mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-25 14:53:34 +00:00
feat(agent): thread per-tool reasoning through provider, session, and all surfaces (#1513)
* feat(agent): thread per-tool reasoning from LLM through to REPL, HTTP, SSE, and DB Add end-to-end agent reasoning summaries so users can see *why* the agent chose specific tools, not just what it did. - Add `reasoning: Option<String>` to `ToolCall` (all providers) - Populate from LLM response content in `Reasoning::respond_with_tools` and `select_tools`, with per-tool override when providers supply it - Extend `Turn` with `narrative` and `TurnToolCall` with `rationale` + `tool_call_id` for identity-based result matching - Persist reasoning in DB via existing tool_calls JSON (no migration) - Add `StatusUpdate::ReasoningUpdate` and `SseEvent::ReasoningUpdate` + `SseEvent::JobReasoning` for real-time streaming - Emit reasoning events in both chat dispatcher and worker job path - Add `/reasoning [N|all]` command for inspecting turn reasoning - Surface `narrative` and `rationale` in HTTP `/api/chat/history` Based on the design from #361 and #456, reconstructed cleanly with Option<String> to minimize blast radius (vs mandatory String that broke compilation in #456). Closes #456 Co-Authored-By: panosAthDBX <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review feedback from Gemini and Copilot - Fix `_ => Ok(None)` in agent_loop.rs to avoid accidental shutdown - Fix fallback in record_tool_result_for/record_tool_error_for to use first pending call instead of last_mut (parallel execution safety) - Include per-tool decisions in WASM channel reasoning messages - Apply truncate_at_tool_tags + clean_response to shared_reasoning in select_tools (parity with respond_with_tools) - Persist turn-level narrative to DB in tool_calls JSON wrapper - Parse both old (array) and new (object) tool_calls formats in build_turns_from_db_messages for backward compatibility - Populate reasoning from action.reasoning in execute_plan ToolCalls [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address second round of review comments + merge fixes - Add reasoning: None to new github_copilot.rs ToolCall sites (from staging merge) - Run cargo fmt on 4 files with formatting diffs - Truncate narrative to 1000 chars before DB persistence - Clone turn data and drop session lock in /reasoning command - Extract ToolDecisionDto::from_json_array shared helper (deduplicate worker/job.rs and orchestrator/api.rs) - Add unit tests for wrapped tool_calls JSON format with narrative [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address third round of review comments (Copilot + serrrfirat) - Reword ToolCall.reasoning docstring to reflect provider-supplied or fallback contract - Sanitize narrative through SafetyLayer before storage/emission - Clean per-tool reasoning via truncate_at_tool_tags + clean_response in select_tools (parity with shared reasoning) - Convert 4 approval-path recording sites in thread_ops.rs to identity-based record_tool_result_for/record_tool_error_for - Preserve tool_call_id and reasoning through restore_from_messages - Fix has_result/has_error to reject JSON null values - Truncate tool_call_id to 128 chars before DB persistence - Add 4 unit tests for record_tool_result_for/error_for edge cases Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address zmanian review — sanitize JobDelegate reasoning + warn on dropped results - Sanitize narrative and per-tool rationale through SafetyLayer in JobDelegate reasoning events (parity with ChatDelegate) - Add tracing::warn when record_tool_result_for/error_for drops a result because no matching or pending tool call exists - Add 3 unit tests for reasoning normalization (thinking tags, tool tags, empty-after-cleaning) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address 4 remaining unreplied review comments - Clean per-tool reasoning in respond_with_tools via truncate_at_tool_tags + clean_response (parity with select_tools) - Handle wrapped JSON format in rebuild_chat_messages_from_db so cold hydration works after persist_tool_calls format change - Update persist_tool_calls doc comment to describe new JSON shape - Sanitize per-tool rationale through SafetyLayer in ChatDelegate before emission and storage (parity with JobDelegate) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address zmanian review round 2 - Add tracing::debug on fallback-to-pending path in record_tool_result_for and record_tool_error_for (item 1) - Add comment explaining why /reasoning is special-cased in agent_loop.rs (item 4) - Items 2 (narrative persistence), 3 (rationale sanitization), and 5 (catch-all fix) were already addressed in prior commits Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: panosAthDBX <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
This commit is contained in:
Illia Polosukhin
co-authored by
panosAthDBX
Claude Opus 4.6
panosAthDBX
Claude Opus 4.6
parent
6daa2f155f
commit
41ed0a0f98
@@ -1250,6 +1250,22 @@ impl Agent {
|
||||
command,
|
||||
message.channel
|
||||
);
|
||||
// /reasoning is special-cased here (not in handle_system_command)
|
||||
// because it needs the session + thread_id to read turn reasoning
|
||||
// data, which handle_system_command's signature doesn't provide.
