llm: add dynamic tool loading (DTL) — Kimi system-tools + Anthropic tool-reference
Nightly Build / build (push) Successful in 6m51s

Replace the old session_mcp_grants/stack_mcp_grants table pair with
a single activated_tools table that anchors each activation at the
assistant message_id that triggered it. The durable write moves from
the activate_tools tool itself to the round loop (handle_tool_call),
which has the message_id the DTL serializer positions injected tool
blocks against.

Introduce DtlMode (None / AnthropicToolReference / KimiSystemTools),
resolved per model from capabilities (opt-in via tool_search)
combined with the provider's dtl_format(). The message builder inserts
Kimi system {tools} blocks at the activation position, or emits
Anthropic tool_reference markers on the tool result. The tool-def
surface (all_tool_defs) switches shape: Anthropic declares everything
deferred; Kimi omits activated tools from the top-level array (system
takes over); None keeps the old grant-set logic.

Anthropic client: accept structured system arrays (cache_control on
the static block when DTL is active), carry defer_loading through
conversion, emit tool_reference blocks on result messages. Prompt
caching enabled exactly when DTL is active (anthropic provider).

MCP server list in the prompt is now a static catalogue (not split
Available/Active) — the split invalidated the cache on every activation.
Groundwork for providers.yaml dtl: key; Moonshot/Kimi providers wired
with kimi_system_tools and the k3* enrich now adds tool_search.
Compactor re-anchors activations whose message was compacted away.
This commit is contained in:
2026-07-24 20:48:04 +01:00
parent 3c52587dee
commit d1d0a2af26
21 changed files with 579 additions and 226 deletions
+1 -1
View File
@@ -452,7 +452,7 @@ impl ChatHub {
/// The next LLM turn will start with no MCP servers activated.
pub async fn reset_mcp(&self, source_id: &str) -> anyhow::Result<()> {
let session_id = self.get_or_create_session(source_id, &self.default_agent).await?;
crate::db::session_mcp_grants::revoke_all(&self.db, session_id).await?;
crate::db::activated_tools::revoke_all_session(&self.db, session_id).await?;
info!(source_id, session_id, "ChatHub: MCP grants reset");
Ok(())
}