main
7 次代码提交
| 作者 | SHA1 | 备注 | 提交日期 | |
|---|---|---|---|---|
 Ali Khokhar
|
af12e7b2bb |
Coordinate provider recovery under concurrent load (#1205)
## Problem Concurrent transient failures could start independent retry, replay, continuation, and repair loops while holding provider concurrency slots. This multiplied upstream attempts and could delay or strand terminal errors under fan-out. ## Changes | Before | After | | --- | --- | | Retry paths owned separate attempt budgets. | One logical-execution session caps all upstream work at five attempts. | | Concurrent failures backed off independently. | One provider-owned recovery episode elects a single half-open probe while followers coalesce. | | Backoff occupied stream concurrency. | Concurrency is held only while an upstream operation or stream is active. | | Provider catalog calls and stream creation used separate admission paths. | Every upstream operation uses one provider-generation admission controller. | | Cancellation could leave recovery ownership or follower state unresolved. | Cancellation releases permits, transfers probe ownership, and unregisters waiting followers. | | Late in-flight failures could cross an exhausted episode boundary. | Every coalesced execution retains that generation's terminal outcome. | | Replay tests allowed loose lifecycle assertions. | Exact SSE contracts prove retries and continuations emit one unduplicated response. | | Recovery wrappers could mask final diagnostics. | Final responses and traces retain the raw provider failure and request ID. | <!-- greptile_comment --> <details open><summary><h3>Greptile Summary</h3></summary> This PR coordinates provider recovery and retry work under concurrent load. The main changes are: - One five-attempt budget for each logical execution. - Provider-wide recovery episodes with one elected probe. - Shared admission for streams, catalog calls, rate limits, and concurrency. - Concurrency permits held only during active upstream work. - Cancellation-safe probe ownership and preserved final diagnostics. </details> <h3>Confidence Score: 5/5</h3> This looks safe to merge. No blocking issues found in the changed code. <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** - Reviewed the coordinated-recovery-01-before.log to understand how the exhausted generation outcome was not preserved in a late in-flight failure. - Reviewed the coordinated-recovery-02-after.log to confirm that the updated implementation preserves the exhausted generation outcome for the same focused contract set. - Validated that the provider-admission-full-current.log shows the complete requested test file passed under Python 3.14 with uv run pytest -n 0. <a href="https://app.greptile.com/trex/runs/15050270/artifacts"><picture><source media="(prefers-color-scheme: dark)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifactsDark.svg?v=4"><source media="(prefers-color-scheme: light)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"><img alt="View all artifacts" src="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"></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> <details open><summary><h3>Important Files Changed</h3></summary> | Filename | Overview | |----------|----------| | src/free_claude_code/providers/admission.py | Adds shared admission, retry budgets, recovery episodes, probe election, and cancellation handling. | | src/free_claude_code/providers/openai_chat/provider.py | Moves stream creation, replay, continuation, and repair onto one admission-owned retry session. | | src/free_claude_code/providers/stream_recovery.py | Selects replay, continuation, repair, or final failure using the remaining shared attempt budget. | | src/free_claude_code/providers/failure_policy.py | Adds recovery exhaustion handling and preserves the underlying provider error for final classification. | | src/free_claude_code/providers/runtime/factory.py | Creates one admission controller per provider generation and passes it through provider factories. | </details> <details open><summary><h3>Sequence Diagram</h3></summary> <a href="#gh-light-mode-only"> ```mermaid %%{init: {'theme': 'neutral'}}%% sequenceDiagram participant E as Execution participant A as Admission controller participant P as Provider participant F as Concurrent follower E->>A: Open attempt A->>P: Send upstream request P-->>E: Retryable failure E->>A: Open recovery episode F->>A: Request admission A-->>F: Coalesce and wait E->>A: Claim probe A->>P: Send half-open probe alt Probe succeeds P-->>E: Valid response E->>A: Close recovery episode A-->>F: Release waiter else Probe fails P-->>E: Retryable failure E->>A: Schedule next probe or finalize error end ``` </a> <a href="#gh-dark-mode-only"> ```mermaid %%{init: {'theme': 'base', 'themeVariables': {"darkMode": true, "background": "#0d1117", "primaryColor": "#21262d", "primaryTextColor": "#e6edf3", "primaryBorderColor": "#8b949e", "lineColor": "#8b949e", "textColor": "#e6edf3", "edgeLabelBackground": "#161b22", "actorBkg": "#21262d", "actorBorder": "#8b949e", "actorTextColor": "#e6edf3", "actorLineColor": "#8b949e", "signalColor": "#8b949e", "signalTextColor": "#e6edf3", "noteBkgColor": "#373320", "noteBorderColor": "#d4a72c", "noteTextColor": "#f0e6c0", "labelBoxBkgColor": "#21262d", "labelBoxBorderColor": "#8b949e", "labelTextColor": "#e6edf3", "loopTextColor": "#e6edf3", "activationBkgColor": "#30363d", "activationBorderColor": "#8b949e"}}}%% sequenceDiagram participant E as Execution participant A as Admission controller participant P as Provider participant F as Concurrent follower E->>A: Open attempt A->>P: Send upstream request P-->>E: Retryable failure E->>A: Open recovery episode F->>A: Request admission A-->>F: Coalesce and wait E->>A: Claim probe A->>P: Send half-open probe alt Probe succeeds P-->>E: Valid response E->>A: Close recovery episode A-->>F: Release waiter else Probe fails P-->>E: Retryable failure E->>A: Schedule next probe or finalize error end ``` </a> </details> <sub>Reviews (2): Last reviewed commit: ["Harden coordinated retry lifecycle invar..."](https://github.com/alishahryar1/free-claude-code/commit/2e871c8649d148b5eb71d21f80bf870ae2d11708) | [Re-trigger Greptile](https://app.greptile.com/api/retrigger?id=45554917)</sub> <!-- /greptile_comment --> |
||
