feat: update README and documentation for new tools and features
- Updated README.md to reflect the addition of 3 new built-in tools, bringing the total to 37. - Revised architecture documentation to indicate the increase in tool count. - Enhanced backend documentation with updated line counts for various modules. - Modified data documentation to change edit log format from JSON to JSONL. - Updated dependencies documentation to reflect version upgrades for several crates. - Improved prompts for auto-reviewer, division implementer, planner, tester, and quality reviewer to enforce stricter coding standards regarding linter bypasses. - Refactored code in various modules to improve clarity and performance, including updates to error handling and tool execution logic. - Added comprehensive tests for IPC frame serialization and deserialization.
This commit is contained in:
+1
-1
@@ -430,7 +430,7 @@ mod tests {
|
||||
return Some(Verdict::Allow);
|
||||
}
|
||||
if l.starts_with("verdict: block") {
|
||||
let reason = line.split_once(':').map(|x| x.1).unwrap_or("blocked").trim().to_string();
|
||||
let reason = line.split_once(':').map_or("blocked", |x| x.1).trim().to_string();
|
||||
return Some(Verdict::Block(reason));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1017,8 +1017,7 @@ fn run_agent_turn(
|
||||
q.push_back(TurnEvent::SystemNote {
|
||||
kind: "pipeline".to_string(),
|
||||
message: format!(
|
||||
"CEO is planning workflow (mode={})...",
|
||||
mode_label,
|
||||
"CEO is planning workflow (mode={mode_label})...",
|
||||
),
|
||||
});
|
||||
}
|
||||
@@ -1054,12 +1053,11 @@ fn run_agent_turn(
|
||||
);
|
||||
let user_msg = ChatMessage::user(format!(
|
||||
"Design a structured multi-agent workflow plan for the following task:\n\n\
|
||||
\"{}\"\n\n\
|
||||
You must output a JSON object representing the 'specialists' configuration for {}.\n\
|
||||
\"{user_request}\"\n\n\
|
||||
You must output a JSON object representing the 'specialists' configuration for {required_divisions}.\n\
|
||||
Each division must have a list of custom specialists defined by a pair of [label, focus_description].\n\n\
|
||||
Return ONLY a JSON object with this exact structure, with no markdown codeblocks and no explanation:\n\
|
||||
{}",
|
||||
user_request, required_divisions, example_json
|
||||
{example_json}"
|
||||
));
|
||||
|
||||
let planner_result = tc.client.chat_with_tools_non_streaming(&[system_msg, user_msg], None);
|
||||
@@ -1070,7 +1068,7 @@ fn run_agent_turn(
|
||||
let mut lines = reply_text.lines();
|
||||
lines.next();
|
||||
let mut content = lines.collect::<Vec<&str>>();
|
||||
if content.last().map(|s| s.trim() == "```").unwrap_or(false) {
|
||||
if content.last().is_some_and(|s| s.trim() == "```") {
|
||||
content.pop();
|
||||
}
|
||||
content.join("\n")
|
||||
@@ -1103,7 +1101,7 @@ fn run_agent_turn(
|
||||
&tc.workspace_roots,
|
||||
Some(events_q),
|
||||
&pipeline_abort,
|
||||
custom_specialists,
|
||||
&custom_specialists,
|
||||
)
|
||||
} else {
|
||||
crate::app::workflow::company::run_company_pipeline_quick(
|
||||
@@ -1112,14 +1110,14 @@ fn run_agent_turn(
|
||||
&tc.workspace_roots,
|
||||
Some(events_q),
|
||||
&pipeline_abort,
|
||||
custom_specialists,
|
||||
&custom_specialists,
|
||||
)
|
||||
}
|
||||
}
|
||||
Err(e) => Err(anyhow::anyhow!("Failed to parse LLM planning JSON: {}. Cleaned JSON was: {}", e, clean_json)),
