Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)
Python
Simplify README around customer workflows (#1345)
Ali Khokharacadf308c4f1
diff --git a/README.md b/README.mdindex 6e4c95b9..eb224957 100644--- a/README.md+++ b/README.md@@ -7,56 +7,32 @@</picture></h1>-Use Claude Code, Codex, Pi, or their IDE extensions through your own provider-backed proxy.-[](https://opensource.org/licenses/MIT)[](https://www.python.org/downloads/)[](https://github.com/astral-sh/uv)-[](https://github.com/Alishahryar1/free-claude-code/actions/workflows/tests.yml)+[](https://github.com/Alishahryar1/free-claude-code/actions/workflows/tests.yml)[](https://pypi.org/project/ty/)[](https://github.com/astral-sh/ruff)[](https://github.com/Delgan/loguru)-Run your coding agents with free, paid, or local models. Choose and validate providers from one local Admin UI.-[Quick Start](#quick-start) · [Providers](#choose-a-provider) · [Clients](#connect-your-client) · [Integrations](#optional-integrations) · [Manage](#manage-your-installation)</div>-<div align="center">- <img src="assets/pic.png" alt="Free Claude Code in action" width="700">- <p><em>Claude Code running through the Free Claude Code proxy.</em></p>-</div>--<div align="center">- <img src="assets/codex.png" alt="Codex CLI in action through Free Claude Code" width="700">- <p><em>Codex CLI using the local FCC Responses provider.</em></p>-</div>--<a id="model-picker"></a>+## What You Get-<div align="center">- <img src="assets/cc-model-picker.png" alt="Claude Code model picker showing gateway models" width="700">- <p><em>Claude Code native <code>/model</code> picker with FCC gateway models.</em></p>-</div>+- **Use your preferred coding agent.** Run Claude Code, Codex, or Pi with FCC.+- **Choose your own models.** Connect free, paid, or local providers and search their models from one Admin UI.+- **Route work your way.** Set one default model or map Fable, Opus, Sonnet, and Haiku separately.+- **Save time and tokens.** Five built-in optimizations handle quota probes, command-prefix detection, title generation, suggestion mode, and filepath extraction locally instead of calling your provider.+- **Keep coding-agent capabilities.** Use streaming, tools, reasoning, and image input with compatible models.+- **Work where you want.** Launch from your desktop, connect supported IDEs, or use optional Discord and Telegram bots with voice notes.<div align="center">- <img src="assets/codex-model-picker.png" alt="Codex model picker showing generated FCC model catalog" width="700">- <p><em>Codex native <code>/model</code> picker with the generated FCC catalog.</em></p>+ <img src="assets/pic.png" alt="Claude Code running with Free Claude Code" width="700">+ <p><em>Claude Code running with FCC.</em></p></div>-## What You Get--- Launch Claude Code with `fcc-claude`, Codex with `fcc-codex`, or Pi with `fcc-pi`.-- Run FCC in the background from a desktop launcher on Windows or macOS.-- Switch among 31 cloud and local providers from the Admin UI.-- Use each coding agent's native model picker.-- Route Fable, Opus, Sonnet, Haiku, and fallback traffic to different models.-- Keep streaming, tool use, reasoning, and image input across compatible models.-- Connect Claude Code and Codex in VS Code or Claude Code through JetBrains ACP.-- Optionally run Claude Code sessions through Discord or Telegram with voice-note transcription.-- Protect the local proxy with optional token authentication.-## Quick Start<a id="install"></a>@@ -105,8 +81,7 @@ To print the installed Free Claude Code version without starting the server,run `fcc-server --version`.When using `fcc-server`, keep the terminal open. The Admin UI opens in your-browser once the server is healthy by default. Its address is shown in the-startup log:+browser after startup by default. Its address is also shown in the log:```textINFO: Admin UI: http://127.0.0.1:8082/admin (local-only)@@ -125,7 +100,7 @@ Use the port shown in your terminal if it differs from `8082`.5. Click **Validate**, then **Apply**.