feat: auto-compact and auto-clear from the statusLine context size

Both checks compared getTotalTokens() against the threshold. That
counter leaves out cache reads, so it stays far below the real context,
and the 500k cap ruled out thresholds on a 1M window.

POST /api/status-telemetry now hands context_window.total_input_tokens
and context_window_size to Session.noteContextReport(), which runs both
checks. The decision is a pure function, decideAutoThreshold(). The
counter stays the fallback when no report has arrived.

After a /compact or /clear the pre-command report is ignored by value,
since it stays the newest number until the command finishes. The first
differing report came later, so a swallowed command fires again instead
of locking the automation off. A counter summed from JSON usage never
drops after a compact, so it counts from its value at the last one. The
pane parser's counter is absolute and only moves past its high, so a
move clears that baseline and it fires as it did before.

Thresholds go up to the reported window, 1M when unknown, and a higher
value stops at the window. MAX_SESSION_TOKENS follows, and the pane
parser's M-suffix guard checks that cap instead of a fixed 0.5.

Refs #585

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
RandalixandClaude Opus 5.5 committed 2026-11-06 13:19:36 +01:00
1 parent fc25bf5f83
commit 84a6896cae
16 files changed
+579 -45

No files matched your search

+21 -6
View File
@@ -153,7 +153,7 @@ import {
buildMuxAttachEnv,
buildShellEnv,
} from './session-cli-builder.js';
import { SessionAutoOps } from './session-auto-ops.js';
import { SessionAutoOps, type ContextReport } from './session-auto-ops.js';
import { detectUsageLimitPause } from './usage-limit-patterns.js';
import { SessionTaskCache } from './session-task-cache.js';
import { InteractivePtyExitBreaker } from './session-pty-exit-breaker.js';
@@ -663,6 +663,7 @@ export class Session extends EventEmitter {
private _watching: string | null = null;
/** Last `prompt_cache` report from the statusline exporter; null until Claude sends one. */
private _promptCache: PromptCacheStatus | null = null;
private _contextReport: ContextReport | null = null;
/** Prompt-cache keep-warm opt-in; undefined = follow the app-wide default. Persisted. */
private _keepWarmEnabled: boolean | undefined;
/** Last status the keep-warm service published for this session; ephemeral. */
@@ -1272,6 +1273,7 @@ export class Session extends EventEmitter {
isWorking: () => this._isWorking,
isStopped: () => this._isStopped,
getTotalTokens: () => this._totalInputTokens + this._totalOutputTokens,
getContextReport: () => this._contextReport,
getSessionId: () => this.id,
});
this._autoOps.on('autoCompact', (data) => this.emit('autoCompact', data));
@@ -1467,6 +1469,7 @@ export class Session extends EventEmitter {
// rather than show the previous conversation's "warm until" against the new one; the
// next statusline render repopulates. A same-id reattach returned above, untouched.
this._promptCache = null;
this._contextReport = null;
}
/**
@@ -1812,6 +1815,17 @@ export class Session extends EventEmitter {
return changed;
}
/**
* Take the context size from a statusline report and run the threshold checks on it. The
* token paths above cannot do this: they only run when the counter moves, and the counter
* does not see the cached context.
*/
noteContextReport(report: ContextReport): void {
this._contextReport = report;
this._autoOps.checkAutoCompact();
this._autoOps.checkAutoClear();
}
/** Prompt-cache keep-warm opt-in; undefined means the app-wide default applies. */
get keepWarmEnabled(): boolean | undefined {
return this._keepWarmEnabled;
@@ -2440,6 +2454,7 @@ export class Session extends EventEmitter {
autoResumeEnabled: this._autoOps.autoResumeEnabled,
autoResumeAt: this._autoOps.autoResumeAt ?? undefined,
promptCache: this._promptCache ?? undefined,
contextWindowSize: this._contextReport?.windowSize,
statusLineExporter: this.statusLineExporter,
keepWarmEnabled: this._keepWarmEnabled,
keepWarm: this._keepWarm ?? undefined,
@@ -4953,9 +4968,9 @@ export class Session extends EventEmitter {
// Matches patterns like "123.4k tokens", "5234 tokens", "1.2M tokens"
//
// SAFETY LIMITS:
// - Max tokens per session: 500k (Claude's context is ~200k)
// - Max tokens per session: MAX_SESSION_TOKENS (the largest context Claude reports is 1M)
// - Max delta per update: 100k (prevents sudden jumps from parsing errors)
// - Rejects "M" suffix values > 0.5 (500k) to prevent false matches
// - Rejects "M" suffix values above that maximum to prevent false matches
private parseTokensFromStatusLine(cleanData: string): void {
// Quick pre-check: skip expensive regex if "token" not present (performance optimization)
if (!cleanData.includes('token')) return;
@@ -4973,9 +4988,8 @@ export class Session extends EventEmitter {
if (suffix === 'k') {
tokenCount *= 1000;
} else if (suffix === 'm') {
// Safety: Reject M values that would result in > 500k tokens
// Claude's context window is ~200k, so anything claiming millions is likely a false match
if (tokenCount > 0.5) {
// Safety: anything claiming more than the largest context is likely a false match
if (tokenCount * 1000000 > MAX_SESSION_TOKENS) {
console.warn(
`[Session ${this.id}] Rejected suspicious M token value: ${tokenMatch[0]} (would be ${tokenCount * 1000000} tokens)`
);
@@ -5011,6 +5025,7 @@ export class Session extends EventEmitter {
this._totalOutputTokens += Math.round(delta * 0.4);
// Check if we should auto-compact or auto-clear
this._autoOps.noteAbsoluteCounter();
this._autoOps.checkAutoCompact();
this._autoOps.checkAutoClear();
}