refactor: migrate monolithic crate to Cargo Workspace with Clean Architecture

Transform the single binary crate into a 9-crate workspace monorepo:

- Root Cargo.toml as [workspace] manager with resolver = "2"
- zesdex-entities: Domain entity types (session, settings, store, message, etc.)
- zesdex-utils: Pure utility functions (error, logger, pagination, slug, clipboard)
- zesdex-dto: Data Transfer Objects for LLM provider API communication
- zesdex-ipc: Unix-socket IPC layer (client/server/framing/protocol)
- zesdex-iam: Identity & Access Management (Clean Architecture: domain/application/infrastructure)
- zesdex-cms: Content Management (Clean Architecture: domain/application/infrastructure)
- zesdex-middleware: HTTP middleware (Auth, CORS, Rate Limiting)
- zesdex-libs: Composition root (AppContext, DB init, JWT, Argon2)
- zesdex-backend: Main binary entry point + seed/migrate binaries
- DevOps: Dockerfile, docker-compose, Nix (flake/shell/default), CI/CD updates
- Remove dead root src/ and src-misc/ directories

All crate re-exports maintain backward compatibility with original
crate::model::*, crate::dto::*, crate::ipc::* module paths.
Feature crates enforce strict layer separation: domain -> application
-> infrastructure with generic trait-based dependency injection.
This commit is contained in:
asepharyana
2026-07-17 09:08:41 +07:00
parent 86cc412395
commit be0a9582bb
248 changed files with 7901 additions and 1505 deletions
@@ -0,0 +1,605 @@
//! Auto-subagent orchestration: the main agent automatically delegates
//! review, test-generation, architecture-review, and security-review tasks
//! to subagents without requiring explicit tool calls from the LLM.
//!
//! Two modes:
//! - **Inline** (`spawn_quick_review`): runs synchronously within the turn
//! after each write/edit tool call. Results are fed back into the LLM
//! conversation so the agent can act on feedback immediately.
//! - **Background** (`spawn_background_*`): runs asynchronously on a
//! dedicated OS thread at the end of a turn. Reports results via
//! `TurnEvent::SystemNote`, consumed by the TUI on the next Tick.
//!
//! Why inline vs background:
//! - Inline reviews give the agent an immediate feedback loop ("I just
//! wrote this file, let me check if it's correct before continuing").
//! - Background reviews catch broader concerns (missing tests, architectural
//! drift, security issues) without blocking the main agent's flow.
use crate::app::state::runtime::TurnEvent;
use crate::app::subagent::context::build_subagent_context;
use crate::app::subagent::engine::run_subagent;
use crate::app::subagent::event::SubagentEvent;
use crate::app::subagent::spawn::AgentDefinition;
use std::collections::VecDeque;
use std::path::Path;
use std::sync::atomic::{AtomicBool, Ordering};
use std::sync::{Arc, Mutex};
/// File extensions that should not trigger auto-review (config, lock, data).
const SKIP_REVIEW_EXTENSIONS: &[&str] = &[
".lock", ".md", ".txt", ".json", ".toml", ".yaml", ".yml", ".svg", ".png", ".jpg", ".ico",
".woff", ".woff2",
];
/// File names that should not trigger auto-review.
const SKIP_REVIEW_FILES: &[&str] = &[
"Cargo.lock",
"yarn.lock",
"package-lock.json",
".gitignore",
".env",
".env.example",
];
/// Prevents a second background subagent of the same kind from spawning
/// while one is already in flight. Without this, a chatty multi-turn edit
/// session could stack overlapping test-gen/arch/security reviews of
/// overlapping file sets, none of which could be told apart in the
/// `SystemNote` toast stream.
static TEST_GEN_RUNNING: AtomicBool = AtomicBool::new(false);
static ARCH_REVIEW_RUNNING: AtomicBool = AtomicBool::new(false);
static SECURITY_REVIEW_RUNNING: AtomicBool = AtomicBool::new(false);
/// RAII guard that resets a per-kind overlap flag back to `false` on drop —
/// including during a panic-triggered unwind inside the spawned thread — so
/// a background review can never wedge itself permanently disabled for the
/// rest of the process if the subagent run panics before reaching its
/// normal completion path.
struct RunningGuard(&'static AtomicBool);
impl Drop for RunningGuard {
fn drop(&mut self) {
self.0.store(false, Ordering::SeqCst);
}
}
/// ─── Helpers ───
///
/// Check whether a file path is worth auto-reviewing (not config/lock/data).
///
/// Vendored/generated directories are matched by path *segment* rather than
/// a `/target/`-style substring check — the substring form misses paths
/// where the directory is the first component (e.g. `target/debug/build.rs`,
/// which has no leading slash), the same class of bug fixed in
/// `is_production_code` below.
pub fn is_reviewable_path(path: &str) -> bool {
let lower = path.to_lowercase();
if SKIP_REVIEW_FILES.iter().any(|f| lower.ends_with(f)) {
return false;
}
if SKIP_REVIEW_EXTENSIONS.iter().any(|e| lower.ends_with(e)) {
return false;
}
// Skip paths that are clearly generated or vendored
let in_vendored_dir = std::path::Path::new(&lower).components().any(|c| {
matches!(
c,
std::path::Component::Normal(seg)
if matches!(seg.to_str(), Some("target" | "node_modules" | ".git" | "vendor"))
)
});
if in_vendored_dir {
return false;
}
true
}
/// Determine whether a file change looks like it modifies production logic
/// (vs. tests, config, or documentation) — used to decide if a test-gen
/// or security-review background subagent should fire.
///
/// Matches test-ness by path *segment* (a directory literally named
/// "test"/"tests"/"__tests__") or by filename convention
/// (`foo_test.rs`, `foo.test.ts`, `test_foo.py`, `foo_spec.rb`), not by a
/// raw substring check — a plain `.contains("test")` would wrongly exclude
/// legitimate production files like `src/attestation.rs` or
/// `src/latest/foo.rs`.
fn is_production_code(path: &str) -> bool {
let lower = path.to_lowercase();
let path_obj = std::path::Path::new(&lower);
let in_test_dir = path_obj.components().any(|c| {
matches!(
c,
std::path::Component::Normal(seg)
if matches!(seg.to_str(), Some("test" | "tests" | "__tests__"))
)
});
let file_stem = path_obj.file_stem().and_then(|s| s.to_str()).unwrap_or("");
let is_test_filename = file_stem.starts_with("test_")
|| file_stem.ends_with("_test")
|| std::path::Path::new(file_stem)
.extension()
.is_some_and(|ext| ext.eq_ignore_ascii_case("test"))
|| file_stem == "spec"
|| file_stem.ends_with("_spec")
|| std::path::Path::new(file_stem)
.extension()
.is_some_and(|ext| ext.eq_ignore_ascii_case("spec"));
if in_test_dir || is_test_filename {
return false;
}
// Only source files — use Path::extension() to avoid clippy
// case_sensitive_file_extension_comparisons lint
path_obj
.extension()
.and_then(|ext| ext.to_str())
.is_some_and(|ext| {
matches!(
ext,
"rs" | "ts"
| "tsx"
| "js"
| "jsx"
| "go"
| "py"
| "java"
| "kt"
| "swift"
| "c"
| "cpp"
| "h"
| "hpp"
)
})
}
/// ─── Inline Quick Review (synchronous, feeds back to LLM) ───
///
/// Spawn a lightweight inline code review subagent for the given file.
