@estebanforge/pi-antigravity-bridge 1.3.2 → 1.4.0

package/CHANGELOG.md

@@ -2,6 +2,55 @@
 
 All notable changes to this project will be documented in this file.
 
+## [1.4.0] - 2026-09-04
+
+### Added
+
+- The official-server ACP engine as a second turn engine behind `config.engine` (env `AGY_ENGINE`, `/agy engine acp|stream-json`), default off: the tested stream-json engine stays default until upstream ships usage fields. New modules: `src/acp/jsonrpc.ts` (NDJSON JSON-RPC session with line buffering - stdio chunks are not newline-aligned), `src/acp/connection.ts` (initialize, session/new and load, config options, in-connection auto permissions, cancel probing), `src/acp/events.ts` (update mapping), `src/acp/driver.ts` (AcpDriver over the shared `TurnDriver` contract in `src/driver-types.ts`). Sessions are engine-scoped (`sid:<id>@acp`) so switching engines never crosses conversations.
+- `/agy engine acp|stream-json` command and `/agy acp-auth` (one-time credential setup for the ACP server, which keeps its own auth state). `/agy doctor` is engine-aware.
+- `scripts/smoke-acp.mjs` (live ACP smoke), `scripts/smoke-acp-bridge.mjs` (live Gate F bridge e2e), `scripts/parity-live.mjs` (live parity run: 7 scenarios through BOTH engines). All quota-gated via `AGY_ACP_LIVE=1`.
+- `docs/ACP-ADOPTION-PLAN.md` (adoption plan, gates, progress tracking) and `docs/ACP-PROTOCOL-REFERENCE.md` (captured wire shapes of the ACP server).
+- Image prompt support on the ACP engine: pi image attachments ride as typed content blocks (`DriverTurnRequest.images`, forwarded by `connection.prompt` ahead of the text block). Models advertise `input: ["text","image"]` only when the engine is `acp` (read at extension load; engine switches require a restart), so the text-only legacy CLI never offers an attach button it cannot honor. Verified live: a 64x64 two-tone PNG answered correctly through the full driver stack (`scripts/smoke-acp-image.mjs`, quota-gated) and in the phase-2 probe (`scripts/probe-acp-phase2.mjs`).
+- `scripts/probe-acp-phase2.mjs`: live probe capturing thought-chunk sparsity, image end-to-end, full tool_call/tool_call_update frames, and the `/plan` command flow (raw frames in `probe-logs/`).
+
+### Changed
+
+- `McpServerHandle` exposes the shared-secret token (`token`), and `TOKEN_HEADER` is exported: engines other than the stream-json discovery file need the header to reach the bridge (the ACP registration was silently sending no header and would have been 403'd).
+- Driver exit handling is connection-scoped in `AcpDriver`: a killed connection's late exit (the current ACP build intercepts SIGTERM and can outlive its replacement) no longer clobbers the live connection or fails the recovery turn.
+- `tool_call_update` display: the completed call's output now prefers the `content[]` text over `rawOutput`, which the server fills with a display title ("Call bridge_echo") rather than the result. The result itself reaches the model out-of-band; only the activity display was wrong.
+- Tool-frame mapping fixes from the phase-2 probe: MCP `rawInput` args unwrap the `arguments` envelope, and the tool name prefers `_meta.mcp.tool` over the "<server>_<tool>" title.
+- Gate C consolidation on the ACP engine: `native-tools.ts` re-exec and `WrapperReplay` parking are retired for ACP turns (tool steps render as thinking labels; `bridge_call` round-trips unaffected); ACP-native edit diffs from `tool_call` `content[]` render directly into the thinking stream via the new in-memory `formatInlineDiff` (same line-numbered format, zero git subprocesses). The git-sourced `diff-render.ts` path remains solely for the `stream-json` engine.
+- G1 digest delivery split by engine: on ACP the digest ships as a native `embeddedContext` resource block in the prompt array (`promptCapabilities.embeddedContext` verified live: a resource block with a secret word was read and answered correctly); `stream-json` keeps the inline text default.
+- `/agy doctor` (ACP): shows server reconnects (connections beyond the first = Gate D kills + replacements) and the handshake `agentInfo` name/title next to the server version.
+
+### Fixed
+
+- `tool_call_update` failed frames whose `rawOutput` matches the RC01
+  approved-but-never-executed sentinel are dropped instead of rendering as a
+  bogus tool error next to a successful edit (run 6, finding 7).
+- `AcpDriver` kills a leaked server process when the initialize handshake
+  fails (spawn succeeded, init timed out) - the detached process would
+  otherwise outlive pi.
+- `AcpDriver` snapshot prefers the active session id over the last settled
+  one, so `/agy doctor` during a live turn shows the correct session.
+- Text dedupe guard: the cumulative-mode flip now requires a respectable
+  accumulation (32+ chars), and a cumulative frame that stops extending the
+  accumulator falls back to append mode - a short markdown opener (`**`,
+  `#`) followed by an ordinary delta no longer corrupts the remaining output
+  (round-7 review, applies to both engines).
+
+- No usage fields anywhere: token display shows zero (Gate B; the stream-json engine stays default until upstream ships usage).
+- No `session/cancel` (-32601): abort tears the connection down and reloads on the next turn; `cancelSupported` is probed once and shown in `/agy doctor`.
+- `tool_call` activity output shows the server's display string, not the MCP result content (the model receives the result out-of-band; only the activity display lacks it).
+- `agent_thought_chunk` is sparse on RC01 (a step-by-step prompt produced zero; reasoning ships as plain message text). The thinking pipeline handles deltas when they occur.
+- ACP has NO review-only mode: the three modes are permission modes only, and the server-intercepted `/plan` command writes its artifact under auto policy. Plan delegations keep the legacy `agy -p --mode plan` path (committed exception).
+
+## [1.3.3] - 2026-09-01
+
+### Added
+
+- pi system prompt injection (G10): pi's composed system prompt - operating instructions plus the global agent-dir `AGENTS.md` and ancestor `AGENTS.md`/`CLAUDE.md` files - is prepended as a delimited block to the first prompt of each NEW agy conversation. agy has no system-prompt flag, so the prompt text is the only delivery path; the block is sent once per conversation and stays byte-identical afterwards, so agy's server-side prompt cache keeps hitting (unlike the per-turn G1 digest, which stays off by default for that reason). On by default (`config.systemPrompt`, `AGY_SYSTEM_PROMPT`, `/agy system-prompt on|off`); existing conversations keep the version they started with.
+
 ## [1.3.2] - 2026-09-01
 