|
Ali Khokhar
|
6455c63e1d |
Make reasoning policy provider-neutral and client-aware (#1148)
## Problem FCC reduced reasoning to global and route booleans, mixing client intent, configuration, provider wire capabilities, output visibility, and history replay. That discarded named client efforts, encouraged model-name checks, and made provider behavior inconsistent. ## Changes | Before | After | | --- | --- | | Admin exposed global and route thinking toggles. | Admin exposes **Off**, **From client**, **Low**, **Medium**, **High**, **X-High**, and **Max**; Fable, Opus, Sonnet, and Haiku also expose **Inherit**. | | Request intent was repeatedly reduced to a boolean across routing and providers. | The application boundary resolves one immutable `ReasoningPolicy` with independent control, named effort, and exact positive token budget. | | Provider adapters could infer reasoning behavior from upstream model names or versions. | Provider profiles translate only documented provider-wide wire capabilities; architecture and contributor rules prohibit model-specific reasoning branches. | | Gateway reasoning controls were ad hoc. | [OpenRouter](https://openrouter.ai/docs/guides/best-practices/reasoning-tokens) and [Vercel AI Gateway](https://vercel.com/docs/ai-gateway/models-and-providers) use documented reasoning objects, including exact budgets where representable. | | Named effort forwarding was inconsistent or absent. | [Gemini](https://ai.google.dev/gemini-api/docs/openai), [Ollama](https://docs.ollama.com/api/openai-compatibility), [LM Studio](https://lmstudio.ai/changelog/lmstudio-v0.4.8), [Fireworks](https://docs.fireworks.ai/guides/querying-text-models/reasoning), [Cohere](https://docs.cohere.com/docs/compatibility-api), [Wafer](https://docs.wafer.ai/serverless/api-reference), [Groq](https://console.groq.com/docs/reasoning), [Cerebras](https://inference-docs.cerebras.ai/capabilities/reasoning), [SambaNova](https://docs.sambanova.ai/docs/api-reference/chat-completions/create-chat-based-completion), and [Mistral](https://docs.mistral.ai/studio-api/conversations/reasoning) receive their documented named vocabularies with explicit provider-owned downgrades. | | Boolean thinking controls were mixed into shared conversion. | [DeepSeek](https://api-docs.deepseek.com/guides/thinking_mode/), [Kimi](https://platform.kimi.ai/docs/guide/use-kimi-k2-thinking-model), [Z.ai](https://docs.z.ai/guides/capabilities/thinking-mode), [Cloudflare Workers AI](https://developers.cloudflare.com/changelog/post/2026-04-20-kimi-k2-6-workers-ai/), and [NVIDIA NIM](https://docs.nvidia.com/nim/large-language-models/1.15.0/thinking-budget-control.html) use provider-owned thinking-object or chat-template controls. | | Effort names and output limits could become fabricated reasoning budgets. | Exact budgets remain exact and are forwarded only through documented fields for OpenRouter, Fireworks, LM Studio, NIM, and [llama.cpp](https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md); named efforts and output limits are never converted into token budgets. | | New-turn reasoning and prior-turn replay shared one switch. | Every profile independently declares native reasoning replay, `<think>` tag replay, provider-specific replay, or no replay; **Off** suppresses new reasoning output without corrupting required history. | | Providers without a stable generic compute control received guessed controls. | [MiniMax](https://platform.minimax.io/docs/api-reference/text-openai-api) requests split output only, while [GitHub Models](https://docs.github.com/en/rest/models/inference), [Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers/en/tasks/chat-completion), Codestral, and OpenCode keep provider defaults and use only their explicit replay profile. | | OpenAI Responses effort became a lossy Anthropic thinking boolean. | Responses preserves `reasoning.effort` through `output_config`, then resolves it through the same application policy as Messages without inventing a budget. | | Legacy booleans remained the persisted contract. | FCC-owned dotenv files migrate to typed `REASONING_*` values, explicit env files receive an actionable warning, documentation describes the ownership boundary, and the package advances to 4.8.0. | | Reasoning behavior was covered by scattered boolean assertions. | New policy, routing, encoder, provider, Admin, migration, Responses, and smoke contracts pass all five local CI checks: 2,368 tests passed, 40 skipped; 92 smoke tests collect and both live config migration checks pass. | <!