///
/// The subagent reads the file (read-only), checks for common issues,
/// and returns a concise text verdict. This runs synchronously so the
/// main agent's `run_agent_turn` can inject the result back into the
/// LLM conversation for immediate action.
///
/// Returns `Ok(verdict)` if the review completed, or an error if the
/// subagent could not be spawned or failed internally. Callers should
/// log and swallow errors gracefully — a failed inline review should
/// never interrupt the main agent's flow.
pub fn spawn_quick_review(
file_path: &str,
session_dir: &Path,
workspaces: &[std::path::PathBuf],
) -> anyhow::Result<String> {
let prompt = format!(
"{}\n\nFile to review: {}",
crate::resources::AUTO_REVIEWER_PROMPT,
file_path,
);
let def = AgentDefinition::new("quick-reviewer".to_string(), "reviewer".to_string())
.with_system_prompt(prompt);
let mut ctx = build_subagent_context(&def);
ctx.session_dir = session_dir.to_path_buf();
ctx.workspaces = workspaces.to_vec();
let (tx, mut rx) = tokio::sync::mpsc::channel(32);
let _drain = std::thread::spawn(move || {
while let Some(event) = rx.blocking_recv() {
match &event {
SubagentEvent::ToolCall { tool, .. } => {
tracing::debug!("[auto-review] tool call: {}", tool);
}
SubagentEvent::ToolResult { tool, .. } => {
tracing::debug!("[auto-review] tool result: {}", tool);
}
SubagentEvent::Completed => {
tracing::debug!("[auto-review] completed");
}
_ => {}
}
}
});
let verdict = run_subagent(&ctx, &tx)?;
tracing::info!(
"[auto-review] quick review for '{}': {}",
file_path,
verdict.lines().next().unwrap_or(&verdict),
);
Ok(verdict)
}
/// ─── Background Subagent Spawners (async, report via `SystemNote`) ───
///
/// Run a subagent built from `def`, retrying once if the first attempt
/// fails. Background subagents call this instead of running once and
/// silently swallowing the error into a note string, so a single transient
/// LLM/tool failure doesn't just disappear.
///
/// `abort_flag` is checked before every attempt (including the first) and
/// forwarded into the subagent's own context, so a cancelled turn stops
/// retrying immediately instead of burning a second attempt.
///
/// Return: `Ok(output)` if either attempt succeeded, `Err(message)`
/// describing the final failure if both attempts failed, or the literal
/// message `"aborted by user"` if `abort_flag` was already set before an
/// attempt could start.
fn run_subagent_with_retry(
def: &AgentDefinition,
session_dir: &Path,
workspaces: &[std::path::PathBuf],
label: &str,
abort_flag: Option<&Arc<AtomicBool>>,
) -> Result<String, String> {
let mut last_err = String::new();
for attempt in 1..=2 {
if abort_flag.is_some_and(|f| f.load(Ordering::SeqCst)) {
return Err("aborted by user".to_string());
}
let mut ctx = build_subagent_context(def);
ctx.session_dir = session_dir.to_path_buf();
ctx.workspaces = workspaces.to_vec();
ctx.abort_flag = abort_flag.cloned();
let (tx, mut rx) = tokio::sync::mpsc::channel(32);
let drain_label = label.to_string();
let _drain = std::thread::spawn(move || {
while let Some(event) = rx.blocking_recv() {
if let SubagentEvent::StepFailed { step, error } = &event {
tracing::warn!("[{drain_label}] step {step} failed: {error}");
}
}
});
match run_subagent(&ctx, &tx) {
Ok(output) => return Ok(output),
Err(e) => {
tracing::warn!("[{label}] attempt {attempt}/2 failed: {e}");
last_err = e.to_string();
}
}
}
Err(format!("failed after 2 attempts: {last_err}"))
}
/// Spawn a background subagent that generates tests for modified files.
///
/// Uses the test-generator prompt and has read-write access so it can
/// create test files. Runs in a separate OS thread and reports completion
/// via `TurnEvent::SystemNote { kind: "bg-test-gen" }`.
///
/// Skipped (no-op) if a test-gen run is already in flight (guarded by
/// `TEST_GEN_RUNNING`) — prevents a chatty multi-turn edit session from
/// stacking overlapping runs. `abort_flag` is forwarded to
/// `run_subagent_with_retry` so the run can be cancelled if the turn aborts.
pub fn spawn_background_test_gen(
file_paths: &[String],
session_dir: &Path,
workspaces: &[std::path::PathBuf],
turn_events: &Arc<Mutex<VecDeque<TurnEvent>>>,
abort_flag: Arc<AtomicBool>,
) {
if file_paths.is_empty() {
return;
}
if TEST_GEN_RUNNING
.compare_exchange(false, true, Ordering::SeqCst, Ordering::SeqCst)
.is_err()
{
tracing::debug!("[bg-test-gen] skipped — a test-gen run is already in flight");
return;
}
let paths = file_paths.to_vec();
let sd = session_dir.to_path_buf();
let ws = workspaces.to_vec();
let events = turn_events.clone();
std::thread::spawn(move || {
let _running_guard = RunningGuard(&TEST_GEN_RUNNING);
tracing::info!(
"[bg-test-gen] spawning for {} file(s): {:?}",
paths.len(),
paths,
);
let file_list = paths.join("\n");
let prompt = format!(
"{}\n\nModified files that need tests:\n{}",
crate::resources::TEST_GENERATOR_PROMPT,
file_list,
);
let def = AgentDefinition::new(
"test-generator".to_string(),
"coder".to_string(), // needs write access
)
.with_system_prompt(prompt);
let result = run_subagent_with_retry(&def, &sd, &ws, "bg-test-gen", Some(&abort_flag));
let message = match &result {
Ok(output) => {
let first = output.lines().next().unwrap_or(output);
format!("Auto test-gen: {first}")
}
Err(e) if e.contains("aborted") => format!("Auto test-gen cancelled: {e}"),
Err(e) => format!("ESCALATED: Auto test-gen {e}"),
};
if let Ok(mut q) = events.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "bg-test-gen".to_string(),
message,
});
}
});
}
/// Spawn a background architecture-review subagent.