 ### Removed

package/README.md

@@ -1,8 +1,12 @@
 # pi-antigravity-bridge
 
-A Gemini model provider **and** the `AskAntigravity` delegation tool for [pi](https://github.com/earendil-works/pi-coding-agent), both built on Google's `agy` CLI. It registers `antigravity/gemini-*` models in pi's `/model` picker (streaming), and provides the `AskAntigravity` tool for one-shot delegation - the same combined shape as `pi-claude-bridge`.
+A Gemini model provider **and** the `AskAntigravity` delegation tool for [pi](https://github.com/earendil-works/pi-coding-agent), built on Google's official Antigravity binaries: the `agy` CLI by default, or **Google's official ACP server** (opt-in). It registers `antigravity/gemini-*` models in pi's `/model` picker (streaming), and provides the `AskAntigravity` tool for one-shot delegation - the same combined shape as `pi-claude-bridge`.
 
-<img width="3024" height="1774" alt="image" src="https://github.com/user-attachments/assets/9fc2f368-7292-4dde-851b-db2bd579263c" align="center" />
+<img width="2566" height="1723" alt="SCR-20260903-sefo" src="https://github.com/user-attachments/assets/20f0c04c-d622-4b11-962a-3478f64570c2" align="center"/>
+
+<br/><br/>
+
+<img width="1272" height="842" alt="SCR-20260903-sfcu" src="https://github.com/user-attachments/assets/c483613b-10ff-4d2f-9893-027d84130ac6" align="center" />
 
 If you also have [`@estebanforge/pi-ask-antigravity`](https://github.com/EstebanForge/pi-ask-antigravity) installed, this bridge takes over: pi-ask-antigravity detects the bridge and registers nothing, so the `AskAntigravity` tool is never duplicated.
 
@@ -12,6 +16,17 @@ You pick a Gemini model in pi's `/model` picker. pi routes each turn through thi
 
 Multi-turn works. The provider binds a pi session to an agy conversation id (persisted under `~/.pi/agent/antigravity-bridge/sessions.json`) and resumes it on the next turn via `--conversation <id>`. agy keeps its own history, so only the latest user message is sent each turn.
 
+### Two engines
+
+Turns run through one of two engines behind the same provider surface (`config.engine`, default `stream-json`):
+
+- **stream-json** (default): the persistent `agy` CLI process. The tested default; live token usage; conversation resume via `--conversation`.
+- **acp**: Google's official ACP server (`agy_acp_server.par`), JSON-RPC 2.0 over stdio. Opt-in while it matures: the current build (RC01) ships no usage fields (token display shows zero) and no cancel (abort tears the server down and reloads it next turn). Everything else is parity-verified live - text streaming, multi-turn resume via `session/load`, bridge tools, effort switching, serialization, abort recovery - see `scripts/parity-live.mjs`.
+
+Engine-dependent features: pi image attachments ride natively only on the ACP engine (the picker offers image attach automatically when `config.engine` is `acp`; the stream-json CLI prompt is text-only). With the optional G1 digest enabled, its delivery also differs: ACP ships it as a native `embeddedContext` resource block, stream-json prepends it to the prompt text.
+
+Switch with `/agy engine acp|stream-json` (takes effect on restart). ACP needs the server binary installed locally (`AGY_ACP_BIN` or `config.acp.bin`; layout and pinning in [docs/ACP-ADOPTION-PLAN.md](docs/ACP-ADOPTION-PLAN.md)), and its own one-time credential setup: run `/agy acp-auth` for the steps. The ACP server keeps its own auth state; the token never touches this code. Sessions are engine-scoped, so switching engines never crosses conversations.
+
 ## What it cannot do
 
