mirror of
https://github.com/Ark0N/Codeman.git
synced 2026-11-21 21:39:33 +01:00
fix(settings): re-evaluate the keep-warm only when its default or cap changes
Merge-time fix for #666 (the review's nit). The settings PUT called `rescheduleAll()` whenever the body carried either keep-warm key, and the browser sends both on every App Settings save, so every save of anything re-read the settings and re-evaluated every session. It now compares the merged settings with the stored ones, following the rule that a settings action resolves from `merged`, never from the raw body. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
2a56b2a997
commit
0ca64f8256
3 files changed
+31
-3
No files matched your search
@@ -161,7 +161,7 @@ Further detail: the handheld OFF default comes from the mobile block in `getDefa
|
||||
|
||||
### Prompt-cache keep-warm
|
||||
|
||||
**Prompt-cache keep-warm** (`src/prompt-cache-keepwarm.ts`; per-session opt-in `keepWarmEnabled` on the Respawn tab, app-wide default `promptCacheKeepWarm` and cap `promptCacheKeepWarmMaxHours` under App Settings → System → Automation, both SYNCED, default OFF and 2 h; step 2 of Discussion #554): shortly before an idle claude session's prompt cache would expire, Codeman sends ONE keep-alive turn (`KEEP_WARM_NUDGE`, under 100 characters so Claude Code never reads the burst as a paste) so the next real prompt still reads the conversation from cache. Measured on two sessions of ~110k tokens: the nudge read 109,831 tokens from cache and wrote 70, replied `ok` in three seconds with no tool use, and a real turn seven minutes past the original expiry stayed a hit while the un-nudged control re-wrote 89,882 tokens with `last_miss_cause: ttl_expired_1h`; the payoff on real usage is concentrated in gaps of one to four hours, which is why there is a cap after the last real prompt rather than an indefinite loop (2 h by default: the maintainer's simulation over 30 days of gaps came out slightly cheaper than 3 h). ⚠️ **Codeman owns the idle policy for a keep-warm session.** Claude Code 2.1.289+ can compact an idle 1h-cache session by itself at 90% of the TTL (a server-flagged experiment, `fireAtFraction` tunable down to 0.5), which on the default timing always lands a minute before the nudge and leaves only a summary to keep warm. So a launch with keep-warm on carries `"idleCompaction": false`, folded LAST into the ONE `--settings` JSON with ultracode, the advisor and the statusLine exporter (`buildSpawnCommandFromRegistry`; never a second `--settings` flag, Claude Code takes one), so a keep-warm-off launch is byte-identical to one from before keep-warm (`test/cli-registry-spawn-golden.test.ts`). The `--settings` flag outranks user, project and local settings, which is why the key is conditional: everywhere else it would take Claude Code's own behaviour away with no way back. `decideIdleCompactionOptOut()` (tmux-manager.ts, pure) decides it once per create and respawn: keep-warm on (`keepWarmOn()`: the session's choice, else the app default, read fresh by `readKeepWarmSettings()`), the exporter `injected` (without `prompt_cache` reports keep-warm cannot run, and the opt-out alone would only cost the user the idle compaction), and claude's `idleCompactionSetting` gate (`capabilities.gates`, 2.1.290, the first release whose settings schema has the key; 2.1.289 already idle-compacts with no opt-out), fail-closed through `launchGatePasses()` exactly like `--name`: an unknown version means no key, and a log line says so. The result is recorded on the mux record (`MuxSession.idleCompactionOff`, like `statusLine`, persisted in mux-sessions.json) and published in the keep-warm status as `idleCompactionOff`; a session switched on after launch is kept warm best-effort (a relaunch to install the opt-out would cost exactly the re-write being avoided) and its readout says Claude Code's idle compaction may still run until its next launch, which any relaunch (dead-pane recovery, a custom-model `restartCli()`) fixes for free since every relaunch re-decides. ⚠️ The deadline is the statusline's `prompt_cache.expires_at` (`Session.promptCache`), never idle detection or the plan tier, and a `5m` lifetime is a hard stop (a nudge every four minutes costs more than the miss it prevents; API-key users get the hour from `CLAUDE_CODE_PROMPT_CACHE_TTL=1h` in `envOverrides`). ⚠️ `decideKeepWarm()` is the ONE rulebook and every guard lives in it, tested as a table: the effective opt-in (`keepWarmOn()`; a session an agent spawned, `parentSessionId`, does not inherit the app default, since an idle