llm: switch Skald to agent-loop Model clients; drop llm-client (phase 1, D13)
The LLM call path now runs on the agent-loop crate's clients and trait: - core-api: BuiltLlmClient.client is Arc<dyn agent_loop::model::Model>; chatbot.rs (ChatbotClient + wire types) deleted; APP_NAME re-exported from agent-loop - providers (openai/anthropic/ollama/openrouter/requesty/declared) build OpenAiModel/AnthropicModel/OllamaModel with the model's wire id - LoggingModel decorator (llm/logging.rs) replaces LoggingChatbotClient; per-request correlation (session/stack/user) travels in the new ModelRequest.log field, never sent to providers - llm_call/llm_loop/compactor speak Model::complete + ModelResponse; retriability via Model::is_retriable (structured status, B6 rule now the crate's default); payload persistence reads RawMeta off ModelResponse/ModelError - crates/llm-client and skald-core/src/chatbot deleted Full workspace test suite green (incl. 162 skald-core + 32 agent-loop).
This commit is contained in:
@@ -5,7 +5,6 @@ members = [
|
||||
"crates/skald-core",
|
||||
"crates/skald-setup",
|
||||
"crates/honcho-client",
|
||||
"crates/llm-client",
|
||||
"crates/core-api",
|
||||
"crates/mcp-client",
|
||||
"crates/plugin-tailscale-remote",
|
||||
@@ -74,7 +73,6 @@ tracing-appender = "0.2"
|
||||
chrono = { version = "0.4", default-features = false, features = ["clock", "std"] }
|
||||
notify = "8"
|
||||
honcho-client = { path = "crates/honcho-client" }
|
||||
llm-client = { path = "crates/llm-client" }
|
||||
core-api = { path = "crates/core-api" }
|
||||
mcp-client = { path = "crates/mcp-client" }
|
||||
plugin-tailscale-remote = { path = "crates/plugin-tailscale-remote" }
|
||||
|
||||
Reference in New Issue
Block a user