feat: Complete DeepSeek API adapter implementation

[dixoxib]

Description

Enhanced DeepSeek API adapter from a minimal 73‑line implementation to a complete, production‑ready adapter with all features expected from a modern LLM provider integration following official docs.

Key improvements:

• Added streaming & non‑streaming chat completions with reasoning support
• Implemented tool calling compatibility and thinking tool-call chains
• Implemented model listing via DeepSeek's /models endpoint
• Enhanced FIM beta endpoint
• Added type safety with comprehensive TypeScript types
• Improved converting with detailed warnings
• Added prefix completion support (beta chat endpoint)
• Added workarounds for DeepSeek Reasoner edge cases
• Improved documentation, configuration and onboarding
• minimal invasive to codebase
• Issue (Apply/edit writes raw model reasoning into files instead of filtering #10783) fixed by adding role filter to chat() (function seems not fully implemented yet)
• token counter now handles pre-filled messages

Files changed: 39 files, including core implementation, tests, documentation, and configuration updates, small fixes.

AI Code Review

• Team members only: AI review runs automatically when PR is opened or marked ready for review
• Team members can also trigger a review by commenting @continue-review

Checklist

• I've read the contributing guide
• The relevant docs have been updated or created
• The relevant tests have been updated or created

Screen recording or screenshot

Key demonstrations:

1. Onboarding
2. DeepSeek Reasoner showing reasoning_content in responses
3. Thinking-Tool-calling-Chains
4. Non-streaming summarize functionality

sv.mp4

Tests

Added/updated tests:

• packages/openai-adapters/src/test/deepseek-converters.test.ts – Comprehensive unit tests for converter functions
• core/llm/llms/DeepSeek.unit.test.ts – Unit tests for DeepSeek provider class
• core/llm/llms/DeepSeek.vitest.ts – Integration tests
• packages/openai-adapters/src/test/DeepSeekApi.test.ts – API adapter test
• core/llm/llms/DeepSeek.tools.test.ts – Thinking tool chain test

The enhancement addresses limitations in the current minimal implementation and enables full DeepSeek functionality including Agent mode with tool calling for Reasoner model.

---

I have read the CLA Document and I hereby sign the CLA

---

Continue Tasks: 🔄 7 running — View all

---

Summary by cubic

Complete DeepSeek provider with chat, reasoning, tools, and FIM (beta). Adds assistant‑only streaming, streamed usage/cost reporting (with cache stats), improved token counting/prefill handling, and a useBetaEndpoints flag while preserving apiBase for official and proxy setups.

• New Features

  • DeepSeek provider: streaming/non‑streaming chat, reasoning_content, thinking→tool call pairing, tool choice, model autodetect; added to onboarding, llm-info, and UI/VS Code.
  • FIM via deepseek-fim-beta; supportsFim true only for FIM beta; uses /beta chat/completions on official api.deepseek.com or when useBetaEndpoints is true; otherwise standard endpoints (no /beta in apiBase, no stray fim prefix).
  • Token/cost: reserve full maxTokens, 1.05 token multiplier, improved pruning, prefill fix, streamed usage stats, DeepSeek pricing with cache hit/miss.
  • Stability: stream/accumulate assistant chunks only; provider supports parallel gen; tests added; docs include proxy guidance.

• Migration

  • Use provider: deepseek with models: deepseek-chat, deepseek-reasoner, deepseek-fim-beta. deepseek-chat is recommended for Agent mode.
  • apiBase defaults to https://api.deepseek.com/ (do not include /beta). Adapter auto‑selects beta endpoints for the official base or when useBetaEndpoints: true (for proxies that require beta paths).
  • Config schema: DeepSeek now uses DeepseekConfig (extends BasePlusConfig) instead of OpenAIConfigSchema; existing configs continue to work.

^{Written for commit 18263ca. Summary will update on new commits.}

[cubic-dev-ai]

2 issues found across 2 files (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="packages/openai-adapters/src/apis/DeepSeek.ts">

<violation number="1" location="packages/openai-adapters/src/apis/DeepSeek.ts:50">
P2: apiBase trailing-slash normalization was removed; relative URL construction can drop path segments for custom bases like https://host/v1, misrouting requests.</violation>

<violation number="2" location="packages/openai-adapters/src/apis/DeepSeek.ts:316">
P2: FIM is a beta feature that requires the beta base URL; building the endpoint as `new URL("completions", this.apiBase)` sends FIM requests to the non‑beta `/completions` path when using the default base URL, which breaks FIM. Restore beta-aware routing or force the beta base URL for FIM calls.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

1 issue found across 2 files (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="packages/openai-adapters/src/apis/DeepSeek.ts">

<violation number="1" location="packages/openai-adapters/src/apis/DeepSeek.ts:123">
P2: Chat endpoint base normalization is applied to all chat requests, causing `/beta/`-scoped `apiBase` values to be stripped for normal chat and potentially breaking custom `/beta/` deployments.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

2 issues found across 5 files (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="packages/openai-adapters/src/apis/DeepSeek.ts">

<violation number="1" location="packages/openai-adapters/src/apis/DeepSeek.ts:123">
P1: Removed `/beta/` base normalization causes malformed or incorrect chat endpoints for clients configured with `apiBase` ending in `/beta/`.</violation>

<violation number="2" location="packages/openai-adapters/src/apis/DeepSeek.ts:321">
P1: FIM endpoint now double-prefixes `beta` when `apiBase` already includes `/beta/`, breaking beta-configured clients.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

1 issue found across 2 files (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="core/llm/countTokens.ts">

<violation number="1" location="core/llm/countTokens.ts:464">
P1: Prefill token budgeting double-counts `msgsCopy` as both non-negotiable and prunable history, causing incorrect pruning and possible premature context overflow errors.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[dixoxib]

@cubic-dev-ai something went wrong, re-run a review.

[cubic-dev-ai]

@cubic-dev-ai something went wrong, re-run a review.

@dixoxib I have started the AI code review. It will take a few minutes to complete.

[cubic-dev-ai]

No issues found across 39 files

[cubic-dev-ai]

1 issue found across 1 file (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="packages/openai-adapters/src/apis/DeepSeek.ts">

<violation number="1" location="packages/openai-adapters/src/apis/DeepSeek.ts:57">
P2: Hostname-gating beta endpoints changes established routing for custom `apiBase` domains, causing prefix/FIM requests to switch off beta paths and potentially break existing proxy setups.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

2 issues found across 5 files (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="packages/openai-adapters/src/types.ts">

<violation number="1" location="packages/openai-adapters/src/types.ts:264">
P1: Added `DeepseekConfigSchema` duplicates the `deepseek` discriminator already present in `OpenAIConfigSchema`, which can make `z.discriminatedUnion("provider", ...)` throw at initialization.</violation>
</file>

<file name="docs/customize/model-providers/more/deepseek.mdx">

<violation number="1" location="docs/customize/model-providers/more/deepseek.mdx:147">
P2: Docs incorrectly label `fim/completions` as a standard OpenAI-compatible endpoint, which can mislead proxy/local users and cause FIM/autocomplete 404s.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

1 issue found across 1 file (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="docs/customize/model-providers/more/deepseek.mdx">

<violation number="1" location="docs/customize/model-providers/more/deepseek.mdx:147">
P2: Documentation incorrectly claims standard `chat/completions` supports prefill for proxy/custom deployments, conflicting with beta-only prefix completion guidance and likely causing misconfiguration.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}