-- greptile_comment --> <details open><summary><h3>Greptile Summary</h3></summary> This PR makes reasoning policy client-aware and independent of provider model names. The main changes are: - Adds one immutable reasoning policy resolved at the application boundary. - Adds typed root and route reasoning settings with Admin UI support. - Moves wire controls and history replay behavior into provider profiles. - Migrates owned dotenv files from legacy thinking booleans. - Expands provider, routing, migration, API, and smoke coverage. </details> <h3>Confidence Score: 5/5</h3> This looks safe to merge. No blocking issues found in the changed code. <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 the contract-validation test suite with the specified test modules, and the tests reported 78 passed in 1.53s with exit code 0. - Reviewed the complete captured output artifact reasoning-contract-02-after.log to verify the final test outcomes and successful contract validation. <a href="https://app.greptile.com/trex/runs/14792858/artifacts"><picture><source media="(prefers-color-scheme: dark)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifactsDark.svg?v=4"><source media="(prefers-color-scheme: light)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"><img alt="View all artifacts" src="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"></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> <details open><summary><h3>Important Files Changed</h3></summary> | Filename | Overview | |----------|----------| | src/free_claude_code/config/env_migrations.py | Migrates legacy reasoning booleans in owned dotenv files and warns for explicit environment files. | | src/free_claude_code/application/reasoning.py | Resolves client controls and configured preferences into one provider-neutral reasoning policy. | | src/free_claude_code/application/routing.py | Carries route-level reasoning preferences into request-scoped policy resolution. | | src/free_claude_code/providers/openai_chat/reasoning.py | Provides shared provider encoders for reasoning controls and replay behavior. | </details> <sub>Reviews (2): Last reviewed commit: ["chore: release reasoning controls as 4.8..."](https://github.com/alishahryar1/free-claude-code/commit/9d4be767f7dbdca5709474012f43dcdc6f4347e3) | [Re-trigger Greptile](https://app.greptile.com/api/retrigger?id=44984039)</sub> <!-- /greptile_comment --> |
||
|
Ali Khokhar
|
f3ea35a777 |
Consolidate OpenAI-compatible provider adapters (#1069)
## Problem Sixteen OpenAI-compatible providers were represented by configuration-only subclasses and one factory function each. The sole provider family also lived under a multi-transport namespace that no longer described the codebase, while provider defaults, IDs, and instance caching passed through redundant forwarding layers. ## Changes | Before | After | | --- | --- | | Sixteen provider IDs used configuration-only subclasses. | Immutable OpenAI-chat profiles configure one concrete provider while preserving each provider's request policy. | | Every provider required a dedicated factory function. | Generic profile construction is the default; only eight adapters with real state or algorithms retain factories. | | The sole provider family lived under `providers/transports/`. | `providers/openai_chat/` directly owns shared request, stream, recovery, tool, and usage behavior. | | Provider defaults and IDs passed through forwarding modules, and constructors repeated fallback resolution. | The neutral catalog resolves complete immutable provider configuration once. | | `ProviderRuntime` wrapped a pass-through provider cache. | `ProviderRuntime` directly owns lazy provider instances and cleanup. | | Production carried the duplicated adapter structure. | The final shape removes a net 873 production lines with no compatibility shim or customer-facing provider change. | <!-- greptile_comment --> <details open><summary><h3>Greptile Summary</h3></summary> This PR consolidates OpenAI-compatible providers behind shared profiles and runtime construction. The main changes are: - OpenAI-chat behavior moved into `providers/openai_chat`. - Configuration-only provider subclasses replaced by immutable profiles. - Provider runtime now owns lazy instance caching and cleanup directly. - Provider defaults and IDs now resolve through the neutral catalog. - Tests and smoke helpers updated for the new provider shape. </details> <h3>Confidence Score: 5/5</h3> This looks safe to merge. No blocking issues found in the changed code. No files need attention. <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** - T-Rex produced a proof for a posted P1 finding and linked it to the corresponding review comment for details. - T-Rex saved contract-validation logs for provider consolidation and preserved four log files that show the test hanging boundary and the timeout exit code 124. <a href="https://app.greptile.com/trex/runs/14125428/artifacts"><picture><source media="(prefers-color-scheme: dark)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifactsDark.svg?v=4"><source media="(prefers-color-scheme: light)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"><img alt="View all artifacts" src="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"></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> <details open><summary><h3>Important Files Changed</h3></summary> | Filename | Overview | |----------|----------| | src/free_claude_code/providers/runtime/config.py | Builds resolved provider configuration from catalog descriptors, including static credentials for local providers. | | src/free_claude_code/providers/openai_chat/provider.py | Creates shared OpenAI-chat clients from resolved configuration and immutable provider profiles. | | src/free_claude_code/providers/openai_chat/profiles.py | Defines declarative profiles for formerly configuration-only OpenAI-compatible adapters. | </details> <!