studio/sol
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity
Files
9e5f7e61becdecaf3ea310e66bbbbfeb79f48e77
sol/config/sol.toml

49 lines
1.4 KiB
TOML
Raw Normal View History

feat: initial Sol virtual librarian implementation Matrix bot with E2EE (matrix-sdk 0.9) that passively archives all messages to OpenSearch and responds to queries via Mistral AI with function calling tools. Core systems: - Archive: bulk OpenSearch indexer with batch/flush, edit/redaction handling, embedding pipeline passthrough - Brain: rule-based engagement evaluator (mentions, DMs, name invocations), LLM-powered spontaneous engagement, per-room conversation context windows, response delay simulation - Tools: search_archive, get_room_context, list_rooms, get_room_members registered as Mistral function calling tools with iterative tool loop - Personality: templated system prompt with Sol's librarian persona 47 unit tests covering config, evaluator, conversation windowing, personality templates, schema serialization, and search query building.
2026-03-20 21:40:13 +00:00
[matrix]
homeserver_url = "http://tuwunel.matrix.svc.cluster.local:6167"
user_id = "@sol:sunbeam.pt"
state_store_path = "/data/matrix-state"
feat: multi-agent architecture with Conversations API and persistent state Mistral Agents + Conversations API integration: - Orchestrator agent created on startup with Sol's personality + tools - ConversationRegistry routes messages through persistent conversations - Per-room conversation state (room_id → conversation_id + token counts) - Function call handling within conversation responses - Configurable via [agents] section in sol.toml (use_conversations_api flag) Multimodal support: - m.image detection and Matrix media download (mxc:// → base64 data URI) - ContentPart-based messages sent to Mistral vision models - Archive stores media_urls for image messages System prompt rewrite: - 687 → 150 lines — dense, few-shot examples, hard rules - {room_context_rules} placeholder for group vs DM behavior - Sender prefixing (<@user:server>) for multi-user turns in group rooms SQLite persistence (/data/sol.db): - Conversation mappings and agent IDs survive reboots - WAL mode for concurrent reads - Falls back to in-memory on failure (sneezes into all rooms to signal) - PVC already mounted at /data alongside Matrix SDK state store New modules: - src/persistence.rs — SQLite state store - src/conversations.rs — ConversationRegistry + message merging - src/agents/{mod,definitions,registry}.rs — agent lifecycle - src/agent_ux.rs — reaction + thread progress UX - src/tools/bridge.rs — tool dispatch for domain agents 102 tests passing.
2026-03-21 22:21:14 +00:00
db_path = "/data/sol.db"
feat: initial Sol virtual librarian implementation Matrix bot with E2EE (matrix-sdk 0.9) that passively archives all messages to OpenSearch and responds to queries via Mistral AI with function calling tools. Core systems: - Archive: bulk OpenSearch indexer with batch/flush, edit/redaction handling, embedding pipeline passthrough - Brain: rule-based engagement evaluator (mentions, DMs, name invocations), LLM-powered spontaneous engagement, per-room conversation context windows, response delay simulation - Tools: search_archive, get_room_context, list_rooms, get_room_members registered as Mistral function calling tools with iterative tool loop - Personality: templated system prompt with Sol's librarian persona 47 unit tests covering config, evaluator, conversation windowing, personality templates, schema serialization, and search query building.
2026-03-20 21:40:13 +00:00
[opensearch]
url = "http://opensearch.data.svc.cluster.local:9200"
index = "sol_archive"
feat: per-user auto-memory with ResponseContext Three memory channels: hidden tool (sol.memory.set/get in scripts), pre-response injection (relevant memories loaded into system prompt), and post-response extraction (ministral-3b extracts facts after each response). User isolation enforced at Rust level — user_id derived from Matrix sender, never from script arguments. New modules: context (ResponseContext), memory (schema, store, extractor). ResponseContext threaded through responder → tools → script runtime. OpenSearch index sol_user_memory created on startup alongside archive.
2026-03-21 15:51:31 +00:00
memory_index = "sol_user_memory"
feat: initial Sol virtual librarian implementation Matrix bot with E2EE (matrix-sdk 0.9) that passively archives all messages to OpenSearch and responds to queries via Mistral AI with function calling tools. Core systems: - Archive: bulk OpenSearch indexer with batch/flush, edit/redaction handling, embedding pipeline passthrough - Brain: rule-based engagement evaluator (mentions, DMs, name invocations), LLM-powered spontaneous engagement, per-room conversation context windows, response delay simulation - Tools: search_archive, get_room_context, list_rooms, get_room_members registered as Mistral function calling tools with iterative tool loop - Personality: templated system prompt with Sol's librarian persona 47 unit tests covering config, evaluator, conversation windowing, personality templates, schema serialization, and search query building.
2026-03-20 21:40:13 +00:00
batch_size = 50
flush_interval_ms = 2000
embedding_pipeline = "tuwunel_embedding_pipeline"
[mistral]
default_model = "mistral-medium-latest"
evaluation_model = "ministral-3b-latest"
research_model = "mistral-large-latest"
max_tool_iterations = 5
[behavior]
feat: per-user auto-memory with ResponseContext Three memory channels: hidden tool (sol.memory.set/get in scripts), pre-response injection (relevant memories loaded into system prompt), and post-response extraction (ministral-3b extracts facts after each response). User isolation enforced at Rust level — user_id derived from Matrix sender, never from script arguments. New modules: context (ResponseContext), memory (schema, store, extractor). ResponseContext threaded through responder → tools → script runtime. OpenSearch index sol_user_memory created on startup alongside archive.