|
||||
if command == "reasoning" {
|
||||
let result = self
|
||||
.handle_reasoning_command(&args, &session, thread_id)
|
||||
.await;
|
||||
return match result {
|
||||
SubmissionResult::Response { content } => Ok(Some(content)),
|
||||
SubmissionResult::Ok { message } => Ok(message),
|
||||
SubmissionResult::Error { message } => {
|
||||
Ok(Some(format!("Error: {}", message)))
|
||||
}
|
||||
_ => Ok(Some(String::new())),
|
||||
};
|
||||
}
|
||||
// Authorization checks (including restart channel check) are enforced in handle_system_command
|
||||
self.handle_system_command(&command, &args, &message.channel)
|
||||
.await
|
||||
|
||||
@@ -414,6 +414,7 @@ mod tests {
|
||||
id: "call_1".to_string(),
|
||||
name: "echo".to_string(),
|
||||
arguments: serde_json::json!({}),
|
||||
reasoning: None,
|
||||
};
|
||||
let delegate = MockDelegate::new(vec![
|
||||
tool_calls_output(vec![tool_call]),
|
||||
|
||||
@@ -465,6 +465,94 @@ impl Agent {
|
||||
}
|
||||
}
|
||||
|
||||
/// Handle `/reasoning [N|all]` — show reasoning history for the active thread.
|
||||
pub(super) async fn handle_reasoning_command(
|
||||
&self,
|
||||
args: &[String],
|
||||
session: &Arc<Mutex<Session>>,
|
||||
thread_id: Uuid,
|
||||
) -> SubmissionResult {
|
||||
// Clone the turn data we need, then drop the session lock.
|
||||
let turns_snapshot: Vec<(
|
||||
usize,
|
||||
Option<String>,
|
||||
Vec<crate::agent::session::TurnToolCall>,
|
||||
)>;
|
||||
{
|
||||
let sess = session.lock().await;
|
||||
let thread = match sess.threads.get(&thread_id) {
|
||||
Some(t) => t,
|
||||
None => return SubmissionResult::error("No active thread."),
|
||||
};
|
||||
|
||||
if thread.turns.is_empty() {
|
||||
return SubmissionResult::ok_with_message("No turns yet.");
|
||||
}
|
||||
|
||||
// Parse argument: default=last turn, "all"=all turns, N=specific turn (1-based).
|
||||
let selected: Vec<&crate::agent::session::Turn> = match args.first().map(|s| s.as_str())
|
||||
{
|
||||
Some("all") => thread.turns.iter().collect(),
|
||||
Some(n) => match n.parse::<usize>() {
|
||||
Ok(0) => return SubmissionResult::error("Turn numbers start at 1."),
|
||||
Ok(num) if num > thread.turns.len() => {
|
||||
return SubmissionResult::error(format!(
|
||||
"Turn {} does not exist (max: {}).",
|
||||
num,
|
||||
thread.turns.len()
|
||||
));
|
||||
}
|
||||
Ok(num) => vec![&thread.turns[num - 1]],
|
||||
Err(_) => return SubmissionResult::error("Usage: /reasoning [N|all]"),
|
||||
},
|
||||
None => {
|
||||
// Default: last turn that has tool calls
|
||||
match thread.turns.iter().rev().find(|t| !t.tool_calls.is_empty()) {
|
||||
Some(t) => vec![t],
|
||||
None => {
|
||||
return SubmissionResult::ok_with_message("No turns with tool calls.");
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
turns_snapshot = selected
|
||||
.into_iter()
|
||||
.map(|t| (t.turn_number, t.narrative.clone(), t.tool_calls.clone()))
|
||||
.collect();
|
||||
}
|
||||
// Session lock is now dropped — format output without holding it.
