Add persistent chat session state (ChatState, sequence tracking, tool
calls). Introduce basic billing record in agent crate. Refine chat
service to route messages through state machine with tool support.
Extract connection pool management and helper utilities.
Remove redundant metrics indirection, expose counters directly.
Trim room.rs boilerplate and move AI queue logic to room_ai_queue.
Simplify ai_streaming by delegating to ai_mode_streaming.
Extract sequence coordination into dedicated module.
Add worker pool management for concurrent AI task handling.
Refine ai_react_streaming for better delta chunk handling.
Add RoomAiService as the central dispatcher that selects execution
path based on mode (react/chat/cot/reflexion/rewoo) and streams
vs nonstreaming preference. Replace monolithic ai_streaming with
mode-aware dispatch and dedicated streaming implementation.
Move tool execution to a spawned task so synchronous git2 operations
don't block the tokio worker thread, allowing heartbeat chunks to be
sent every 10s during long tool execution.
Also add analysis-first reasoning prompt to system messages.
Add scan_repo_tree_for_skills and scan_skills_from_tree functions that
traverse git objects directly instead of filesystem, enabling skill
discovery in bare repositories created via git2::Repository::init_bare.
Add repo_search, repo_readme, repo_commit_log, repo_contributors,
and repo_diff_summary function call tools for AI to search code,
read README, query commit history, list contributors, and diff revisions.
Add repo_overview, repo_file_tree, repo_languages, and repo_dependencies
function call tools for AI to quickly analyze repository structure,
language breakdown, and dependency manifests.
Backend:
- New GET /api/agents/models/catalog endpoint with page/per_page/search
params, excludes deprecated models, returns pricing data via
model→version→pricing join
- ModelWithPricingResponse includes input_price, output_price, currency
- ModelListResponse with pagination metadata (total, page, per_page)
- Batch-fetches default versions + latest pricing to avoid N+1
Frontend:
- RoomSettingsPanel: replace Dialog with inline two-step panel
- Step 1: paginated model browser with search, shows context length,
max output tokens, pricing per 1K tokens, capability/modality badges
- Step 2: selected model info card + AI configuration form
- Removed Dialog import and related unused dependencies
Backend:
- room_ai_list: batch-fetch models, skip entries where model_name
cannot be resolved (instead of falling back to "AI {uid}")
- room_ai_upsert: return None for model_name when lookup fails
(instead of "AI {uid}")
Frontend:
- room-context: discard configs with missing modelName after retries
- DiscordMemberList: filter out configs without modelName
- MessageInput: filter out configs without modelName
- RoomSettingsPanel: prefer model_name from API, fallback to
availableModels lookup, never render raw UID
- RoomAiTasksPanel: fix broken id/name mapping (was cfg.id/cfg.name
which don't exist), filter out configs without model_name
In actix-web, separate web::scope() trees don't merge. The /projects
scope was intercepting /api/projects/{name}/skills before the separate
skill scope could match, causing 404 on all skill endpoints.
Move skill routes into init_project_routes as /{project_name}/skills/*
and remove the standalone configure(skill::init_skill_routes) call.
- Implement SSHandle struct with comprehensive Git service handling capabilities
- Add support for multiple authentication methods including password, public key and certificate
- Integrate Git command parsing and execution with proper channel management
- Implement branch protection rules enforcement during Git operations
- Add robust error handling and logging for SSH connections and Git processes
- Create secure Git command execution with environment isolation
- Implement proper resource cleanup for channels and subprocesses
- Add support for receive-pack, upload-pack and upload-archive services
- Integrate with existing authz and database services for permission checks
- Implement proper data forwarding between SSH channels and Git processes
fix(config): improve environment loading with error reporting
- Replace silent dotenv loading failures with informative error messages
- Handle global config race conditions safely during application startup
- Improve config loading reliability and debugging capabilities
fix(link-unfurl): handle server-side rendering compatibility
- Add undefined window object check for SSR environments
- Prevent client-side only code from breaking server-side rendering
refactor(agent): improve tool registry error handling
- Replace panics with graceful error logging for duplicate tool registrations
- Add proper error type definitions for tool registry operations
- Implement safe merging of registries with duplicate detection
fix(room-context): enhance WebSocket connection reliability
- Add proper error handling for room subscription operations
- Improve connection management with better error suppression
- Add console warnings for debugging connection issues
feat(ws-client): add comprehensive WebSocket client implementation
- Create RoomWsClient class with complete WebSocket communication layer
- Implement request-response pattern with timeout handling
- Add support for various room-related events and actions
- Include proper connection status tracking and management
- Implement callback system for different event types
- Add automatic reconnection and error recovery mechanisms
- Apply same deduplication logic as service scanner
- Keep latest version by commit_sha when duplicates found
- Fix type error: Ok("skill.md") → Some("skill.md".to_string())
- Change deduplication key from slug to {repo_id}+{blob_hash}
- Keep latest version by commit_sha when duplicates found
- Use git2 to open repos and get correct workdir and commit_sha
- Fix case-insensitive SKILL.md detection in scanner
Add room parameter (UUID) and pn (project name) to search/messages API.