|
||||
Err(e) => Err(anyhow::anyhow!("Failed to parse LLM planning JSON: {e}. Cleaned JSON was: {clean_json}")),
|
||||
}
|
||||
}
|
||||
Err(e) => Err(anyhow::anyhow!("Failed to query LLM for planning workflow: {}", e)),
|
||||
Err(e) => Err(anyhow::anyhow!("Failed to query LLM for planning workflow: {e}")),
|
||||
};
|
||||
|
||||
match pipeline_result {
|
||||
@@ -1304,44 +1302,60 @@ fn run_agent_turn(
|
||||
let tool_calls = response.tool_calls.clone().unwrap_or_default();
|
||||
archive_message(tc.db.as_ref(), &tc.session_id, &response);
|
||||
msgs.push(response);
|
||||
for tool_call in tool_calls {
|
||||
let mut results_vec = Vec::new();
|
||||
std::thread::scope(|s| {
|
||||
let mut handles = Vec::new();
|
||||
let tc_ref = tc;
|
||||
for tool_call in &tool_calls {
|
||||
let handle = s.spawn(move || {
|
||||
let tool_name = tool_call.function.name.clone();
|
||||
let args = crate::dto::chat::tool::sanitize_tool_arguments(
|
||||
&tool_call.function.arguments,
|
||||
);
|
||||
|
||||
let ws_roots: Vec<&std::path::Path> =
|
||||
tc_ref.workspace_roots.iter().map(std::path::PathBuf::as_path).collect();
|
||||
let verdict = crate::app::harness::Harness::gate_tool_call(
|
||||
&tool_name,
|
||||
&args,
|
||||
&ws_roots,
|
||||
);
|
||||
|
||||
let is_edit_tool = tool_name == "write" || tool_name == "edit";
|
||||
let (output, is_error, is_edit) = match verdict {
|
||||
Verdict::Allow => match execute_one_tool(
|
||||
&tc_ref.tools,
|
||||
&tc_ref.ctx,
|
||||
&tool_name,
|
||||
&tool_call.id,
|
||||
&args,
|
||||
&tc_ref.edit_log_session_dir,
|
||||
&tc_ref.session_id,
|
||||
tc_ref.db.as_ref(),
|
||||
) {
|
||||
Ok(result) => (result, false, is_edit_tool),
|
||||
Err(e) => (e.to_string(), true, false),
|
||||
},
|
||||
Verdict::Block(reason) => (format!("Blocked: {reason}"), true, false),
|
||||
};
|
||||
(tool_call, tool_name, args, output, is_error, is_edit)
|
||||
});
|
||||
handles.push(handle);
|
||||
}
|
||||
for h in handles {
|
||||
if let Ok(res) = h.join() {
|
||||
results_vec.push(res);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
for (tool_call, tool_name, args, output, is_error, is_edit) in results_vec {
|
||||
if tc.abort_flag.load(std::sync::atomic::Ordering::SeqCst) {
|
||||
if let Ok(mut q) = events_q.lock() {
|
||||
q.push_back(TurnEvent::Error("Turn aborted by user".to_string()));
|
||||
}
|
||||
return Ok(());
|
||||
}
|
||||
let tool_name = tool_call.function.name.clone();
|
||||
let args = crate::dto::chat::tool::sanitize_tool_arguments(
|
||||
&tool_call.function.arguments,
|
||||
);
|
||||
|
||||
let ws_roots: Vec<&std::path::Path> =
|
||||
tc.workspace_roots.iter().map(std::path::PathBuf::as_path).collect();
|
||||
let verdict = crate::app::harness::Harness::gate_tool_call(
|
||||
&tool_name,
|
||||
&args,
|
||||
|
||||
&ws_roots,
|
||||
);
|
||||
|
||||
let is_edit_tool = tool_name == "write" || tool_name == "edit";
|
||||
let (output, is_error, is_edit) = match verdict {
|
||||
Verdict::Allow => match execute_one_tool(
|
||||
&tc.tools,
|
||||
&tc.ctx,
|
||||
&tool_name,
|
||||
&tool_call.id,
|
||||
&args,
|
||||
&tc.edit_log_session_dir,
|
||||
&tc.session_id,
|
||||
tc.db.as_ref(),
|
||||
) {
|
||||
Ok(result) => (result, false, is_edit_tool),
|
||||
Err(e) => (e.to_string(), true, false),
|
||||
},
|
||||
