feat(web): show error details for failed tool calls (#490)

* feat(web): show error details and input params for failed tool calls

Failed tool calls in the gateway UI previously showed only a red X icon
with an empty expandable body. This change:

- Adds optional `error` and `parameters` fields to `ToolCompleted` SSE
  events so the browser receives failure details in real-time
- Auto-expands failed tool cards to make errors immediately visible
- Adds `StatusUpdate::tool_completed()` constructor that centralizes
  the 5 duplicated construction sites and applies `redact_params()` to
  prevent sensitive values (e.g. secret_save's "value" param) from
  leaking through SSE broadcasts
- Adds `sensitive_params()` trait method to `Tool` for declaring which
  parameters must be redacted before logging, hooks, and UI display
- Adds `redact_params()` utility and wires it through hooks, approvals,
  ActionRecord storage, and debug logs in dispatcher/worker
- Adds `SecretListTool` and `SecretDeleteTool` for LLM-driven secret
  management (values never returned, only names/metadata)
- Fixes auth flow: setup-only extensions show configure modal instead
  of OAuth card; auth_completed SSE dismisses both UI paths
- CI: release workflow creates PR instead of pushing directly to main
- Registry: MissingChecksum error enables source fallback for
  bootstrapping when checksums haven't been populated yet

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* style: apply cargo fmt

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: keep original params in PendingApproval for execution, redact only for display

Address two PR review comments:

1. execute_chat_tool_standalone now redacts sensitive params before logging,
   matching the pattern already used in worker.rs.

2. PendingApproval previously stored redacted parameters, which meant
   approved tool calls received "[REDACTED]" instead of the actual values.
   Add a display_parameters field for UI/logs and keep parameters as the
   original values used for execution.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: address PR review comments

- worker.rs: redact sensitive params before BeforeToolCall hook, matching
  dispatcher.rs — hooks in the autonomous job path now receive redacted
  params instead of raw values
- registry.rs: fix docstring for register_secrets_tools (list, delete,
  not save/list/delete — no SecretSaveTool is registered)
- app.js: fix double toast/loadExtensions in submitConfigureModal —
  for non-OAuth success the auth_completed SSE already handles both,
  so skip them in the HTTP response handler to avoid duplicates

[skip-regression-check]

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
This commit is contained in:
Henry Park
2026-03-04 15:38:26 -08:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 13697976db
commit 902492bcdb
23 changed files with 704 additions and 69 deletions
+26 -15
View File
@@ -21,6 +21,7 @@ use crate::channels::{IncomingMessage, StatusUpdate};
use crate::context::JobContext;
use crate::error::Error;
use crate::llm::ChatMessage;
use crate::tools::redact_params;
impl Agent {
/// Hydrate a historical thread from DB into memory if not already present.
@@ -357,7 +358,7 @@ impl Agent {
let request_id = pending.request_id;
let tool_name = pending.tool_name.clone();
let description = pending.description.clone();
let parameters = pending.parameters.clone();
let parameters = pending.display_parameters.clone();
thread.await_approval(pending);
let _ = self
.channels
@@ -751,14 +752,17 @@ impl Agent {
.execute_chat_tool(&pending.tool_name, &pending.parameters, &job_ctx)
.await;
let tool_ref = self.tools().get(&pending.tool_name).await;
let _ = self
.channels
.send_status(
&message.channel,
StatusUpdate::ToolCompleted {
name: pending.tool_name.clone(),
success: tool_result.is_ok(),
},
StatusUpdate::tool_completed(
pending.tool_name.clone(),
&tool_result,
&pending.display_parameters,
tool_ref.as_deref(),
),
&message.metadata,
)
.await;
@@ -908,14 +912,17 @@ impl Agent {
.execute_chat_tool(&tc.name, &tc.arguments, &job_ctx)
.await;
let deferred_tool = self.tools().get(&tc.name).await;
let _ = self
.channels
.send_status(
&message.channel,
StatusUpdate::ToolCompleted {
name: tc.name.clone(),
success: result.is_ok(),
},
StatusUpdate::tool_completed(
tc.name.clone(),
&result,
&tc.arguments,
deferred_tool.as_deref(),
),
&message.metadata,
)
.await;
@@ -957,13 +964,16 @@ impl Agent {
)
.await;
let par_tool = tools.get(&tc.name).await;
let _ = channels
.send_status(
&channel,
StatusUpdate::ToolCompleted {
name: tc.name.clone(),
success: result.is_ok(),
},
StatusUpdate::tool_completed(
tc.name.clone(),
&result,
&tc.arguments,
par_tool.as_deref(),
),
&metadata,
)
.await;
@@ -1086,6 +1096,7 @@ impl Agent {
request_id: Uuid::new_v4(),
tool_name: tc.name.clone(),
parameters: tc.arguments.clone(),
display_parameters: redact_params(&tc.arguments, tool.sensitive_params()),
description: tool.description().to_string(),
tool_call_id: tc.id.clone(),
context_messages: context_messages.clone(),
@@ -1095,7 +1106,7 @@ impl Agent {
let request_id = new_pending.request_id;
let tool_name = new_pending.tool_name.clone();
let description = new_pending.description.clone();
let parameters = new_pending.parameters.clone();
let parameters = new_pending.display_parameters.clone();
{
let mut sess = session.lock().await;
@@ -1162,7 +1173,7 @@ impl Agent {
let request_id = new_pending.request_id;
let tool_name = new_pending.tool_name.clone();
let description = new_pending.description.clone();
let parameters = new_pending.parameters.clone();
let parameters = new_pending.display_parameters.clone();
thread.await_approval(new_pending);
let _ = self
.channels