worker that reported done looks exactly like one that will be prompted again and most never are; its own switch still works), the launch's `statusLineExporter` is `injected` (which also stops every CLI without cache telemetry; the toggle line says why in the readout's own `PROMPT_CACHE_NOT_COLLECTED` words), a warm cache with an expiry, no `compactedAt` this gap (a compaction already replaced the context, and the stamp is dropped at the next request, which re-opens the next gap), not a `5m` lifetime, at least `KEEP_WARM_MIN_TOKENS` at stake, a live pane (a pid AND no recorded `paneExit`: an agent that exited in a `remain-on-exit` pane keeps its pid), no usage-limit pause (auto-resume's, or, read off the same pane capture as the composer, a usage-limit message whose reset is still ahead, since auto-resume tracks pauses only while it is on), no automation (respawn running, a Ralph loop active, a task assigned, or an agent long-polling `wait`), inside the cap measured from `lastRealPromptAt` (else `createdAt`), due at `expires_at` minus `KEEP_WARM_LEAD_MS` but not within `KEEP_WARM_LAST_CHANCE_MS`, idle, no open permission or question dialog, an EMPTY composer (`composerIsEmpty()` in session-submit-verifier.ts reads the last glyph line AND its Line truncated
|
||||
**Prompt-cache keep-warm** (`src/prompt-cache-keepwarm.ts`; per-session opt-in `keepWarmEnabled` on the Respawn tab, app-wide default `promptCacheKeepWarm` and cap `promptCacheKeepWarmMaxHours` under App Settings → System → Automation, both SYNCED, default OFF and 2 h; step 2 of Discussion #554): shortly before an idle claude session's prompt cache would expire, Codeman sends ONE keep-alive turn (`KEEP_WARM_NUDGE`, under 100 characters so Claude Code never reads the burst as a paste) so the next real prompt still reads the conversation from cache. Measured on two sessions of ~110k tokens: the nudge read 109,831 tokens from cache and wrote 70, replied `ok` in three seconds with no tool use, and a real turn seven minutes past the original expiry stayed a hit while the un-nudged control re-wrote 89,882 tokens with `last_miss_cause: ttl_expired_1h`; the payoff on real usage is concentrated in gaps of one to four hours, which is why there is a cap after the last real prompt rather than an indefinite loop (2 h by default: the maintainer's simulation over 30 days of gaps came out slightly cheaper than 3 h). ⚠️ **Codeman owns the idle policy for a keep-warm session.** Claude Code 2.1.289+ can compact an idle 1h-cache session by itself at 90% of the TTL (a server-flagged experiment, `fireAtFraction` tunable down to 0.5), which on the default timing always lands a minute before the nudge and leaves only a summary to keep warm. So a launch with keep-warm on carries `"idleCompaction": false`, folded LAST into the ONE `--settings` JSON with ultracode, the advisor and the statusLine exporter (`buildSpawnCommandFromRegistry`; never a second `--settings` flag, Claude Code takes one), so a keep-warm-off launch is byte-identical to one from before keep-warm (`test/cli-registry-spawn-golden.test.ts`). The `--settings` flag outranks user, project and local settings, which is why the key is conditional: everywhere else it would take Claude Code's own behaviour away with no way back. `decideIdleCompactionOptOut()` (tmux-manager.ts, pure) decides it once per create and respawn: keep-warm on (`keepWarmOn()`: the session's choice, else the app default, read fresh by `readKeepWarmSettings()`), the exporter `injected` (without `prompt_cache` reports keep-warm cannot run, and the opt-out alone would only cost the user the idle compaction), and claude's `idleCompactionSetting` gate (`capabilities.gates`, 2.1.290, the first release whose settings schema has the key; 2.1.289 already idle-compacts with no opt-out), fail-closed through `launchGatePasses()` exactly like `--name`: an unknown version means no key, and a log line says so. The result is recorded on the mux record (`MuxSession.idleCompactionOff`, like `statusLine`, persisted in mux-sessions.json) and published in the keep-warm status as `idleCompactionOff`; a session switched on after launch is kept warm best-effort (a relaunch to install the opt-out would cost exactly the re-write being avoided) and its readout says Claude Code's idle compaction may still run until its next launch, which any relaunch (dead-pane recovery, a custom-model `restartCli()`) fixes for free since every relaunch re-decides. ⚠️ The deadline is the statusline's `prompt_cache.expires_at` (`Session.promptCache`), never idle detection or the plan tier, and