///
/// Inspects the modified files for architectural consistency (layering,
/// coupling, module boundaries). Reports via
/// `TurnEvent::SystemNote { kind: "bg-arch-review" }`.
///
/// Skipped (no-op) if an arch-review run is already in flight (guarded by
/// `ARCH_REVIEW_RUNNING`). `abort_flag` is forwarded to
/// `run_subagent_with_retry` so the run can be cancelled if the turn aborts.
pub fn spawn_background_arch_review(
file_paths: &[String],
session_dir: &Path,
workspaces: &[std::path::PathBuf],
turn_events: &Arc<Mutex<VecDeque<TurnEvent>>>,
abort_flag: Arc<AtomicBool>,
) {
if file_paths.is_empty() {
return;
}
if ARCH_REVIEW_RUNNING
.compare_exchange(false, true, Ordering::SeqCst, Ordering::SeqCst)
.is_err()
{
tracing::debug!("[bg-arch-review] skipped — an arch-review run is already in flight");
return;
}
let paths = file_paths.to_vec();
let sd = session_dir.to_path_buf();
let ws = workspaces.to_vec();
let events = turn_events.clone();
std::thread::spawn(move || {
let _running_guard = RunningGuard(&ARCH_REVIEW_RUNNING);
let file_list = paths.join("\n");
let prompt = format!(
"{}\n\nModified files for architecture review:\n{}",
crate::resources::ARCH_REVIEWER_PROMPT,
file_list,
);
let def = AgentDefinition::new("arch-reviewer".to_string(), "reviewer".to_string())
.with_system_prompt(prompt);
let result = run_subagent_with_retry(&def, &sd, &ws, "bg-arch-review", Some(&abort_flag));
let message = match &result {
Ok(output) => {
let first = output.lines().next().unwrap_or(output);
format!("Architecture review: {first}")
}
Err(e) if e.contains("aborted") => format!("Architecture review cancelled: {e}"),
Err(e) => format!("ESCALATED: Architecture review {e}"),
};
if let Ok(mut q) = events.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "bg-arch-review".to_string(),
message,
});
}
});
}
/// Spawn a background security-review subagent.
///
/// Checks modified files for security vulnerabilities. Reports via
/// `TurnEvent::SystemNote { kind: "bg-security-review" }`.
///
/// Skipped (no-op) if a security-review run is already in flight (guarded by
/// `SECURITY_REVIEW_RUNNING`). `abort_flag` is forwarded to
/// `run_subagent_with_retry` so the run can be cancelled if the turn aborts.
pub fn spawn_background_security_review(
file_paths: &[String],
session_dir: &Path,
workspaces: &[std::path::PathBuf],
turn_events: &Arc<Mutex<VecDeque<TurnEvent>>>,
abort_flag: Arc<AtomicBool>,
) {
if file_paths.is_empty() {
return;
}
// Only review production code files for security — test files and
// config files are out of scope for security review.
let prod_paths: Vec<String> = file_paths
.iter()
.filter(|p| is_production_code(p))
.cloned()
.collect();
if prod_paths.is_empty() {
return;
}
if SECURITY_REVIEW_RUNNING
.compare_exchange(false, true, Ordering::SeqCst, Ordering::SeqCst)
.is_err()
{
tracing::debug!(
"[bg-security-review] skipped — a security-review run is already in flight"
);
return;
}
let paths = prod_paths;
let sd = session_dir.to_path_buf();
let ws = workspaces.to_vec();
let events = turn_events.clone();
std::thread::spawn(move || {
let _running_guard = RunningGuard(&SECURITY_REVIEW_RUNNING);
let file_list = paths.join("\n");
let prompt = format!(
"{}\n\nModified files for security review:\n{}",
crate::resources::SECURITY_REVIEWER_PROMPT,
file_list,
);
let def = AgentDefinition::new("security-reviewer".to_string(), "reviewer".to_string())
.with_system_prompt(prompt);
let result =
run_subagent_with_retry(&def, &sd, &ws, "bg-security-review", Some(&abort_flag));
let message = match &result {
Ok(output) => {
let first = output.lines().next().unwrap_or(output);
format!("Security review: {first}")
}
Err(e) if e.contains("aborted") => format!("Security review cancelled: {e}"),
Err(e) => format!("ESCALATED: Security review {e}"),
};
if let Ok(mut q) = events.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "bg-security-review".to_string(),
message,
});
}
});
}
/// Convenience: spawn all applicable background subagents for a set of edited
/// file paths. Called once at the end of a main agent turn.
///
/// Flow: always spawns arch-review and security-review if there are
/// reviewable production files → spawns test-gen only if there are source
/// files that aren't already tests.
///
/// `abort_flag` is cloned and forwarded to all three spawn calls so a
/// single cancellation source stops every kind of background review.
pub fn spawn_all_background(
file_paths: &[String],
session_dir: &Path,
workspaces: &[std::path::PathBuf],
turn_events: &Arc<Mutex<VecDeque<TurnEvent>>>,
abort_flag: Arc<AtomicBool>,
) {
if file_paths.is_empty() {
return;
}
// Background test-gen: only for non-test source files
let source_paths: Vec<String> = file_paths
.iter()
.filter(|p| is_production_code(p))
.cloned()
.collect();
spawn_background_test_gen(
&source_paths,
session_dir,
workspaces,
turn_events,
abort_flag.clone(),
);
// Background arch review: for all files that are reviewable
let reviewable: Vec<String> = file_paths
.iter()
.filter(|p| is_reviewable_path(p))
.cloned()
.collect();
spawn_background_arch_review(
&reviewable,
session_dir,
workspaces,
turn_events,
abort_flag.clone(),
);
// Background security review: only production source files
spawn_background_security_review(
&source_paths,
session_dir,
workspaces,
turn_events,
abort_flag,
);
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn reviewable_path_skips_lockfiles_and_known_extensions() {
assert!(!is_reviewable_path("Cargo.lock"));
assert!(!is_reviewable_path("package.json"));
assert!(!is_reviewable_path("logo.svg"));
}
#[test]
fn reviewable_path_skips_vendored_and_generated_dirs() {
assert!(!is_reviewable_path("target/debug/build.rs"));
assert!(!is_reviewable_path("node_modules/foo/index.js"));
}
#[test]
fn reviewable_path_accepts_ordinary_source_files() {
assert!(is_reviewable_path("src/main.rs"));
}
#[test]
fn production_code_excludes_dedicated_test_directories() {
assert!(!is_production_code("src/tests/foo.rs"));
assert!(!is_production_code("__tests__/baz.test.ts"));
}
#[test]
fn production_code_excludes_test_filename_conventions() {
assert!(!is_production_code("src/foo_test.rs"));
assert!(!is_production_code("src/test_foo.py"));
assert!(!is_production_code("src/foo.spec.ts"));
}
#[test]
fn production_code_does_not_false_positive_on_substring_test() {
// Regression: a plain `.contains("test")` would wrongly exclude
// these legitimate production files.