Verdict::Block(reason) => (format!("Blocked: {reason}"), true, false),
|
||||
};
|
||||
|
||||
if is_edit {
|
||||
edits_this_turn += 1;
|
||||
@@ -1399,7 +1413,6 @@ fn run_agent_turn(
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
let tool_path = args.get("path").and_then(|v| v.as_str()).map(std::string::ToString::to_string);
|
||||
|
||||
{
|
||||
|
||||
@@ -280,7 +280,7 @@ mod tests {
|
||||
assert_eq!(events.len(), 1);
|
||||
match &events[0] {
|
||||
StreamEvent::Token(t) => assert_eq!(t, "hello"),
|
||||
other => panic!("expected Token, got {:?}", other),
|
||||
other => panic!("expected Token, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -293,7 +293,7 @@ mod tests {
|
||||
assert_eq!(e2.len(), 1);
|
||||
match &e2[0] {
|
||||
StreamEvent::Token(t) => assert_eq!(t, "partial"),
|
||||
other => panic!("expected Token, got {:?}", other),
|
||||
other => panic!("expected Token, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -329,7 +329,7 @@ mod tests {
|
||||
assert_eq!(name.as_deref(), Some("bash"));
|
||||
assert_eq!(arguments_delta, "{\"cmd\"");
|
||||
}
|
||||
other => panic!("expected ToolCallDelta, got {:?}", other),
|
||||
other => panic!("expected ToolCallDelta, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -346,7 +346,7 @@ mod tests {
|
||||
assert_eq!(*completion_tokens, 5);
|
||||
assert_eq!(*total_tokens, 15);
|
||||
}
|
||||
other => panic!("expected Usage, got {:?}", other),
|
||||
other => panic!("expected Usage, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -368,7 +368,7 @@ mod tests {
|
||||
assert_eq!(a, "a");
|
||||
assert_eq!(b, "b");
|
||||
}
|
||||
other => panic!("expected two Tokens, got {:?}", other),
|
||||
other => panic!("expected two Tokens, got {other:?}"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
+55
-52
@@ -391,67 +391,62 @@ pub fn run_subagent(ctx: &SubagentContext, tx: &mpsc::Sender<SubagentEvent>) ->
|
||||
// Push the assistant message with tool_calls into the conversation
|
||||
messages.push(response);
|
||||
|
||||
for tool_call in &tool_calls {
|
||||
// Check abort flag before each tool execution
|
||||
if ctx.abort_flag.as_ref().is_some_and(|f| f.load(std::sync::atomic::Ordering::SeqCst)) {
|
||||
let _ = tx.blocking_send(SubagentEvent::StepFailed {
|
||||
step,
|
||||
error: "subagent aborted by parent during tool execution".to_string(),
|
||||
});
|
||||
anyhow::bail!("subagent aborted by parent during tool call at step {step}");
|
||||
}
|
||||
let mut results_vec = Vec::new();
|
||||
std::thread::scope(|s| {
|
||||
let mut handles = Vec::new();
|
||||
let tools_ref = &tools;
|
||||
let tool_ctx_ref = &tool_ctx;
|
||||
for tool_call in &tool_calls {
|
||||
let handle = s.spawn(move || {
|
||||
// Check abort flag before each tool execution
|
||||
if ctx.abort_flag.as_ref().is_some_and(|f| f.load(std::sync::atomic::Ordering::SeqCst)) {
|
||||
return (tool_call, Err(anyhow::anyhow!("subagent aborted by parent during tool execution")));
|
||||
}
|
||||
|
||||
let tool_name = &tool_call.function.name;
|
||||
let args = crate::dto::chat::tool::sanitize_tool_arguments(&tool_call.function.arguments);
|
||||
let explicitly_allowed = ctx.allowed_tools.contains(tool_name);
|
||||
let generally_allowed = ctx.allowed_tools.is_empty() || explicitly_allowed;
|
||||
|
||||
// Level 1: allowlist check — is this tool even permitted?
