feat(rag): retry a failed LLM request before the first token lands — BOR_LLM_RETRIES/BOR_LLM_RETRY_DELAY with a live 'retrying' status

2026-09-02 10:52:38 -04:00
parent f04ddbe1f8
commit 88293ed02f
44 changed files with 2488 additions and 56 deletions
@@ -98,6 +98,15 @@ def app_server(mock_llm: int) -> Iterator[str]:
    # The production default stays 0.62 (re-tuned against the real
    # `embed` model's 0.41–0.84 cosine range, PLAN A8).
    env["BOR_RELEVANCE_THRESHOLD"] = "0.30"
+    # Phase 67 (LLM retry): the e2e pins the retry MECHANISM with instant
+    # waits (BOR_LLM_RETRY_DELAY=0 — the 5 s default is unit-pinned via
+    # tests/unit/test_config.py). BOR_LLM_RETRIES is forced to the code
+    # default (derived from the class field, never drifts from
+    # app/config.py) so the exhaustion test relies on the REAL budget and
+    # an operator's local (gitignored) .env cannot leak a different one
+    # into the app under test (the phase-61 leak-guard pattern).
+    env["BOR_LLM_RETRY_DELAY"] = "0"
+    env["BOR_LLM_RETRIES"] = str(_Settings.model_fields["llm_retries"].default)
    env.setdefault("BOR_DATABASE_URL", "postgresql+psycopg://reese:reese@localhost:5432/brain_of_reese")
    # Phase 16: admin auth must be set or create_app() refuses to boot.
    env["BOR_ADMIN_PASSWORD"] = ADMIN_PASSWORD