assert!(is_production_code("src/attestation.rs"));
assert!(is_production_code("src/latest/foo.rs"));
}
#[test]
fn production_code_requires_known_source_extension() {
assert!(!is_production_code("README.md"));
assert!(is_production_code("src/main.rs"));
}
#[test]
fn running_guard_resets_flag_on_drop_even_after_panic() {
static TEST_FLAG: AtomicBool = AtomicBool::new(false);
TEST_FLAG.store(true, Ordering::SeqCst);
let result = std::panic::catch_unwind(|| {
let _guard = RunningGuard(&TEST_FLAG);
panic!("simulated failure inside guarded region");
});
assert!(result.is_err());
assert!(
!TEST_FLAG.load(Ordering::SeqCst),
"guard must reset the flag even when the guarded closure panics"
);
}
}
@@ -0,0 +1,60 @@
//! Construction of a `SubagentContext` from an `AgentDefinition`,
//! including the default read-only tool set for reviewer agents.
use super::spawn::AgentDefinition;
use std::path::PathBuf;
use std::sync::{atomic::AtomicBool, Arc, Mutex};
/// Default read-only tool names granted to `role == "reviewer"` agents.
pub const REVIEWER_ALLOWED: &[&str] = &["read", "grep", "glob", "recall", "remember"];
/// Per-invocation configuration for a subagent: prompt, allowed tools,
/// step budget, session directory, and optional workflow-findings Arc
/// for cross-agent communication within a workflow run.
pub struct SubagentContext {
pub system_prompt: String,
pub allowed_tools: Vec<String>,
pub max_steps: usize,
pub session_dir: PathBuf,
pub workspaces: Vec<PathBuf>,
/// Ephemeral findings shared between sibling subagents in the same
/// workflow run. Set by the workflow engine; `note_finding` writes
/// into this from tool code via `ToolCtx.workflow_findings`.
pub workflow_findings: Option<Arc<Mutex<Vec<String>>>>,
/// Atomic abort flag: when set to `true`, the subagent loop will exit
/// at the earliest opportunity (before the next LLM call). Mirrors the
/// main agent's `abort_flag` mechanism so that long-running or stuck
/// subagents can be cancelled from the parent.
pub abort_flag: Option<Arc<AtomicBool>>,
}
/// Build a `SubagentContext` from an `AgentDefinition`.
///
/// Flow: copy optional `allowed_tools` from the def → fall back to the
/// reviewer-allowlist when the def has none and the role is "reviewer" →
/// fall back to an empty list (i.e. "all tools allowed") for other roles.
/// `max_steps` is read from the definition, defaulting to 25 if absent.
///
/// Return: a context with empty `system_prompt`, empty `workspaces`,
/// empty `session_dir`, resolved `max_steps`, and the resolved allowed-tool list.
pub fn build_subagent_context(def: &AgentDefinition) -> SubagentContext {
let allowed_tools = def.allowed_tools.clone().unwrap_or_else(|| {
if def.role == "reviewer" {
REVIEWER_ALLOWED
.iter()
.map(std::string::ToString::to_string)
.collect()
} else {
Vec::new()
}
});
let max_steps = def.max_steps.unwrap_or(usize::MAX);
SubagentContext {
system_prompt: String::new(),
allowed_tools,
max_steps,
session_dir: PathBuf::new(),
workspaces: Vec::new(),
workflow_findings: None,
abort_flag: None,
}
}
@@ -0,0 +1,150 @@
//! Access tiers for the anonymous processing nodes spawned by the
//! hive-mind orchestrator (`app::workflow::hive_mind`).
//!
//! Nodes have no persistent identity of their own — the Core Intelligence
//! addresses each one only by directive and access tier. Since node
//! designations are system-assigned coordinates rather than named roles,
//! tool access can't be a lookup table keyed by role name. Instead the
//! Core Intelligence picks one of these three tiers per node, matched to
//! what that node's specific directive needs — this keeps the Harness
//! gate meaningful while the node roster itself stays fully dynamic.
/// The three tool-access tiers a hive-mind node can be granted.
pub mod tool_scope {
/// Read-only investigation: no file mutation, no shell, no VCS.
pub const READ: &str = "read";
/// Read-tier plus file mutation and non-destructive shell (tests/builds).
pub const WRITE: &str = "write";
/// Write-tier plus delete, git, and the remaining LSP actions.
pub const FULL: &str = "full";
/// The read-only tool set — reused by `context::dedup` as the
/// authoritative "safe to deduplicate" classification, so there's a
/// single list of read-only tool names in the codebase instead of two.
pub const READ_TOOLS: &[&str] = &[
"read",
"grep",
"glob",
"search",
"seqthink",
"recall",
"lsp_connect",
"lsp_diagnostics",
"lsp_hover",
"lsp_definition",
"lsp_references",
"read_findings",
];
const WRITE_TOOLS: &[&str] = &[
"read",
"grep",
"glob",
"search",
"seqthink",
"recall",
"lsp_connect",
"lsp_diagnostics",
"lsp_hover",
"lsp_definition",
"lsp_references",
"read_findings",
"write",
"edit",
"bash",
"todowrite",
"todofinish",
"remember",
];
const FULL_TOOLS: &[&str] = &[
"read",
"grep",
"glob",
"search",
"seqthink",
"recall",
"lsp_connect",
"lsp_diagnostics",
"lsp_hover",
"lsp_definition",
"lsp_references",
"read_findings",
"write",
"edit",
"bash",
"todowrite",
"todofinish",
"remember",
"delete",
"git_operator",
"lsp_completion",
"lsp_disconnect",
];
/// Resolve a tier name to its concrete tool allowlist.
///
/// Unrecognized scope strings fall back to `READ` — the least-privileged
/// tier — rather than silently granting broader access.