<div align="center">- <img src="assets/admin-page.png" alt="Local admin UI for proxy settings" width="700">+ <img src="assets/admin-page.png" alt="Free Claude Code Admin UI" width="700"></div>### 4. Run Your Coding Agent@@ -156,6 +131,13 @@ fcc-codex exec "hello"`fcc-pi` registers FCC only for that Pi process; your existing Pi settings, sessions, credentials, and extensions remain unchanged.+<a id="model-picker"></a>++<div align="center">+ <img src="assets/cc-model-picker.png" alt="Claude Code model picker showing FCC models" width="700">+ <p><em>Select an FCC model from Claude Code's native <code>/model</code> picker.</em></p>+</div>+## Choose A Provider1. Open a provider link below for its key, models, or setup instructions.@@ -165,6 +147,9 @@ fcc-codex exec "hello"models, enter `<provider-id>/<exact-provider-model-id>` manually.4. Click **Validate**, then **Apply**.+<details>+<summary><strong>Provider catalog</strong></summary>+| Provider | Admin UI setting | Example `MODEL` || --- | --- | --- || [NVIDIA NIM](https://build.nvidia.com/settings/api-keys) | `NVIDIA_NIM_API_KEY` | `nvidia_nim/nvidia/nemotron-3-super-120b-a12b` |@@ -199,39 +184,38 @@ fcc-codex exec "hello"| [llama.cpp](https://github.com/ggml-org/llama.cpp) | `LLAMACPP_BASE_URL` | `llamacpp/<model-id>` || [Ollama](https://ollama.com/) | `OLLAMA_BASE_URL` | `ollama/<model-tag>` |-Important provider notes:+</details>++<details>+<summary><strong>Provider-specific setup</strong></summary>- OpenAI uses your ChatGPT subscription rather than an API key. Connect from- **Providers → Connected accounts**; browser PKCE is the default and device- code is available for headless setups. FCC stores its own renewable- credentials under `~/.fcc/auth/` and leaves Codex login untouched. Restart- an already-running agent after connecting to refresh its model picker.+ **Providers → Connected accounts** in the Admin UI. Use device code on+ headless systems. Restart an already-running agent after connecting.- Azure OpenAI uses the deployment names from your resource. Set`AZURE_OPENAI_BASE_URL` to its complete v1 endpoint, such as`https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/`, and select a- deployment that supports Chat Completions. Azure does not expose custom- deployment names through its data-plane model list, so enter the deployment- name as a custom model slug.+ deployment that supports Chat Completions. Enter the deployment name as a+ custom model slug if it does not appear in the model dropdown.- Mistral Codestral uses a separate key from Mistral La Plateforme.- Kimi Code subscription keys use `kimi_code/`; Kimi API credit keys use`kimi/`. Kimi Code plans are for personal interactive coding-agent use under[Kimi's community guidelines](https://www.kimi.com/code/docs/en/kimi-code/community-guidelines.html).- OpenCode Zen and OpenCode Go share `OPENCODE_API_KEY` but use the explicit`opencode_zen/` and `opencode_go/` model prefixes.-- Amazon Bedrock uses its Mantle OpenAI-compatible endpoint. Set- `BEDROCK_BASE_URL` to the endpoint for the same region as the API key and- select one of the models returned by FCC's model picker.+- For Amazon Bedrock, set `BEDROCK_BASE_URL` to the URL for the same region as+ the API key and select one of the listed models.- Vertex AI uses Google Application Default Credentials instead of an API key.Locally, run `gcloud auth application-default login` once; service-accountfiles and attached service accounts also work. Set `VERTEX_PROJECT_ID`, and- optionally change `VERTEX_LOCATION` from its `global` default. FCC refreshes- expiring access tokens automatically.+ optionally change `VERTEX_LOCATION` from its `global` default.- Cloudflare requires both its API token and account ID.-- Ollama Cloud connects directly to `ollama.com`; use the exact model IDs shown- by FCC's model picker. Local Ollama remains available through the separate- `ollama/` prefix.