fix(acp): replace Goose native system prompt (#5964)

## Why

Buzz currently appends its managed prompt to Goose's native prompt, so
managed agents receive both instruction sets instead of the intended
Buzz-only system prompt.

## What

- Send Goose's custom session system-prompt request with `mode: "set"`
- Lock the replacement contract in the ACP request test

## Risk Assessment

Low — the change is limited to Goose session setup; adapters that do not
implement Goose's custom method keep the existing method-not-found
fallback behavior.

## References

Goose v1.46.0 routes `set` to `override_system_prompt`, and its prompt
builder selects that override instead of rendering the native
`system.md`: [ACP
handler](https://github.com/aaif-goose/goose/blob/98c11ce2ee7b9b302978aa64b1eab7d0895607c7/crates/goose/src/acp/server/manage_sessions.rs#L57-L93),
[prompt
builder](https://github.com/aaif-goose/goose/blob/98c11ce2ee7b9b302978aa64b1eab7d0895607c7/crates/goose/src/agents/prompt_manager.rs#L153-L191).

Validated end to end against the official Goose v1.46.0 binary with a
local OpenAI-compatible capture server: the provider request contained
the exact Buzz replacement prompt and did not contain Goose's native
base-prompt marker.

---

**Update Aug 15, 13:17 CDT:** Added the [Terra-high prompt-ablation
comparison](https://github.com/squareup/buzz-benchmarks/blob/4492f76349ccb638219f7d070735a4d2b679bc26/data/prompt-ablation/20260815-terra-high/comparison.md).

The Goose conditions used GPT 5.6 Terra at high effort on the same 11
Terminal-Bench 2.1 tasks, with two attempts per task and concurrency
four. The matched `append-full` and `set-full` runs used the same
persona and included the same Buzz platform prompt; Active-h is the
primary measure because it excludes Buzz lifecycle overhead.

| Goose condition | Pass | Active-h | Median active | Agent-h | Wall-h |
Tool calls |
|---|---:|---:|---:|---:|---:|---:|
| Native prompt + Buzz prompt (`append-full`) | 21/22 | 0.3042 | 0.85
min | 0.3974 | 0.1496 | 234 |
| Native prompt + persona only (`append-persona-only`) | 22/22 | 0.3050
| 0.75 min | 0.3990 | 0.1498 | 204 |
| Buzz prompt replaces native prompt (`set-full`) | 22/22 | 0.3340 |
0.87 min | 0.4296 | 0.1551 | 275 |

Replacing instead of appending produced one additional passing attempt,
but it was not an efficiency improvement in this small sample: versus
`append-full`, `set-full` increased Active-h by 9.8%, median active by
2.0%, Agent-h by 8.1%, Wall-h by 3.7%, and tool calls by 17.5%. It was
faster on only two of eleven per-task active-time medians
(`distribution-search` and `prove-plus-comm`). With two attempts per
task, these are directional results rather than confidence intervals;
they support this change as an instruction-isolation/correctness fix,
not a performance optimization, and argue against Goose's appended
native prompt being the main source of active-time cost.

Generated with Codex

Signed-off-by: Atish Patel <atishpatel2012@gmail.com>
Co-authored-by: Codex <noreply@openai.com>

crates/buzz-acp/src/acp.rs

@@ -702,7 +702,7 @@ impl AcpClient {
             .session_id)
     }
 
-    /// Send Goose's custom system-prompt request after `session/new`.
+    /// Replace Goose's native system prompt after `session/new`.
     pub async fn session_set_goose_system_prompt(
         &mut self,
         session_id: &str,
@@ -712,7 +712,7 @@ impl AcpClient {
             "_goose/unstable/session/system-prompt/set",
             serde_json::json!({
                 "sessionId": session_id,
-                "mode": "append",
+                "mode": "set",
                 "key": "buzz",
                 "text": text,
             }),
@@ -3421,7 +3421,7 @@ mod tests {
     }
 
     #[tokio::test]
-    async fn goose_system_prompt_request_uses_append_contract() {
+    async fn goose_system_prompt_request_uses_set_contract() {
         let script = r#"
             read -t 2 REQ
             echo '{"jsonrpc":"2.0","id":0,"result":{"_receivedRequest":'"$REQ"'}}'
@@ -3438,7 +3438,7 @@ mod tests {
             "_goose/unstable/session/system-prompt/set"
         );
         assert_eq!(received["params"]["sessionId"], "ses_goose");
-        assert_eq!(received["params"]["mode"], "append");
+        assert_eq!(received["params"]["mode"], "set");
         assert_eq!(received["params"]["key"], "buzz");
         assert_eq!(received["params"]["text"], "Be terse");
     }