feat(plugin): auto-inject retrieves on the conversation, not the typed words alone (#4364)

The prompt hook sent only the operator's message, so a mid-session
follow-up ("yes do that") named nothing a note, lesson or rule could
match. The hook now reads the tail of the last assistant reply from the
transcript and sends it as `ctx`; the notes and rule arms append it to a
short prompt (<= 280 chars), prompt first, capped at 600 chars. No model
tokens: it is embedding input, and the injected menu's budget is unchanged.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/test_autoinject_context.py

@@ -0,0 +1,98 @@
+"""The auto-inject query carries the conversation beside a thin prompt (#4364).
+
+The notes arm used to retrieve against the operator's typed words alone, and a
+mid-session follow-up — "yes do that", "now fix the filter" — names nothing a
+record can match. The hook now reads the tail of the last assistant reply out
+of the transcript and sends it as `ctx`; the server appends it to a SHORT
+prompt only. Two halves, pinned separately: what the server builds, and what
+the hook extracts.
+"""
+from __future__ import annotations
+
+import json
+import subprocess
+from pathlib import Path
+
+from scribe.services.plugin_context import (
+    _AUTOINJECT_CONTEXT_MAX,
+    _AUTOINJECT_CONTEXT_PROMPT_MAX,
+    _autoinject_query,
+)
+from tests.helpers import need_tools
+
+DEFS = Path(__file__).resolve().parents[1] / "plugin" / "hooks" / "scribe_defs.sh"
+
+
+# --- the query the server builds ---------------------------------------------
+
+def test_a_short_prompt_is_followed_by_the_context():
+    q = _autoinject_query("yes do that", "I'll move the library filters into the side column.")
+    assert q.startswith("yes do that\n\n")
+    assert "library filters" in q
+
+
+def test_a_prompt_that_says_what_it_is_about_is_left_alone():
+    long_prompt = "x" * (_AUTOINJECT_CONTEXT_PROMPT_MAX + 1)
+    assert _autoinject_query(long_prompt, "anything at all") == long_prompt
+
+
+def test_no_context_is_the_prompt_unchanged():
+    assert _autoinject_query("yes do that", "") == "yes do that"
+    assert _autoinject_query("yes do that", "   \n ") == "yes do that"
+
+
+def test_context_is_cut_from_the_end_of_the_reply():
+    # The reply's close is where it says what it did and what is next — the
+    # part the operator's follow-up is answering.
+    ctx = "HEAD " + "m" * 2000 + " TAIL"
+    q = _autoinject_query("ok", ctx)
+    tail = q.split("\n\n", 1)[1]
+    assert len(tail) == _AUTOINJECT_CONTEXT_MAX
+    assert tail.endswith("TAIL") and "HEAD" not in tail
+
+
+# --- what the hook extracts --------------------------------------------------
+
+def _rec(role: str, blocks: list[dict], sidechain: bool = False) -> str:
+    return json.dumps({
+        "type": role, "isSidechain": sidechain,
+        "message": {"role": role, "content": blocks},
+    }, separators=(",", ":"))
+
+
+def recent(tmp_path: Path, lines: list[str]) -> str:
+    need_tools("bash", "awk", "grep", "tail")
+    t = tmp_path / "t.jsonl"
+    t.write_text("\n".join(lines) + "\n")
+    r = subprocess.run(
+        ["bash", "-c", f'set -uo pipefail\n. "{DEFS}"\nscribe_recent_context "{t}"'],
+        capture_output=True,
+    )
+    assert r.returncode == 0, r.stderr.decode()
+    return r.stdout.decode().strip()
+
+
+def test_the_hook_reads_the_last_assistant_text(tmp_path):
+    out = recent(tmp_path, [
+        _rec("assistant", [{"type": "text", "text": "an older reply"}]),
+        _rec("assistant", [{"type": "tool_use", "id": "t1", "name": "Bash", "input": {}}]),
+        _rec("assistant", [{"type": "text", "text": "Shall I file it as an issue?\nNext: the hook."}]),
+    ])
+    assert out == "Shall I file it as an issue? Next: the hook."
+
+
+def test_a_subagent_reply_is_not_this_session(tmp_path):
+    out = recent(tmp_path, [
+        _rec("assistant", [{"type": "text", "text": "the session's reply"}]),
+        _rec("assistant", [{"type": "text", "text": "a subagent's report"}], sidechain=True),
+    ])
+    assert out == "the session's reply"
+
+
+def test_the_hook_caps_what_it_sends(tmp_path):
+    out = recent(tmp_path, [_rec("assistant", [{"type": "text", "text": "a" * 5000 + "END"}])])
+    assert len(out) == 600 and out.endswith("END")
+
+
+def test_no_transcript_is_silence_not_failure(tmp_path):
+    assert recent(tmp_path, []) == ""