+- For Ollama Cloud, use the exact model IDs shown in the model picker. Local+ Ollama uses the separate `ollama/` prefix.- Prefer tool-capable models for coding agents. Local models also need enough context for the agent's system prompt and tool definitions.+</details>+<details><summary><strong>Local provider setup</strong></summary>@@ -254,13 +238,17 @@ Use the tag shown by `ollama list` with the `ollama/` prefix. `OLLAMA_BASE_URL`</details>-### Optional Model-Tier Routing+<details>+<summary><strong>Optional model-tier routing</strong></summary>`MODEL` is the fallback for every request. Select a model for `MODEL_FABLE`, `MODEL_OPUS`, `MODEL_SONNET`, or `MODEL_HAIKU` to override an individual Claude Code tier; select **None** to use `MODEL`.For example, route Opus to `nvidia_nim/nvidia/nemotron-3-super-120b-a12b`, Sonnet to `open_router/openrouter/free`, Haiku to `lmstudio/qwen3.5-coder`, and keep `MODEL` on `zai/glm-5.2`.-### Reasoning Control+</details>++<details>+<summary><strong>Reasoning control</strong></summary>Open **Admin UI → Model Config → Reasoning** and select the behavior you want.@@ -273,6 +261,8 @@ Open **Admin UI → Model Config → Reasoning** and select the behavior you wanProviders that do not support a selected control retain their own behavior.+</details>+<a id="connect-your-client"></a>## Connect Your Client@@ -304,28 +294,30 @@ Match the port and authentication token to the Admin UI, then reload the extensi<details><summary><strong>Codex App</strong></summary>-Start FCC, then add its provider and generated model catalog to your user-level Codex configuration.+Start FCC, then edit your Codex configuration:++- Windows: `%USERPROFILE%\.codex\config.toml`+- macOS: `~/.codex/config.toml`-**Windows** — edit `%USERPROFILE%\.codex\config.toml` and replace `YOUR_USERNAME`:+Add the matching model-catalog path and replace `YOUR_USERNAME`.++Windows:```toml-model_provider = "fcc"-model = "nvidia_nim/nvidia/nemotron-3-super-120b-a12b"model_catalog_json = "C:/Users/YOUR_USERNAME/.fcc/codex-model-catalog.json"+```-[model_providers.fcc]-name = "Free Claude Code"-base_url = "http://127.0.0.1:8082/v1"-http_headers = { Authorization = "Bearer freecc" }-wire_api = "responses"+macOS:++```toml+model_catalog_json = "/Users/YOUR_USERNAME/.fcc/codex-model-catalog.json"```-**macOS** — edit `~/.codex/config.toml` and replace `YOUR_USERNAME`:+Then add the shared FCC settings:```tomlmodel_provider = "fcc"model = "nvidia_nim/nvidia/nemotron-3-super-120b-a12b"-model_catalog_json = "/Users/YOUR_USERNAME/.fcc/codex-model-catalog.json"[model_providers.fcc]name = "Free Claude Code"@@ -334,7 +326,8 @@ http_headers = { Authorization = "Bearer freecc" }wire_api = "responses"```-Match the model, port, and bearer token to the Admin UI. Restart the Codex App after setup or model changes, then use its model picker to select any FCC provider/model slug.+Match the model, port, and bearer token to the Admin UI. Restart the Codex App+after setup or model changes, then select an FCC model from its model picker.</details>@@ -416,10 +409,6 @@ Restart Claude Code or the IDE after saving the file.Configure integrations from **Admin UI → Messaging**, then click **Validate** and **Apply**.-<div align="center">- <img src="assets/admin-messaging.png" alt="Admin UI Messaging view with bot and voice settings" width="700">-</div>-<details><summary><strong>Discord bot</strong></summary>@@ -458,38 +447,28 @@ Configure integrations from **Admin UI → Messaging**, then click **Validate**<details><summary><strong>Voice notes</strong></summary>-Re-run the installer with the voice backend you need.+Choose the voice backend you want, then re-run the installer with its option.