///
/// Return: an owned `Vec<String>` suitable for `AgentDefinition::with_allowed_tools`.
pub fn tools_for(scope: &str) -> Vec<String> {
let tools: &[&str] = match scope {
FULL => FULL_TOOLS,
WRITE => WRITE_TOOLS,
_ => READ_TOOLS,
};
tools.iter().map(|s| (*s).to_string()).collect()
}
}
#[cfg(test)]
mod tests {
use super::tool_scope::{tools_for, FULL, READ, WRITE};
#[test]
fn read_tier_excludes_write_tools() {
let tools = tools_for(READ);
assert!(!tools.contains(&"write".to_string()));
assert!(!tools.contains(&"bash".to_string()));
}
#[test]
fn write_tier_includes_bash_but_not_delete_or_git() {
let tools = tools_for(WRITE);
assert!(tools.contains(&"bash".to_string()));
assert!(tools.contains(&"write".to_string()));
assert!(!tools.contains(&"delete".to_string()));
assert!(!tools.contains(&"git_operator".to_string()));
}
#[test]
fn full_tier_includes_delete_and_git() {
let tools = tools_for(FULL);
assert!(tools.contains(&"delete".to_string()));
assert!(tools.contains(&"git_operator".to_string()));
}
#[test]
fn unknown_scope_falls_back_to_read() {
let tools = tools_for("bogus");
assert!(!tools.contains(&"write".to_string()));
assert!(!tools.contains(&"delete".to_string()));
}
#[test]
fn read_tier_is_subset_of_write_tier_and_write_is_subset_of_full() {
use std::collections::HashSet;
let read: HashSet<_> = tools_for(READ).into_iter().collect();
let write: HashSet<_> = tools_for(WRITE).into_iter().collect();
let full: HashSet<_> = tools_for(FULL).into_iter().collect();
assert!(
read.is_subset(&write),
"read tier must be a subset of write tier"
);
assert!(
write.is_subset(&full),
"write tier must be a subset of full tier"
);
}
}
@@ -0,0 +1,690 @@
//! Subagent execution loop: drive an LLM conversation, gate tool calls
//! against the context's allowlist, run tools, and stream progress events
//! to the parent via an mpsc channel.
//!
//! Security: subagent tool gating mirrors the main agent's `Harness` checks
//! (path traversal, reason validation, stub/denial/assumption scanning,
//! bash exfiltration and destructive-pattern detection) so that subagents
//! are not a weaker link than the main agent.
use std::fmt::Write;
use sha2::Digest;
use tokio::sync::mpsc;
use crate::dto::chat::message::ChatMessage;
use crate::dto::provider::request::ToolDef;
use crate::tool::{all_tools, tool_defs, tool_is_risky};
use super::context::SubagentContext;
use super::event::SubagentEvent;
/// Maps a subagent's allowed tool names to concrete Tool trait objects and
/// OpenAI-style tool definitions.
///
/// Flow: load `all_tools()` → if `allowed_tools` is empty, use all; else
/// filter by membership → derive `ToolDef`s for the LLM.
///
/// Why: an empty allowlist means "no restriction" (matches
/// `build_subagent_context`'s default for non-reviewer roles).
///
/// Return: `(tool impls, schema defs)` for the subagent to use.
fn build_subagent_tools(allowed_tools: &[String]) -> (Vec<Box<dyn crate::tool::Tool>>, Vec<ToolDef>) {
let all = all_tools();
let filtered: Vec<Box<dyn crate::tool::Tool>> = if allowed_tools.is_empty() {
all.into_iter()
.filter(|t| t.name() != "hive_mind" && t.name() != "workflow_run")
.collect()
} else {
all.into_iter()
.filter(|t| {
allowed_tools.contains(&t.name().to_string())
&& t.name() != "hive_mind"
&& t.name() != "workflow_run"
})
.collect()
};
let defs = tool_defs(&filtered);
(filtered, defs)
}
/// Resolve the API key, model, and base URL from persisted app config.
///
/// Flow: try the settings key for the active provider → fall back to the
/// provider's `api_key_env` env-var → fall back to the provider's
/// `default_api_key` → fall back to an empty string.
///
/// Why: matches the main agent's credential resolution exactly, so
/// subagents automatically inherit the same provider settings.
///
/// Return: `(api_key, model, optional_base_url, provider_name)`. `api_key`
/// is empty when every resolution path was exhausted — callers must check
/// for this before issuing requests (see `run_subagent`).
fn resolve_provider_config() -> (String, String, Option<String>, String) {
let settings = crate::model::settings::Settings::load();
let app_config = crate::model::app_config::AppConfig::load();
let mut api_key = settings.api_keys.get(&settings.provider).cloned().unwrap_or_else(|| {
tracing::warn!("[subagent] no API key for provider '{}' in settings, trying env/default", settings.provider);
String::new()
});
let model = settings.model.clone();
let base_url = app_config.providers.get(&settings.provider)
.map(|p| p.api_base.clone());
if api_key.is_empty() {
if let Some(provider_cfg) = app_config.providers.get(&settings.provider) {
api_key = provider_cfg.api_key_env.as_ref()
.and_then(|env| std::env::var(env).ok())
.or_else(|| provider_cfg.default_api_key.clone())
.unwrap_or_else(|| {
tracing::warn!("[subagent] all API key resolution paths exhausted for '{}'", settings.provider);
String::new()
});
}
}
(api_key, model, base_url, settings.provider)
}
/// Reject an empty API key with an actionable error instead of letting the
/// caller send a request that is guaranteed to fail once it reaches the network.
///
/// Return: `Ok(())` if `api_key` is non-empty, `Err` with a message naming
/// `provider` and where to fix it otherwise.
fn require_api_key(api_key: &str, provider: &str) -> anyhow::Result<()> {
if api_key.is_empty() {
anyhow::bail!(
"no API key configured for provider '{provider}' — set one in Settings or ~/.claude/settings.json"
);
}
Ok(())
}
// ─── Subagent-level tool gating (mirrors Harness checks) ───
const STUB_PATTERNS: &[&str] = &[
"todo!()", "todo!(",
"unimplemented!()", "unimplemented!(",
"FIXME", "fixme:", "XXX:", "PLACEHOLDER",
"REPLACE_ME", "stub_value", "stub_function",
"fake_response", "fake_data",
"not implemented", "not yet implemented",
"to be implemented", "to be done",
];
const DENIAL_PATTERNS: &[&str] = &[
"// skip", "// skipping", "// skipping for now",
"// for now just", "// punt", "// hack:",
"// workaround:", "// cba", "// later",
"// do later", "// ignore for now", "// disable",
"// bypass", "// quick fix", "// temp fix",
"// temporary fix", "// temp:", "// temporary:",
"// noop",
];
const ASSUMPTION_PATTERNS: &[&str] = &[
"// assume", "// probably", "// guess",
"// should work", "// hopefully", "// i think",
"// should be fine", "// likely",
];
const EXFIL_PATTERNS: &[&str] = &[
"curl ", "wget ", "nc -e ", "ncat ", "/dev/tcp/",
"base64 -d |", "base64 --decode |",
"openssl s_client", "ssh -R ",
"scp /", "rsync /",
];
const SENSITIVE_PATH_PATTERNS: &[&str] = &[
".ssh/id_rsa", ".ssh/id_ed25519",
".aws/credentials", ".aws/config",
".kube/config", ".docker/config.json",
"/etc/shadow", "/etc/passwd", "/proc/self/environ",
];
const MIN_REASON_LEN: usize = 8;
/// Gate a tool call in the subagent context. Returns `Some(block_reason)` if
/// the call should be blocked, `None` to allow.
