feat(13-01): Rust assistant spine — one curated tool, one backend, one RPC surface

D-01/D-02/D-06 tracer slice: a new crate::assistant module (CallerScope,
PermissionCategory, ToolExecCtx, chat()) runs a multi-turn tool-calling loop
(run_loop/execute_tool, MAX_TURNS=8) against a curated single-tool registry
(system_disk_status, hand-written JSON Schema — no schemars) via a Claude
Messages API backend. execute_tool is the single choke point: unknown tools
are refused not ignored, D-16 category grants are re-checked even though the
system prompt already omits ungranted tools, and every real tool dispatches
through the SAME handle_system_disk_status RPC handler every other
authenticated caller uses (assistant_dispatch_tool bridge in
api/rpc/assistant_chat.rs) — never an AI-only backdoor.

assistant.chat is registered in dispatcher.rs as a single guarded
`m if m.starts_with("assistant.")` arm reached only after the existing
session-cookie + CSRF + role.can_access() gate in api/rpc/mod.rs — asserted
directly by assistant_methods_require_session against the live
UNAUTHENTICATED_METHODS list (visibility only widened to pub(crate) for that
assertion; the list's contents are untouched, per the Phase-10 hard
constraint).

Key read from data_dir/secrets/claude-api-key — the same path
mesh/rpc/mesh/assistant.rs already probes — never a second key location.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
archipelago
2026-08-03 14:37:16 -04:00
co-authored by Claude Opus 5
parent 15774d266f
commit fe6ccff73c
11 changed files with 924 additions and 2 deletions
+237
View File
@@ -0,0 +1,237 @@
//! The multi-turn tool-calling loop (D-01/D-02). No analog exists elsewhere
//! in this codebase — this is the first tool-calling agent loop ever
//! written here (confirmed by 13-RESEARCH.md/13-AI-SPEC.md); built directly
//! from `13-AI-SPEC.md` §3/§4's sketch.
//!
//! Concurrency discipline inherited from `mesh/listener/assist.rs`'s own
//! doc comment ("Spawned off the radio loop so it never blocks"): never
//! hold a shared lock across a `.await` that can block for human-response
//! time. `execute_tool` below holds no lock at all in this tracer — there
//! is nothing yet to hold one across (13-08's confirm gate is what
//! introduces that discipline requirement for real).
use anyhow::Result;
use super::backends::{Backend, BackendTurn};
use super::tools::{ChatMessage, Role, ToolCall, ToolResult};
use super::tools::ToolDef;
use super::ToolExecCtx;
/// Hard stop — a looping model must never spin unbounded (D-05).
pub const MAX_TURNS: usize = 8;
pub async fn run_loop(
backend: &dyn Backend,
system: &str,
tools: &[ToolDef],
mut history: Vec<ChatMessage>,
ctx: &ToolExecCtx,
) -> Result<String> {
for _ in 0..MAX_TURNS {
match backend.send(system, tools, &history).await? {
BackendTurn::Text(answer) => return Ok(answer),
BackendTurn::ToolCalls(calls) => {
history.push(ChatMessage {
role: Role::Assistant,
text: None,
tool_calls: calls.clone(),
tool_results: vec![],
});
let mut results = Vec::with_capacity(calls.len());
for call in &calls {
results.push(execute_tool(call, ctx).await);
}
history.push(ChatMessage {
role: Role::Tool,
text: None,
tool_calls: vec![],
tool_results: results,
});
}
}
}
anyhow::bail!("assistant loop exceeded MAX_TURNS without a final answer — stopping, not looping forever")
}
/// The single choke point every tool call passes through, regardless of
/// which backend produced it. Enforces, in order: D-06 (curated allowlist —
/// unknown names are refused, never silently ignored), D-16 (default-closed
/// category grants — re-checked here even though the system prompt already
/// omits ungranted tools; never trust that as the only enforcement layer),
/// schema validation (never coerce, never guess), and D-07 (every
/// destructive tool suspends for confirmation — 13-08 fills that branch in;
/// there are no destructive tools registered yet, so it is unreachable
/// today).
async fn execute_tool(call: &ToolCall, ctx: &ToolExecCtx) -> ToolResult {
let Some(tool) = ctx.registry.get(&call.name) else {
return ToolResult {
call_id: call.id.clone(),
is_error: true,
content: format!("no such tool: {}", call.name),
};
};
if !ctx.caller.granted_categories().contains(&tool.category) {
return ToolResult {
call_id: call.id.clone(),
is_error: true,
content: "not permitted — this category is not granted".to_string(),
};
}
if let Err(e) = tool.validate(&call.arguments) {
return ToolResult {
call_id: call.id.clone(),
is_error: true,