-- greptile_failed_comments --> <h3>Comments Outside Diff (2)</h3> 1. General comment <a href="#"><img alt="P1" src="https://greptile-static-assets.s3.amazonaws.com/badges/p1.svg?v=9" align="top"></a> **NIM OpenAI-compatible 504 exhausted streaming retry path hangs instead of completing with the expected user-facing error** - **Bug** - The broader provider consolidation suite failed all parametrized `test_nim_stream_openai_5xx_exhausted_emits_user_message` cases under xdist with worker crashes. A serial isolation run narrowed this to the same OpenAI-compatible NIM exhausted 5xx streaming path: 500, 502, and 503 completed, but the 504 case did not finish before the explicit 120s timeout, producing exit code 124. This contradicts the expected streaming retry contract that exhausted transient provider failures terminate and emit the configured user-facing error. - **Cause** - The OpenAI-compatible streaming retry/exhaustion path for NIM 504 responses appears to wait indefinitely or otherwise fail to terminate after retries are exhausted. The exact code-level loop/await point was not isolated within the validation budget, but the failure is anchored to the provider streaming retry contract exercised by `tests/providers/test_openai_compat_5xx_retry.py::test_nim_stream_openai_5xx_exhausted_emits_user_message[504-temporarily unavailable]`. - **Fix** - Inspect the OpenAI-compatible/NIM streaming retry exhaustion handling for 504 responses and ensure retry limits are enforced, the async stream is closed/cancelled on exhaustion, and the provider raises/emits the same terminal user-facing error contract as the 500/502/503 cases. Add or keep a serial regression test for the 504 exhausted stream path to prevent hangs. <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> 2. General comment <a href="#"><img alt="P1" src="https://greptile-static-assets.s3.amazonaws.com/badges/p1.svg?v=9" align="top"></a> **OpenAI-compatible 5xx retry suite hangs on exhausted 502 retry path** - **Bug** - The recommended non-xdist retry validation does not complete. A verbose rerun with a 60 second timeout shows the suite passes tests through the exhausted 500 case, then times out while running `test_nim_stream_openai_5xx_exhausted_emits_user_message[502-temporarily unavailable]`. This indicates the consolidated OpenAI-compatible provider retry/error path can hang for at least the 502 exhausted-error scenario, preventing reliable validation and potentially blocking callers from receiving the expected `ExecutionFailure`. - **Cause** - The OpenAI-compatible provider's exhausted 502 retry/error handling path appears not to terminate promptly under the mocked repeated `openai.InternalServerError` scenario. The exact code location was not changed during validation, but the failure is isolated to the shared OpenAI-chat 5xx retry behavior exercised by `NvidiaNimProvider.stream_response`. - **Fix** - Debug the shared OpenAI-chat retry loop/error classification for 502 responses. Ensure retries are bounded, patched `asyncio.sleep` is awaited without real backoff during tests, and exhausted 502/503/504 errors consistently raise `ExecutionFailure` with the expected temporary-unavailable message instead of continuing work indefinitely. <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> <!-- /greptile_failed_comments --> <sub>Reviews (2): Last reviewed commit: ["Prove local provider credential resoluti..."](https://github.com/alishahryar1/free-claude-code/commit/ba226d97efdae1889bea0372c7bacf268122d65c) | [Re-trigger Greptile](https://app.greptile.com/api/retrigger?id=43580983)</sub> <!-- /greptile_comment --> |
||
|
Ali Khokhar
|
4a0a0360de |
Move protocol models to their protocol owners (#1044)
## Problem Anthropic Messages and OpenAI Responses wire models lived under the inbound API adapter. Neutral protocol and provider code therefore duck-typed requests, obscuring ownership and weakening dependency boundaries. ## Changes | Before | After | | --- | --- | | The API package owned Anthropic and Responses protocol models. | Each protocol package owns and publicly exports its wire models. | | Core and provider request paths accepted `Any` and probed known fields with `getattr()`. | Core, transports, and providers consume concrete `MessagesRequest` values. | | Responses conversion and streaming received a dumped request mapping. | Responses conversion and streaming receive one concrete `OpenAIResponsesRequest`. | | Anthropic request snapshots lived in generic tracing code. | Anthropic request snapshots live with the protocol while generic tracing stays protocol-independent. | | Protocol tests and provider request doubles reflected the old API ownership. | Protocol tests live under core and provider tests construct real wire requests. | | The API model package mixed protocol and model-catalog schemas. | The API model package is removed, with catalog schemas beside catalog construction and no compatibility shim. | | Package version was `3.4.18`. | Package version is `3.4.19` with an updated lockfile. | <!-- greptile_comment --> <details open><summary><h3>Greptile Summary</h3></summary> This PR moves protocol request models to their protocol-owned packages. The main changes are: - Anthropic Messages models now live under `core.anthropic`. - OpenAI Responses models now live under `core.openai_responses`. - API handlers, routes, providers, and tests now use concrete protocol request types. - Anthropic request snapshots moved beside the Anthropic protocol models. - API model catalog schemas were kept with catalog response construction. - The package version and lockfile were updated. </details> <h3>Confidence Score: 5/5</h3> This looks safe to merge. No blocking issues were found in the changed code. Internal callers were updated to pass the new concrete protocol models, and no stale internal imports from the removed API model package were identified. No files need attention. <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** - The Pytest run for protocol ownership focused tests completed, showing 71 passed in 6.24s and EXIT\_CODE: 0. - A protocol import smoke script was generated for the import/conversion/trace workflow. - The protocol import smoke run completed successfully, including model ownership output, adapter