///
/// Flow: always blocks dangerous patterns — path traversal, stub/denial/
/// assumption language, bash exfiltration, destructive commands, sensitive
/// path reads — regardless of the allowed-tools list. Tools that are not
/// risky only get the basic allowlist check.
fn gate_subagent_tool_call(
tool_name: &str,
args: &serde_json::Value,
) -> Option<String> {
// File-mutating tools: write / edit / delete
if matches!(tool_name, "write" | "edit" | "delete") {
if let Some(path) = args.get("path").and_then(|v| v.as_str()) {
if path.contains("..") {
return Some("path traversal detected in 'path' argument".to_string());
}
}
}
// write / edit require a non-trivial `reason`
if matches!(tool_name, "write" | "edit" | "delete") {
let reason = args.get("reason").and_then(|v| v.as_str()).unwrap_or("");
if reason.trim().len() < MIN_REASON_LEN {
return Some(format!(
"{tool_name} requires a non-trivial 'reason' (>= {MIN_REASON_LEN} chars) explaining why",
));
}
}
// write / edit content must not contain stubs, denial, or assumption language
if matches!(tool_name, "write" | "edit") {
let content = match tool_name {
"write" => args.get("content").and_then(|v| v.as_str()).unwrap_or(""),
"edit" => {
let old = args.get("old").and_then(|v| v.as_str()).unwrap_or("");
let new = args.get("new").and_then(|v| v.as_str()).unwrap_or("");
// For edits, scanning old+new together catches stubs in both
return if contains_any(old, STUB_PATTERNS) || contains_any(new, STUB_PATTERNS) {
Some("content contains stub/placeholder pattern; production code must be fully implemented".to_string())
} else if contains_any(new, DENIAL_PATTERNS) {
Some("content contains denial/punt pattern; implement properly instead of skipping".to_string())
} else if contains_any(new, ASSUMPTION_PATTERNS) {
Some("content contains assumption pattern; verify against data instead of guessing".to_string())
} else {
return None;
};
}
_ => "",
};
if contains_any(content, STUB_PATTERNS) {
return Some("content contains stub/placeholder pattern; production code must be fully implemented".to_string());
}
if contains_any(content, DENIAL_PATTERNS) {
return Some("content contains denial/punt pattern; implement properly instead of skipping".to_string());
}
if contains_any(content, ASSUMPTION_PATTERNS) {
return Some("content contains assumption pattern; verify against data instead of guessing".to_string());
}
}
// Bash: exfiltration, sensitive paths, destructive commands
if tool_name == "bash" {
let cmd = args.get("command").and_then(|v| v.as_str()).unwrap_or("");
if cmd.contains("..") {
return Some("path traversal detected in bash command".to_string());
}
// Only check exfiltration for non-standard commands
let is_standard = cmd.trim_start().starts_with("cargo")
|| cmd.trim_start().starts_with("rustc")
|| cmd.trim_start().starts_with("git ")
|| cmd.trim_start().starts_with("ls")
|| cmd.trim_start().starts_with("pwd")
|| cmd.trim_start().starts_with("echo")
|| cmd.trim_start().starts_with("cat")
|| cmd.trim_start().starts_with("find")
|| cmd.trim_start().starts_with("grep")
|| cmd.trim_start().starts_with("test");
if !is_standard {
for pat in EXFIL_PATTERNS {
if cmd.contains(pat) {
return Some(format!("potential data-exfiltration command blocked (matched '{pat}')"));
}
}
}
for pat in SENSITIVE_PATH_PATTERNS {
if cmd.contains(pat) {
return Some(format!("refused to read/write sensitive path '{pat}'"));
}
}
let dangerous = ["rm -rf /", "rm -rf --no-preserve-root", "rm -rf ~",
"rm -fr /", "mkfs.", "dd if=", ":(){", "> /dev/sda",
"chmod -R 000 /", "shutdown ", "poweroff ", "reboot ", "halt "];
for pat in &dangerous {
if cmd.contains(pat) {
return Some(format!("destructive command pattern blocked: {pat}"));
}
}
if contains_any(cmd, STUB_PATTERNS) {
return Some("bash command contains stub pattern".to_string());
}
}
// git_operator: require reason
if tool_name == "git_operator" {
let reason = args.get("reason").and_then(|v| v.as_str()).unwrap_or("");
if reason.trim().len() < MIN_REASON_LEN {
return Some("git_operator requires a non-trivial 'reason' (>= 8 chars)".to_string());
}
}
None
}
/// Check if `text` matches any pattern (case-insensitive substring).
fn contains_any(text: &str, patterns: &[&str]) -> bool {
let lower = text.to_lowercase();
patterns.iter().any(|p| lower.contains(&p.to_lowercase()))
}
/// Build an ASCII tree of the workspace directory structure for the
/// system prompt, so the LLM can see the file layout.
///
/// Flow: for each root, walk using `ignore::WalkBuilder` (respecting
/// `.gitignore` and hidden files) → prefix `[DIR]` for directories →
/// truncate after 1000 entries.
fn generate_workspace_tree(roots: &[std::path::PathBuf]) -> String {
let mut out = String::new();
out.push_str("Current Workspace Directory Structure:\n");
for root in roots {
writeln!(out, "Root: {}", root.display()).unwrap();
let walker = ignore::WalkBuilder::new(root)
.hidden(true)
.git_ignore(true)
.build();
let mut count = 0;
for entry in walker.flatten() {
let path = entry.path();
if let Ok(rel) = path.strip_prefix(root) {
if rel.as_os_str().is_empty() { continue; }
let is_dir = entry.file_type().is_some_and(|ft| ft.is_dir());
let prefix = if is_dir { "[DIR] " } else { " " };
writeln!(out, " {}{}", prefix, rel.display()).unwrap();
count += 1;
if count > 1000 {
out.push_str(" ... (truncated)\n");
break;
}
}
}
}
out
}
fn format_subagent_progress(prefix: &str, text: &str) -> String {
let lines: Vec<&str> = text.lines().filter(|l| !l.trim().is_empty()).collect();
if lines.is_empty() {
format!("{prefix}...")
} else if lines.len() == 1 {
format!("{prefix}: {}", lines[0])
} else {
lines[lines.len() - 2..].join("\n")
}
}
/// Synchronous subagent entry point: run up to `ctx.max_steps` iterations
/// of the LLM tool loop.
///
/// Flow: inject system prompt (with workspace tree if available) → for each
/// step: resolve provider config, build an LLM client, call
/// `chat_with_tools_streaming` (with abort check per SSE event), process
/// tool calls (gated against both the allowlist and Harness-style content
/// safety checks) or collect text output → send `SubagentEvent`s on `tx` →
/// break on first text-only (non-empty) response.