Service layer supports filtering messages by room and project scope.
Frontend search page updated with room-scoped search support.
Billing is now handled internally by chat_service.process via record_ai_session.
Remove the old billing.rs file and explicit record_ai_usage calls from all 4
AI streaming modes (nonstreaming, react_nonstreaming, react_streaming, streaming).
- HookWorker gains optional embed_service field
- Captures changed tag names during webhook dispatch, batch-embeds after completion
- HookService auto-inits EmbedService from config for standalone git-hook binary
- Adds agent dep to git crate (no circular dep)
- SSH/HTTP servers no longer call start_worker (dedicated git-hook handles it)
- git_tag_search FC tool for agent semantic tag search with project isolation
- After issue_create: spawn embed_issue_chunked (non-blocking)
- After skill_create/update: spawn embed_skill
- After repo create/update in fctool: spawn embed_repo
- Wire EmbedService through AppService, available for all triggers
- make_persist_fn now accepts embed_service, collects persisted text messages
- Filters non-text, non-empty, non-system/tool messages
- Groups by room→project_name, batch-embeds via embed_memories_batch
- Removes old per-message synchronous embed_memory call
- Workers thread embed_service through to persist_fn
Add with_embed_service() builder and embed_service() accessor to ToolContext,
wired through ChatService so function-calling tools can access Qdrant vector search.
- chunk_text(): char-boundary-safe text chunking at paragraph/sentence breaks (7000 char limit)
- embed_memories_batch(): groups messages by room, batch-embeds all texts to reduce Qdrant calls
- embed_issue_chunked(): auto-chunks long issue bodies
- embed_skill(): upgraded with auto-chunking via chunk_text
- TagEmbedInput struct for batch tag embedding
- embed_tags_batch() / search_tags() with project isolation
- ensure_collections() now creates embed_repo_tag collection
- ai_react_nonstreaming now passes real input/output tokens to billing
- Was passing hardcoded 0,0 despite destructuring token data
- Also fix unused variable warnings
Critical fixes:
- Wrap balance updates in database transactions with SELECT FOR UPDATE
- Move history insert after balance validation to prevent orphaned records
- Use Decimal throughout to avoid silent conversion failures
- Prevent concurrent requests from causing negative balances
Tasks resolved:
- Task #4: Silent Decimal conversion failures
- Task #5: Missing transaction isolation (race conditions)
- Task #6: History inserted before validation
- process_react now returns (String, i64, i64) tuple with token counts
- Extract token stats from rig Agent FinalResponse usage field
- Both streaming and non-streaming ReAct modes now bill correctly
- Add record_ai_session() helper calling billing::record_ai_usage()
- Replace all Set(None) cost/currency with actual calculated values
- Cost computed from model_pricing via Decimal precision
- Use AgentBuilder for native tool-calling with stream_prompt()
- Add RecordingTool wrapper preserving retry + DB recording
- Fix tool_choice bug in do_completion (same as call_stream_once)
- Add seq field to RoomMessageStreamChunkEvent for strict ordering
- Map streaming events: Text→Answer, Reasoning→Thought, ToolCall→Action
- Only final event has done=true, removed premature stream ending
- Store __chunks__ JSON in thinking_content for ordered replay
- issue_triage.rs: use check_project_access instead of nonexistent get_project_member
- email/lib.rs: make EMAIL_REGEX pub to suppress dead_code warning
- tracing_fmt.rs: minor import ordering cleanup and code formatting
- Import room_message_reaction, room_message_edit_history, room_notifications modules
- Fix room_message_edit_history: no Room column, use subquery via messages
- Change publish_project_room_event from Result to () handling
- Add QuerySelect import for limit() method in workers.rs
- Add Offline status to ModelStatus enum
- Sync marks all models offline first, then activates found ones
- Deduplicate by model name (ignoring provider)
- Deactivate orphaned models (offline -> deprecated)
- Add models_offline and models_deactivated to SyncModelsResponse
- Add deduplicate_existing_models() for cleanup
- Rename upsert_model to upsert_model_by_name
