Query: # Eighth independent review: pre-existing sidecar composition

The fifth terminal acceptance review rejected the candidate after all focused
checks passed. Continue the same self-update and correct this production-path
collision:

- `append_persistent_model_status()` currently treats any existing non-empty
  `api_content` as an already installed status projection and returns it
  unchanged.
- Hermes already uses `api_content` for ordinary API-only composition,
  including memory/plugin prefetch context and sanitization-divergence replay.
  `build_turn_context()` can populate the current user sidecar before the model
  status helper runs. On that normal path, enabling the feature silently adds
  no `<agent_status>` block.
- Existing tests cover only messages with no pre-existing sidecar.

Compose safely with pre-existing string sidecars while remaining idempotent.
Distinguish a projection owned by this feature from unrelated API-only content
using a bounded, deterministic representation that survives persistence and
reload. Never parse or delete clean transcript content. If using an ownership
marker/suffix, recognize only the exact feature-owned terminal form and preserve
the pre-existing sidecar byte-for-byte; malformed/lookalike user or plugin text
must be treated as ordinary base content rather than destructively replaced.
Retain fail-closed handling for unsupported types and stable-row database
backfill.

Add regression coverage for a realistic pre-existing string `api_content`
sidecar (representing memory/plugin prefetch), repeated same-message request
builds, database close/reopen, and exact byte preservation of the original
sidecar plus exactly one status projection. Include a malformed/lookalike marker
case if the chosen ownership scheme can collide with ordinary content.

Run the focused tests, existing sidecar/cache/turn-context regressions,
compilation, and `git diff --check`. Update `BOOK_SELF_EVOLUTION_REPORT.md` with
this eighth review and exact results. Do not edit the book, commit, push, or
claim downstream task improvement.

Initializing agent...
↻ Resumed session 20260802_031522_523cd2 (8 user messages, 203 total messages)
────────────────────────────────────────

  ┊ 💻 preparing terminal…
  ┊ 💻 $         python3 - <<'PY' from pathlib import Path print(Path('agent/model_status_context.py').read_text()) print(Path('tests/agent/test_model_status_context.py').read_text()) PY  0.0s

┌─ Reasoning ──────────────────────────────────────────────────────────────────┐
**Evaluating assertions and tests**

I'm considering the current assertions and thinking that there’s one noted. It seems
 like I need to add some preexisting tests and also look at any malformed lookalike
 types. I wonder if having existing tests expecting equality might help clarify things
. So, my next step will be to search for any relevant information or examples that
 could assist in this situation. Let's figure this out together!
└──────────────────────────────────────────────────────────────────────────────┘
  ┊ 💻 preparing terminal…
  ┊ 💻 $         python3 - <<'PY' from pathlib import Path p=Path('agent/model_status_context.py') + 2 commands  1.2s
  ┊ 💻 preparing terminal…
  ┊ 💻 preparing terminal…
  ┊ 💻 preparing terminal…
  ┊ 💻 $         uv run --with pytest pytest tests/agent/test_api_content_sidecar.py tests/run_agent/test_background_review_cache_parity.py tests/agent/test_turn_context.py -q  10.4s
  ┊ 💻 $         python3 -m py_compile agent/model_status_context.py agent/conversation_loop.py agent/agent_init.py run_agent.py hermes_state.py + 1 command  0.2s
  ┊ 💻 $         git diff --stat + 1 command  0.0s
  ┊ 💻 preparing terminal…
  ┊ 💻 $         python3 - <<'PY' from pathlib import Path p=Path('BOOK_SELF_EVOLUTION_REPORT.md') + 5 commands  0.1s

╭─ ⚕ Hermes ───────────────────────────────────────────────────────────────────╮
Addressed the eighth-review pre-existing-sidecar collision.

Changes:

- Existing string api_content is now preserved byte-for-byte as the base.
- Added an exact feature-owned projection envelope:
  - <hermes_status_projection>
  - the <agent_status> block
  - </hermes_status_projection>
- Retries recognize only the exact terminal owned projection and reuse it unchanged.
- Malformed or lookalike markers remain ordinary base content and are never removed.
- Pre-existing memory/plugin sidecars now receive exactly one status projection.
- Unsupported values remain fail-closed.
- Stable row-identity backfill remains unchanged.
- Added coverage for:
  - realistic pre-existing API-only sidecars;
  - repeated same-message builds;
  - persistence/reload;
  - exact base-byte preservation;
  - malformed/lookalike marker behavior;
  - exactly one status block.

Verification:

- uv run --with pytest pytest tests/agent/test_model_status_context.py -q
  - Passed: 8 passed in 0.84s
- uv run --with pytest pytest tests/agent/test_api_content_sidecar.py tests/run_agent/test_background_review_cache_parity.py tests/agent/test_turn_context.py -q
  - Passed: 36 passed in 9.41s
- python3 -m py_compile agent/model_status_context.py agent/conversation_loop.py agent/agent_init.py run_agent.py hermes_state.py
  - Passed.
- git diff --check
  - Passed.

BOOK_SELF_EVOLUTION_REPORT.md now includes the eighth review round and exact results. No book changes, commit, push, or downstream task-improvement claim was made.
╰──────────────────────────────────────────────────────────────────────────────╯

Resume this session with:
  hermes --resume 20260802_031522_523cd2

Session:        20260802_031522_523cd2
Duration:       44s
Messages:       215 (9 user, 197 tool calls)