payload evidence, and trace snapshot evidence, with EXIT\_CODE: 0. <a href="https://app.greptile.com/trex/runs/14066157/artifacts"><picture><source media="(prefers-color-scheme: dark)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifactsDark.svg?v=4"><source media="(prefers-color-scheme: light)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"><img alt="View all artifacts" src="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"></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> <details open><summary><h3>Important Files Changed</h3></summary> | Filename | Overview | |----------|----------| | src/free_claude_code/core/anthropic/models.py | Anthropic wire request and response models moved under the Anthropic protocol package. | | src/free_claude_code/core/anthropic/native_messages_request.py | Native Anthropic serialization now expects concrete `MessagesRequest` instances. | | src/free_claude_code/core/anthropic/conversion.py | OpenAI chat conversion now reads fields directly from `MessagesRequest`. | | src/free_claude_code/core/anthropic/request_snapshot.py | Anthropic request snapshotting moved from generic tracing into the protocol package. | | src/free_claude_code/core/openai_responses/models.py | OpenAI Responses ingress models moved under the Responses protocol package. | | src/free_claude_code/core/openai_responses/input.py | Responses conversion now consumes the concrete request model instead of a dumped mapping. | | src/free_claude_code/core/openai_responses/streaming/assembler.py | Responses stream assembly now reads request attributes from `OpenAIResponsesRequest`. | | src/free_claude_code/api/routes.py | Routes now import protocol request models from their new core owners. | | src/free_claude_code/api/model_catalog.py | Model-list response schemas now live with model catalog construction. | </details> <details open><summary><h3>Flowchart</h3></summary> <a href="#gh-light-mode-only"> ```mermaid %%{init: {'theme': 'neutral'}}%% flowchart LR API[API routes and handlers] --> Anthropic[core.anthropic models and helpers] API --> Responses[core.openai_responses models and adapter] Responses --> Anthropic Providers[Provider clients and transports] --> Anthropic Anthropic --> Trace[core.trace sanitization] API --> Catalog[api.model_catalog response schemas] ``` </a> <a href="#gh-dark-mode-only"> ```mermaid %%{init: {'theme': 'base', 'themeVariables': {"darkMode": true, "background": "#0d1117", "primaryColor": "#21262d", "primaryTextColor": "#e6edf3", "primaryBorderColor": "#8b949e", "lineColor": "#8b949e", "textColor": "#e6edf3", "edgeLabelBackground": "#161b22", "actorBkg": "#21262d", "actorBorder": "#8b949e", "actorTextColor": "#e6edf3", "actorLineColor": "#8b949e", "signalColor": "#8b949e", "signalTextColor": "#e6edf3", "noteBkgColor": "#373320", "noteBorderColor": "#d4a72c", "noteTextColor": "#f0e6c0", "labelBoxBkgColor": "#21262d", "labelBoxBorderColor": "#8b949e", "labelTextColor": "#e6edf3", "loopTextColor": "#e6edf3", "activationBkgColor": "#30363d", "activationBorderColor": "#8b949e"}}}%% flowchart LR API[API routes and handlers] --> Anthropic[core.anthropic models and helpers] API --> Responses[core.openai_responses models and adapter] Responses --> Anthropic Providers[Provider clients and transports] --> Anthropic Anthropic --> Trace[core.trace sanitization] API --> Catalog[api.model_catalog response schemas] ``` </a> </details> <sub>Reviews (1): Last reviewed commit: ["Move protocol models to their protocol o..."](https://github.com/alishahryar1/free-claude-code/commit/f1be5c1af4a10da710f80b5f9e7f6044a601f6af) | [Re-trigger Greptile](https://app.greptile.com/api/retrigger?id=43459428)</sub> <!-- /greptile_comment --> |
||
|
Ali Khokhar
|
4951983b5e |
Replace global runtime resources with explicit ownership (#1042)
## Problem Provider, messaging, and transcription resources relied on process-global state, leaving replacement, cancellation, and shutdown ownership ambiguous. Separate server lifetimes could share event-loop-bound resources or retain failed cleanup work. ## Changes | Before | After | | --- | --- | | Provider clients found limiters through global singleton and scoped registries. | Each provider instance receives and owns one explicitly constructed limiter. | | Messaging queues and voice pipelines relied on singleton or module-global state. | Each platform owns its limiter and outbox, while the application owns one injected transcriber. | | Messaging shutdown mixed ingress, active work, delivery, and SDK cleanup. | Application shutdown quiesces ingress, drains work, closes delivery, then releases transcription and providers. | | Cancelled or failed provider cleanup could be forgotten or treated as complete. | The provider manager retains shielded generation and unpublished-runtime cleanup until it succeeds. | | Discord and Telegram startup tasks could outlive or poison runtime readiness. | Platform runtimes observe long-lived tasks and retry only independently repeatable lifecycle steps. | | Constructor-captured security and diagnostic settings appeared hot-applicable. | Admin marks those settings restart-required so applied policy matches the running resource graph. | | Lifecycle races lacked direct ownership coverage. | Deterministic cancellation, retry, isolation, teardown, and live smoke contracts protect the final ownership model. | <!