vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(#2351): scan error result raw so prompt-too-long in result field is detected

Browse source
This commit is contained in:
damocles 2026-07-10 16:37:36 +02:00
commit 9aaf8b93fb
1 changed files with 43 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

55
hive-claude/src/classify.rs
View file

@ -75,18 +75,29 @@ impl Sentinels {
if matches!(ty, Some("assistant" | "user")) {
return;
}
// The terminal `result` event carries the model's final answer in its
// `result` field — model-authored text, same trust level as an
// assistant message. A marker quoted there (e.g. the model explaining
// *this* code, or echoing an error string back) would falsely trip a
// sentinel and needlessly kill/downgrade the turn. So for a `result`
// event, scan the control fields (`subtype` / `error` / `is_error`)
// but scrub the model-authored `result` field first; a genuine
// prompt-too-long/auth/session signal lives in those control fields
// (it's emitted *instead of* a successful model answer), never in the
// `result` text. Other control events (`error` / `system`) are
// claude-authored end to end, so they scan raw.
if ty == Some("result") {
// A `result` event's `result` field is the model's final answer on a
// SUCCESSFUL turn — model-authored text, same trust level as an
// assistant message. A marker quoted there (the model explaining *this*
// code, or echoing an error string back) would falsely trip a sentinel
// and needlessly kill/downgrade the turn, so for a *success* result we
// scrub `result` before scanning and rely on the control fields.
//
// But on an ERROR result the same `result` field carries claude-code's
// OWN failure text — a genuine "Prompt is too long" (an API 400) lands
// there, emitted *instead of* a model answer. The model can't forge
// `is_error` / a non-`success` subtype (the CLI sets them from the real
// outcome), so an error result is claude-authored end to end and is
// safe to scan raw. Scrubbing it unconditionally (the original
// result-scrub fix) blinded prompt-too-long / auth detection — hence
// keying the scrub on success only. Other control events are
// claude-authored throughout, so they also scan raw.
let error_result = ty == Some("result")
&& (event.get("is_error").and_then(serde_json::Value::as_bool) == Some(true)
|| event
.get("subtype")
.and_then(serde_json::Value::as_str)
.is_some_and(|s| s != "success"));
if ty == Some("result") && !error_result {
let mut scrubbed = event.clone();
if let Some(obj) = scrubbed.as_object_mut() {
obj.remove("result");
@ -164,6 +175,26 @@ mod tests {
assert!(matches!(s.soft_error(), Some(Error::PromptTooLong)));
}
#[test]
fn prompt_too_long_in_error_result_field_is_detected() {
// Regression guard: claude-code reports a genuine "Prompt is too long"
// (API 400) in the `result` field of an ERROR result event. The earlier
// result-scrub blinded this by stripping `result` unconditionally. An
// error result is claude-authored (the model can't forge `is_error`),
// so it must be scanned raw.
for raw in [
r#"{"type":"result","subtype":"error_during_execution","is_error":true,"result":"API Error: 400 Prompt is too long"}"#,
r#"{"type":"result","subtype":"success","is_error":true,"result":"Prompt is too long"}"#,
] {
let s = Sentinels::default();
s.scan_stdout_json(&json(raw), raw);
assert!(
matches!(s.soft_error(), Some(Error::PromptTooLong)),
"prompt-too-long in an error result's `result` field must be detected: {raw}"
);
}
}
#[test]
fn result_field_model_text_quoting_marker_is_ignored() {
// The terminal `result` event's `result` field is the model's final