a `5m` lifetime is a hard stop (a nudge every four minutes costs more than the miss it prevents; API-key users get the hour from `CLAUDE_CODE_PROMPT_CACHE_TTL=1h` in `envOverrides`). ⚠️ `decideKeepWarm()` is the ONE rulebook and every guard lives in it, tested as a table: the effective opt-in (`keepWarmOn()`; a session an agent spawned, `parentSessionId`, does not inherit the app default, since an idle worker that reported done looks exactly like one that will be prompted again and most never are; its own switch still works), the launch's `statusLineExporter` is `injected` (which also stops every CLI without cache telemetry; the toggle line says why in the readout's own `PROMPT_CACHE_NOT_COLLECTED` words), a warm cache with an expiry, no `compactedAt` this gap (a compaction already replaced the context, and the stamp is dropped at the next request, which re-opens the next gap), not a `5m` lifetime, at least `KEEP_WARM_MIN_TOKENS` at stake, a live pane (a pid AND no recorded `paneExit`: an agent that exited in a `remain-on-exit` pane keeps its pid), no usage-limit pause (auto-resume's, or, read off the same pane capture as the composer, a usage-limit message whose reset is still ahead, since auto-resume tracks pauses only while it is on), no automation (respawn running, a Ralph loop active, a task assigned, or an agent long-polling `wait`), inside the cap measured from `lastRealPromptAt` (else `createdAt`), due at `expires_at` minus `KEEP_WARM_LEAD_MS` but not within `KEEP_WARM_LAST_CHANCE_MS`, idle, no open permission or question dialog, an EMPTY composer (`composerIsEmpty()` in session-submit-verifier.ts reads the last glyph line AND its Line truncated
|
||||
|
||||
### Cron jobs
|
||||
|
||||
|
||||
@@ -1113,7 +1113,11 @@ export function registerSystemRoutes(
|
||||
toggleService((merged.subagentTrackingEnabled as boolean) ?? true, subagentWatcher, 'Subagent watcher');
|
||||
// The prompt-cache keep-warm keeps its default and cap in memory; a changed default or cap
|
||||
// makes it re-read them and re-evaluate every session now rather than at its next cache report.
|
||||
if ('promptCacheKeepWarm' in settingsToStore || 'promptCacheKeepWarmMaxHours' in settingsToStore) {
|
||||
// Compared on `merged`, not tested for in the body: the browser sends both keys on every save.
|
||||
if (
|
||||
merged.promptCacheKeepWarm !== existing.promptCacheKeepWarm ||
|
||||
merged.promptCacheKeepWarmMaxHours !== existing.promptCacheKeepWarmMaxHours
|
||||
) {
|
||||
ctx.keepWarm.rescheduleAll();
|
||||
}
|
||||
|
||||
|
||||
@@ -48,7 +48,13 @@ const { EXISTING_SETTINGS, subagentWatcher, imageWatcher, workflowRunWatcher } =
|
||||
};
|
||||
return {
|
||||
// Persisted settings.json for these tests: two watchers ON, subagent tracking OFF.
|
||||
EXISTING_SETTINGS: { subagentTrackingEnabled: false, imageWatcherEnabled: true, showUltracodeAgents: true },
|
||||
EXISTING_SETTINGS: {
|
||||
subagentTrackingEnabled: false,
|
||||
imageWatcherEnabled: true,
|
||||
showUltracodeAgents: true,
|
||||
promptCacheKeepWarm: false,
|
||||
promptCacheKeepWarmMaxHours: 2,
|
||||
},
|
||||
subagentWatcher: makeWatcher(false),
|
||||
imageWatcher: makeWatcher(true),
|
||||
workflowRunWatcher: makeWatcher(true),
|
||||
@@ -143,4 +149,22 @@ describe('PUT /api/settings — partial body must not reset service toggles', ()
|
||||
// showUltracodeAgents is still true in settings.json, so it stays up.
|
||||
expect(workflowRunWatcher.stop).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
/**
|
||||
* The browser sends both keep-warm keys on every App Settings save, so testing for the keys in
|
||||
* the body re-read the settings and re-evaluated every session on each save of anything.
|
||||
*/
|
||||
it('re-evaluates the prompt-cache keep-warm only when its default or cap changes', async () => {
|
||||
const put = (payload: Record<string, unknown>) =>
|
||||
harness.app.inject({ method: 'PUT', url: '/api/settings', payload });
|
||||
|
||||
expect((await put({ promptCacheKeepWarm: false, promptCacheKeepWarmMaxHours: 2 })).statusCode).toBe(200);
|
||||
expect(harness.ctx.keepWarm.rescheduleAll).not.toHaveBeenCalled();
|
||||
|
||||
expect((await put({ promptCacheKeepWarm: false, promptCacheKeepWarmMaxHours: 3 })).statusCode).toBe(200);
|
||||
expect(harness.ctx.keepWarm.rescheduleAll).toHaveBeenCalledTimes(1);
|
||||
|
||||
expect((await put({ promptCacheKeepWarm: true })).statusCode).toBe(200);
|
||||
expect(harness.ctx.keepWarm.rescheduleAll).toHaveBeenCalledTimes(2);
|
||||
});
|
||||
});
|
||||
Reference in new issue
Block a user