docs: bump version to v0.3, drop LiteLLM docstrings, fix index test table

DOCUMENTATION_INDEX.md

@@ -6,7 +6,7 @@ context diagram, and this index linking everything together. The Product Design
 the canonical authority spec on top of those.
 
 - **Repo:** `/Users/ernestprovo/dev/conclave/`
-- **Version:** 0.1.0 (package) · **License:** MIT
+- **Version:** 0.3.0 · **License:** MIT
 - **Last updated:** 2026-06-08
 
 ---
@@ -60,6 +60,9 @@ Package root: `src/conclave/` (installed as the `conclave` package; console scri
 | Adapter tests | [`tests/test_adapters.py`](tests/test_adapters.py) | Per-adapter `build_request` + `parse_response` for openai-compat/anthropic/gemini: system-hoist, max_tokens, role mapping, usage parsing, empty/malformed/error-status raises. |
 | Provider highway tests | [`tests/test_providers.py`](tests/test_providers.py) | `resolve_adapter` (built-in prefixes, per-provider URLs, custom endpoints, unknown-prefix raise), end-to-end `call_model`, and `redact()` (bearer/`sk-`/env-var-value/`x-api-key` scrubbing; pre-redacted provider errors). |
 | Registry/config tests | [`tests/test_registry_config.py`](tests/test_registry_config.py) | Name resolution, key-presence logic, config merge. |
+| CLI tests | [`tests/test_cli.py`](tests/test_cli.py) | Typer `CliRunner`: exit-code contract (0 success / 1 zero-usable-answers / 2 usage error), `--json` payload + exit code, human renderers per mode, `providers` table never prints secrets, aclose lifecycle. |
+| Transport tests | [`tests/test_transport.py`](tests/test_transport.py) | `post_json` via httpx `MockTransport`: success/error-status/non-JSON fallback, timeout & connect/HTTP errors → `TransportError` (key never leaks), client reuse/pooling, aclose idempotency. |
+| Logging tests | [`tests/test_logging.py`](tests/test_logging.py) | `CONCLAVE_LOG_LEVEL` resolution (default `WARNING`, case-insensitive, unknown → `WARNING`), factory contract, one-shot configuration. |
 | Fixtures | [`tests/conftest.py`](tests/conftest.py) | Shared fixtures; mocks the httpx transport so the suite needs no network and no API keys. |
 
 Run: `pytest` (config in `pyproject.toml`, `asyncio_mode = "auto"`).
@@ -70,6 +73,9 @@ Run: `pytest` (config in `pyproject.toml`, `asyncio_mode = "auto"`).
 |------|------|---------|
 | Packaging | [`pyproject.toml`](pyproject.toml) | hatchling build, deps (httpx, pydantic, rich, typer, pyyaml — no LLM SDK), dev extras, console script, pytest config. License: MIT. |
 | License | [`LICENSE`](LICENSE) | MIT License. Copyright (c) 2026 Ernest Provo. Matches the `pyproject.toml` license field. |
+| Security policy | [`SECURITY.md`](SECURITY.md) | BYO-keys vulnerability reporting policy: how to report, scope, and the key-handling guarantees consumers can rely on. |
+| Contributing guide | [`CONTRIBUTING.md`](CONTRIBUTING.md) | Dev setup, the BYO-keys contract for contributors, and the PR checklist (tests, ruff lint/format, coverage). |
+| Code of conduct | [`CODE_OF_CONDUCT.md`](CODE_OF_CONDUCT.md) | Contributor Covenant v2.1. |
 
 ---
 
@@ -83,6 +89,7 @@ Run: `pytest` (config in `pyproject.toml`, `asyncio_mode = "auto"`).
 
 | Date | Change |
 |------|--------|
+| 2026-06-08 | v0.3.0 version bump; CI foundation (Actions matrix, ruff, coverage floor, gitleaks, branch protection); redact() custom-endpoint key-leak fix (#14); status_error consolidation + conditional temperature (#16/#22); provider-metadata single-source + import-time drift guard + config memoization (#19/#15); CLI exit-code contract + httpx client lifecycle (#17/#20); transport/cli/logging test backfill (#18); public release + community files. |
 | 2026-06-08 | PDD §11 repositioned vs. new direct peers (`llm-council-core`, `the-llm-council`); §12 Q1/Q3/Q4/Q5 resolved. Index Tests table updated for the PR #2 split (`test_adapters.py`, `test_providers.py`). |
 | 2026-06-07 | v0.3 provider-highway refactor (LiteLLM removed → owned httpx transport + adapter registry); 3-core docs + PDD authored. |
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "conclave"
-version = "0.1.0"
+version = "0.3.0"
 description = "Bring-your-own-keys multi-model council CLI + library. Fan a prompt to N foundation models concurrently and merge their answers."
 readme = "README.md"
 requires-python = ">=3.11"

src/conclave/__init__.py

@@ -43,7 +43,7 @@
 )
 from .transport import aclose
 
-__version__ = "0.1.0"
+__version__ = "0.3.0"
 
 __all__ = [
     "Council",

src/conclave/config.py

@@ -70,10 +70,10 @@ class ConclaveConfig(BaseModel):
     endpoints: dict[str, CustomEndpoint] = Field(default_factory=dict)
 
     def resolve_model_id(self, name: str) -> str:
-        """Map a friendly name to a LiteLLM model id.
+        """Map a friendly name to a provider-prefixed model id.
 
