## Problem
Provider construction, model discovery, validation, and cleanup lived in
one registry module. API and admin routes depended on registry-shaped
app state and legacy process-level provider helpers.
## Changes
| Before | After |
| --- | --- |
| `providers.registry` mixed provider factories, config, cache,
discovery, validation, and cleanup. | `providers.runtime` splits
factories, config, cache, model cache, discovery, validation, and
runtime orchestration. |
| API and admin routes read `app.state.provider_registry` and sometimes
created registries ad hoc. | API and admin routes use app-scoped
`ProviderRuntime` through `app.state.provider_runtime`. |
| `api.dependencies` kept process-global provider cache helpers. |
`api.dependencies` resolves providers only through the app-scoped
runtime. |
| Registry-shaped tests preserved old internal boundaries. |
Runtime-shaped tests assert provider config, construction, cache,
discovery, validation, and import boundaries. |
<!-- greptile_comment -->
<details open><summary><h3>Greptile Summary</h3></summary>
This PR moves provider lifecycle ownership from the old registry module
into an app-scoped runtime package. The main changes are:
- Split provider config, factory wiring, instance cache, model cache,
discovery, validation, and cleanup into `providers.runtime` modules.
- Updated API and admin routes to resolve providers and model metadata
through `app.state.provider_runtime`.
- Removed legacy process-global provider helpers and the deleted
`providers.registry` module.
- Updated docs, smoke metadata, import-boundary checks, and tests for
the new runtime ownership model.
- Bumped the package version and lockfile metadata for the production
refactor.
</details>
<h3>Confidence Score: 5/5</h3>
The provider runtime refactor appears merge-safe with no identified
blocking issues.
The changes consistently move provider ownership to app-scoped runtime
modules and update API, admin, docs, smoke metadata, import-boundary
checks, and tests around that architecture.
<details><summary><h3><a href="https://www.greptile.com/trex"><img
alt="T-Rex"
src="https://greptile-static-assets.s3.amazonaws.com/trex/trex_green.svg"
height="20" align="absmiddle"></a> T-Rex Logs</h3></summary>
**What T-Rex did**
- Ran a baseline and head comparison of provider registry and runtime
states, verifying the after-state shows head
state\_has\_provider\_registry=False and
state\_has\_provider\_runtime=True, that GET /v1/models and admin
endpoints respond with 200, and that provider\_resolver\_called via
runtime, with assertions passing.
- Verified that the four focused provider-runtime contract tests passed
in both the before and after refactor runs, including runtime split
checks, with exit code 0.
- Identified environmental blockers that prevented the smoke-runtime
workflow from running, including uv unavailability, missing pytest for
/usr/local/bin/python, and Python 3.11 being used despite pyproject.toml
requiring \>=3.14.
<a
href="https://app.greptile.com/trex/runs/12528505/artifacts"><picture><source
media="(prefers-color-scheme: dark)"
srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifactsDark.svg?v=1"><source
media="(prefers-color-scheme: light)"
srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=1"><img
alt="View all artifacts"
src="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=1"
height="32"></picture></a>
<sub><a href="https://www.greptile.com/trex"><img alt="T-Rex"
src="https://greptile-static-assets.s3.amazonaws.com/trex/trex_green.svg"
height="14" align="absmiddle"></a> Ran code and verified through
T-Rex</sub>
</details>
<sub>Reviews (1): Last reviewed commit: ["Refactor provider runtime
ownership"](https://github.com/alishahryar1/free-claude-code/commit/01d589488185c1f85112f1a49c47f04512846161)
| [Re-trigger
Greptile](https://app.greptile.com/api/retrigger?id=40312173)</sub>
<!-- /greptile_comment -->
## Problem
The CLI package preserved a generic adapter layer and managed Codex
parser path that did not match the supported customer workflows.
Messaging runs Claude Code sessions, while Codex is supported through
`fcc-codex` and extensions.
## Changes
| Before | After |
| --- | --- |
| `fcc-claude` and `fcc-codex` shared generic adapter plumbing. |
`fcc-claude` and `fcc-codex` use explicit launcher modules. |
| Messaging depended on a generic CLI session abstraction. | Messaging
depends on managed Claude Code sessions. |
| Codex catalog generation lived as a top-level CLI helper. | Codex
catalog generation lives under the Codex launcher owner. |
| Tests asserted deleted internal adapter shapes. | Tests assert
launcher, managed-Claude, and customer-surface behavior. |
## Summary
- Split monolithic `core/openai_responses/conversion.py` and `sse.py`
into focused protocol modules (input, output, stream, tools, reasoning,
events, etc.) behind an `OpenAIResponsesAdapter` facade.
- Wire `ClaudeProxyService.create_response()` through the adapter
instead of importing conversion helpers directly, tightening the
API/import boundary.
- Add Codex bridging for Responses `custom_tool_call` items and document
the adapter architecture in `ARCHITECTURE.md`.
## Test plan
- [x] `uv run pytest tests/core/openai_responses/
tests/api/test_openai_responses.py tests/cli/test_adapters.py
tests/contracts/test_import_boundaries.py`
- [x] Full CI via `.\scripts\ci.ps1`
Update live smoke model defaults for NIM, OpenRouter, and Gemini; normalize tool-call indexes; downgrade DeepSeek forced tool_choice; and add coverage for the provider smoke fixes.