-- greptile_comment --> <details open><summary><h3>Greptile Summary</h3></summary> This PR moves runtime resources from global state into explicitly owned application objects. The main changes are: - Provider generations own their rate limiters and cleanup tasks. - Messaging platforms own their limiter, outbox, ingress, and delivery lifecycle. - Application shutdown now runs through ordered cleanup gates. - Voice transcription is injected as an owned runtime resource. - Admin config marks constructor-captured settings as restart-required. </details> <h3>Confidence Score: 4/5</h3> The shutdown path needs a bounded cleanup result before merging. Cleanup steps that hang never reach the retryable incomplete-shutdown path. ASGI shutdown can remain stuck while waiting for an external SDK, transcriber, workflow, or provider cleanup. The retry ownership model works only after cleanup returns or raises. src/free_claude_code/runtime/application.py <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** - T-Rex ran the requested verification, but its local artifact references were not uploaded. - The validation run completed successfully with EXIT\_CODE: 0 and 62 tests passed in 3.91 seconds, using the command uv run pytest -vv tests/runtime/test\_application\_runtime.py tests/runtime/test\_provider\_manager.py tests/providers/test\_provider\_runtime.py. <a href="https://app.greptile.com/trex/runs/14064214/artifacts"><picture><source media="(prefers-color-scheme: dark)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifactsDark.svg?v=4"><source media="(prefers-color-scheme: light)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"><img alt="View all artifacts" src="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"></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> <details open><summary><h3>Important Files Changed</h3></summary> | Filename | Overview | |----------|----------| | src/free_claude_code/runtime/application.py | Refactors shutdown into ordered retryable cleanup gates, but cleanup awaitables can still block shutdown forever. | | src/free_claude_code/runtime/asgi.py | Reports incomplete runtime shutdown when `close()` returns false. | | src/free_claude_code/runtime/provider_manager.py | Adds owned provider cleanup retry state and shielded generation cleanup. | </details> <a href="https://app.greptile.com/api/ide/codex?prompt=IMPORTANT%3A%20Work%20in%20the%20repository%20%22alishahryar1%2Ffree-claude-code%22%20on%20the%20existing%20branch%20%22refactor%2Fruntime-owned-resources%22.%20Checkout%20that%20branch%20%E2%80%94%20do%20NOT%20create%20a%20new%20branch%20or%20open%20a%20new%20PR.%20Push%20your%20changes%20to%20%22refactor%2Fruntime-owned-resources%22.%0A%0AFix%20the%20following%201%20code%20review%20issue.%20Work%20through%20them%20one%20at%20a%20time%2C%20proposing%20concise%20fixes.%0A%0A---%0A%0A%23%23%23%20Issue%201%20of%201%0Asrc%2Ffree_claude_code%2Fruntime%2Fapplication.py%3A59%0A**Cleanup%20Await%20Blocks%20Shutdown**%0A%0AWhen%20a%20platform%20SDK%20stop%2C%20workflow%20drain%2C%20transcriber%20close%2C%20or%20provider%20cleanup%20hangs%2C%20this%20helper%20waits%20forever%20and%20never%20returns%20%60False%60.%20ASGI%20shutdown%20stays%20stuck%20in%20%60runtime.close%28%29%60%20instead%20of%20reporting%20an%20incomplete%20shutdown%2C%20so%20the%20retained%20resource%20graph%20cannot%20be%20retried%20cleanly.%0A%0A&repo=alishahryar1%2Ffree-claude-code&pr=1042&platform=github"><picture><source media="(prefers-color-scheme: dark)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/FixAllInCodexDark.svg?v=6"><source media="(prefers-color-scheme: light)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/FixAllInCodex.svg?v=6"><img alt="Fix All in Codex" src="https://greptile-static-assets.s3.amazonaws.com/badges/FixAllInCodex.svg?v=6"></picture></a> <sub>Reviews (2): Last reviewed commit: ["Report incomplete runtime shutdown to AS..."](https://github.com/alishahryar1/free-claude-code/commit/338b2bd179c3875b15bbd52818dd04c780e5d46d) | [Re-trigger Greptile](https://app.greptile.com/api/retrigger?id=43454593)</sub> > Greptile also left **1 inline comment** on this PR. **Context used:** - Context used - CLAUDE.md ([source](https://app.greptile.com/alishahryar1/github/Alishahryar1/free-claude-code/-/custom-context?memory=d2fd24d8-0dec-4faf-8ee4-e085e215a2f8)) <!-- /greptile_comment --> |
||
|
Ali Khokhar
|
71a78a0c5a |
Move runtime packages under src namespace (#1029)
## Problem Runtime modules were published as generic top-level packages like `api`, `cli`, and `providers`. That shape is fragile for PyPI packaging and weakens explicit ownership boundaries. ## Changes | Before | After | | --- | --- | | Runtime code lived in root-level packages. | Runtime code lives under `src/free_claude_code/`. | | Console scripts targeted top-level modules. | Console scripts target namespaced modules. | | Tests and smoke helpers imported old package roots. | Tests and smoke helpers import `free_claude_code.*`. | | Packaging listed six root packages. | Packaging builds the single namespaced package. | | Contracts allowed old root package directories. | Contracts require the src namespace and reject old root imports. | <!-- greptile_comment --> <details open><summary><h3>Greptile Summary</h3></summary> This PR moves the runtime packages into the `src/free_claude_code` namespace. The main changes are: - Console scripts now point to `free_claude_code.