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
- message.rs: after creating a text message, spawn async task to
embed and upsert into Qdrant collection "room:{project}:{room_id}"
- service.rs: RoomService now takes optional EmbedService, embed on
every message creation
- build.rs: generate .gz and .br compressed variants at build time,
embed both into the FRONTEND constant
- dist.rs: content-type for SPA fallback uses index.html path explicitly,
explicit extension mapping for Vite content-hashed filenames
- frontend lib: get_frontend_asset_compressed returns (data, encoding, etag)
CommitReflogEntry now includes offset_minutes field, populated from
sig.when().offset_minutes() — matches git's internal timezone offset
representation. Used by git_tools for accurate reflog timestamps.
