fix: retry on transient LLM response body truncation
CI / test (pull_request) Successful in 15s
CI / review (/openai/v1, gpt-4.1, gpt41, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 25s
CI / review (/openai/v1, gpt-4.1-mini, gpt41-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 29s
CI / review (/anthropic/v1, claude-sonnet-4-6, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Successful in 49s
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 50s
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m15s
CI / review (/openai/v1, gpt-5-mini, gpt5-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 52s

Addresses intermittent 'unexpected end of JSON input' failures where the
LLM response body is truncated in transit between the proxy and client.

Root cause: network-level truncation where io.ReadAll returns partial data
(observed in 3/50 CI runs through HAI proxy). The response body reading
was already using io.ReadAll correctly, but transient network issues
between the proxy and client can still cause partial reads.

Changes:
- Add Content-Length validation in doRequest: detect when fewer bytes
  arrive than the server declared, triggering a retry
- Add retry logic in Complete: retries once on retryable errors (body
  read failures, content-length mismatches) with a 500ms backoff
- Add parse-level retry in main: if ParseResponse fails, re-requests
  from the LLM once before giving up (defensive, since retries always
  succeed per issue evidence)
- Improve ParseResponse error diagnostics: log raw vs cleaned lengths
  and a preview of the cleaned content to aid future debugging

Does NOT retry on API errors (4xx/5xx) or structural issues — only
transient body read problems.

Closes #47
This commit is contained in:
claw
2026-05-07 00:44:32 -07:00
parent cabbb5a55a
commit db479d0ff4
4 changed files with 216 additions and 18 deletions
+28 -12
View File
@@ -254,25 +254,41 @@ func main() {
slog.Warn("context trimmed to fit budget", "trimmed", budgetResult.Trimmed)
}
// Step 8: Call LLM
// Step 8: Call LLM (with retry on parse failure)
slog.Info("sending request to LLM", "model", *llmModel)
messages := []llm.Message{
{Role: "system", Content: budgetResult.SystemPrompt},
{Role: "user", Content: budgetResult.UserPrompt},
}
response, err := llmClient.Complete(ctx, messages)
if err != nil {
slog.Error("LLM request failed", "model", *llmModel, "error", err)
os.Exit(1)
}
slog.Info("LLM response received", "bytes", len(response))
var response string
var result *review.ReviewResult
for attempt := 1; attempt <= 2; attempt++ {
if attempt > 1 {
slog.Warn("retrying LLM request after parse failure", "attempt", attempt)
time.Sleep(time.Second)
}
// Step 9: Parse response
result, err := review.ParseResponse(response)
if err != nil {
slog.Error("failed to parse LLM response", "error", err)
os.Exit(1)
response, err = llmClient.Complete(ctx, messages)
if err != nil {
slog.Error("LLM request failed", "model", *llmModel, "error", err, "attempt", attempt)
if attempt == 2 {
os.Exit(1)
}
continue
}
slog.Info("LLM response received", "bytes", len(response), "attempt", attempt)
// Step 9: Parse response
result, err = review.ParseResponse(response)
if err != nil {
slog.Error("failed to parse LLM response", "error", err, "attempt", attempt)
if attempt == 2 {
os.Exit(1)
}
continue
}
break
}
slog.Info("review parsed", "verdict", result.Verdict, "findings", len(result.Findings))