* feat: add session deep links for chats
* feat: add deep links for history and group chat
* Fix profile-aware session deep links
---------
Co-authored-by: Maxim Kirilyuk <werserk@inbox.ru>
* feat: support profile-aware group chat bridge flows
* feat: route cron jobs through hermes cli
* Fix group chat routing and isolate bridge tests
* Add Grok image-to-video media skill
* Default Grok videos to media directory
* Fix bridge profile fallback and cron repeat clearing
* Refine bridge chat and gateway platform handling
* Filter bridge tool-call text deltas
* Preserve structured bridge chat history
* Prepare beta release build artifacts
* Fix Windows run profile resolution
* Fix Windows path compatibility checks
* Fix profile-scoped model page display
* Hide Windows subprocess windows for jobs and updates
* Hide Windows file backend subprocess windows
* Avoid Windows gateway restart lock conflicts
* Treat Windows gateway lock as running on startup
* Force release Windows gateway lock on restart
* Tighten Windows gateway lock cleanup
* Update chat e2e source expectation
* Bump package version to 0.5.30
---------
Co-authored-by: Codex <codex@openai.com>
* feat(bridge): refactor compression to use DB history and add structured logging
- Extract buildDbHistory() to share message loading between buildCompressedHistory and forceCompressBridgeHistory
- forceCompressBridgeHistory now reads from local DB instead of using Python-provided messages, ensuring consistency with api_server path
- Pass sessionId to compressor for snapshot-aware compression
- Add force_compress flag to bridge chat requests
- Add bridgeLogger structured logging for compression lifecycle
- Simplify schemas, session-sync, and providers
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix bridge compression history handling
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* feat: add CLI chat sessions with Python agent bridge
Introduce a new CLI chat mode that connects Web UI directly to Hermes
Agent's AIAgent via a Python bridge subprocess and Socket.IO, bypassing
the API Server /v1/responses path. Supports streaming, slash commands
(/new, /undo, /retry, /branch, /compress, /save, /title), interrupt,
and steer.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat: update CLI chat session bridge
* fix: extend agent bridge startup timeouts
* docs: update bridge chat session design
* feat: align bridge compression and provider registry
* chore: bump version to 0.5.20
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
- visualize input, output, and cache token segments in usage charts
- add usage period selector for 7d, 30d, 90d, and 365d
- guard usage stats against stale overlapping period requests
- normalize blank model usage into unknown buckets
- add client and server coverage for usage analytics behavior
Prevents infinite retry loop on /api/hermes/available-models when
accessing the app without a token, which triggers server-side 429
rate limiting. Both loadModels() and fetchProviders() now bail out
early if hasApiKey() returns false.
Closes#606
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* feat(models): add WUI model display aliases
Persist display-only model aliases in Web UI app config, surface them in the model selector/search, and keep canonical model IDs for Hermes calls.
* fix(models): improve WUI model alias editing
* fix(models): clarify unlisted model picker
* fix(models): scope aliases to providers
* feat(models): add WUI model visibility filter
Store provider model visibility in Web UI app config and filter the WUI model picker/model page without rewriting Hermes CLI config or canonical model IDs.
* fix(models): sync sidebar after visibility changes
Defer all non-user message DB writes until response completion or
abort, instead of writing tool calls immediately during streaming.
This ensures correct message ordering and prevents the abort handler
from overwriting displayed messages with incomplete DB data.
- Remove immediate addMessage() calls from response.output_item.done
- Remove immediate addMessage() from insertResponseTextOnce
- Add flushResponseRunToDb() to batch-write all run messages on
both normal completion (markCompleted) and abort (handleAbort)
- Skip user messages in flush (already written in handleRun)
- Remove refreshActiveSession() from abort.completed frontend handler
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* refactor: migrate from /v1/runs to /v1/responses streaming API
Replace EventSource-based polling with direct SSE streaming via the
/v1/responses endpoint across all server-side callers (chat-run-socket,
context-compressor, gateway-client, agent-clients). Messages are now
written to DB in real-time during streaming, eliminating post-run sync.
Frontend chat store adds tool_call_id tracking for deduplication.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* chore: bump version to 0.5.16 and add changelog
- Persist real API usage to usage table on response.completed
- Remove unused codex_reasoning_items field from message schema
- Fix unused variable warnings in chat-run-socket
- Bump version to 0.5.16
- Add changelog entries for 0.5.16 (8 locales)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
- Fix kanban loading spinner flickering on auto-refresh (silent mode)
- Fix group chat room-list transparent background on mobile
- Fix group chat sidebar auto-opening on mobile entry
- Fix page-header title overlapped by hamburger button on mobile
- Move hamburger button position to top: 10px
- Add changelog note about upgrading hermes-agent for kanban support
- Add i18n translations for all 8 locales
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* fix: support run approval prompts in chat
* fix(chat): render approval prompts
* fix(chat): dedupe approval pattern labels
* chore: sync approval flow with current main
- update Hermes Agent approval support guidance to PR #21899
- initialize Hermes table schemas in session-sync tests
Allow sending multiple messages while a run is active. Messages are
queued on the server and processed sequentially after each run
completes. Each completed assistant message triggers speech playback
independently, and the UI shows queue status with a badge indicator.
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Frontend:
- Filter out assistant messages with empty content in mapHermesMessages()
- Prevents displaying 194/585 empty messages in long sessions
- Reduces visual clutter and improves UX
Backend:
- Add message count limit (<= 200) to compression threshold checks
- Prevents compressing sessions with too many messages
- Improves compression performance and reliability
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
ekko