|
||||
if !generally_allowed {
|
||||
return (tool_call, Ok(format!("tool '{tool_name}' not allowed for this subagent")));
|
||||
}
|
||||
|
||||
// Level 2: risky tool check — risky tools require explicit permission
|
||||
if tool_is_risky(tool_name) && !explicitly_allowed {
|
||||
return (tool_call, Ok(format!("risky tool '{tool_name}' requires explicit permission; not allowed for this subagent")));
|
||||
}
|
||||
|
||||
// Level 3: Harness-style content safety gating
|
||||
if let Some(block_reason) = gate_subagent_tool_call(tool_name, &args) {
|
||||
return (tool_call, Ok(format!("Blocked by subagent gate: {block_reason}")));
|
||||
}
|
||||
|
||||
let result = match tools_ref.iter().find(|t| t.name() == tool_name.as_str()) {
|
||||
Some(tool) => tool.run(tool_ctx_ref, &args),
|
||||
None => Err(anyhow::anyhow!("tool '{tool_name}' not found")),
|
||||
};
|
||||
(tool_call, result)
|
||||
});
|
||||
handles.push(handle);
|
||||
}
|
||||
for h in handles {
|
||||
if let Ok(res) = h.join() {
|
||||
results_vec.push(res);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
for (tool_call, result) in results_vec {
|
||||
let tool_name = &tool_call.function.name;
|
||||
let args = crate::dto::chat::tool::sanitize_tool_arguments(&tool_call.function.arguments);
|
||||
let explicitly_allowed = ctx.allowed_tools.contains(tool_name);
|
||||
let generally_allowed = ctx.allowed_tools.is_empty() || explicitly_allowed;
|
||||
|
||||
let _ = tx.blocking_send(SubagentEvent::ToolCall {
|
||||
tool: tool_name.clone(),
|
||||
args: args.clone(),
|
||||
});
|
||||
|
||||
// Level 1: allowlist check — is this tool even permitted?
|
||||
if !generally_allowed {
|
||||
let msg = format!("tool '{tool_name}' not allowed for this subagent");
|
||||
messages.push(ChatMessage::tool_result(tool_call.id.clone(), msg.clone()));
|
||||
let _ = tx.blocking_send(SubagentEvent::ToolResult {
|
||||
tool: tool_name.clone(),
|
||||
output: msg,
|
||||
});
|
||||
continue;
|
||||
}
|
||||
|
||||
// Level 2: risky tool check — risky tools require explicit permission
|
||||
if tool_is_risky(tool_name) && !explicitly_allowed {
|
||||
let msg = format!("risky tool '{tool_name}' requires explicit permission; not allowed for this subagent");
|
||||
messages.push(ChatMessage::tool_result(tool_call.id.clone(), msg.clone()));
|
||||
let _ = tx.blocking_send(SubagentEvent::ToolResult {
|
||||
tool: tool_name.clone(),
|
||||
output: msg,
|
||||
});
|
||||
continue;
|
||||
}
|
||||
|
||||
// Level 3: Harness-style content safety gating — mirrors the main
|
||||
// agent's gate_tool_call checks (path traversal, reason validation,
|
||||
// stub/denial/assumption scanning, bash exfiltration, destructive
|
||||
// commands, sensitive path reads).
|
||||
if let Some(block_reason) = gate_subagent_tool_call(tool_name, &args) {
|
||||
let msg = format!("Blocked by subagent gate: {block_reason}");
|
||||
messages.push(ChatMessage::tool_result(tool_call.id.clone(), msg.clone()));
|
||||
let _ = tx.blocking_send(SubagentEvent::ToolResult {
|
||||
tool: tool_name.clone(),
|
||||
output: msg,
|
||||
});
|
||||
continue;
|
||||
}
|
||||
|
||||
let result = match tools.iter().find(|t| t.name() == tool_name.as_str()) {
|
||||
Some(tool) => tool.run(&tool_ctx, &args),
|
||||
None => Err(anyhow::anyhow!("tool '{tool_name}' not found")),
|
||||
};
|
||||
|
||||
match result {
|
||||
Ok(output_text) => {
|
||||
messages.push(ChatMessage::tool_result(tool_call.id.clone(), output_text.clone()));
|
||||
@@ -461,6 +456,14 @@ pub fn run_subagent(ctx: &SubagentContext, tx: &mpsc::Sender<SubagentEvent>) ->
|
||||
});
|
||||
}
|
||||
Err(e) => {
|
||||
let err_str = e.to_string();
|
||||
if err_str.contains("subagent aborted by parent") {
|
||||
let _ = tx.blocking_send(SubagentEvent::StepFailed {
|
||||
step,
|
||||
error: err_str.clone(),
|
||||
});
|
||||
anyhow::bail!("{err_str}");
|
||||
}
|
||||
let msg = format!("tool '{tool_name}' failed: {e}");
|
||||
messages.push(ChatMessage::tool_result(tool_call.id.clone(), msg.clone()));
|
||||
let _ = tx.blocking_send(SubagentEvent::ToolResult {
|
||||
|
||||
@@ -93,13 +93,14 @@ fn make_division_phase(
|
||||
/// context to flow through the pipeline.