++| Voice backend | macOS/Linux option | Windows option |+| --- | --- | --- |+| NVIDIA NIM transcription | `--voice-nim` | `-VoiceNim` |+| Local Whisper on CPU or CUDA | `--voice-local` | `-VoiceLocal` |+| Both backends | `--voice-all` | `-VoiceAll` |+| Local Whisper with CUDA 13.0 | `--voice-local --torch-backend cu130` | `-VoiceLocal -TorchBackend cu130` |++The examples below install NVIDIA NIM transcription. To use another backend,+replace the final option with the matching one from the table.macOS/Linux:```bash-# NVIDIA NIM transcriptioncurl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-nim--# Local Whisper on CPU or CUDA-curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-local--# Both backends-curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-all--# Local Whisper with the CUDA 13.0 PyTorch backend-curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-local --torch-backend cu130```Windows PowerShell:```powershell-# NVIDIA NIM transcription& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceNim--# Local Whisper on CPU or CUDA-& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceLocal--# Both backends-& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceAll--# Local Whisper with the CUDA 13.0 PyTorch backend-& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceLocal -TorchBackend cu130```Restart `fcc-server`. In **Admin UI → Messaging → Voice**, enable voice notes, select `cpu`, `cuda`, or `nvidia_nim`, and choose the Whisper model. Local gated models need `HUGGINGFACE_API_KEY`; NVIDIA NIM transcription needs `NVIDIA_NIM_API_KEY`.@@ -504,8 +483,7 @@ Re-run the matching command from [Install Or Update](#install).### Uninstall-Stop every running FCC command first. The uninstaller verifies every FCC command is gone-before deleting its managed data.+Stop every running FCC command before uninstalling.**Removes**diff --git a/smoke/features.py b/smoke/features.pyindex b5bbdeaf..e4221ad6 100644--- a/smoke/features.py+++ b/smoke/features.py@@ -1,22 +1,18 @@"""Public feature inventory for contract, prerequisite, and product smoke tests.-The inventory is intentionally explicit. README-advertised behavior and exposed-public surface area must have deterministic pytest contract coverage plus a-product E2E scenario when that behavior is a user-facing product path. Liveness-and route probes live in ``smoke/prereq`` and do not count as product coverage.+The inventory is intentionally explicit. Public product behavior must have+deterministic pytest contract coverage plus a product E2E scenario when that+behavior is a user-facing product path. Liveness and route probes live in+``smoke/prereq`` and do not count as product coverage."""from dataclasses import dataclass-from typing import Literal--FeatureSource = Literal["readme", "public_surface"]@dataclass(frozen=True, slots=True)class FeatureCoverage:feature_id: strtitle: str- source: FeatureSourcepytest_contract_tests: tuple[str, ...]live_prereq_tests: tuple[str, ...]product_e2e_tests: tuple[str, ...]@@ -30,28 +26,10 @@ class FeatureCoverage:return bool(self.pytest_contract_tests)-README_FEATURES: tuple[str, ...] = (- "zero_cost_provider_access",- "drop_in_claude_code_replacement",- "drop_in_codex_replacement",- "pi_cli_integration",- "provider_matrix",- "per_model_mapping",- "thinking_token_support",- "heuristic_tool_parser",- "discord_telegram_bot",- "optional_authentication",- "vscode_extension",- "intellij_extension",- "voice_notes",-)--FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("zero_cost_provider_access","Configured provider accepts real conversation turns",- "readme",("tests/api/test_dependencies.py", "tests/providers/"),("test_configured_provider_models_stream_successfully",),("test_provider_text_multiturn_e2e",),@@ -62,7 +40,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("drop_in_claude_code_replacement","Claude-compatible API, CLI, and editor protocol flows work",- "readme",("tests/api/test_api.py", "tests/cli/test_cli.py"),("test_probe_and_models_routes", "test_claude_cli_prompt_when_available"),(@@ -86,7 +63,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("drop_in_codex_replacement","OpenAI Responses API and Codex CLI adapter route through the proxy",- "readme",("tests/api/test_openai_responses.py","tests/cli/test_entrypoints.py",@@ -102,7 +78,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("pi_cli_integration","Pi discovers FCC models and sends Anthropic Messages through the proxy",- "readme",("tests/cli/test_entrypoints.py",),("test_probe_and_models_routes",),("test_pi_cli_prompt_e2e",),@@ -113,7 +88,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("provider_matrix","Every configured provider prefix can satisfy conversation scenarios",- "readme",("tests/api/test_dependencies.py", "tests/providers/"),("test_configured_provider_models_stream_successfully",),("test_provider_matrix_presence_e2e", "test_provider_text_multiturn_e2e"),@@ -124,7 +98,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("per_model_mapping","Fable, Opus, Sonnet, Haiku, and fallback mappings route explicitly",- "readme",("tests/application/test_routing.py", "tests/config/test_config.py"),("test_model_mapping_configuration_is_consistent",),("test_model_mapping_matrix_e2e",),@@ -135,7 +108,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("mixed_provider_mapping","Model-specific overrides can route to different providers",- "public_surface",("tests/application/test_routing.py", "tests/config/test_config.py"),("test_mixed_provider_model_mapping_when_configured",),("test_model_mapping_matrix_e2e",),@@ -146,7 +118,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("thinking_token_support","Thinking history, adaptive thinking, and redacted blocks are accepted",- "readme",("tests/contracts/test_stream_contracts.py","tests/providers/test_open_router.py",@@ -166,7 +137,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("heuristic_tool_parser","Tool use and tool result continuation survive provider/client paths",- "readme",("tests/providers/test_parsers.py", "tests/contracts/test_stream_contracts.py"),("test_live_tool_use_when_configured_model_supports_tools",),(@@ -183,7 +153,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("request_optimization","Local request optimizations return product responses without providers",- "public_surface",("tests/api/test_optimization_handlers.py","tests/api/test_routes_optimizations.py",@@ -197,7 +166,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("smart_rate_limiting","Transient retries and disconnect cleanup preserve follow-up requests",- "public_surface",("tests/providers/test_provider_admission.py","tests/providers/test_nvidia_nim_degraded_retry.py",@@ -211,7 +179,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("provider_hot_swap","Provider config changes preserve active streams while new requests switch",- "public_surface",("tests/runtime/test_provider_manager.py","tests/api/test_response_streams.py",@@ -226,7 +193,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("discord_telegram_bot","Discord and Telegram product flows render progress and transcripts",- "readme",("tests/messaging/test_discord_platform.py","tests/messaging/test_telegram.py",@@ -250,7 +216,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("subagent_control","Task-like tool output is rendered and controlled as foreground work",- "public_surface",("tests/providers/test_subagent_interception.py",),(),("test_messaging_subagent_control_e2e",),@@ -261,7 +226,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("extensible_provider_platform_abcs","Provider and platform factories expose built-in extension points",- "public_surface",("tests/contracts/test_feature_manifest.py","tests/providers/test_provider_runtime.py",@@ -275,7 +239,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("optional_authentication","Canonical bearer proxy authentication is enforced",- "readme",("tests/api/test_auth.py",),("test_bearer_auth_is_the_only_supported_header_shape",),("test_api_bearer_auth_contract_e2e",),@@ -286,7 +249,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("vscode_extension","VS Code protocol-shaped requests work against the proxy",- "readme",("tests/core/anthropic/test_models.py::test_messages_request_accepts_adaptive_thinking_type",),@@ -299,7 +261,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("intellij_extension","JetBrains/ACP protocol-shaped requests work against the proxy",- "readme",("tests/core/anthropic/test_models.py::test_messages_request_accepts_adaptive_thinking_type",),@@ -312,7 +273,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("voice_notes","Voice note intake, cancellation, and transcription backends work",- "readme",("tests/messaging/test_voice_handlers.py","tests/messaging/test_transcription.py",@@ -330,7 +290,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("anthropic_api_routes","Messages, count_tokens, errors, and stop use Anthropic-compatible shapes",- "public_surface",("tests/api/test_api.py",),("test_probe_and_models_routes", "test_stop_endpoint_reports_no_messaging"),(@@ -346,7 +305,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("probe_routes","HEAD and OPTIONS compatibility probes are accepted",- "public_surface",("tests/api/test_api.py::test_probe_endpoints_return_204_with_allow_headers",),("test_probe_and_models_routes",),(),@@ -358,7 +316,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("count_tokens_contract","Token counting accepts full Claude content payloads",- "public_surface",("tests/api/test_request_utils.py",),("test_count_tokens_accepts_thinking_tools_and_results",),("test_api_count_tokens_full_payload_e2e",),@@ -369,7 +326,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("provider_proxy_timeout_config","Provider proxies and HTTP timeout settings reach provider config",- "public_surface",("tests/api/test_dependencies.py", "tests/providers/test_provider_runtime.py"),(),("test_proxy_timeout_config_e2e",),@@ -380,7 +336,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("lmstudio_endpoint","LM Studio Messages and local no-key operation work when running",- "public_surface",("tests/providers/test_lmstudio.py",),("test_lmstudio_models_endpoint_when_available",),("test_lmstudio_messages_e2e",),@@ -391,7 +346,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("llamacpp_endpoint","llama.cpp OpenAI Chat and local no-key operation work when running",- "public_surface",("tests/providers/test_llamacpp.py",),("test_llamacpp_models_endpoint_when_available",),("test_llamacpp_openai_chat_e2e",),@@ -402,7 +356,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("ollama_endpoint","Ollama OpenAI Chat and local no-key operation work when running",- "public_surface",("tests/providers/test_ollama.py",),("test_ollama_models_endpoint_when_available",),("test_ollama_openai_chat_e2e",),@@ -413,7 +366,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("package_cli_entrypoints","Installed package scripts report version and start the server",- "public_surface",("tests/cli/test_entrypoints.py", "tests/core/test_version.py"),("test_fcc_server_entrypoint_starts_server",),(@@ -427,7 +379,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("claude_cli_drop_in","Claude CLI can send adaptive thinking and tool-shaped history",- "public_surface",("tests/cli/test_cli.py",),("test_claude_cli_prompt_when_available",),(@@ -448,7 +399,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("messaging_commands","Messaging commands clear exact reply subtrees or whole managed chats",- "public_surface",("tests/messaging/test_handler.py","tests/messaging/test_handler_integration.py",@@ -469,7 +419,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("tree_threading","Reply-based branches fork sessions and stay scoped",- "public_surface",("tests/messaging/test_tree_queue.py","tests/messaging/test_tree_concurrency.py",@@ -489,7 +438,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("restart_restore","Persisted