fix(history): exclude non-interactive (SDK-driven) transcripts from Past Sessions

Automated tools (CI review bots, etc.) invoke Claude Code via the SDK
and write their transcripts into the same ~/.claude/projects tree as
real interactive sessions, but were never something a user can resume
into -- no PTY, no running process. Their one-shot review prompts also
embed the full diff inline as a single message, often exceeding the
16KB head / 32KB tail windows this scanner reads, so they cluttered
Past Sessions two ways: as blank rows when the huge message couldn't
be parsed, or as N identical "Review this change for security
vulnerabilities..." rows when it could.

Claude Code stamps `entrypoint` on its own message records ('cli' for
a real interactive session, e.g. 'sdk-py' for an SDK invocation).
Exclude any transcript whose entrypoint isn't 'cli' from the history
list entirely, checked last so it reuses whatever head/tail the prompt
extraction already read. Missing entrypoint (older transcripts) reads
as interactive -- fail open, matching every other gating check in this
codebase. Shared by /api/history/sessions and /api/sessions/unified,
since both call the same scanProjectDir().

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
timkjr
2026-08-05 11:11:18 -05:00
co-authored by Claude Sonnet 5
parent e2a644997e
commit e888c65c52
2 changed files with 85 additions and 0 deletions
+40
View File
@@ -2456,6 +2456,30 @@ export function registerSessionRoutes(
return undefined;
}
/**
* The `entrypoint` field Claude Code stamps on its own message records:
* 'cli' for a real interactive session, something else (e.g. 'sdk-py') for
* an SDK/automated invocation. Used to exclude non-interactive transcripts
* (CI review bots, etc.) from the resumable history list — they were never
* something a user can resume into.
*/
function extractTranscriptEntrypoint(text: string): string | undefined {
let start = 0;
while (start < text.length) {
const end = text.indexOf('\n', start);
const line = end === -1 ? text.slice(start) : text.slice(start, end);
start = end === -1 ? text.length : end + 1;
if (!line.includes('"entrypoint"')) continue;
try {
const entry = JSON.parse(line);
if (typeof entry.entrypoint === 'string') return entry.entrypoint;
} catch {
// Malformed/truncated line — skip
}
}
return undefined;
}
/**
* Extract the text of the LAST user message from a JSONL transcript chunk
* (COD-145). Mirrors `extractFirstUserPrompt` exactly — same user-message
@@ -2763,6 +2787,22 @@ export function registerSessionRoutes(
const lastPrompt =
(tail ? extractLastUserPrompt(tail) : undefined) ?? (head ? extractLastUserPrompt(head) : undefined);
// Automated/SDK-driven invocations (CI review bots, etc.) write transcripts
// into the same ~/.claude/projects tree as interactive sessions but were
// never something a user can resume into — no PTY, no running process, and
// their "conversation" is typically a single one-shot prompt (often with a
// full diff embedded, which is exactly why it dwarfs this scanner's read
// windows and shows up above as blank or as an identical boilerplate
// sentence across many rows). Checked last, so it reuses whatever `head`/
// `tail` the prompt extraction above already read rather than triggering
// an extra file read. Missing entrypoint (older transcripts) reads as
// interactive — fail open, matching every other gating check in this
// codebase.
const entrypoint =
(head ? extractTranscriptEntrypoint(head) : undefined) ??
(tail ? extractTranscriptEntrypoint(tail) : undefined);
if (entrypoint && entrypoint !== 'cli') continue;
out.push({
sessionId,
workingDir,