steve 15fb8e19a8 feat: add llm.Foreman() constructor for foreman daemon integration ...

Foreman is a private queued Ollama endpoint with observability. Since it
speaks native Ollama on the wire, the constructor delegates to the existing
ollama provider — no new code paths. Streaming, tool use, and think all
work transparently.

baseURL is positional and required (no sensible default for a private
daemon). apiKey can be empty for network-trusted deployments.

See ADR-0011 in the foreman repo for the integration design.

2026-05-23 22:36:31 +00:00

..

agent

feat: comprehensive token usage tracking for V2

2026-03-02 04:33:18 +00:00

anthropic

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

cmd/llm

feat: add DeepSeek, Moonshot, xAI, Groq, Ollama; drop v1; migrate TUI to v2

2026-04-24 13:34:39 +00:00

deepseek

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

google

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

groq

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

internal

Add go-llm v2: redesigned API for simpler LLM abstraction

2026-02-07 20:00:08 -05:00

moonshot

feat: add DeepSeek, Moonshot, xAI, Groq, Ollama; drop v1; migrate TUI to v2

2026-04-24 13:34:39 +00:00

ollama

refactor(v2/ollama): drop openaicompat shim, use native provider

2026-05-01 18:29:59 +00:00

openai

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

openaicompat

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

provider

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

sandbox

Add comprehensive test suite for sandbox package (78 tests)

2026-02-08 01:10:59 -05:00

tools

Add go-llm v2: redesigned API for simpler LLM abstraction

2026-02-07 20:00:08 -05:00

xai

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

chat_test.go

test(v2): end-to-end cache-hint propagation through Chat.Send

2026-04-09 19:40:39 +00:00

chat.go

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

CLAUDE.md

docs(v2): update CLAUDE.md for native Ollama provider

2026-05-01 18:31:00 +00:00

constructors.go

feat: add llm.Foreman() constructor for foreman daemon integration

2026-05-23 22:36:31 +00:00

errors.go

Add structured output support with Generate[T] and GenerateWith[T]

2026-02-07 22:36:33 -05:00

generate_test.go

feat: comprehensive token usage tracking for V2

2026-03-02 04:33:18 +00:00

generate.go

feat: comprehensive token usage tracking for V2

2026-03-02 04:33:18 +00:00

go.mod

feat: add DeepSeek, Moonshot, xAI, Groq, Ollama; drop v1; migrate TUI to v2

2026-04-24 13:34:39 +00:00

go.sum

feat: add DeepSeek, Moonshot, xAI, Groq, Ollama; drop v1; migrate TUI to v2

2026-04-24 13:34:39 +00:00

llm.go

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

mcp.go

Add go-llm v2: redesigned API for simpler LLM abstraction

2026-02-07 20:00:08 -05:00

message_test.go

Add comprehensive test suite for v2 module with mock provider

2026-02-07 22:00:49 -05:00

message.go

feat: add audio input support to v2 providers

2026-02-08 21:00:56 -05:00

middleware_test.go

feat: comprehensive token usage tracking for V2

2026-03-02 04:33:18 +00:00

middleware.go

feat: comprehensive token usage tracking for V2

2026-03-02 04:33:18 +00:00

mock_provider_test.go

Add comprehensive test suite for v2 module with mock provider

2026-02-07 22:00:49 -05:00

model_test.go

Add agent sub-package for composable LLM agents

2026-02-07 23:17:19 -05:00

pricing_test.go

feat: comprehensive token usage tracking for V2

2026-03-02 04:33:18 +00:00

pricing.go

feat: comprehensive token usage tracking for V2

2026-03-02 04:33:18 +00:00

registry.go

feat(v2/registry): register ollama-cloud as a first-class provider

2026-05-01 18:30:40 +00:00

request_test.go

test(v2): cover empty-messages and disabled-but-non-nil cacheConfig edges

2026-04-09 19:24:55 +00:00

request.go

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

response.go

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

stream_test.go

Add comprehensive test suite for v2 module with mock provider

2026-02-07 22:00:49 -05:00

stream.go

feat(v2): add ReasoningLevel option; thinking/reasoning across providers

2026-04-25 03:58:42 +00:00

tool_coerce_test.go

fix(v2): coerce string-encoded numbers/bools in tool arguments

2026-04-27 22:12:56 +00:00

tool_coerce.go

fix(v2): coerce string-encoded numbers/bools in tool arguments

2026-04-27 22:12:56 +00:00

tool_test.go

Add go-llm v2: redesigned API for simpler LLM abstraction

2026-02-07 20:00:08 -05:00

tool.go

fix(v2): coerce string-encoded numbers/bools in tool arguments

2026-04-27 22:12:56 +00:00

transcriber.go

Add transcription API to v2 module

2026-02-07 20:24:20 -05:00