2026-03-21 15:51:31 +00:00
response_delay_min_ms = 100
response_delay_max_ms = 2300
feat: initial Sol virtual librarian implementation Matrix bot with E2EE (matrix-sdk 0.9) that passively archives all messages to OpenSearch and responds to queries via Mistral AI with function calling tools. Core systems: - Archive: bulk OpenSearch indexer with batch/flush, edit/redaction handling, embedding pipeline passthrough - Brain: rule-based engagement evaluator (mentions, DMs, name invocations), LLM-powered spontaneous engagement, per-room conversation context windows, response delay simulation - Tools: search_archive, get_room_context, list_rooms, get_room_members registered as Mistral function calling tools with iterative tool loop - Personality: templated system prompt with Sol's librarian persona 47 unit tests covering config, evaluator, conversation windowing, personality templates, schema serialization, and search query building.
2026-03-20 21:40:13 +00:00
spontaneous_delay_min_ms = 15000
spontaneous_delay_max_ms = 60000
feat: per-user auto-memory with ResponseContext Three memory channels: hidden tool (sol.memory.set/get in scripts), pre-response injection (relevant memories loaded into system prompt), and post-response extraction (ministral-3b extracts facts after each response). User isolation enforced at Rust level — user_id derived from Matrix sender, never from script arguments. New modules: context (ResponseContext), memory (schema, store, extractor). ResponseContext threaded through responder → tools → script runtime. OpenSearch index sol_user_memory created on startup alongside archive.
2026-03-21 15:51:31 +00:00
spontaneous_threshold = 0.85
feat: initial Sol virtual librarian implementation Matrix bot with E2EE (matrix-sdk 0.9) that passively archives all messages to OpenSearch and responds to queries via Mistral AI with function calling tools. Core systems: - Archive: bulk OpenSearch indexer with batch/flush, edit/redaction handling, embedding pipeline passthrough - Brain: rule-based engagement evaluator (mentions, DMs, name invocations), LLM-powered spontaneous engagement, per-room conversation context windows, response delay simulation - Tools: search_archive, get_room_context, list_rooms, get_room_members registered as Mistral function calling tools with iterative tool loop - Personality: templated system prompt with Sol's librarian persona 47 unit tests covering config, evaluator, conversation windowing, personality templates, schema serialization, and search query building.
2026-03-20 21:40:13 +00:00
room_context_window = 30
dm_context_window = 100
backfill_on_join = true
backfill_limit = 10000
feat: per-user auto-memory with ResponseContext Three memory channels: hidden tool (sol.memory.set/get in scripts), pre-response injection (relevant memories loaded into system prompt), and post-response extraction (ministral-3b extracts facts after each response). User isolation enforced at Rust level — user_id derived from Matrix sender, never from script arguments. New modules: context (ResponseContext), memory (schema, store, extractor). ResponseContext threaded through responder → tools → script runtime. OpenSearch index sol_user_memory created on startup alongside archive.
2026-03-21 15:51:31 +00:00
instant_responses = false
cooldown_after_response_ms = 15000
evaluation_context_window = 200
reaction_threshold = 0.6
reaction_enabled = true
detect_sol_in_conversation = true
script_timeout_secs = 5
script_max_heap_mb = 64
script_fetch_allowlist = []
memory_extraction_enabled = true
# evaluation_prompt_active = "custom prompt when Sol is already in conversation..."
# evaluation_prompt_passive = "custom prompt when Sol hasn't spoken yet..."
feat: multi-agent architecture with Conversations API and persistent state Mistral Agents + Conversations API integration: - Orchestrator agent created on startup with Sol's personality + tools - ConversationRegistry routes messages through persistent conversations - Per-room conversation state (room_id → conversation_id + token counts) - Function call handling within conversation responses - Configurable via [agents] section in sol.toml (use_conversations_api flag) Multimodal support: - m.image detection and Matrix media download (mxc:// → base64 data URI) - ContentPart-based messages sent to Mistral vision models - Archive stores media_urls for image messages System prompt rewrite: - 687 → 150 lines — dense, few-shot examples, hard rules - {room_context_rules} placeholder for group vs DM behavior - Sender prefixing (<@user:server>) for multi-user turns in group rooms SQLite persistence (/data/sol.db): - Conversation mappings and agent IDs survive reboots - WAL mode for concurrent reads - Falls back to in-memory on failure (sneezes into all rooms to signal) - PVC already mounted at /data alongside Matrix SDK state store New modules: - src/persistence.rs — SQLite state store - src/conversations.rs — ConversationRegistry + message merging - src/agents/{mod,definitions,registry}.rs — agent lifecycle - src/agent_ux.rs — reaction + thread progress UX - src/tools/bridge.rs — tool dispatch for domain agents 102 tests passing.
2026-03-21 22:21:14 +00:00
[agents]
orchestrator_model = "mistral-medium-latest"
domain_model = "mistral-medium-latest"
compaction_threshold = 118000
use_conversations_api = true
Reference in New Issue Copy Permalink