessionsOnStartup(): void {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
logger.info(`[session-sync] sync complete: synced=${totalSynced}, skipped=${totalSkipped}, errors=${totalErrors}`)
|
logger.info(`[session-sync] sync complete: synced=${totalSynced}, errors=${totalErrors}`)
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -49,7 +49,7 @@ export const PROVIDER_PRESETS: ProviderPreset[] = [
|
|||||||
value: 'deepseek',
|
value: 'deepseek',
|
||||||
builtin: true,
|
builtin: true,
|
||||||
base_url: 'https://api.deepseek.com',
|
base_url: 'https://api.deepseek.com',
|
||||||
models: ['deepseek-chat', 'deepseek-reasoner'],
|
models: ['deepseek-v4-flash', 'deepseek-v4-pro'],
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
label: 'Z.AI / GLM',
|
label: 'Z.AI / GLM',
|
||||||
|
|||||||
Reference in New Issue
Block a user