|
||||
|
||||
let mut output = String::new();
|
||||
for (turn_number, narrative, tool_calls) in &turns_snapshot {
|
||||
output.push_str(&format!("--- Turn {} ---\n", turn_number + 1));
|
||||
if let Some(narrative) = narrative {
|
||||
output.push_str(&format!("Reasoning: {}\n", narrative));
|
||||
}
|
||||
if tool_calls.is_empty() {
|
||||
output.push_str(" (no tool calls)\n");
|
||||
} else {
|
||||
for tc in tool_calls {
|
||||
let status = if tc.error.is_some() {
|
||||
"error"
|
||||
} else if tc.result.is_some() {
|
||||
"ok"
|
||||
} else {
|
||||
"pending"
|
||||
};
|
||||
output.push_str(&format!(" {} [{}]", tc.name, status));
|
||||
if let Some(ref rationale) = tc.rationale {
|
||||
output.push_str(&format!(" — {}", rationale));
|
||||
}
|
||||
output.push('\n');
|
||||
}
|
||||
}
|
||||
output.push('\n');
|
||||
}
|
||||
|
||||
SubmissionResult::response(output.trim_end())
|
||||
}
|
||||
|
||||
/// Handle system commands that bypass thread-state checks entirely.
|
||||
pub(super) async fn handle_system_command(
|
||||
&self,
|
||||
@@ -480,6 +568,7 @@ impl Agent {
|
||||
" /version Show version info\n",
|
||||
" /tools List available tools\n",
|
||||
" /debug Toggle debug mode\n",
|
||||
" /reasoning [N|all] Show agent reasoning for turns\n",
|
||||
" /ping Connectivity check\n",
|
||||
"\n",
|
||||
"Jobs:\n",
|
||||
|
||||
+79
-5
@@ -420,6 +420,19 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
|
||||
content: Option<String>,
|
||||
reason_ctx: &mut ReasoningContext,
|
||||
) -> Result<Option<LoopOutcome>, Error> {
|
||||
// Extract and sanitize the narrative before consuming `content`.
|
||||
let narrative = content
|
||||
.as_deref()
|
||||
.filter(|c| !c.trim().is_empty())
|
||||
.map(|c| {
|
||||
let sanitized = self
|
||||
.agent
|
||||
.safety()
|
||||
.sanitize_tool_output("agent_narrative", c);
|
||||
sanitized.content
|
||||
})
|
||||
.filter(|c| !c.trim().is_empty());
|
||||
|
||||
// Add the assistant message with tool_calls to context.
|
||||
// OpenAI protocol requires this before tool-result messages.
|
||||
reason_ctx
|
||||
@@ -440,6 +453,41 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
|
||||
)
|
||||
.await;
|
||||
|
||||
// Build per-tool decisions for the reasoning update.
|
||||
// Sanitize each rationale through SafetyLayer (parity with JobDelegate).
|
||||
let decisions: Vec<crate::channels::ToolDecision> = tool_calls
|
||||
.iter()
|
||||
.filter_map(|tc| {
|
||||
tc.reasoning.as_ref().map(|r| {
|
||||
let sanitized = self
|
||||
.agent
|
||||
.safety()
|
||||
.sanitize_tool_output("tool_rationale", r)
|
||||
.content;
|
||||
crate::channels::ToolDecision {
|
||||
tool_name: tc.name.clone(),
|
||||
rationale: sanitized,
|
||||
}
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
|
||||
// Emit reasoning update to channels.
|
||||
if narrative.is_some() || !decisions.is_empty() {
|
||||
let _ = self
|
||||
.agent
|
||||
.channels
|
||||
.send_status(
|
||||
&self.message.channel,
|
||||
StatusUpdate::ReasoningUpdate {
|
||||
narrative: narrative.clone().unwrap_or_default(),
|
||||
decisions: decisions.clone(),
|
||||
},
|
||||
&self.message.metadata,
|
||||
)
|
||||
.await;
|
||||
}
|
||||
|
||||
// Record tool calls in the thread with sensitive params redacted.
|
||||
{
|
||||
let mut redacted_args: Vec<serde_json::Value> = Vec::with_capacity(tool_calls.len());
|
||||
@@ -455,8 +503,23 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
|
||||
if let Some(thread) = sess.threads.get_mut(&self.thread_id)
|
||||
&& let Some(turn) = thread.last_turn_mut()
|
||||
{
|
||||
// Set turn-level narrative.