- Start SSH rate limiter cleanup task that was missing (prevent memory leak)
- Create single ToolContext outside tool execution loop so max_tool_calls
and max_depth guards actually fire across batch tool calls (was creating
fresh context per call, bypassing all limits)
- Fix second copy of push_subscription unwrap that was in a
tokio::spawn block with different indentation
- Replace constant UUID parse unwrap with expect()
- SSH rate limiter: wire SshRateLimiter into SSHServer with IP-based
rate limiting on new_client connections
- Room startup: cap initial room load at 1000 via limit() to prevent
resource exhaustion on large instances
- WS token exposure: only include token in URL for cross-origin
connections; same-origin web clients authenticate via secure cookies
- CSRF: confirmed SameSite::Lax + Secure + HttpOnly are all set
(session config defaults)
When a user mentions a repository in room chat, extract the repo name
from @[repo:name:label] brackets, look up the full repo model from the
database, and inject its details (name, description, default branch,
visibility) into the AI message context. Works independently of
embed_service availability.
Add RoomAiUpdated, RepoCreated, RepoUpdated, RepoDeleted event types.
Publish RoomAiUpdated after room_ai upsert/delete and repo events
after repo create/update. Always set model_name in AI list response
(fallback to "AI {uuid}" when model lookup fails) so frontend never
displays a raw UUID.
When APP_AI_BASIC_URL already ends with /v1 (e.g. openrouter.ai/api/v1),
appending /v1/models produces /v1/v1/models. Detect trailing /v1 and
only append /models in that case.
Move git_tools, file_tools, and project_tools from libs/service into a
new libs/fctool crate with correct workspace dependencies. Fixes the
rev.len() >= 40 bug in all git tool resolve functions (OID check needs
exact 40-char hex, not just >= 40). Adds 4 new git blob tools
(blob_get, blob_exists, blob_content, blob_create). Fixes parameter
naming inconsistency in repos.rs and adds project_name to list_repos
output. Removes unused excel/pdf/ppt/word file tools.
1. WS disconnect now unsubscribes from user_notification_inner.
Previously, every WebSocket connection created a broadcast channel
for user notifications that was never removed on disconnect, causing
unbounded growth proportional to unique connected users over time.
2. Room worker tasks now use the manager's room_shutdown_txs channel
instead of a local broadcast channel. shutdown_room() sends on this
channel, so when a room is deleted the worker task receives the signal
and terminates, releasing its DashMap (capacity 10,000) and all
captured closures. Previously the worker ran forever.
When stdout is connected to a TTY, use tracing_subscriber's pretty
format with colors instead of single-line JSON. Non-TTY (container
logs, pipes) continue to output JSON for log aggregation.
Override auto-detection via APP_LOG_FORMAT=json|pretty.
Also adds APP_LOG_PRETTY=true to use serde_json::to_string_pretty
for human-readable JSON output (useful for development/debugging).
The upstream AI endpoint already returns complete model metadata:
- name, owned_by, context_length, max_output_tokens
- capabilities (vision, tool_call, reasoning)
- pricing (input, output, cache_read, cache_write, currency)
Remove the OpenRouter fallback entirely and parse the upstream
response directly for all sync operations. Both sync_upstream_models
(API) and sync_once (background task) now use a single unified path.
Changes:
- Remove OpenRouter types and fetch_openrouter_models()
- Add UpstreamModel / UpstreamCapabilities / UpstreamPricing types
- Parse capabilities from upstream instead of inferring from name
- Use real pricing from upstream instead of defaulting to 0.00
- Simplify sync flow: list → parse → upsert (no filtering/matching)
- Add provider normalizations for moonshot, zai, minimax, qwen
The upstream AI endpoint returns an OpenAI-compatible format, but the
response body parsing was fragile. Make it resilient:
1. Try standard OpenAI format: { "data": [{id}, ...] }
2. Try raw array: [{id}, ...]
3. Try alternate format: { "models": [{id}, ...] }
4. Log actual response body (first 500 chars) when all formats fail
Also adds a warning log with the raw response on parse failure so
future debugging is straightforward.