|
||||
///
|
||||
/// Returns a consolidated executive summary string.
|
||||
#[allow(clippy::ref_option)]
|
||||
pub fn run_company_pipeline(
|
||||
user_request: &str,
|
||||
session_dir: &std::path::Path,
|
||||
workspaces: &[std::path::PathBuf],
|
||||
turn_events: Option<&Arc<Mutex<std::collections::VecDeque<crate::app::state::runtime::TurnEvent>>>>,
|
||||
abort_flag: &Option<Arc<AtomicBool>>,
|
||||
custom_specialists: HashMap<String, Vec<(String, String)>>,
|
||||
custom_specialists: &HashMap<String, Vec<(String, String)>>,
|
||||
) -> anyhow::Result<String> {
|
||||
let divisions = division::all_divisions();
|
||||
|
||||
@@ -179,20 +180,21 @@ pub fn run_company_pipeline(
|
||||
.map(|f| f.clone())
|
||||
.unwrap_or_default();
|
||||
|
||||
Ok(build_executive_summary(user_request, &results, &all_findings, &divisions, &custom_specialists))
|
||||
Ok(build_executive_summary(user_request, &results, &all_findings, &divisions, custom_specialists))
|
||||
}
|
||||
|
||||
/// Run a quick company pipeline that skips non-essential divisions
|
||||
/// for simple tasks. Flow: Strategy → Engineering → Quality.
|
||||
///
|
||||
/// This is for smaller tasks where security audit and full docs are overkill.
|
||||
#[allow(clippy::ref_option)]
|
||||
pub fn run_company_pipeline_quick(
|
||||
user_request: &str,
|
||||
session_dir: &std::path::Path,
|
||||
workspaces: &[std::path::PathBuf],
|
||||
turn_events: Option<&Arc<Mutex<std::collections::VecDeque<crate::app::state::runtime::TurnEvent>>>>,
|
||||
abort_flag: &Option<Arc<AtomicBool>>,
|
||||
custom_specialists: HashMap<String, Vec<(String, String)>>,
|
||||
custom_specialists: &HashMap<String, Vec<(String, String)>>,
|
||||
) -> anyhow::Result<String> {
|
||||
let divisions = division::all_divisions();
|
||||
let quick_divisions = &divisions[..3];
|
||||
@@ -252,7 +254,7 @@ pub fn run_company_pipeline_quick(
|
||||
.map(|f| f.clone())
|
||||
.unwrap_or_default();
|
||||
|
||||
Ok(build_executive_summary(user_request, &results, &all_findings, quick_divisions, &custom_specialists))
|
||||
Ok(build_executive_summary(user_request, &results, &all_findings, quick_divisions, custom_specialists))
|
||||
}
|
||||
|
||||
/// Build a compressed executive summary from pipeline results.