///
/// Why: runs synchronously on a dedicated thread so the main async event
/// loop is not blocked. Tool gating prevents restricted, risky, or
/// malicious/poor-quality tool calls from executing.
///
/// Return: the concatenated text output, or an `anyhow::Error` if the LLM
/// call fails at any step.
#[allow(clippy::too_many_lines)]
pub fn run_subagent(ctx: &SubagentContext, tx: &mpsc::Sender<SubagentEvent>) -> anyhow::Result<String> {
let mut output = String::new();
let mut messages: Vec<ChatMessage> = Vec::new();
// Build system prompt with workspace tree context if we have workspaces,
// giving subagents the same project-awareness as the main agent.
let system_with_context = if ctx.workspaces.is_empty() {
ctx.system_prompt.clone()
} else {
let tree_info = generate_workspace_tree(&ctx.workspaces);
format!("{}\n\n{}", ctx.system_prompt, tree_info)
};
messages.push(ChatMessage::system(system_with_context));
let tool_ctx = crate::tool::ToolCtx::builder()
.session_dir(ctx.session_dir.clone())
.workspaces(ctx.workspaces.clone())
.origin(crate::app::state::types::Origin::SubAgent)
.workflow_findings(ctx.workflow_findings.clone())
.build();
// Build tool list once before the loop
let (tools, tdefs) = build_subagent_tools(&ctx.allowed_tools);
let tdefs_opt: Option<Vec<ToolDef>> = if tdefs.is_empty() { None } else { Some(tdefs) };
// Cache provider config once before the loop instead of re-resolving
// from disk on every step (Settings::load + AppConfig::load each parse
// JSON files, and the config cannot change between steps).
let (api_key, model, base_url, provider) = resolve_provider_config();
// Fail fast on a missing key instead of sending a doomed request: an
// empty api_key still reaches the network (base_url falls back to a
// default endpoint), so without this check every step burns a full
// 10-retry timeout/backoff cycle against a server that was never going
// to authenticate, and the real cause (no key configured) never
// surfaces past a buried WARN log.
if let Err(error) = require_api_key(&api_key, &provider) {
let error = error.to_string();
let _ = tx.blocking_send(SubagentEvent::StepFailed { step: 0, error: error.clone() });
anyhow::bail!(error);
}
let client = crate::service::provider::LlmClient::new(api_key, model, base_url);
for step in 0..ctx.max_steps {
// Check abort flag before each LLM call so a stuck subagent can
// be cancelled from the parent (mirrors main agent behaviour).
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".to_string(),
});
anyhow::bail!("subagent aborted by parent at step {step}");
}
let tx_clone = tx.clone();
let mut current_thinking = String::new();
let mut current_token = String::new();
let mut step_usage: Option<(u64, u64)> = None;
// Use streaming API so the abort flag is checked per SSE event,
// making the subagent responsive to cancellation even during an
// LLM call (non-streaming would block for 10-30s unchecked).
let stream_result = client.chat_with_tools_streaming(
&messages,
tdefs_opt.clone(),
Some(0.7),
Some(4096),
|event| -> bool {
// Check abort on every SSE event for responsive cancellation.
if ctx.abort_flag.as_ref().is_some_and(|f| f.load(std::sync::atomic::Ordering::SeqCst)) {
return false; // signals provider to abort
}
match event {
crate::app::runtime::stream::StreamEvent::Reasoning(text) => {
current_thinking.push_str(text);
let prog = format_subagent_progress("thinking", &current_thinking);
let _ = tx_clone.blocking_send(SubagentEvent::Progress(prog));
}
crate::app::runtime::stream::StreamEvent::Token(text) => {
current_token.push_str(text);
let prog = format_subagent_progress("replying", &current_token);
let _ = tx_clone.blocking_send(SubagentEvent::Progress(prog));
}
crate::app::runtime::stream::StreamEvent::Usage { prompt_tokens, completion_tokens, .. } => {
// Capture usage so the drain thread can route it
// to the parent's `UsageStats::review_tokens`.
// Last writer wins — providers send exactly one
// Usage event per streaming call.
step_usage = Some((*prompt_tokens, *completion_tokens));
}
_ => {}
}
true
},
);
let (response, returned_usage) = match stream_result {
Ok(result) => result,
Err(e) => {
let is_abort = ctx.abort_flag.as_ref().is_some_and(|f| f.load(std::sync::atomic::Ordering::SeqCst))
|| e.to_string().contains("aborted");
let _ = tx.blocking_send(SubagentEvent::StepFailed {
step,
error: if is_abort {
"subagent aborted by user".to_string()
} else {
e.to_string()
},
});
if is_abort {
anyhow::bail!("subagent aborted by parent at step {step}");
}
// No non-streaming fallback — API must support streaming.
// Non-streaming calls block for up to 1 min without checking
// abort_flag, making cancellation unresponsive.
anyhow::bail!("subagent call failed at step {step}: {e}");
}
};
// Emit the token usage from this streaming call so the parent's
// drain thread can accumulate it and update the Usage panel.
// Without this, the Usage panel always shows zeros because the
// subagent never tells the parent about the tokens consumed.
let (mut tok_in, mut tok_out) = returned_usage.unwrap_or((0, 0));
if tok_in == 0 {
let prompt_chars: usize = messages.iter()
.filter_map(|m| m.content.as_deref())
.map(str::len)
.sum();
tok_in = (prompt_chars / 4).max(1) as u64;
}
if tok_out == 0 {
let response_chars = response.content.as_deref().map_or(0, str::len);
tok_out = (response_chars / 4).max(1) as u64;
}
let _ = tx.blocking_send(SubagentEvent::Usage {
tokens_in: tok_in,
tokens_out: tok_out,
});
let has_tool_calls = response.tool_calls.is_some()
&& response.tool_calls.as_ref().is_some_and(|tc| !tc.is_empty());
let content = response.content.clone().unwrap_or_default();
// Emit thinking/reasoning text as StepCompleted so the parent's
// drain thread can show it as progress instead of just the tool name.
