The agent config reload logic was missing skills and mcp_servers from
the change detection, so edits to these fields in agent.toml weren't
being picked up when loading agents from SQLite.
Added both fields to the comparison to ensure proper hot-reload.
- #771: Fix Qwen tool_calls orphaning after context overflow. Added safe drain boundaries
in compactor and context_overflow to avoid splitting tool pairs. Added missing
validate_and_repair call in streaming loop.
- #811: LINE webhook signature now uses raw request bytes (not re-serialized JSON) for
HMAC. Channel secret is trimmed. Debug logging added for mismatches.
- #752: Local skill install now hot-reloads kernel via POST /api/skills/reload. TUI skill
list fixed to parse wrapper object. ClawHub install also triggers reload.
- #772: exec_policy mode=full now bypasses approval gate for shell_exec tools. Non-shell
tools like file_delete still respect approval settings.
- #661: Closed as resolved by #770 splice() reactivity fix and #836 tool ID fix.
All tests passing. 10 files changed, 436 insertions.
- #875: Install script uses robust sed parsing instead of fragile cut for version detection
- #872: Session endpoint returns full tool results (removed 2000-char truncation)
- #867: agent_send/agent_spawn get 600s timeout (was 120s), regular tools keep 120s
- #824: Doctor workspace skills count uses direct return value from load_workspace_skills
- #833: Model switching respects provider via new find_model_for_provider() lookup
- #766: Closed as resolved by combined heartbeat fixes (v0.5.3 + merged PRs)
All tests passing. Live tested with daemon.
- Add missing budget_config field to AppState in all 3 test files
- Fix redundant closures and unwrap_or_else in openfang-memory semantic.rs
- Fix needless_borrow in openfang-api routes.rs (toml::from_str)
- Update parse_researcher_hand test to match new max_iterations = 25
- Update tar to 0.4.45 to fix RUSTSEC-2026-0067 and RUSTSEC-2026-0068
- Apply cargo fmt fixes in ws.rs and feishu.rs
Replace the custom JSON-RPC + stdio/SSE transport layer with the rmcp
SDK (crate 'rmcp'). This gives us spec-compliant Streamable-HTTP
transport, automatic Mcp-Session-Id tracking, SSE stream parsing, and
content-type negotiation out of the box while deleting ~300 lines of
hand-rolled plumbing.
Key changes:
- Add rmcp dependency with transport feature
- Replace McpTransportHandle enum with rmcp RunningService
- Replace manual JSON-RPC send_request/send_notification with rmcp client calls
- Add custom HTTP headers support for authenticated remote MCP servers
- Simplify tool discovery and invocation through rmcp's typed API
Add generic MQTT 3.1.1/5.0 support for IoT and messaging integration:
- MqttConfig with broker_url, TLS, QoS, auth via env vars
- MqttAdapter implementing ChannelAdapter trait
- Support for text and JSON {"text": "..."} payloads
- Command messages via /command args syntax
- Auto-reconnect with exponential backoff
- Message chunking for long responses
Configuration example:
[channels.mqtt]
broker_url = "tcp://broker.hivemq.com:1883"
subscribe_topic = "openfang/inbox"
publish_topic = "openfang/outbox"