tree state restores reply routing after restart",- "public_surface",("tests/messaging/test_restart_reply_restore.py",),(),("test_restart_restore_and_session_persistence_e2e",),@@ -500,7 +448,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("session_persistence","Session JSON preserves scoped trees and message logs",- "public_surface",("tests/messaging/test_session_store_edge_cases.py",),(),("test_restart_restore_and_session_persistence_e2e",),@@ -511,7 +458,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("config_env_precedence","FCC_ENV_FILE, dotenv, and process env precedence are deterministic",- "public_surface",("tests/config/test_config.py",),(),("test_env_precedence_e2e",),@@ -522,7 +468,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("removed_env_migration","Removed thinking env vars are ignored without changing defaults",- "public_surface",("tests/config/test_config.py",),(),("test_removed_env_migration_e2e",),@@ -533,7 +478,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = (FeatureCoverage("streaming_error_mapping","Canonical execution failures map to protocol-correct terminal output",- "public_surface",("tests/api/test_execution_failure_contract.py","tests/core/test_failure_protocol_mapping.py",@@ -553,10 +497,6 @@ FEATURE_INVENTORY: tuple[FeatureCoverage, ...] = ()-def feature_ids(*, source: FeatureSource | None = None) -> set[str]:+def feature_ids() -> set[str]:"""Return feature IDs covered by the inventory."""- return {- feature.feature_id- for feature in FEATURE_INVENTORY- if source is None or feature.source == source- }+ return {feature.feature_id for feature in FEATURE_INVENTORY}diff --git a/tests/contracts/test_feature_manifest.py b/tests/contracts/test_feature_manifest.pyindex fb0c84bd..5d4df81a 100644--- a/tests/contracts/test_feature_manifest.py+++ b/tests/contracts/test_feature_manifest.py@@ -19,37 +19,7 @@ from free_claude_code.providers.openai_chat import ()from free_claude_code.providers.openai_codex import OpenAICodexProviderfrom free_claude_code.providers.vertex import VertexProvider-from smoke.features import FEATURE_INVENTORY, README_FEATURES, feature_ids--VALID_SOURCE = {"readme", "public_surface"}---def test_every_readme_feature_has_inventory_entry() -> None:- missing = sorted(set(README_FEATURES) - feature_ids(source="readme"))- extra_readme = sorted(feature_ids(source="readme") - set(README_FEATURES))- assert not missing, f"README features missing inventory entries: {missing}"- assert not extra_readme, (- f"README inventory entries not in README_FEATURES: {extra_readme}"- )---def test_readme_provider_table_covers_full_catalog() -> None:- repo_root = Path(__file__).resolve().parents[2]- readme = (repo_root / "README.md").read_text(encoding="utf-8")- provider_section = readme.split("## Choose A Provider", 1)[1].split("\n## ", 1)[0]- rows = [line for line in provider_section.splitlines() if line.startswith("| [")]-- assert f"Switch among {len(PROVIDER_CATALOG)} cloud and local providers" in readme- prefixes: list[str] = []- for row in rows:- example_cell = row.split("|")[3]- match = re.search(r"`([a-z0-9_]+)/", example_cell)- assert match is not None, row- prefixes.append(match.group(1))-- assert len(rows) == len(PROVIDER_CATALOG)- assert len(prefixes) == len(set(prefixes))- assert set(prefixes) == set(PROVIDER_CATALOG)+from smoke.features import FEATURE_INVENTORYdef test_feature_inventory_is_unique_and_decision_complete() -> None:@@ -58,7 +28,6 @@ def test_feature_inventory_is_unique_and_decision_complete() -> None:assert "claude_pick" not in idsfor feature in FEATURE_INVENTORY:- assert feature.source in VALID_SOURCE, featureassert feature.title.strip(), featureassert feature.skip_policy.strip(), featureassert feature.pytest_contract_tests, feature@@ -92,7 +61,7 @@ def test_product_coverage_is_not_satisfied_by_prereq_probes() -> None:assert all("_e2e" in name for name in