|
||||
if turn.narrative.is_none() {
|
||||
turn.narrative = narrative;
|
||||
}
|
||||
for (tc, safe_args) in tool_calls.iter().zip(redacted_args) {
|
||||
turn.record_tool_call(&tc.name, safe_args);
|
||||
let sanitized_rationale = tc.reasoning.as_ref().map(|r| {
|
||||
self.agent
|
||||
.safety()
|
||||
.sanitize_tool_output("tool_rationale", r)
|
||||
.content
|
||||
});
|
||||
turn.record_tool_call_with_reasoning(
|
||||
&tc.name,
|
||||
safe_args,
|
||||
sanitized_rationale,
|
||||
Some(tc.id.clone()),
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -726,7 +789,7 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
|
||||
if let Some(thread) = sess.threads.get_mut(&self.thread_id)
|
||||
&& let Some(turn) = thread.last_turn_mut()
|
||||
{
|
||||
turn.record_tool_error(error_msg.clone());
|
||||
turn.record_tool_error_for(&tc.id, error_msg.clone());
|
||||
}
|
||||
}
|
||||
reason_ctx
|
||||
@@ -852,16 +915,19 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
|
||||
Err(e) => format!("Tool '{}' failed: {}", tc.name, e),
|
||||
};
|
||||
|
||||
// Record sanitized result in thread
|
||||
// Record sanitized result in thread (identity-based matching).
|
||||
{
|
||||
let mut sess = self.session.lock().await;
|
||||
if let Some(thread) = sess.threads.get_mut(&self.thread_id)
|
||||
&& let Some(turn) = thread.last_turn_mut()
|
||||
{
|
||||
if is_tool_error {
|
||||
turn.record_tool_error(result_content.clone());
|
||||
turn.record_tool_error_for(&tc.id, result_content.clone());
|
||||
} else {
|
||||
turn.record_tool_result(serde_json::json!(result_content));
|
||||
turn.record_tool_result_for(
|
||||
&tc.id,
|
||||
serde_json::json!(result_content),
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1462,11 +1528,13 @@ mod tests {
|
||||
id: "call_2".to_string(),
|
||||
name: "http".to_string(),
|
||||
arguments: serde_json::json!({"url": "https://example.com"}),
|
||||
reasoning: None,
|
||||
},
|
||||
ToolCall {
|
||||
id: "call_3".to_string(),
|
||||
name: "echo".to_string(),
|
||||
arguments: serde_json::json!({"message": "done"}),
|
||||
reasoning: None,
|
||||
},
|
||||
],
|
||||
user_timezone: None,
|
||||
@@ -1652,6 +1720,7 @@ mod tests {
|
||||
id: "call_1".to_string(),
|
||||
name: "echo".to_string(),
|
||||
arguments: serde_json::json!({"message": "hi"}),
|
||||
reasoning: None,
|
||||
}],
|
||||
),
|
||||
ChatMessage::tool_result("call_1", "echo", "hi"),
|
||||
@@ -1744,11 +1813,13 @@ mod tests {
|
||||
id: "c1".to_string(),
|
||||
name: "http".to_string(),
|
||||
arguments: serde_json::json!({}),
|
||||
reasoning: None,
|
||||
},
|
||||
ToolCall {
|
||||
id: "c2".to_string(),
|
||||
name: "echo".to_string(),
|
||||
arguments: serde_json::json!({}),
|
||||
reasoning: None,
|
||||
},
|
||||
],
|
||||
),
|
||||
@@ -1782,6 +1853,7 @@ mod tests {
|
||||
id: "c1".to_string(),
|
||||
name: "echo".to_string(),
|
||||
arguments: serde_json::json!({}),
|
||||
reasoning: None,
|
||||
}],
|
||||
),
|
||||
ChatMessage::tool_result("c1", "echo", "done"),
|
||||
@@ -1912,6 +1984,7 @@ mod tests {
|
||||
id: crate::llm::generate_tool_call_id(0, 0),
|
||||
name: "echo".to_string(),
|
||||
arguments: serde_json::json!({"message": "looping"}),
|
||||
reasoning: None,
|
||||
}],
|
||||
input_tokens: 0,
|
||||
output_tokens: 5,
|
||||
@@ -2065,6 +2138,7 @@ mod tests {
|
||||
id: crate::llm::generate_tool_call_id(0, 0),
|
||||
name: "nonexistent_tool".to_string(),
|
||||
arguments: serde_json::json!({}),
|
||||
reasoning: None,
|
||||
}],
|
||||
input_tokens: 0,
|
||||
output_tokens: 5,
|
||||
|
||||
+192
-1
@@ -449,6 +449,7 @@ impl Thread {
|
||||
id: call_id.clone(),
|
||||
name: tc.name.clone(),
|
||||
arguments: tc.parameters.clone(),
|
||||
reasoning: None,
|
||||
})
|
||||
.collect();
|
||||
|
||||
@@ -522,7 +523,12 @@ impl Thread {
|
||||
&& let Some(ref tcs) = assistant_msg.tool_calls
|
||||
{
|
||||
for tc in tcs {
|
||||
turn.record_tool_call(&tc.name, tc.arguments.clone());
|
||||
turn.record_tool_call_with_reasoning(
|
||||
&tc.name,
|
||||
tc.arguments.clone(),
|
||||
tc.reasoning.clone(),
|
||||
Some(tc.id.clone()),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -602,6 +608,10 @@ pub struct Turn {
|
||||
pub completed_at: Option<DateTime<Utc>>,
|
||||
/// Error message (if failed).
