mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-27 08:00:17 +00:00
fix: persist turns after approval and add agent-level tests (#250)
* fix: persist turns after approval and add agent-level tests Port relevant changes from PR #112 that were not carried over to #237: - Add persist_turn calls in process_approval for the response, error, and auth-required paths. Previously, turns completed after tool approval were never persisted to DB — if the process crashed after approval the entire turn (user message + assistant response) was lost. - Add agent-level unit tests: StaticLlmProvider mock, make_test_agent helper, tests for auto-approval logic, destructive shell command detection, and PendingApproval backward-compatible deserialization (without deferred_tool_calls field). - Remove unused _thread_state binding in process_approval. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address 14 audit findings in src/agent/ Audit of the agent module found 2 High, 7 Medium, 3 Low, and 2 Nit severity issues. This commit fixes all of them: High: - Remove 4 `.expect()` calls in session.rs (entry API, match, direct indexing, if-let) to eliminate panic paths in production - Add typed RoutineError enum replacing Result<_, String> across routine.rs, routine_engine.rs, and callers in history/store.rs and db/libsql/mod.rs Medium: - Sanitize routine names in path construction to prevent directory traversal (routine_engine.rs) - Log warnings for 5 silently-swallowed errors in scheduler.rs, compaction.rs, and worker.rs - Extract shared handle_auth_intercept helper to deduplicate auth interception in thread_ops.rs - Add session count warning threshold in session_manager.rs - Make FullJob stub degradation visible via warn-level log and prepended warning in output Low: - Restrict dead code visibility with #[cfg(test)] on 19 unused items in submission.rs, task.rs, and undo.rs - Narrow pub to pub(crate) on self_repair.rs builder methods - Remove TaskStatus from mod.rs re-exports (test-only type) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review comments - Reorder persist_turn before persist_response_chain so the conversation row exists before the metadata UPDATE runs - Add persist_response_chain call to handle_auth_intercept so auth-required paths preserve the response chain - Harden sanitize_routine_name to use allowlist (alphanumeric, dash, underscore) instead of denylist replacements - Fix stale active_thread ID in get_or_create_thread: fall back to create_thread() when the stored ID is missing from the map - Persist turn on approval rejection so user messages survive crashes after a tool is rejected Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>
This commit is contained in:
Illia Polosukhin
co-authored by
Claude Opus 4.6
Claude Opus 4.6
parent
97a7637f30
commit
3f135bdde9
+58
-25
@@ -25,6 +25,7 @@ use crate::agent::routine::{
|
||||
use crate::channels::{IncomingMessage, OutgoingResponse};
|
||||
use crate::config::RoutineConfig;
|
||||
use crate::db::Database;
|
||||
use crate::error::RoutineError;
|
||||
use crate::llm::{ChatMessage, CompletionRequest, FinishReason, LlmProvider};
|
||||
use crate::workspace::Workspace;
|
||||
|
||||
@@ -174,23 +175,26 @@ impl RoutineEngine {
|
||||
}
|
||||
|
||||
/// Fire a routine manually (from tool call or CLI).
|
||||
pub async fn fire_manual(&self, routine_id: Uuid) -> Result<Uuid, String> {
|
||||
pub async fn fire_manual(&self, routine_id: Uuid) -> Result<Uuid, RoutineError> {
|
||||
let routine = self
|
||||
.store
|
||||
.get_routine(routine_id)
|
||||
.await
|
||||
.map_err(|e| format!("DB error: {e}"))?
|
||||
.ok_or_else(|| format!("routine {routine_id} not found"))?;
|
||||
.map_err(|e| RoutineError::Database {
|
||||
reason: e.to_string(),
|
||||
})?
|
||||
.ok_or(RoutineError::NotFound { id: routine_id })?;
|
||||
|
||||
if !routine.enabled {
|
||||
return Err(format!("routine '{}' is disabled", routine.name));
|
||||
return Err(RoutineError::Disabled {
|
||||
name: routine.name.clone(),
|
||||
});
|
||||
}
|
||||
|
||||
if !self.check_concurrent(&routine).await {
|
||||
return Err(format!(
|
||||
"routine '{}' already at max concurrent runs",
|
||||
routine.name
|
||||
));
|
||||
return Err(RoutineError::MaxConcurrent {
|
||||
name: routine.name.clone(),
|
||||
});
|
||||
}
|
||||
|
||||
let run_id = Uuid::new_v4();
|
||||
@@ -209,7 +213,9 @@ impl RoutineEngine {
|
||||
};
|
||||
|
||||
if let Err(e) = self.store.create_routine_run(&run).await {
|
||||
return Err(format!("failed to create run record: {e}"));
|
||||
return Err(RoutineError::Database {
|
||||
reason: format!("failed to create run record: {e}"),
|
||||
});
|
||||
}
|
||||
|
||||
// Execute inline for manual triggers (caller wants to wait)
|
||||
@@ -313,13 +319,27 @@ async fn execute_routine(ctx: EngineContext, routine: Routine, run: RoutineRun)
|
||||
max_tokens,
|
||||
} => execute_lightweight(&ctx, &routine, prompt, context_paths, *max_tokens).await,
|
||||
RoutineAction::FullJob { description, .. } => {
|
||||
// Full job mode: for now, execute as lightweight with the description
|
||||
// as prompt. Full scheduler integration will come as a follow-up.
