Repository navigation
chore: pin acp-kernel 0.0.97 — post-fold echo discrimination (kernel #463) - #1505
Conversation
📦 Built Package ArtifactBranch: Option A — Install this exact build (recommended)npm install -g billion-context@0.0.1442-pr.1505.849e967This exact version is immutable and reproducible. The rolling Option B — Download artifact
tar xzf billion-context-pr1505.tgz
npm install -g packageInstall instructions are refreshed on each push. |
Kernel #458 (acp-kernel 0.0.96) stops the pre-fold original from leaking raw back onto the wire on host resend — stored refs are re-projected to their canonical 📦 placeholder instead. The two #1457 lanes passed on 0.0.95 only because that leak re-served BIG_TEXT on turn 3; their comment claimed a 're-issued retrieve on resent call+ack' mechanism that never existed (no executeRetrieve call site on ingress, no injection message on the 0.0.95 wire). Both lanes now assert the real contract: - turn 3: placeholder re-projected, NO raw original on the wire, correction note still commits on the confirmed 2xx - new final turn: the model follows the note and re-issues acp_retrieve via the plugin tool endpoint; the re-queued injection rides that forward with the full text and commits as one delivery (retrieveDelivered === 1) These tests now require acp-kernel >= 0.0.96 — part of the 0.0.97 pin bump in this PR.
[bot] 🏷 Review complete — CI red root-caused, fix landed (e98f3a5), all checks now green. Ready for human merge. What I verified① Direction & diff cleanliness. Branch vs ② Reproduced the CI failure locally and found the mechanism. On the pre-fix head:
③ Post-fix state (verified).
④ Behavior change disclosure (per policy, old → new):
⑤ Sequencing note: sibling branch No action taken beyond verification: I pushed nothing (my local duplicate commit was reset away after your 中文摘要:核查了 0.0.95→0.0.97 pin 升级——CI 红灯的根因是跳版带入的 kernel #458(存 ref 原始字节重传不再泄漏回线上、改投占位符,bc#1456 泄漏修复),旧 #1457 测试尾部靠该泄漏才通过、其注释声称的"重发即重取"机制并不存在;你在 e98f3a5 的修法正确且更完整(补了真实重取回合),本地与远端 CI 现已全绿,可以合并。 |
What & why
Pin-only bump
acp-kernel0.0.95 → 0.0.97. Supersedes #1488 (the 0.0.96 pin bump — 0.0.96 carries a P0 regression; see below). Precedent: #1423.v0.0.97 = v0.0.96 + the regression fix. Everything #1488 wanted from 0.0.96 rides in here too — 0.0.97 fully contains 0.0.96's payload:
parseStoredPlaceholder()strict whole-body parser — text merely mentioning[acp-storedno longer misclassified as a canonical placeholder; all three call sites require the exact two-line canonical shape citing the message's own refremintCoveredLiveIds— live resend of already-covered content gets deterministic_Ninstance suffixes instead of colliding with the folded copy's reflastPassIdssnapshot discriminates post-fold resends (echo → keep id, prune swallows) from genuinely new instances (→ renumber); missing snapshot → one pass of 0.0.95 semanticsWhy skip 0.0.96
0.0.96's #459 regression: stateless hosts resend folded originals every turn → live ids ∈ covered got renumbered as "new instances" → prune escape (
baseIdOfstrips#tailbut not_n) → folded content rejoined the wire beside its summary every turn → wire re-inflation → e2e-codex-fake overflow → preflight 502 → turn lost. bc master pins 0.0.95, so the regression never shipped here — this bump skips over it.Changes
package.json:"acp-kernel": "0.0.97"package-lock.json: regeneratedBehavior changes
None at the bc layer. Kernel-side: post-fold resends of folded originals are kept under their stable refs and pruned (pre-0.0.96 contract restored); genuinely new duplicate instances still renumber (#1476 preserved); placeholder parsing strict + raw replays re-projected (#1456/#1460 fixed); old persisted
CompressionStatewithoutlastPassIdsdegrades gracefully for one pass.Tests
npm run typecheck✅ locallynpm test→ remote CI (local sandbox aborted; e2e-codex-fake needsACP_TEST_E2E_FAKE=1with real codex)tests/e2e/e2e-codex-fake.test.tsoverflow lane — the test that caught the 0.0.96 regressionConfig surface
None.
Fixes #1456
Supersedes #1488
Refs #1460 (design issue — working-set half remains open), refs #1476 (closed at kernel merge; this pin delivers the fix to bili users)
Test updates (e98f3a5)
CI on the initial pin bump showed 4 test-matrix lanes red while every e2e lane was green. Root cause: two
#1457lanes intests/ccr-plugin.test.tsassertedf3.includes(GONE)— "re-issued retrieve (resent call+ack) still serves the stored text" — which passed on 0.0.95 only because the pre-fold original leaked raw back onto the wire on host resend. No re-issue mechanism ever existed (noexecuteRetrievecall site on ingress; no[acp-retrieved]injection on the 0.0.95 turn-3 wire — verified by dumping the forward). Kernel #458 (0.0.96) deliberately kills that leak: stored refs re-arriving are re-projected to their canonical📦 [acp-stored ...]placeholder.Both lanes were updated to the real contract:
[acp-storedpresent,GONEabsent — no raw leak), correction note still commits on the confirmed 2xx.acp_retrievethrough the plugin tool endpoint; the re-queued injection rides that forward with the full text ([acp-retrieved+GONE) and commits as one delivery (retrieveDelivered === 1).Local run on 0.0.97:
tests/ccr-plugin.test.ts12/12 pass. Note these two tests now require acp-kernel ≥ 0.0.96 — intentionally coupled to this bump.