The check_compatibility(false) method was added in the previous commit
but does not exist in sqlx 0.8.x used by sea-orm 2.0. The warning
"Failed to obtain server version" is cosmetic and does not affect
functionality.
When OpenRouter's public /api/v1/models endpoint fails (network error,
timeout, parse failure), the entire sync was aborted — meaning models
accessible from the user's AI endpoint were never synced.
Now: if OpenRouter fetch fails, fall back to sync_models_direct for all
available models instead of returning an error. Both sync_upstream_models
(API) and sync_once (background task) have this fix.
Cloud-managed PostgreSQL variants (PolarDB, CockroachDB, etc.) may
not return a standard version string, causing:
"Failed to obtain server version. Unable to check client-server
compatibility."
Setting check_compatibility(false) on both writer and reader
connections silences this harmless warning.
When upstream /v1/models returns models not yet in OpenRouter's catalog
(e.g. brand-new models like DeepSeek-V4), also upsert them through the
same pipeline (provider → model → version → pricing → capabilities →
parameter_profile) with inferred defaults, instead of silently dropping
them. Previously the direct-sync fallback only triggered when *zero*
OpenRouter matches existed.
Remove daily report system (page, API routes, cron scheduler) as it is
no longer needed. Add /api/metrics endpoint exposing total and time-
windowed counts (27h, 7d, 30d) for users, workspaces, projects, repos,
rooms, and skills.
Also clean up dead code:
- Remove OpenRouter sync and alerts check routes
- Remove syncModels/checkAlerts from adminrpc client
- Remove unused adminRpcAvailable state from platform sessions page
- Fix handleEdit displayName comparison bug in platform users page
- Simplify pricing sync to create 0-price defaults
Add MsgJsonFormat custom event formatter that outputs JSON with _msg as
the first field, required by VictoriaLogs for full-text search. HTTP
middleware stores interpolated "METHOD /path" in thread-local buffer
for the formatter to read on span-close events.
- Save thinking_content as {"__chunks__": [{type, content}]} for replay
- Tool call sanitization — don't expose raw results to frontend
- Billing record_ai_usage integration
- Room service module refactoring into service/ directory
- StreamChunk/StreamChunkType types for preserving arrival order
- Chunk collection in call_stream_once and process_stream
- Add "error sending request" and "Http client error" to retryable errors
- StreamResult includes chunks vector for ordered replay
CNPG's cluster-ro service already handles load balancing and failover,
so the application-level Vec + random_range is redundant.
- db_read: Vec<DatabaseConnection> → Option<DatabaseConnection>
- database_read_replicas returns Option<String> instead of Vec<String>
- health checks now explicitly ping both writer() and reader()
- remove unused rand dependency from libs/db
- Main sitemap index at /sitemap.xml referencing 4 sub-sitemaps
- /sidemap/static: fixed routes (homepage, auth, marketing pages)
- /sidemap/users: public user profiles sorted alphabetically
- /sidemap/projects: public projects sorted alphabetically
- /sidemap/repos: public repos sorted alphabetically
- Redis cache with 8h TTL (no refresh on access), key: sidemap:{type}
- robots.txt Sitemap URL uses main_domain() with https:// forced
- All sitemap loc entries use https:// base URL
Health monitoring:
- gitserver: /health endpoint on port 8021 (DB + Redis ping)
- git-hook: hyper health server on port 8083 with /health
- email-worker: hyper health server on port 8084 with /health
- K8s probes updated to httpGet for all three services
Metrics (via /metrics endpoint):
- git-hook: hook_tasks_total/success/failed/locked/retried/exhausted,
hook_sync_branches/tags_changed_total
- email: email_queued/consumed/sent/failed_total,
email_validation_skipped/build_errors/send_attempts_total
- Add sender_type field to TypingEvent (user/ai)
- Change Redis TTL from 10s to 60s for AI typing persistence
- Broadcast typing.start/stop with sender_type=ai when AI stream starts/ends
- Replay active AI typing events from Redis on new WS subscribe
- Fix ai.stream_chunk WS payload missing display_name and chunk_type
- Add initial thinking chunk on AI stream start for immediate indicator
- service now delegates model/provider/pricing logic to agent crate
- ChatService built at startup with EmbedService (graceful degradation)
- RoomService wired with EmbedService for Qdrant embedding
- Add error types for embedding service