 agy runs its own closed tool loop (`read_file`, `write_file`, `edit_file`, `run_command`) against `--add-dir`. Its read-only steps (`view_file`, `list_dir`, `grep_search`, `find_by_name`) re-run as real pi builtins (`read`, `ls`, `grep`, `find`) so their cards render natively; mutating steps never execute in pi - they replay through a display-only `antigravity` wrapper tool. What used to be a hard wall for pi's other tools is bridgeable; see [MCP tool bridge](#mcp-tool-bridge-agy-uses-pis-tools) below.
@@ -91,8 +106,9 @@ If `agy models` fails at load (binary missing, auth not done, network stall), a
 | --- | --- | --- |
 | `bridgeTools` | `none` (bridge off), `mcp` (pi-mcp-adapter tools), `all` (every non-builtin tool, incl. other `Ask*` delegations) | `mcp` |
 | `digest` | `off` (stable prompts; agy's prompt cache hits) or `on` (inject a delta of pi-side context - compaction summaries, other-provider turns - into each agy prompt; the delta changes every turn, so agy re-bills the full context). Enable for mixed-provider sessions where agy must see pi-side context | `off` |
+| `systemPrompt` | `on` (prepend pi's system prompt - operating instructions plus the global agent-dir `AGENTS.md` and ancestor `AGENTS.md`/`CLAUDE.md` - to the first prompt of each new agy conversation) or `off` (agy-native behavior) | `on` |
 
-Env overrides: `AGY_BRIDGE_TOOLS`, `AGY_DIGEST`.
+Env overrides: `AGY_BRIDGE_TOOLS`, `AGY_DIGEST`, `AGY_SYSTEM_PROMPT`. Env wins over the file, so while `AGY_DIGEST` or `AGY_SYSTEM_PROMPT` is set, the matching `/agy digest` or `/agy system-prompt` toggle persists a value that never takes effect.
 
 ### The /agy command
 
@@ -108,6 +124,9 @@ Env overrides: `AGY_BRIDGE_TOOLS`, `AGY_DIGEST`.
 /agy model flash|pro|gemini   default model alias for the AskAntigravity tool
 /agy thinking low|medium|high default thinking tier for the AskAntigravity tool
 /agy digest on|off        inject pi-side context into agy prompts (default off; see table above)
+/agy system-prompt on|off send pi's system prompt + AGENTS.md to new agy conversations (default on)
+/agy engine acp|stream-json   switch the turn engine (restart to apply; default stream-json)
+/agy acp-auth                 one-time credential setup for the ACP engine
 /agy patch-cleanup        restore the original pi files if an older version patched them
 /agy clear                drop all session bindings (force fresh conversations)
 ```
@@ -129,6 +148,8 @@ For isolation when running any agent that executes commands without a confirmati
 | Variable | Purpose |
 | --- | --- |
 | `AGY_BIN` | Path to the agy binary. Defaults to `agy` on PATH. |
+| `AGY_ENGINE` | Turn engine: `stream-json` (default) or `acp`. Wins over the config file. |
+| `AGY_ACP_BIN` | Path to the ACP server binary (`agy_acp_server.par`). Defaults to `agy_acp_server.par` on PATH. Wins over `config.acp.bin`. |
 | `AGY_EXTRA_ARGS` | Extra args appended to every invocation. Whitespace-split. |
 | `AGY_CONVERSATIONS_DIR` | Override the conversations DB directory. |
 | `AGY_MODE` | Override execution mode: `plan` (review-only) or `accept-edits` (default). Wins over the config file. |
@@ -144,7 +165,7 @@ Build, test, and debug instructions live in [docs/DEVELOPMENT.md](docs/DEVELOPME
 
 Google's [Antigravity ToS](https://antigravity.google/terms) (Section 6) prohibits accessing the service "in connection with products not provided by us", and names as its example using tools like Hermes/OpenClaw with Antigravity OAuth. That targets reusing your credentials in a non-Google harness that calls Google's backend directly.
 
-This extension does not do that. It spawns the official, unmodified `agy` binary as a subprocess; `agy` performs its own OAuth and makes its own calls to Google. This code never sees, extracts, or reuses your token, and never contacts Antigravity's backend. It only reads what `agy` itself produces locally: its stream-json output. From Google's server-side view there is no signal that distinguishes "agy launched by pi" from "agy launched by a terminal, an IDE task runner, or cron": same signed binary, same authenticated calls.
+This extension does not do that. It spawns official, unmodified Google binaries as subprocesses - the `agy` CLI, or the official ACP server when enabled - which perform their own OAuth and make their own calls to Google. This code never sees, extracts, or reuses your token, and never contacts Antigravity's backend. It only reads what the binary itself produces locally: its stream-json output, or its ACP JSON-RPC messages. From Google's server-side view there is no signal that distinguishes "agy launched by pi" from "agy launched by a terminal, an IDE task runner, or cron": same signed binaries, same authenticated calls.
 
 Google's reported enforcement to date (the February 2026 suspensions) targeted token-reuse tools, not spawning the official CLI.