|
||||
@@ -277,8 +279,7 @@ fn build_executive_summary(
|
||||
let mut start_index = 0;
|
||||
for div in divisions {
|
||||
let count = custom_specialists.get(div.name)
|
||||
.map(Vec::len)
|
||||
.unwrap_or(0);
|
||||
.map_or(0, Vec::len);
|
||||
|
||||
let mut division_verdicts = Vec::new();
|
||||
for offset in 0..count {
|
||||
@@ -393,7 +394,7 @@ mod tests {
|
||||
("Custom Label".to_string(), "Custom Focus Description".to_string())
|
||||
]
|
||||
);
|
||||
let specs = make_division_specialists(div, "Test Request", &custom.get("Strategy").unwrap());
|
||||
let specs = make_division_specialists(div, "Test Request", custom.get("Strategy").unwrap());
|
||||
assert_eq!(specs.len(), 1);
|
||||
if let ScriptPrimitive::Agent(prompt) = &specs[0] {
|
||||
assert!(prompt.contains("Custom Label"));
|
||||
|
||||
+24
-26
@@ -98,7 +98,7 @@ pub type LiveStateFn = Arc<dyn Fn(String, String, AgentStatus) + Send + Sync>;
|
||||
/// a stuck stage from blocking the entire pipeline forever.
|
||||
///
|
||||
/// Return: the agent's text output, or an error on failure.
|
||||
#[allow(clippy::too_many_lines, clippy::too_many_arguments)]
|
||||
#[allow(clippy::too_many_lines, clippy::too_many_arguments, clippy::ref_option)]
|
||||
fn spawn_single_agent(
|
||||
agent_id: &str,
|
||||
agent_name: &str,
|
||||
@@ -185,7 +185,7 @@ fn spawn_single_agent(
|
||||
// Link the shared findings Arc so note_finding calls within this
|
||||
// subagent write into the same vec visible to sibling agents.
|
||||
ctx.workflow_findings = Some(findings.clone());
|
||||
ctx.abort_flag = abort_flag.clone();
|
||||
ctx.abort_flag.clone_from(abort_flag);
|
||||
|
||||
// Create an mpsc channel and drain events in a background thread.
|
||||
// The drain thread also pushes intra-division progress updates to the
|
||||
@@ -269,34 +269,30 @@ fn spawn_single_agent(
|
||||
let deadline = Duration::from_millis(timeout);
|
||||
let mut elapsed = Duration::ZERO;
|
||||
loop {
|
||||
match done_rx.recv_timeout(poll_interval) {
|
||||
Ok(r) => break r,
|
||||
Err(_) => {
|
||||
elapsed += poll_interval;
|
||||
if elapsed >= deadline {
|
||||
break Err(anyhow::anyhow!(
|
||||
"subagent '{bg_name}' timed out after {timeout}ms",
|
||||
));
|
||||
}
|
||||
if bg_abort.as_ref().is_some_and(|f| f.load(Ordering::SeqCst)) {
|
||||
break Err(anyhow::anyhow!(
|
||||
"subagent '{bg_name}' aborted by user",
|
||||
));
|
||||
}
|
||||
}
|
||||
if let Ok(r) = done_rx.recv_timeout(poll_interval) {
|
||||
break r;
|
||||
}
|
||||
elapsed += poll_interval;
|
||||
if elapsed >= deadline {
|
||||
break Err(anyhow::anyhow!(
|
||||
"subagent '{bg_name}' timed out after {timeout}ms",
|
||||
));
|
||||
}
|
||||
if bg_abort.as_ref().is_some_and(|f| f.load(Ordering::SeqCst)) {
|
||||
break Err(anyhow::anyhow!(
|
||||
"subagent '{bg_name}' aborted by user",
|
||||
));
|
||||
}
|
||||
}
|
||||
} else {
|
||||
loop {
|
||||
match done_rx.recv_timeout(poll_interval) {
|
||||
Ok(r) => break r,
|
||||
Err(_) => {
|
||||
if bg_abort.as_ref().is_some_and(|f| f.load(Ordering::SeqCst)) {
|
||||
break Err(anyhow::anyhow!(
|
||||
"subagent '{bg_name}' aborted by user",
|
||||
));
|
||||
}
|
||||
}
|
||||
if let Ok(r) = done_rx.recv_timeout(poll_interval) {
|
||||
break r;
|
||||
}
|
||||
if bg_abort.as_ref().is_some_and(|f| f.load(Ordering::SeqCst)) {
|
||||
break Err(anyhow::anyhow!(
|
||||
"subagent '{bg_name}' aborted by user",
|
||||
));
|
||||
}
|
||||
}
|
||||
};
|
||||
@@ -358,6 +354,7 @@ type ParallelResult = (usize, anyhow::Result<Vec<String>>);
|
||||
/// Return: a `Vec<String>` of all agent outputs (or error strings) in
|
||||
/// the order they were submitted.