*` entrypoints. - Runtime imports, tests, and smoke helpers now use the namespaced package. - Packaging now builds the single `src/free_claude_code` package. - Contract tests now reject old top-level runtime package roots and imports. </details> <h3>Confidence Score: 5/5</h3> This PR is safe to merge with minimal risk. The changes are a broad but mostly mechanical namespace and package-layout migration with updated packaging, tests, and contract coverage. No files require special attention. <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** - Reviewed the primary contract validation by examining the namespace validation log, which documents the exact commands executed, the working directory, exit codes, pytest output, wheel build output, install output, and import/entrypoint resolution. - Verified the wheel listing by inspecting the wheel listing artifact, confirming the available wheel filenames for the namespace validation. - Ran and inspected the isolated import/entrypoint validation harness saved as package-installed-import-check.py to validate import resolution and entrypoint exposure. - Captured and noted the wheel filename record in package-wheel-filename.txt to enable traceability of the observed artifact. <a href="https://app.greptile.com/trex/runs/13810533/artifacts"><picture><source media="(prefers-color-scheme: dark)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifactsDark.svg?v=4"><source media="(prefers-color-scheme: light)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"><img alt="View all artifacts" src="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"></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> <details open><summary><h3>Important Files Changed</h3></summary> | Filename | Overview | |----------|----------| | pyproject.toml | Updates packaging to build the single `src/free_claude_code` package and retargets console scripts to namespaced modules. | | src/free_claude_code/config/env_template.py | Loads `.env.example` from packaged resources with a source-checkout fallback after the runtime package move. | | src/free_claude_code/cli/entrypoints.py | Updates CLI entrypoint imports to `free_claude_code.*` and continues to use the shared env template loader. | | src/free_claude_code/api/routes.py | Retargets API route dependencies and handlers to the namespaced package without changing route behavior. | | src/free_claude_code/api/app.py | Updates app factory imports to the namespaced package while preserving middleware, routers, and exception handling. | | src/free_claude_code/providers/runtime/factory.py | Updates lazy provider factory imports to `free_claude_code.providers.*` under the new package layout. | | tests/contracts/test_import_boundaries.py | Adds contract coverage requiring runtime packages to live under `src/free_claude_code` and rejecting old top-level imports. | | smoke/lib/child_process.py | Updates smoke child-process helpers to import CLI entrypoints from the namespaced package. | | README.md | Updates the project layout and extension guidance to refer to `src/free_claude_code` and importable `free_claude_code.*` modules. | | uv.lock | Reflects the package version bump associated with the runtime packaging move. | </details> <details open><summary><h3>Sequence Diagram</h3></summary> <a href="#gh-light-mode-only"> ```mermaid %%{init: {'theme': 'neutral'}}%% sequenceDiagram participant User as User / CLI participant Script as Console script participant Pkg as free_claude_code package participant API as free_claude_code.api participant Runtime as free_claude_code.providers.runtime participant Provider as Provider adapter User->>Script: run fcc-server / free-claude-code Script->>Pkg: load free_claude_code.cli.entrypoints:serve Pkg->>API: create FastAPI app and routes API->>Runtime: resolve configured provider Runtime->>Provider: instantiate namespaced adapter Provider-->>Runtime: stream/model responses Runtime-->>API: provider result API-->>User: Anthropic/OpenAI-compatible response ``` </a> <a href="#gh-dark-mode-only"> ```mermaid %%{init: {'theme': 'base', 'themeVariables': {"darkMode": true, "background": "#0d1117", "primaryColor": "#21262d", "primaryTextColor": "#e6edf3", "primaryBorderColor": "#8b949e", "lineColor": "#8b949e", "textColor": "#e6edf3", "edgeLabelBackground": "#161b22", "actorBkg": "#21262d", "actorBorder": "#8b949e", "actorTextColor": "#e6edf3", "actorLineColor": "#8b949e", "signalColor": "#8b949e", "signalTextColor": "#e6edf3", "noteBkgColor": "#373320", "noteBorderColor": "#d4a72c", "noteTextColor": "#f0e6c0", "labelBoxBkgColor": "#21262d", "labelBoxBorderColor": "#8b949e", "labelTextColor": "#e6edf3", "loopTextColor": "#e6edf3", "activationBkgColor": "#30363d", "activationBorderColor": "#8b949e"}}}%% sequenceDiagram participant User as User / CLI participant Script as Console script participant Pkg as free_claude_code package participant API as free_claude_code.api participant Runtime as free_claude_code.providers.runtime participant Provider as Provider adapter User->>Script: run fcc-server / free-claude-code Script->>Pkg: load free_claude_code.cli.entrypoints:serve Pkg->>API: create FastAPI app and routes API->>Runtime: resolve configured provider Runtime->>Provider: instantiate namespaced adapter Provider-->>Runtime: stream/model responses Runtime-->>API: provider result API-->>User: Anthropic/OpenAI-compatible response ``` </a> </details> <sub>Reviews (2): Last reviewed commit: ["Fix documented package import paths"](https://github.com/alishahryar1/free-claude-code/commit/bfa9f2704c45f3684da39657d5e13f3814e5d450) | [Re-trigger Greptile](https://app.greptile.com/api/retrigger?id=42950471)</sub> <!-- /greptile_comment --> |
||
|
Ali Khokhar
|
bd85deb736 |
Fix OpenAI chat reasoning and tool history replay (#1002)