feature.product_e2e_tests), feature-def test_provider_and_platform_registries_include_advertised_builtins() -> None:+def test_provider_and_platform_registries_include_builtins() -> None:specialized_provider_classes = {"openai": OpenAICodexProvider,"nvidia_nim": NvidiaNimProvider,diff --git a/tests/contracts/test_architecture_contracts.py b/tests/contracts/test_packaging_contracts.pysimilarity index 62%rename from tests/contracts/test_architecture_contracts.pyrename to tests/contracts/test_packaging_contracts.pyindex 1d7d01f1..910fc4d2 100644--- a/tests/contracts/test_architecture_contracts.py+++ b/tests/contracts/test_packaging_contracts.py@@ -1,30 +1,6 @@import reimport tomllibfrom pathlib import Path-from urllib.parse import unquote, urlsplit---def test_architecture_document_exists() -> None:- repo_root = Path(__file__).resolve().parents[2]-- assert (repo_root / "ARCHITECTURE.md").is_file()---def test_architecture_document_relative_links_resolve() -> None:- repo_root = Path(__file__).resolve().parents[2]- architecture = repo_root / "ARCHITECTURE.md"- text = architecture.read_text(encoding="utf-8")-- missing: list[str] = []- for match in re.finditer(r"(?<!!)\[[^\]]+\]\(([^)]+)\)", text):- raw_target = match.group(1).strip()- target = raw_target.split("#", 1)[0]- if not target or urlsplit(target).scheme:- continue- if not (repo_root / unquote(target)).exists():- missing.append(raw_target)-- assert missing == []def test_root_env_example_is_the_single_template_source() -> None:diff --git a/tests/contracts/test_smoke_tiers.py b/tests/contracts/test_smoke_tiers.pyindex 801cf9d5..842b7f4f 100644--- a/tests/contracts/test_smoke_tiers.py+++ b/tests/contracts/test_smoke_tiers.py@@ -9,15 +9,6 @@ from smoke.lib.report_summary import format_summary, summarize_reportsfrom smoke.lib.skips import skip_if_upstream_unavailable_events-def test_smoke_readme_uses_env_gated_serial_commands() -> None:- repo_root = Path(__file__).resolve().parents[2]- text = (repo_root / "smoke" / "README.md").read_text(encoding="utf-8")-- assert "FCC_LIVE_SMOKE=1" in text- assert "-n 0" in text- assert "-m live" not in text--def test_smoke_report_summary_counts_regression_classes(tmp_path: Path) -> None:report = {"outcomes": [diff --git a/tests/scripts/test_installers.py b/tests/scripts/test_installers.pyindex 68944683..9766fd6a 100644--- a/tests/scripts/test_installers.py+++ b/tests/scripts/test_installers.py@@ -1649,16 +1649,6 @@ def test_install_ps1_uses_x64_python_for_windows_arm_compatibility() -> None:assert '$PythonRequest = "cpython-3.14.0-windows-x86_64-none"' in powershell-def test_readme_install_section_has_no_manual_git_prerequisite() -> None:- readme = (_repo_root() / "README.md").read_text(encoding="utf-8")- install_section = readme.split("### 1. Install Or Update", 1)[1].split(- "### 2. Start FCC", 1- )[0]-- assert "Install Git" not in install_section- assert "official native installers" not in install_section--@pytest.mark.parametrize("powershell", _powershells())def test_install_ps1_rejects_invalid_download_before_execution(powershell: str,diff --git a/tests/scripts/test_uninstallers.py b/tests/scripts/test_uninstallers.pyindex 48fe0df7..c15c8245 100644--- a/tests/scripts/test_uninstallers.py+++ b/tests/scripts/test_uninstallers.py@@ -676,17 +676,3 @@ def test_uninstallers_guard_running_commands_and_preserve_shared_owners() -> Nonassert "is not installed" in textassert "no tool" not in textassert "nothing to uninstall" not in text---def test_readme_uninstall_uses_raw_urls_and_verification_contract() -> None:- text = (_repo_root() / "README.md").read_text(encoding="utf-8")-- assert (- 'curl -fsSL "https://raw.githubusercontent.com/'- 'Alishahryar1/free-claude-code/main/scripts/uninstall.sh" | sh'- ) in text- assert (- '& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/'- 'Alishahryar1/free-claude-code/main/scripts/uninstall.ps1")))'- ) in text- assert "verifies every FCC command is gone" in text