fix(deps): constrain OpenAI SDK below v3

pyproject.toml

@@ -23,7 +23,9 @@ classifiers = [
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
 ]
 dependencies = [
-    "openai>=2.45",  # GPT-5.6: typed reasoning.mode, prompt_cache_options, and cache_write_tokens
+    # 2.45 adds the GPT-5.6 typed fields used below. Version 3 replaces the
+    # httpx transport family, so migrate the streaming retry boundary first.
+    "openai>=2.45,<3",
     "anthropic>=0.117",  # tracks the release current at claude-opus-5 onboarding; hard runtime floor is still 0.105 (mid-conversation system blocks) — Opus 5 itself needs no new SDK surface (model ids are opaque strings; "refusal" has been in the StopReason literal since ~0.95). Raise this when adopting fast mode / server-side fallbacks / advisor / mid-conversation tool changes, which DO need newer typed params.
     "httpx>=0.28",
     "mcp>=1.27,<2",  # v2 is a breaking rewrite (2.0.0a1 live 2026-06-11; stable ~2026-07-27) — streamablehttp_client removed, 2-tuple transport, snake_case types; migrate deliberately

uv.lock

@@ -2639,7 +2639,7 @@ requires-dist = [
     { name = "lacme", specifier = ">=1.0.5" },
     { name = "mcp", specifier = ">=1.27,<2" },
     { name = "mypy", marker = "extra == 'dev'", specifier = ">=1.14" },
-    { name = "openai", specifier = ">=2.45" },
+    { name = "openai", specifier = ">=2.45,<3" },
     { name = "pillow", specifier = ">=10" },
     { name = "psycopg", extras = ["binary"], specifier = ">=3.2" },
     { name = "pydantic", specifier = ">=2.0" },