feat: /acp compact — dedicated compression model (session shared-prefix + models.json) - #241

📦 Built Extension Artifact

Branch: feat/acp-compact-compression-model (c5e7de8)

Option A — Install from npm PR tag (recommended)

pi install npm:billion-context-pi@pr-241

Each push to this PR publishes a new version under the pr-241 npm tag.

Option B — Download artifact

1. Download the artifact from the Actions run
2. Extract the tarball and install:

tar xzf billion-context-pi-pr241.tgz
pi install ./package

This comment is automatically updated on each push.

🤖 ework agent · vllm-qwen/qwen3.8-27b

[bot] Reviewing this PR now. Branch feat/acp-compact-compression-model checked out locally (2 commits: 631d51e + c5e7de8). Running typecheck, tests, and build, and reading through the diff — I'll report findings here shortly.

🤖 ework agent · vllm-qwen/qwen3.8-27b

[bot] Review complete — LGTM, all CI checks green. Merging is left to you (human-only per AGENTS.md).

CI (run on branch feat/acp-compact-compression-model, commits 631d51e + c5e7de8)

Verified integration points

• Pins intact: acp-kernel 0.0.46, pi-coding-agent 0.83.0 unchanged; new devDep @earendil-works/pi-ai pinned exactly to 0.83.0 (type-only, so devDep placement is correct). The 1.3K-line lockfile diff is just pi-ai's transitive deps (AWS/Anthropic SDKs) — expected.
• Shared-prefix capture (src/index.ts:367): runtime.setLastSentMessages(sid, rebuilt) stores exactly the array returned as { messages: rebuilt } — the final ACP-transformed messages (tags + injected nudge). Correct source.
• Prefix fidelity: getSystemPromptText(ctx) uses ctx.getSystemPrompt() (same prompt Pi sends), convertToLlm(AgentMessage[]): Message[] exists in pi-coding-agent 0.83.0, and collectActiveTools's {name, description, parameters} mapping matches pi-ai's Tool/Context shapes exactly. So the session-mode request should be byte-identical to the main model's prefix → cache hit.
• Fallbacks: per-range try/catch → main-model summary retained on any failure; unresolvable ref, missing session model, and empty response all degrade gracefully with a ⚠️ note in the panel. Session never blocked.
• Tests: the 4 session tests use a real mock SSE server and assert the shared prefix ("lorem ipsum") is actually present in the outbound request body, plus the unreachable-model fallback path. Good coverage of the load-bearing behavior.
• Docs: README + CONFIGURATION cover both modes, the fallback guarantee, resolution rules, and the global-file scope.

Non-blocking observations

1. Fallback quality cliff: when a compression model is set, the tool description tells the main model to pass a minimal placeholder ("compressed"). If the compression call fails for that range, the block's stored summary is that placeholder — much weaker than the old "main model writes full summaries" behavior, and the only recovery is decompress + re-compress. The session is never interrupted (as designed), but consider either (a) stating this tradeoff explicitly in the tool description/docs, or (b) asking the main model for a 1–2 sentence real summary instead of a bare placeholder so the fallback is still useful.
2. Project-level override edge case: /acp compact writes the global ~/.pi/acp.json, but loadUserConfig lets a project .pi/acp.json override per-field. If a project file sets compressionModelId, the next reloadConfig (forced by lastUserConfigKey = undefined) re-reads and the project value wins over the command's in-memory update. CONFIGURATION documents the scope, but the command's "applies across sessions" message could mislead in that corner.
3. Memory: lastSentMessages holds a full copy of the transformed messages per session until clearSessionTracking — fine, just noting it's a duplicate of data already in memory.
4. Minor: commandArgString(args: string) is typed string but handles arrays (test convenience) — the type is a slight lie; harmless.
5. truncateContent(content, 120000) caps range content only in models.json mode; session mode sends the full (cached) context with no cap. Inconsistent but each is reasonable for its mode.

None of these block the merge. Nice work — the session-mode design (isolation without a cheaper model, via cache) is the interesting part.

解决冲突 更新最新代码

🤖 Powered by ework · qwen3.8-27b

上游同步完成，冲突已解决，已更新到最新代码。

现状：feat/rollover-cache-stability 已合并 origin/master @ 2650a99（v0.1.70 时期，acp-kernel 0.0.69），merge commit 16c4c3a，已推送。PR #243 现在基于最新 master。

冲突（12 个文件，均保留双方特性后解决）：

• CHANGELOG.md：保留 master 新条目 + 本功能条目
• src/config.ts：AdapterConfig 字段合并（rollover + promptSections/nudgeSections/toolPrompts/delegatePrompt）
• src/compress-tool.ts：imports 合并；rollover 分支改用 compress 摘要双重转义(\uXXXX)入库+渲染;幻觉用户原话被摘要永久化为 CURRENT TASK 导致循环复发 #309 之后的 sanitizedRanges（延迟记录与摘要净化两者都保留）；panel 格式跟随 master 的 block-span 新格式
• src/index.ts（5 处）：imports 合并；restore-merge 块置于 reasoning-drop/degeneration-collapse 之前；wireSystemPrompt 在 pack-aware base 之后追加 ROLLOVER_PROMPT_SECTION
• src/runtime.ts / src/state.ts / src/status-tool.ts：接口 / 持久化 / 状态面板合并
• 测试文件：tests/density-usage-fixes.test.ts 随 master 删除 density 一并 git rm；其余保留双方断言

移植工作：被 master 移除的 calibrateTokens/density API → 改用 #289 的 sentViewTokenCount/adjustedTokenCount；master 新增测试文件的 57 处 createAcpExtension 调用点补了 rollover: false pin（legacy 行为测试不受 rollover 默认开启影响）。

调试发现：验证时发现 master 新增的 host gate（isUnsupportedHost）要求 sessionManager 暴露 buildContextEntries()——我的 rollover 测试 fake 缺该方法，导致 session_start 提前返回、跳过 absorb 注册。这是本地偶发失败的根因（已按 master 的 host contract 修正），与合并本身无关。

验证：typecheck 干净；全量测试绿 ×3（823 tests / 817 pass / 0 fail / 6 skip）；构建成功（dist 554 KB 自包含）。注意：本机磁盘 97% 且外部进程会间歇性删除 /tmp 下的文件（观察到 TAP 文件与测试状态目录在命令之间被清掉），本地全量跑偶发的瞬时失败与此无关——以 CI 为准。

未改版本号（release-branch-only 规则）；PR #243 等你 review 和合并。

一句话总结：把 PR #243 同步到最新 master（v0.1.70 / acp-kernel 0.0.69），解决了 12 个文件的冲突并保留双方特性，本地全量测试通过，待人工合并。