content: format!("invalid arguments: {e}"),
};
}
if tool.destructive {
return ToolResult {
call_id: call.id.clone(),
is_error: true,
content: "destructive tool execution is not yet implemented".to_string(),
};
}
match call.name.as_str() {
// Dispatches to the SAME RpcHandler method every other authenticated
// caller uses (no AI-only backdoor) — see `assistant_dispatch_tool`
// in `api/rpc/assistant_chat.rs` for why this bridge exists.
"system_disk_status" => match ctx
.handler
.assistant_dispatch_tool("system.disk-status")
.await
{
Ok(v) => ToolResult {
call_id: call.id.clone(),
is_error: false,
content: v.to_string(),
},
Err(e) => ToolResult {
call_id: call.id.clone(),
is_error: true,
content: format!("tool execution failed: {e}"),
},
},
other => ToolResult {
call_id: call.id.clone(),
is_error: true,
content: format!("no execution wired for tool: {other}"),
},
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::assistant::backends::scripted::ScriptedBackend;
use crate::assistant::tools::{registry, system_disk_status_tool};
use crate::assistant::{CallerScope, PermissionCategory};
use crate::api::rpc::RpcHandler;
use serde_json::json;
use std::sync::Arc;
/// A minimal but real `RpcHandler` for tests: a fresh temp `data_dir`
/// (no `/var/lib/archipelago` writes), no orchestrator (container RPCs
/// aren't exercised here), matching the doc comment on `orchestrator`
/// that this is exactly why the field is `Option`.
async fn test_rpc_handler() -> (Arc<RpcHandler>, tempfile::TempDir) {
let tmp = tempfile::tempdir().expect("tempdir");
let mut config = crate::config::Config::default();
config.data_dir = tmp.path().to_path_buf();
let state_manager = Arc::new(crate::state::StateManager::new());
let metrics_store = Arc::new(crate::monitoring::MetricsStore::new());
let session_store =
crate::session::SessionStore::new_for_tests(tmp.path().join("sessions.json"));
let handler = RpcHandler::new(
config,
state_manager,
metrics_store,
session_store,
None,
None,
)
.await
.expect("RpcHandler::new");
(Arc::new(handler), tmp)
}
fn local_operator_ctx(handler: Arc<RpcHandler>) -> ToolExecCtx {
ToolExecCtx {
registry: registry(),
caller: CallerScope::LocalOperator {
session_id: "test-session".to_string(),
},
handler,
}
}
#[tokio::test]
async fn disk_status_tool_executes() {
let (handler, _tmp) = test_rpc_handler().await;
// The real figures the tool path returns must match what the SAME
// handler returns when dispatched directly — proving `execute_tool`
// is not a parallel, AI-only code path.
let direct = handler
.assistant_dispatch_tool("system.disk-status")
.await
.expect("direct dispatch");
let ctx = local_operator_ctx(handler.clone());
let call = ToolCall {
id: "call-1".to_string(),
name: "system_disk_status".to_string(),
arguments: json!({}),
};
let result = execute_tool(&call, &ctx).await;
assert!(!result.is_error, "tool call errored: {}", result.content);
assert_eq!(result.content, direct.to_string());
assert!(result.content.contains("total_bytes"));
// Exercise the whole loop: a ScriptedBackend that names the tool,
// then answers — proving the real figures reached the final answer
// path (the answer itself is the second scripted turn, matching
// AI-SPEC's run_loop shape; the tool result that fed into it is
// asserted above).
let backend = ScriptedBackend::new(vec![
BackendTurn::ToolCalls(vec![call.clone()]),
BackendTurn::Text("Disk space report generated.".to_string()),
]);
let tools_list = vec![system_disk_status_tool()];
let answer = run_loop(&backend, "system prompt", &tools_list, vec![], &ctx)
.await
.expect("run_loop");
assert_eq!(answer, "Disk space report generated.");
}
#[tokio::test]
async fn unknown_tool_is_refused_not_ignored() {
let (handler, _tmp) = test_rpc_handler().await;
let ctx = local_operator_ctx(handler);
let call = ToolCall {
id: "call-1".to_string(),
name: "delete_everything".to_string(),
arguments: json!({}),
};
let result = execute_tool(&call, &ctx).await;
assert!(result.is_error);
assert!(result.content.contains("no such tool"), "{}", result.content);
}
/// Phase-10 hard constraint: `assistant.*` must never be reachable
/// unauthenticated. Asserted directly against the live list, not
/// assumed.
#[test]
fn assistant_methods_require_session() {
let has_assistant_method = crate::api::rpc::UNAUTHENTICATED_METHODS
.iter()
.any(|m| m.starts_with("assistant."));
assert!(
!has_assistant_method,
"assistant.* must never be added to UNAUTHENTICATED_METHODS (Phase-10 hard constraint)"
);
}
}