## Problem OpenAI-chat providers lost explicit empty reasoning state and could replay invalid tool-call history when unrelated messages appeared before matching tool results. ## Changes | Before | After | | --- | --- | | Empty `reasoning_content` and empty thinking blocks were treated as absent. | Empty reasoning is preserved as explicit replay state. | | OpenAI-chat conversion only deferred post-tool assistant text. | OpenAI-chat conversion buffers later transcript messages until required tool results are emitted. | | Responses prior tool calls and outputs were emitted one item per message. | Responses prior tool calls and outputs are grouped into valid Anthropic tool-use/result messages. | | Empty streamed `reasoning_content` produced no thinking block. | Empty streamed `reasoning_content` starts thinking state without visible delta text. | <!-- greptile_comment --> <details open><summary><h3>Greptile Summary</h3></summary> This PR fixes OpenAI chat reasoning replay and tool-history ordering. The main changes are: - Preserves explicit empty `reasoning_content` and empty thinking blocks. - Reworks OpenAI chat conversion around a ledger that waits for required tool results before replaying buffered transcript messages. - Groups prior Responses tool calls and outputs into valid Anthropic tool-use and tool-result messages. - Starts streamed thinking state when empty `reasoning_content` is received. - Adds focused tests for nested tool turns, out-of-order results, multi-tool replay, and empty reasoning. </details> <h3>Confidence Score: 5/5</h3> Safe to merge with low risk. No blocking issues were found in the changed conversion paths. The updated ledger covers the prior invalid replay cases and the tests include nested, out-of-order, multi-tool, and empty reasoning scenarios. The required patch version and lockfile updates are present. No files require special attention. <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 the focused OpenAI conversion regression suite with Pytest, capturing the command, working directory, pass count, exit code, and elapsed time. - Encountered an external timeout during the initial Pytest run at 98% progress, then re-ran the same focused suite to completion for definitive proof. - Validated code quality with Ruff by executing the lint command and obtaining a successful output. <a href="https://app.greptile.com/trex/runs/13503694/artifacts"><picture><source media="(prefers-color-scheme: dark)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifactsDark.svg?v=4"><source media="(prefers-color-scheme: light)" srcset="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"><img alt="View all artifacts" src="https://greptile-static-assets.s3.amazonaws.com/badges/ViewAllArtifacts.svg?v=4"></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> <details open><summary><h3>Important Files Changed</h3></summary> | Filename | Overview | |----------|----------| | core/anthropic/conversion.py | Replaces single pending-tool state with a ledger that buffers transcript segments until required OpenAI chat tool results can be emitted in valid order. | | core/openai_responses/input.py | Groups consecutive prior Responses tool calls/results into Anthropic tool-use/result turns and preserves explicit empty reasoning. | | core/openai_responses/reasoning.py | Updates reasoning extraction and combination helpers so empty strings remain explicit replay state without adding spurious separators. | | providers/deepseek/compat.py | Treats empty top-level or block-level thinking as replayable when detecting DeepSeek tool-history compatibility. | | providers/transports/openai_chat/stream.py | Starts an Anthropic thinking block for empty streamed `reasoning_content` while only emitting deltas for non-empty text. | | tests/providers/test_converter.py | Adds OpenAI chat conversion coverage for buffered tool history, nested pending tool turns, and explicit empty reasoning. | | tests/core/openai_responses/test_conversion.py | Adds Responses conversion tests for grouped prior tool calls/results and empty reasoning attachment. | | pyproject.toml | Bumps the package patch version for the production conversion fixes. | | uv.lock | Keeps the lockfile package version in sync with `pyproject.toml`. | </details> <details open><summary><h3>Sequence Diagram</h3></summary> <a href="#gh-light-mode-only"> ```mermaid %%{init: {'theme': 'neutral'}}%% sequenceDiagram participant A as Anthropic transcript participant L as OpenAI chat ledger participant O as OpenAI chat history A->>L: Assistant tool_use segment L->>O: Emit assistant tool_calls A->>L: Later plain user/assistant messages L-->>L: Buffer until required tool_result ids arrive A->>L: User tool_result blocks L->>O: Emit matching role: tool results in tool_call order L->>O: Emit deferred assistant post-tool content L->>O: Drain buffered plain transcript messages ``` </a> <a href="#gh-dark-mode-only"> ```mermaid %%{init: {'theme': 'base', 'themeVariables': {"darkMode": true, "background": "#0d1117", "primaryColor": "#21262d", "primaryTextColor": "#e6edf3", "primaryBorderColor": "#8b949e", "lineColor": "#8b949e", "textColor": "#e6edf3", "edgeLabelBackground": "#161b22", "actorBkg": "#21262d", "actorBorder": "#8b949e", "actorTextColor": "#e6edf3", "actorLineColor": "#8b949e", "signalColor": "#8b949e", "signalTextColor": "#e6edf3", "noteBkgColor": "#373320", "noteBorderColor": "#d4a72c", "noteTextColor": "#f0e6c0", "labelBoxBkgColor": "#21262d", "labelBoxBorderColor": "#8b949e", "labelTextColor": "#e6edf3", "loopTextColor": "#e6edf3", "activationBkgColor": "#30363d", "activationBorderColor": "#8b949e"}}}%% sequenceDiagram participant A as Anthropic transcript participant L as OpenAI chat ledger participant O as OpenAI chat history A->>L: Assistant tool_use segment L->>O: Emit assistant tool_calls A->>L: Later plain user/assistant messages L-->>L: Buffer until required tool_result ids arrive A->>L: User tool_result blocks L->>O: Emit matching role: tool results in tool_call order L->>O: Emit deferred assistant post-tool content L->>O: Drain buffered plain transcript messages ``` </a> </details> <sub>Reviews (3): Last reviewed commit: ["Refactor OpenAI chat tool history replay"](https://github.com/alishahryar1/free-claude-code/commit/ae1635d2ce3a232ba7f4c0b9787f7b604b625544) | [Re-trigger Greptile](https://app.greptile.com/api/retrigger?id=42274270)</sub> <!-- /greptile_comment --> |