jinye 32e2741577 perf(core): clear tool results to a low watermark to preserve prompt cache (#8464) ... * perf(core): clear tool results to a low watermark to preserve prompt cache Size-triggered microcompaction now clears oldest compactable tool results down to half the threshold instead of stopping just below it, so the conversation prefix stays stable between clearings and provider prompt caches keep matching. The recent-result budget now protects committed results only; pending results no longer consume protection slots but stay counted, uncleared, and live for file-read-cache resolution. Adds the watermark to cleanup metadata and the debug log. Fixes #8463 * fix(core): harden size-cleanup protection against zero-char and pending refs Review follow-up for the low-watermark change: keepRecent now selects from committed results that are actually clearable (positive, successful, uncleared output), so trailing errors, prior placeholders, and empty outputs no longer absorb protection slots. Pending refs are dropped from the keep set entirely — a pending read may be a cache-hit placeholder rather than file bytes, so it must not suppress eviction reporting; over-disarming only costs a redundant re-read. Adds regression tests for both plus the protected-saturation consecutive-trigger corner. * qwen: address PR review feedback (#8464) Pin the (soft-exceeded) log marker with the one-line assertion suggested by the sandboxed verification report (finding S-1): the all-protected overage test now asserts 'target 250000 (soft-exceeded)', killing the surviving mutant M4. * qwen: address PR review feedback (#8464) * qwen: address PR review feedback (#8464) * qwen: address PR review feedback (#8464) Two P1 context-integrity fixes from review: (1) media-only tool results (image/PDF reads with empty text output and bytes on functionResponse.parts) stay in the idle-path keepRecent candidates instead of being dropped by the zero-char filter; (2) only write_file results vouch for file residency in kept-path accounting — edit calls carry just old/new snippets while still setting the cache's sticky full-read flags, so a kept edit can no longer suppress eviction reporting after the full read is blanked. Regression tests for both. * qwen: address PR review feedback (#8464) Pin the absence of the (soft-exceeded) marker at the exact watermark boundary: clearing that lands the virtual total exactly on the watermark must not be flagged. Kills the >= and always-true mutants of the marker condition that previously survived the suite. * qwen: address PR review feedback (#8464) --------- Co-authored-by: Shaojin Wen <shaojin.wensj@alibaba-inc.com>		2026-08-04 19:00:11 +00:00
..
assets	feat: support workspace display names (#7179)	2026-07-20 15:16:44 +00:00
design	fix(serve): detect lineEnding across the file, not the returned slice (#8383)	2026-08-04 16:26:54 +00:00
developers	feat(serve): add a required external tool guard provider (#8125)	2026-08-04 14:37:13 +00:00
e2e-tests	feat(worktree): Phase D — startup --worktree flag + symlinkDirectories + PR refs (#4381)	2026-05-27 17:04:51 +08:00
images	fix(web-shell): render built-in tag icons (#7024)	2026-07-17 15:33:34 +00:00
plans	feat(browser-ext): add alpha readiness diagnostics (#6739)	2026-08-04 03:23:47 +00:00
superpowers	feat(cli): reference prior sessions via @ and add completion tabs (#7302)	2026-07-24 06:11:48 +00:00
users	perf(core): clear tool results to a low watermark to preserve prompt cache (#8464)	2026-08-04 19:00:11 +00:00
verification/abort-controller-refactor	fix(core): stop AbortSignal listener leak in long sessions (MaxListenersExceededWarning) (#4366)	2026-05-26 14:21:49 +08:00
_meta.ts	feat: refactor docs	2025-12-05 10:51:57 +08:00
index.md	fix: lint issues	2025-12-19 15:52:11 +08:00