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
#[allow(clippy::ref_option, clippy::too_many_lines)]
|
||||
pub fn execute_primitive(
|
||||
primitive: &ScriptPrimitive,
|
||||
args: &HashMap<String, String>,
|
||||
@@ -529,6 +526,7 @@ pub fn run_workflow(
|
||||
/// `spawn_agents` invocations remain fully isolated.
|
||||
///
|
||||
/// Return: a human-readable summary string.
|
||||
#[allow(clippy::ref_option)]
|
||||
pub fn run_workflow_tracked(
|
||||
script: &WorkflowScript,
|
||||
args: &HashMap<String, String>,
|
||||
|
||||
@@ -73,3 +73,123 @@ pub fn serialize_frame<T: serde::Serialize>(value: &T) -> Result<Vec<u8>> {
|
||||
pub fn deserialize_frame<'a, T: serde::Deserialize<'a>>(data: &'a [u8]) -> Result<T> {
|
||||
Ok(serde_json::from_slice(data)?)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// Write a value, read it back, and verify exact equality.
|
||||
fn roundtrip_bytes(data: &[u8]) {
|
||||
let mut buf: Vec<u8> = Vec::new();
|
||||
write_frame(&mut buf, data).unwrap();
|
||||
let read_back = read_frame(&mut buf.as_slice())
|
||||
.unwrap()
|
||||
.expect("expected Some(frame)");
|
||||
assert_eq!(read_back, data);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_write_read_roundtrip_empty() {
|
||||
roundtrip_bytes(b"");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_write_read_roundtrip_small_text() {
|
||||
roundtrip_bytes(b"hello world");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_write_read_roundtrip_binary() {
|
||||
roundtrip_bytes(&[0x00, 0xFF, 0xAB, 0xCD, 0x01, 0x02, 0x03]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_write_read_roundtrip_large() {
|
||||
let data = vec![0x42u8; 100_000];
|
||||
roundtrip_bytes(&data);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_write_rejects_too_large_frame() {
|
||||
let oversized = vec![0u8; MAX_FRAME_SIZE + 1];
|
||||
let mut buf = Vec::new();
|
||||
let result = write_frame(&mut buf, &oversized);
|
||||
assert!(result.is_err());
|
||||
let err = result.unwrap_err().to_string();
|
||||
assert!(err.contains("too large") || err.contains("64 MiB"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_read_rejects_too_large_header() {
|
||||
// Manually craft a 4-byte length header that exceeds MAX_FRAME_SIZE
|
||||
let len = (MAX_FRAME_SIZE as u32).wrapping_add(1);
|
||||
let header = len.to_be_bytes();
|
||||
let mut buf = Vec::from(&header[..]);
|
||||
buf.extend_from_slice(b"dummy");
|
||||
let result = read_frame(&mut buf.as_slice());
|
||||
assert!(result.is_err());
|
||||
let err = result.unwrap_err().to_string();
|
||||
assert!(err.contains("too large"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_read_empty_buf_returns_none() {
|
||||
let empty: &[u8] = &[];
|
||||
let result = read_frame(&mut &empty[..]).unwrap();
|
||||
assert!(result.is_none(), "expected None for empty reader");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_read_partial_header_returns_none() {
|
||||
// Only 2 bytes of the 4-byte header → EOF
|
||||
let partial: &[u8] = &[0x00, 0x01];
|
||||
let result = read_frame(&mut &partial[..]).unwrap();
|
||||
assert!(result.is_none(), "expected None for partial header");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_read_truncated_payload_returns_err() {
|
||||
let mut buf = Vec::new();
|
||||
let header = (10u32).to_be_bytes();
|
||||
buf.extend_from_slice(&header);
|
||||
buf.extend_from_slice(b"abc"); // only 3 of 10 bytes
|
||||
let result = read_frame(&mut buf.as_slice());
|
||||