         If ``name`` is unknown it is passed through verbatim, so a user can name
-        a council member by a raw LiteLLM id (e.g. ``"openai/gpt-4o"``).
+        a council member by a raw provider-prefixed id (e.g. ``"openai/gpt-4o"``).
         """
         return self.models.get(name, name)
 

src/conclave/council.py

@@ -1,7 +1,7 @@
 """The Council: concurrent multi-model fan-out plus synthesis.
 
 ``Council`` is the primary importable entry point. It resolves friendly names to
-LiteLLM model ids, skips any member whose API key is absent, fans the prompt out
+provider-prefixed model ids, skips any member whose API key is absent, fans the prompt out
 concurrently, collects partial results even when some members fail, and (in
 synthesize mode) asks a synthesizer model to merge the answers into one.
 
@@ -42,7 +42,7 @@ class Council:
     """A council of foundation models with an optional synthesizer.
 
     Args:
-        models: Friendly names (or raw LiteLLM ids) of council members.
+        models: Friendly names (or raw provider-prefixed model ids) of council members.
         synthesizer: Friendly name of the synthesizer model. If ``None``, the
             config default is used.
         config: Pre-loaded config; if ``None``, loaded from disk + defaults.

src/conclave/models.py

@@ -22,7 +22,7 @@ class ModelAnswer(BaseModel):
 
     Attributes:
         name: Friendly council member name (e.g. ``"grok"``).
-        model_id: Resolved LiteLLM model id (e.g. ``"xai/grok-4.3"``).
+        model_id: Resolved provider-prefixed model id (e.g. ``"xai/grok-4.3"``).
         answer: The raw text answer, or ``None`` if the call failed.
         latency_s: Wall-clock seconds for the call.
         usage: Token usage if reported by the provider.
@@ -73,7 +73,7 @@ class AdversarialResult(BaseModel):
             judge could not run.
         verdict_error: Error message if the judge step failed, else ``None``.
         judge: Friendly name of the judge (synthesizer) model.
-        judge_model_id: Resolved LiteLLM id of the judge.
+        judge_model_id: Resolved provider-prefixed id of the judge.
     """
 
     proposer: str
@@ -101,7 +101,7 @@ class CouncilResult(BaseModel):
             ``debate`` this mirrors the final round so existing consumers that
             read ``answers``/``synthesis`` keep working unchanged.
         synthesizer: Friendly name of the synthesizer model, if synthesis ran.
-        synthesizer_model_id: Resolved LiteLLM id of the synthesizer.
+        synthesizer_model_id: Resolved provider-prefixed id of the synthesizer.
         synthesis: The merged consolidated answer, or ``None`` if not produced.
             For ``debate`` this holds the final synthesized answer; for
             ``adversarial`` it mirrors the judge's verdict.

src/conclave/registry.py

@@ -2,7 +2,7 @@
 
 This module owns, in ONE place, everything that defines a built-in provider:
 
-* its LiteLLM provider prefix,
+* its provider prefix,
 * the env var(s) that satisfy its key,
 * (for OpenAI-compatible providers) its full ``/chat/completions`` URL,
 * the friendly-name -> default model id mapping.
@@ -65,7 +65,7 @@ class OpenAICompatProvider:
     env_vars: tuple[str, ...]
 
 
-# Friendly name -> default LiteLLM model id. Overridable via ~/.conclave/config.yml.
+# Friendly name -> default provider-prefixed model id. Overridable via ~/.conclave/config.yml.
 DEFAULT_MODELS: dict[str, str] = {
     "grok": "xai/grok-4.3",
     "gemini": "gemini/gemini-2.5-pro",
@@ -100,7 +100,7 @@ class OpenAICompatProvider:
     "anthropic": ("ANTHROPIC_API_KEY",),
 }
 
-# Derived: LiteLLM provider prefix -> the env var(s) that satisfy it. Built from
+# Derived: provider prefix -> the env var(s) that satisfy it. Built from
 # the single-source tables above so it can never drift from them. The first
 # present var in the list is the active key. Order matters for fallbacks.
 PROVIDER_ENV_VARS: dict[str, list[str]] = {
@@ -165,14 +165,14 @@ def _assert_metadata_consistent() -> None:
 
 
 def provider_prefix(model_id: str) -> str:
-    """Extract the LiteLLM provider prefix from a model id.
+    """Extract the provider prefix from a model id.
 
     Args:
         model_id: e.g. ``"xai/grok-4.3"``.
 
     Returns:
         The provider prefix (``"xai"``). If the id has no ``/`` we treat the
-        whole string as the prefix, which mirrors LiteLLM's bare-name handling.
+        whole string as the prefix (the bare-name convention for unprefixed ids).
     """
     return model_id.split("/", 1)[0] if "/" in model_id else model_id