|
||||
pub error: Option<String>,
|
||||
/// Agent's reasoning narrative for this turn.
|
||||
/// Cleaned via `clean_response` and sanitized through `SafetyLayer` before storage.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub narrative: Option<String>,
|
||||
/// Transient image content parts for multimodal LLM input.
|
||||
/// Not serialized — images are only needed for the current LLM call.
|
||||
/// The text description in `user_input` persists for compaction/context.
|
||||
@@ -621,6 +631,7 @@ impl Turn {
|
||||
started_at: Utc::now(),
|
||||
completed_at: None,
|
||||
error: None,
|
||||
narrative: None,
|
||||
image_content_parts: Vec::new(),
|
||||
}
|
||||
}
|
||||
@@ -656,6 +667,26 @@ impl Turn {
|
||||
parameters: params,
|
||||
result: None,
|
||||
error: None,
|
||||
rationale: None,
|
||||
tool_call_id: None,
|
||||
});
|
||||
}
|
||||
|
||||
/// Record a tool call with reasoning context.
|
||||
pub fn record_tool_call_with_reasoning(
|
||||
&mut self,
|
||||
name: impl Into<String>,
|
||||
params: serde_json::Value,
|
||||
rationale: Option<String>,
|
||||
tool_call_id: Option<String>,
|
||||
) {
|
||||
self.tool_calls.push(TurnToolCall {
|
||||
name: name.into(),
|
||||
parameters: params,
|
||||
result: None,
|
||||
error: None,
|
||||
rationale,
|
||||
tool_call_id,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -672,6 +703,60 @@ impl Turn {
|
||||
call.error = Some(error.into());
|
||||
}
|
||||
}
|
||||
|
||||
/// Record a tool result by tool_call_id, with fallback to first pending call.
|
||||
pub fn record_tool_result_for(&mut self, tool_call_id: &str, result: serde_json::Value) {
|
||||
if let Some(call) = self
|
||||
.tool_calls
|
||||
.iter_mut()
|
||||
.find(|c| c.tool_call_id.as_deref() == Some(tool_call_id))
|
||||
{
|
||||
call.result = Some(result);
|
||||
} else if let Some(call) = self
|
||||
.tool_calls
|
||||
.iter_mut()
|
||||
.find(|c| c.result.is_none() && c.error.is_none())
|
||||
{
|
||||
tracing::debug!(
|
||||
tool_call_id = %tool_call_id,
|
||||
fallback_tool = %call.name,
|
||||
"tool_call_id not found, falling back to first pending call"
|
||||
);
|
||||
call.result = Some(result);
|
||||
} else {
|
||||
tracing::warn!(
|
||||
tool_call_id = %tool_call_id,
|
||||
"Tool result dropped: no matching or pending tool call"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// Record a tool error by tool_call_id, with fallback to first pending call.
|
||||
pub fn record_tool_error_for(&mut self, tool_call_id: &str, error: impl Into<String>) {
|
||||
if let Some(call) = self
|
||||
.tool_calls
|
||||
.iter_mut()
|
||||
.find(|c| c.tool_call_id.as_deref() == Some(tool_call_id))
|
||||
{
|
||||
call.error = Some(error.into());
|
||||
} else if let Some(call) = self
|
||||
.tool_calls
|
||||
.iter_mut()
|
||||
.find(|c| c.result.is_none() && c.error.is_none())
|
||||
{
|
||||
tracing::debug!(
|
||||
tool_call_id = %tool_call_id,
|
||||
fallback_tool = %call.name,
|
||||
"tool_call_id not found, falling back to first pending call"
|
||||
);
|
||||
call.error = Some(error.into());
|
||||
} else {
|
||||
tracing::warn!(
|
||||
tool_call_id = %tool_call_id,
|
||||
"Tool error dropped: no matching or pending tool call"
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Record of a tool call made during a turn.