## Summary
Adds support for the **OpenCode Go** subscription gateway at
`opencode.ai/zen/go/v1`, as requested in #504.
OpenCode Go exposes the same OpenAI-compatible Chat Completions API as
OpenCode Zen, so the implementation reuses `OpenCodeProvider` with a
configurable `provider_name` parameter — avoiding code duplication.
### Changes
- **Provider**: `OpenCodeProvider` now accepts `provider_name` (defaults
to `"OPENCODE"` for backward compatibility)
- **Catalog**: New `opencode_go` descriptor with correct base URL,
credential, and capabilities
- **Registry**: `_create_opencode_go` factory that passes
`provider_name="OPENCODE_GO"`
- **Settings**: `opencode_go_api_key` and `opencode_go_proxy` fields
- **Admin UI**: OpenCode Go API key, proxy, and smoke model config
fields
- **API services**: `opencode_go` added to OpenAI Chat Completions
upstream IDs
- **Smoke config**: Default smoke model `opencode_go/gpt-5.3-codex`
- **Tests**: New test for base URL, provider name, and API key; existing
tests updated
## Test plan
- [x] `test_opencode_go_provider_config_uses_correct_base_url_and_name`
— passes
- [x] `test_create_provider_instantiates_each_builtin` — covers
opencode_go
- [x]
`test_provider_and_platform_registries_include_advertised_builtins` —
covers opencode_go
- [x] `uv run ruff format`, `ruff check`, `ty check`, `pytest` — pass
locally on Python 3.14
Closes#504.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Alishahryar1 <alishahryar2@gmail.com>
- OpenAI-compat: emit minimal text block when only reasoning_content streams
(e.g. NIM) so clients get a text segment.
- Provider prereq: pass if text or thinking content is non-empty after strip.
- Add unit test for reasoning-only stream placeholder text.
- Make AnthropicToOpenAIConverter stateful: assistant text after tool_use is
deferred until matching tool_result, then replayed as a follow-up assistant
turn.
- After native streamed tool_use, emit top-level SSE error on transport
failure instead of assistant text_delta (avoids bad transcript shape).
- Add NIM preflight, streaming, converter, and product smoke regressions.
- Point DeepSeek at api.deepseek.com/anthropic with x-api-key headers
- Native request builder, DeepSeek-specific thinking/block sanitization
- Drop deepseek from OpenAI-chat server-tool preflight; update tests and docs
- Default smoke model deepseek-v4-pro; re-export dump_raw_messages_request
- Add ReasoningReplayMode and top-level reasoning replay in OpenAI conversion
- DeepSeek/NIM request bodies use reasoning_content when thinking is enabled
- NIM retries without reasoning_content on 400 from upstream
- Per-provider smoke models (FCC_SMOKE_MODEL_*) independent of MODEL mapping
- Fix smoke model override parsing for owner/model names with slashes
- Live smoke: reasoning tool continuation uses synthetic thinking+tool history
- Tests and docs updated
Consolidates the incremental refactor work into a single change set: modular web tools (api/web_tools), native Anthropic request building and SSE block policy, OpenAI conversion and error handling, provider transports and rate limiting, messaging handler and tree queue, safe logging, smoke tests, and broad test coverage.
- Updated DEFAULT_TARGETS in config.py to include new targets: clients, llamacpp, and lmstudio, while removing contract and optimizations.
- Introduced TARGET_ALIASES for better target management.
- Added TARGET_REQUIRED_ENV to specify environment variables needed for each target.
- Enhanced SmokeOutcome in report.py to include classification of outcomes for better reporting.
- Implemented classify_outcome function to categorize smoke test results.
- Added new test for stop endpoint in test_api_live.py to ensure proper error handling.
- Updated test_auth_live.py to enforce auth token requirements and utilize environment files.
- Changed target from vscode to clients in test_client_shapes_live.py.
- Removed obsolete test_feature_manifest.py and test_stream_contracts.py files.
- Added new skip helpers in skips.py to manage upstream unavailability scenarios.
- Created new tests for local provider endpoints in test_local_provider_endpoints_live.py.
- Added comprehensive feature inventory tests in tests/contracts/test_feature_manifest.py.
- Implemented stream contract tests in tests/contracts/test_stream_contracts.py.
## Summary
- add an opt-in local `smoke/` pytest suite for API, auth, providers,
CLI, IDE-shaped requests, messaging, voice, tools, and thinking stream
contracts
- keep smoke tests out of normal CI collection with `testpaths =
["tests"]`
- write sanitized smoke artifacts under `.smoke-results/`
## Verification
- `uv run ruff format`
- `uv run ruff check`
- `uv run ty check`
- `uv run ty check smoke`
- `FCC_LIVE_SMOKE=1 FCC_SMOKE_TARGETS=all FCC_SMOKE_RUN_VOICE=1 uv run
pytest smoke -n 0 -m live -s --tb=short` -> 17 passed, 9 skipped
- `uv run pytest` -> 904 passed
## Notes
- Skipped live checks require local credentials/tools/services, such as
provider models, Telegram/Discord targets, voice backend, or Claude CLI.
- `claude-pick` smoke was intentionally removed.
Alishahryar1
