Fix build warnings across workspace

- Remove redundant token fields from StreamEvent::Finished (data
  already delivered via Usage event)
- Remove dead hotkey_adjust_sampling, MAX_HISTORY, now()
- Fix unused variable warnings (delta, log)
- Suppress deserialization-only field warnings (jsonrpc, role)
- Make start_stream/chat_completion_stream_temp pub(crate)
- Remove unnecessary pub(crate) re-export of internal types

Remaining warnings are TODO items: SkipIndex (scoring not wired),
notify (MCP notifications not wired).

Co-Authored-By: Proof of Concept <poc@bcachefs.org>

src/agent/api/mod.rs

@@ -13,8 +13,6 @@ mod openai;
 
 // Public API types — used outside agent::api
 pub use types::{Message, MessageContent, ContentPart, ImageUrl, Role, ToolCall, FunctionCall, Usage};
-// Internal types — re-exported for sibling modules within agent/
-pub(crate) use types::{ChatRequest, ReasoningConfig, ChatCompletionChunk, ChunkChoice, Delta, ToolCallDelta, FunctionCallDelta};
 
 use anyhow::Result;
 use std::time::{Duration, Instant};
@@ -72,8 +70,6 @@ pub(crate) enum StreamEvent {
     /// Stream finished.
     Finished {
         reason: String,
-        prompt_tokens: u32,
-        completion_tokens: u32,
     },
     /// Error from the stream.
     Error(String),
@@ -105,7 +101,7 @@ impl ApiClient {
     /// Start a streaming chat completion. Returns a receiver of StreamEvents.
     /// The caller (runner) reads events and handles routing to the UI.
     ///
-    pub fn start_stream(
+    pub(crate) fn start_stream(
         &self,
         messages: &[Message],
         tools: &[agent_tools::Tool],
@@ -137,7 +133,7 @@ impl ApiClient {
         (rx, AbortOnDrop(handle))
     }
 
-    pub async fn chat_completion_stream_temp(
+    pub(crate) async fn chat_completion_stream_temp(
         &self,
         messages: &[Message],
         tools: &[agent_tools::Tool],

src/agent/api/openai.rs

@@ -181,14 +181,7 @@ pub(super) async fn stream_events(
     );
 
     let reason = finish_reason.unwrap_or_default();
-    let (pt, ct) = usage.as_ref()
-        .map(|u| (u.prompt_tokens, u.completion_tokens))
-        .unwrap_or((0, 0));
-    let _ = tx.send(StreamEvent::Finished {
-        reason,
-        prompt_tokens: pt,
-        completion_tokens: ct,
-    });
+    let _ = tx.send(StreamEvent::Finished { reason });
 
     Ok(())
 }

src/agent/api/types.rs

@@ -154,7 +154,6 @@ pub(crate) struct ReasoningConfig {
 }
 
 #[derive(Debug, Clone, Deserialize)]
-#[allow(dead_code)]
 pub struct Usage {
     pub prompt_tokens: u32,
     pub completion_tokens: u32,
@@ -171,7 +170,6 @@ pub(crate) struct ChatCompletionChunk {
 }
 
 #[derive(Debug, Deserialize)]
-#[allow(dead_code)]
 pub(crate) struct ChunkChoice {
     pub delta: Delta,
     pub finish_reason: Option<String>,
@@ -180,8 +178,8 @@ pub(crate) struct ChunkChoice {
 /// The delta within a streaming chunk. All fields optional because each
 /// chunk only carries the incremental change.
 #[derive(Debug, Deserialize, Default)]
-#[allow(dead_code)]
 pub(crate) struct Delta {
+    #[allow(dead_code)] // present for deserialization
     pub role: Option<Role>,
     pub content: Option<String>,
     /// Reasoning/thinking content — sent by some models (Qwen, DeepSeek)
@@ -276,7 +274,6 @@ impl Message {
         }
     }
 
-    #[allow(dead_code)]
     pub fn assistant(content: impl Into<String>) -> Self {
         Self {
             role: Role::Assistant,

src/agent/oneshot.rs

@@ -14,7 +14,7 @@ use std::fs;
 use std::path::PathBuf;
 use std::sync::OnceLock;
 
-use super::api::{self, ApiClient, Message, Usage};
+use super::api::{ApiClient, Message, Usage};
 use super::tools::{self as agent_tools};
 use super::Agent;