|
||||
@@ -685,6 +770,12 @@ pub struct TurnToolCall {
|
||||
pub result: Option<serde_json::Value>,
|
||||
/// Error from the tool (if failed).
|
||||
pub error: Option<String>,
|
||||
/// Agent's reasoning for choosing this tool.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub rationale: Option<String>,
|
||||
/// The tool_call_id from the LLM, for identity-based result matching.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub tool_call_id: Option<String>,
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
@@ -1309,6 +1400,7 @@ mod tests {
|
||||
id: "call_0".to_string(),
|
||||
name: "search".to_string(),
|
||||
arguments: serde_json::json!({"q": "test"}),
|
||||
reasoning: None,
|
||||
};
|
||||
let messages = vec![
|
||||
ChatMessage::user("Find test"),
|
||||
@@ -1339,6 +1431,7 @@ mod tests {
|
||||
id: "call_0".to_string(),
|
||||
name: "http".to_string(),
|
||||
arguments: serde_json::json!({}),
|
||||
reasoning: None,
|
||||
};
|
||||
let messages = vec![
|
||||
ChatMessage::user("Fetch URL"),
|
||||
@@ -1404,11 +1497,13 @@ mod tests {
|
||||
id: "call_a".to_string(),
|
||||
name: "search".to_string(),
|
||||
arguments: serde_json::json!({"q": "data"}),
|
||||
reasoning: None,
|
||||
};
|
||||
let tc2 = ToolCall {
|
||||
id: "call_b".to_string(),
|
||||
name: "write".to_string(),
|
||||
arguments: serde_json::json!({"path": "out.txt"}),
|
||||
reasoning: None,
|
||||
};
|
||||
let messages = vec![
|
||||
ChatMessage::user("Find and save"),
|
||||
@@ -1620,4 +1715,100 @@ mod tests {
|
||||
let merged = thread.drain_pending_messages().unwrap();
|
||||
assert_eq!(merged, "failed batch\nnew msg");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_record_tool_result_for_by_id() {
|
||||
let mut turn = Turn::new(0, "test");
|
||||
turn.record_tool_call_with_reasoning(
|
||||
"tool_a",
|
||||
serde_json::json!({}),
|
||||
None,
|
||||
Some("id_a".into()),
|
||||
);
|
||||
turn.record_tool_call_with_reasoning(
|
||||
"tool_b",
|
||||
serde_json::json!({}),
|
||||
None,
|
||||
Some("id_b".into()),
|
||||
);
|
||||
|
||||
// Record result for second tool by ID
|
||||
turn.record_tool_result_for("id_b", serde_json::json!("result_b"));
|
||||
assert!(turn.tool_calls[0].result.is_none());
|
||||
assert_eq!(
|
||||
turn.tool_calls[1].result.as_ref().unwrap(),
|
||||
&serde_json::json!("result_b")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_record_tool_error_for_by_id() {
|
||||
let mut turn = Turn::new(0, "test");
|
||||
turn.record_tool_call_with_reasoning(
|
||||
"tool_a",
|
||||
serde_json::json!({}),
|
||||
None,
|
||||
Some("id_a".into()),
|
||||
);
|
||||
turn.record_tool_call_with_reasoning(
|
||||
"tool_b",
|
||||
serde_json::json!({}),
|
||||
None,
|
||||
Some("id_b".into()),
|
||||
);
|
||||
|
||||
turn.record_tool_error_for("id_a", "failed");
|
||||
assert_eq!(turn.tool_calls[0].error.as_deref(), Some("failed"));
|
||||
assert!(turn.tool_calls[1].error.is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_record_tool_result_for_fallback_to_pending() {
|
||||
let mut turn = Turn::new(0, "test");
|
||||
turn.record_tool_call_with_reasoning(
|
||||
"tool_a",
|
||||
serde_json::json!({}),
|
||||
None,
|
||||
Some("id_a".into()),
|
||||
);
|
||||
turn.record_tool_call_with_reasoning(
|
||||
"tool_b",
|
||||
serde_json::json!({}),
|
||||
None,
|
||||
Some("id_b".into()),
|
||||
);
|
||||
|
||||
// First tool already has a result
|
||||
turn.tool_calls[0].result = Some(serde_json::json!("done"));
|
||||
|
||||
// Unknown ID should fall back to first pending (tool_b)
|
||||
turn.record_tool_result_for("unknown_id", serde_json::json!("fallback"));