|
||||
tracing::info!(
|
||||
// Full job mode: scheduler integration not yet implemented.
|
||||
// Execute as lightweight and prepend a warning to the summary.
|
||||
tracing::warn!(
|
||||
routine = %routine.name,
|
||||
"FullJob mode executing as lightweight (scheduler integration pending)"
|
||||
"FullJob mode not yet implemented; falling back to lightweight execution"
|
||||
);
|
||||
execute_lightweight(&ctx, &routine, description, &[], ctx.max_lightweight_tokens).await
|
||||
match execute_lightweight(&ctx, &routine, description, &[], ctx.max_lightweight_tokens)
|
||||
.await
|
||||
{
|
||||
Ok((status, summary, tokens)) => {
|
||||
let warning = "[Note: FullJob mode is not yet implemented. This routine ran as \
|
||||
a single LLM call without tool access. Configure as 'lightweight' \
|
||||
or wait for full scheduler integration.]";
|
||||
let summary = match summary {
|
||||
Some(s) => Some(format!("{warning}\n\n{s}")),
|
||||
None => Some(warning.to_string()),
|
||||
};
|
||||
Ok((status, summary, tokens))
|
||||
}
|
||||
Err(e) => Err(e),
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
@@ -331,7 +351,7 @@ async fn execute_routine(ctx: EngineContext, routine: Routine, run: RoutineRun)
|
||||
Ok(execution) => execution,
|
||||
Err(e) => {
|
||||
tracing::error!(routine = %routine.name, "Execution failed: {}", e);
|
||||
(RunStatus::Failed, Some(e), None)
|
||||
(RunStatus::Failed, Some(e.to_string()), None)
|
||||
}
|
||||
};
|
||||
|
||||
@@ -384,6 +404,20 @@ async fn execute_routine(ctx: EngineContext, routine: Routine, run: RoutineRun)
|
||||
.await;
|
||||
}
|
||||
|
||||
/// Sanitize a routine name for use in workspace paths.
|
||||
/// Only keeps alphanumeric, dash, and underscore characters; replaces everything else.
|
||||
fn sanitize_routine_name(name: &str) -> String {
|
||||
name.chars()
|
||||
.map(|c| {
|
||||
if c.is_ascii_alphanumeric() || c == '-' || c == '_' {
|
||||
c
|
||||
} else {
|
||||
'_'
|
||||
}
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Execute a lightweight routine (single LLM call).
|
||||
async fn execute_lightweight(
|
||||
ctx: &EngineContext,
|
||||
@@ -391,7 +425,7 @@ async fn execute_lightweight(
|
||||
prompt: &str,
|
||||
context_paths: &[String],
|
||||
max_tokens: u32,
|
||||
) -> Result<(RunStatus, Option<String>, Option<i32>), String> {
|
||||
) -> Result<(RunStatus, Option<String>, Option<i32>), RoutineError> {
|
||||
// Load context from workspace
|
||||
let mut context_parts = Vec::new();
|
||||
for path in context_paths {
|
||||
@@ -408,8 +442,9 @@ async fn execute_lightweight(
|
||||
}
|
||||
}
|
||||
|
||||
// Load routine state from workspace
|
||||
let state_path = format!("routines/{}/state.md", routine.name);
|
||||
// Load routine state from workspace (name sanitized to prevent path traversal)
|
||||
let safe_name = sanitize_routine_name(&routine.name);
|
||||
let state_path = format!("routines/{safe_name}/state.md");
|
||||
let state_content = match ctx.workspace.read(&state_path).await {
|
||||
Ok(doc) => Some(doc.content),
|
||||
Err(_) => None,
|
||||
@@ -469,7 +504,9 @@ async fn execute_lightweight(
|
||||
.llm
|
||||
.complete(request)
|
||||
.await
|
||||
.map_err(|e| format!("LLM call failed: {e}"))?;
|
||||
.map_err(|e| RoutineError::LlmFailed {
|
||||
reason: e.to_string(),
|
||||
})?;
|
||||
|
||||
let content = response.content.trim();
|
||||
let tokens_used = Some((response.input_tokens + response.output_tokens) as i32);
|
||||
@@ -477,13 +514,9 @@ async fn execute_lightweight(
|
||||
// Empty content guard (same as heartbeat)
|
||||
if content.is_empty() {
|
||||
return if response.finish_reason == FinishReason::Length {
|
||||
Err(
|
||||
"LLM response truncated (finish_reason=length) with no content. \
|
||||
Model may have exhausted token budget on reasoning."
|
||||
.to_string(),
|
||||
)
|
||||
Err(RoutineError::TruncatedResponse)
|
||||
} else {
|
||||
Err("LLM returned empty content.".to_string())
|
||||
Err(RoutineError::EmptyResponse)
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user