assert!(result.is_err(), "truncated payload should error");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_serialize_deserialize_roundtrip() {
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
|
||||
struct Msg {
|
||||
id: u32,
|
||||
content: String,
|
||||
tags: Vec<String>,
|
||||
}
|
||||
|
||||
let original = Msg {
|
||||
id: 42,
|
||||
content: "hello world".into(),
|
||||
tags: vec!["foo".into(), "bar".into()],
|
||||
};
|
||||
|
||||
let bytes = serialize_frame(&original).unwrap();
|
||||
let deserialized: Msg = deserialize_frame(&bytes).unwrap();
|
||||
assert_eq!(original, deserialized);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_serialize_rejects_oversized_value() {
|
||||
let huge = vec![0u8; MAX_FRAME_SIZE + 1];
|
||||
let result = serialize_frame(&huge);
|
||||
assert!(result.is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_deserialize_malformed_json_errors() {
|
||||
let bad_json = b"this is not json";
|
||||
let result: Result<String> = deserialize_frame(bad_json);
|
||||
assert!(result.is_err());
|
||||
}
|
||||
}
|
||||
|
||||
@@ -145,8 +145,8 @@ mod tests {
|
||||
log.append(EditLogEntry {
|
||||
ts: i,
|
||||
tool: "edit".to_string(),
|
||||
path: format!("file{}.txt", i),
|
||||
reason: format!("reason {}", i),
|
||||
path: format!("file{i}.txt"),
|
||||
reason: format!("reason {i}"),
|
||||
content_sha256: "hash".to_string(),
|
||||
bytes_delta: 10 + i,
|
||||
origin: "main".to_string(),
|
||||
|
||||
+1
-1
@@ -375,7 +375,7 @@ mod tests {
|
||||
};
|
||||
mem.write(&dir).unwrap();
|
||||
let names = Memory::list(&dir);
|
||||
assert!(names.contains(&"alpha".to_string()), "list should contain 'alpha', got: {:?}", names);
|
||||
assert!(names.contains(&"alpha".to_string()), "list should contain 'alpha', got: {names:?}");
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
}
|
||||
|
||||
|
||||
+1
-1
@@ -141,7 +141,7 @@ impl ToolCtxBuilder {
|
||||
|
||||
/// Construct one instance of every built-in tool, in the fixed order exposed to the LLM.
|
||||
///
|
||||
/// Return: boxed trait objects for all 28 tools (fs, search, bash, git, memory, plan,
|
||||
/// Return: boxed trait objects for all 37 tools (fs, search, bash, git, memory, plan,
|
||||
/// workflow, utility).
|
||||
pub fn all_tools() -> Vec<Box<dyn Tool>> {
|
||||
vec![
|
||||
|
||||
@@ -206,7 +206,7 @@ impl Tool for CompanyPipeline {
|
||||
let specs = v.as_array().map(|arr| {
|
||||
arr.iter().filter_map(|item| {
|
||||
let pair = item.as_array()?;
|
||||
let label = pair.get(0)?.as_str()?.to_string();
|
||||
let label = pair.first()?.as_str()?.to_string();
|
||||
let focus = pair.get(1)?.as_str()?.to_string();
|
||||
Some((label, focus))
|
||||
}).collect()
|
||||
@@ -225,7 +225,7 @@ impl Tool for CompanyPipeline {
|
||||
&ctx.workspaces,
|
||||
ctx.turn_events.as_ref(),
|
||||
&no_abort,
|
||||
custom_specialists,
|
||||
&custom_specialists,
|
||||
)
|
||||
}
|
||||
_ => {
|
||||
@@ -235,7 +235,7 @@ impl Tool for CompanyPipeline {
|
||||
&ctx.workspaces,
|
||||
ctx.turn_events.as_ref(),
|
||||
&no_abort,
|
||||
custom_specialists,
|
||||
&custom_specialists,
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -273,7 +273,7 @@ impl Tool for ReadFindings {
|
||||
.map(|(i, f)| format!("{}. {}", i + 1, f))
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n");
|
||||
Ok(format!("Findings in this workflow run:\n{}", formatted))
|
||||
Ok(format!("Findings in this workflow run:\n{formatted}"))
|
||||
}
|
||||
} else {
|
||||
Ok("No findings database available (called outside a workflow run).".to_string())
|
||||
|
||||
Reference in New Issue
Block a user