|
||||
assert_eq!(
|
||||
turn.tool_calls[0].result.as_ref().unwrap(),
|
||||
&serde_json::json!("done")
|
||||
);
|
||||
assert_eq!(
|
||||
turn.tool_calls[1].result.as_ref().unwrap(),
|
||||
&serde_json::json!("fallback")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_record_tool_result_for_no_pending_is_noop() {
|
||||
let mut turn = Turn::new(0, "test");
|
||||
turn.record_tool_call_with_reasoning(
|
||||
"tool_a",
|
||||
serde_json::json!({}),
|
||||
None,
|
||||
Some("id_a".into()),
|
||||
);
|
||||
turn.tool_calls[0].result = Some(serde_json::json!("done"));
|
||||
|
||||
// No pending calls, unknown ID — should be a no-op
|
||||
turn.record_tool_result_for("unknown_id", serde_json::json!("lost"));
|
||||
assert_eq!(
|
||||
turn.tool_calls[0].result.as_ref().unwrap(),
|
||||
&serde_json::json!("done")
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -92,6 +92,17 @@ impl SubmissionParser {
|
||||
args: vec![],
|
||||
};
|
||||
}
|
||||
if lower == "/reasoning" || lower.starts_with("/reasoning ") {
|
||||
let args: Vec<String> = trimmed
|
||||
.split_whitespace()
|
||||
.skip(1)
|
||||
.map(|s| s.to_string())
|
||||
.collect();
|
||||
return Submission::SystemCommand {
|
||||
command: "reasoning".to_string(),
|
||||
args,
|
||||
};
|
||||
}
|
||||
if lower == "/restart" {
|
||||
tracing::debug!("[SubmissionParser::parse] Recognized /restart command");
|
||||
return Submission::SystemCommand {
|
||||
|
||||
+58
-11
@@ -513,10 +513,10 @@ impl Agent {
|
||||
};
|
||||
|
||||
thread.complete_turn(&response);
|
||||
let (turn_number, tool_calls) = thread
|
||||
let (turn_number, tool_calls, narrative) = thread
|
||||
.turns
|
||||
.last()
|
||||
.map(|t| (t.turn_number, t.tool_calls.clone()))
|
||||
.map(|t| (t.turn_number, t.tool_calls.clone(), t.narrative.clone()))
|
||||
.unwrap_or_default();
|
||||
let _ = self
|
||||
.channels
|
||||
@@ -534,6 +534,7 @@ impl Agent {
|
||||
&message.user_id,
|
||||
turn_number,
|
||||
&tool_calls,
|
||||
narrative.as_deref(),
|
||||
)
|
||||
.await;
|
||||
self.persist_assistant_response(
|
||||
@@ -725,7 +726,9 @@ impl Agent {
|
||||
///
|
||||
/// Stored between the user and assistant messages so that
|
||||
/// `build_turns_from_db_messages` can reconstruct the tool call history.
|
||||
/// Content is a JSON array of tool call summaries.
|
||||
/// Content is a JSON object: `{ "calls": [...], "narrative": "..." }`.
|
||||
/// The `calls` array contains tool call summaries with optional `rationale`
|
||||
/// and `tool_call_id` fields. Legacy rows may be plain JSON arrays.
|
||||
pub(super) async fn persist_tool_calls(
|
||||
&self,
|
||||
thread_id: Uuid,
|
||||
@@ -733,6 +736,7 @@ impl Agent {
|
||||
user_id: &str,
|
||||
turn_number: usize,
|
||||
tool_calls: &[crate::agent::session::TurnToolCall],
|
||||
narrative: Option<&str>,
|
||||
) {
|
||||
if tool_calls.is_empty() {
|
||||
return;
|
||||
@@ -767,11 +771,30 @@ impl Agent {
|
||||
if let Some(ref error) = tc.error {
|
||||
obj["error"] = serde_json::Value::String(truncate_preview(error, 200));
|
||||
}
|
||||
if let Some(ref rationale) = tc.rationale {
|
||||
obj["rationale"] = serde_json::Value::String(truncate_preview(rationale, 500));
|
||||
}
|
||||
if let Some(ref tool_call_id) = tc.tool_call_id {
|
||||
obj["tool_call_id"] =
|
||||
serde_json::Value::String(truncate_preview(tool_call_id, 128));
|
||||
}
|
||||
obj
|
||||
})
|
||||
.collect();
|
||||
|
||||
let content = match serde_json::to_string(&summaries) {
|
||||
// Wrap in an object with optional narrative so it can be reconstructed.