if !content.is_empty() {
let _ = tx.blocking_send(SubagentEvent::StepCompleted {
output: content.clone(),
});
}
if has_tool_calls {
let tool_calls = response.tool_calls.clone().unwrap_or_default();
// Push the assistant message with tool_calls into the conversation
messages.push(response);
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) => {
let is_edit = tool_name == "write" || tool_name == "edit";
if is_edit && !tool_call.id.is_empty() {
if let Ok(conn) = crate::model::msglog::open_or_create(&ctx.session_dir) {
let path = args.get("path").and_then(|v| v.as_str()).unwrap_or("");
if let Ok(abs_path) = crate::tool::resolve_path(&tool_ctx_ref.workspaces, path) {
if let Ok(bytes) = std::fs::read(&abs_path) {
let session_id = ctx.session_dir
.file_name()
.and_then(|n| n.to_str())
.unwrap_or("unknown");
let _ = crate::model::msglog::store_blob(
&conn, session_id, &tool_call.id, &bytes, None,
);
}
}
}
}
let run_res = tool.run(tool_ctx_ref, &args);
if is_edit && run_res.is_ok() {
let reason = args
.get("reason")
.and_then(|v| v.as_str())
.unwrap_or("unnamed");
let path = args
.get("path")
.and_then(|v| v.as_str())
.unwrap_or("unknown");
let content_sha256 = {
let content = args.get("content").or_else(|| args.get("new"));
let hash = sha2::Sha256::digest(
content.and_then(|v| v.as_str()).unwrap_or("").as_bytes(),
);
hex::encode(hash)
};
let bytes_delta = if tool_name == "write" {
args.get("content")
.and_then(|v| v.as_str())
.map_or(0, |s| s.len() as i64)
} else {
let old = args.get("old").and_then(|v| v.as_str()).unwrap_or("");
let new = args.get("new").and_then(|v| v.as_str()).unwrap_or("");
(new.len() as i64 - old.len() as i64).abs()
};
let session_id = ctx.session_dir
.file_name()
.and_then(|n| n.to_str())
.unwrap_or("unknown")
.to_string();
let entry = crate::model::editlog::EditLogEntry {
ts: chrono::Utc::now().timestamp_millis(),
tool: tool_name.clone(),
path: path.to_string(),
reason: reason.to_string(),
content_sha256,
bytes_delta,
origin: tool_ctx_ref.origin.tag(),
session_id,
};
let mut el = crate::model::editlog::EditLog::new(&ctx.session_dir);
el.append(entry).ok();
}
run_res
}
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 _ = tx.blocking_send(SubagentEvent::ToolCall {
tool: tool_name.clone(),
args: args.clone(),
});
match result {
Ok(output_text) => {
messages.push(ChatMessage::tool_result(tool_call.id.clone(), output_text.clone()));
let _ = tx.blocking_send(SubagentEvent::ToolResult {
tool: tool_name.clone(),
args: args.clone(),
});
let is_readonly = tool_name == "read"
|| tool_name == "view_file"
|| tool_name == "grep"
|| tool_name == "grep_search"
|| tool_name == "glob"
|| tool_name == "dir_list"
|| tool_name == "list_dir";
if is_readonly {
if let Some(ref findings) = ctx.workflow_findings {
if let Ok(mut f) = findings.lock() {
let args_json = serde_json::to_string(&args).unwrap_or_default();
let mut shared_text = output_text;
if shared_text.len() > 50_000 {
shared_text.truncate(50_000);
shared_text.push_str("\n...[truncated]");
}
f.push(format!("[Auto-Shared] Sibling drone executed '{tool_name}' with args {args_json}:\n{shared_text}"));
}
}
}
}
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 {
tool: tool_name.clone(),
args: args.clone(),
});
}
}
}
} else {
// Text-only response — accumulate and finish
if !content.is_empty() {
output.push_str(&content);
output.push('\n');
}
let _ = tx.blocking_send(SubagentEvent::StepCompleted {
output: content.clone(),
});
// Break only when we got real content; empty means something went wrong
if !content.is_empty() {
break;
}
}
}
let _ = tx.blocking_send(SubagentEvent::Completed);
Ok(output)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn require_api_key_rejects_empty_key_with_provider_named_in_message() {
let err = require_api_key("", "claude").unwrap_err();
assert!(err.to_string().contains("claude"));
}
#[test]
fn require_api_key_accepts_non_empty_key() {
assert!(require_api_key("sk-live-abc123", "claude").is_ok());
}
}
@@ -0,0 +1,40 @@
//! Event variants that a running subagent can emit to its parent via the
//! shared mpsc channel.
use serde_json::Value;
/// Progress and outcome events emitted by `run_subagent` as it processes
/// LLM responses and tool calls.
#[derive(Debug, Clone)]
pub enum SubagentEvent {
StepCompleted {
output: String,
},
StepFailed {
step: usize,
error: String,
},
Completed,
ToolCall {
tool: String,
args: Value,
},
ToolResult {
tool: String,
args: Value,
},
Progress(String),
/// Token usage reported by the LLM after one streaming call inside the
/// subagent. The drain thread accumulates these across all steps and
/// forwards the total to the parent's `TurnEvent::ReviewUsage` handler
/// so the Usage panel can split "main" tokens from "self-learning"
/// tokens (review, test-gen, arch-review, security-review, etc.).
///
/// Why a separate variant instead of folding into `Completed`: usage
/// is reported per-step, so the parent can update the running total
/// incrementally rather than waiting for the whole subagent run to
/// finish. The drain thread still aggregates before forwarding.
Usage {
tokens_in: u64,
tokens_out: u64,
},
}
@@ -0,0 +1,8 @@
//! Subagent management: spawning, context building, engine loop, and
//! progress events.
pub mod auto;
pub mod context;
pub mod division;
pub mod engine;
pub mod event;
pub mod spawn;
@@ -0,0 +1,56 @@
//! `AgentDefinition` -- declarative specification for instantiating a
//! subagent from workflow scripts or programmatic calls.
use serde::{Deserialize, Serialize};
/// Declarative specification for instantiating a subagent: name, role,
/// optional system prompt, allowed tools, step budget, and temperature.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct AgentDefinition {
pub name: String,
pub role: String,
pub system_prompt: Option<String>,
pub allowed_tools: Option<Vec<String>>,
pub max_steps: Option<usize>,
pub temperature: Option<f32>,
}
impl AgentDefinition {
/// Create an agent definition with the required name and role; all
/// optional fields start as `None`.
pub fn new(name: String, role: String) -> Self {
AgentDefinition {
name,
role,
system_prompt: None,
allowed_tools: None,
max_steps: None,
temperature: None,
}
}
/// Builder method: set the system prompt for this agent.
pub fn with_system_prompt(mut self, prompt: String) -> Self {
self.system_prompt = Some(prompt);
self
}
/// Builder method: set the allowed tool list for this agent.
pub fn with_allowed_tools(mut self, tools: Vec<String>) -> Self {
self.allowed_tools = Some(tools);
self
}
/// Builder method: set the maximum step count for this agent.
#[allow(dead_code)]
pub fn with_max_steps(mut self, steps: usize) -> Self {
self.max_steps = Some(steps);
self
}
/// Builder method: set the temperature for this agent.
#[allow(dead_code)]
pub fn with_temperature(mut self, temp: f32) -> Self {
self.temperature = Some(temp);
self
}
}