|
||||
// safety: no byte-index slicing here; comment describes JSON shape
|
||||
let wrapper = if let Some(n) = narrative {
|
||||
serde_json::json!({
|
||||
"narrative": truncate_preview(n, 1000),
|
||||
"calls": summaries,
|
||||
})
|
||||
} else {
|
||||
serde_json::json!({
|
||||
"calls": summaries,
|
||||
})
|
||||
};
|
||||
let content = match serde_json::to_string(&wrapper) {
|
||||
Ok(c) => c,
|
||||
Err(e) => {
|
||||
tracing::warn!("Failed to serialize tool calls: {}", e);
|
||||
@@ -1104,9 +1127,12 @@ impl Agent {
|
||||
&& let Some(turn) = thread.last_turn_mut()
|
||||
{
|
||||
if is_tool_error {
|
||||
turn.record_tool_error(result_content.clone());
|
||||
turn.record_tool_error_for(&pending.tool_call_id, result_content.clone());
|
||||
} else {
|
||||
turn.record_tool_result(serde_json::json!(result_content));
|
||||
turn.record_tool_result_for(
|
||||
&pending.tool_call_id,
|
||||
serde_json::json!(result_content),
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1358,9 +1384,12 @@ impl Agent {
|
||||
&& let Some(turn) = thread.last_turn_mut()
|
||||
{
|
||||
if is_deferred_error {
|
||||
turn.record_tool_error(deferred_content.clone());
|
||||
turn.record_tool_error_for(&tc.id, deferred_content.clone());
|
||||
} else {
|
||||
turn.record_tool_result(serde_json::json!(deferred_content));
|
||||
turn.record_tool_result_for(
|
||||
&tc.id,
|
||||
serde_json::json!(deferred_content),
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1459,10 +1488,10 @@ impl Agent {
|
||||
let (response, suggestions) =
|
||||
crate::agent::dispatcher::extract_suggestions(&response);
|
||||
thread.complete_turn(&response);
|
||||
let (turn_number, tool_calls) = thread
|
||||
let (turn_number, tool_calls, narrative) = thread
|
||||
.turns
|
||||
.last()
|
||||
.map(|t| (t.turn_number, t.tool_calls.clone()))
|
||||
.map(|t| (t.turn_number, t.tool_calls.clone(), t.narrative.clone()))
|
||||
.unwrap_or_default();
|
||||
// User message already persisted at turn start; save tool calls then assistant response
|
||||
self.persist_tool_calls(
|
||||
@@ -1471,6 +1500,7 @@ impl Agent {
|
||||
&message.user_id,
|
||||
turn_number,
|
||||
&tool_calls,
|
||||
narrative.as_deref(),
|
||||
)
|
||||
.await;
|
||||
self.persist_assistant_response(
|
||||
@@ -1816,7 +1846,20 @@ fn rebuild_chat_messages_from_db(
|
||||
"assistant" => result.push(ChatMessage::assistant(&msg.content)),
|
||||
"tool_calls" => {
|
||||
// Try to parse the enriched JSON and rebuild tool messages.
|
||||
if let Ok(calls) = serde_json::from_str::<Vec<serde_json::Value>>(&msg.content) {
|
||||
// Supports two formats:
|
||||
// - Old: plain JSON array of tool call summaries
|
||||
// - New: wrapped object { "calls": [...], "narrative": "..." }
|
||||
let calls: Vec<serde_json::Value> =
|
||||
match serde_json::from_str::<serde_json::Value>(&msg.content) {
|
||||
Ok(serde_json::Value::Array(arr)) => arr,
|
||||
Ok(serde_json::Value::Object(obj)) => obj
|
||||
.get("calls")
|
||||
.and_then(|v| v.as_array())
|
||||
.cloned()
|
||||
.unwrap_or_default(),
|
||||
_ => Vec::new(),
|
||||
};
|
||||
{
|
||||
if calls.is_empty() {
|
||||
continue;
|
||||
}
|
||||
@@ -1839,6 +1882,10 @@ fn rebuild_chat_messages_from_db(
|
||||
.get("parameters")
|
||||
.cloned()
|
||||
.unwrap_or(serde_json::json!({})),
|
||||
reasoning: c
|
||||
.get("rationale")
|
||||
.and_then(|v| v.as_str())
|
||||
.map(String::from),
|
||||
})
|
||||
.collect();
|
||||
|
||||
|
||||
Reference in New Issue
Block a user