Commit Graph

11 Commits

Author SHA1 Message Date
Artem Yadelskyi 0675ce7c38 feat(fmt): Fix formatting 2026-02-20 20:03:11 +02:00
Artem Yadelskyi ad8c2d48c8 Merge branch 'main' into fix-formatting
# Conflicts:
#	cmd/picoclaw/main.go
#	pkg/agent/context.go
#	pkg/agent/loop.go
#	pkg/channels/dingtalk.go
#	pkg/channels/feishu_64.go
#	pkg/channels/line.go
#	pkg/channels/manager.go
#	pkg/config/config.go
#	pkg/migrate/migrate_test.go
#	pkg/providers/anthropic/provider_test.go
#	pkg/providers/claude_provider_test.go
#	pkg/providers/http_provider.go
#	pkg/providers/openai_compat/provider.go
#	pkg/providers/protocoltypes/types.go
#	pkg/providers/types.go
2026-02-20 20:02:53 +02:00
Artem Yadelskyi a896831903 feat(fmt): Fix formatting 2026-02-19 22:05:15 +02:00
Artem Yadelskyi 2038f04d0d Merge branch 'main' into fix-formatting
# Conflicts:
#	pkg/agent/loop.go
#	pkg/agent/loop_test.go
#	pkg/channels/discord.go
#	pkg/channels/onebot.go
#	pkg/config/config.go
#	pkg/tools/subagent_tool_test.go
2026-02-19 22:04:48 +02:00
yinwm 7f241647be feat(providers): add thought_signature support for gemini
Add support for persisting thought_signature metadata from Google/Gemini 3
models. This introduces ExtraContent and GoogleExtra types to handle
provider-specific metadata, and ensures thought signatures are properly
preserved through the tool call lifecycle.
2026-02-20 00:36:31 +08:00
yinwm 68cdafc5f2 refactor(providers): restructure provider creation with protocol-based configuration
- Move provider creation logic to factory_provider.go with protocol-based approach
- Add OpenAIProviderConfig with WebSearch support and embedded ProviderConfig
- Add maxTokensField to OpenAI-compatible provider for configurable token field
- Introduce new providers: Ollama, DeepSeek, GitHubCopilot, Antigravity, Qwen
- Remove redundant CreateProvider function from factory.go
- Add ThoughtSignature field to FunctionCall for tool response handling
- Remove duplicate Name field assignment in tool loop
- Update tests to reflect new provider configuration structure
2026-02-20 00:12:01 +08:00
fipso bb0424e1e2 fix: also use max_completion_tokens for gpt5 era models (#445) 2026-02-19 01:29:34 +01:00
Artem Yadelskyi 9e120f90ea feat(fmt): Run formatters 2026-02-18 21:48:23 +02:00
Jared Mahotiere c4cbb5fb35 providers: finalize PR213 review fixes
Phase 1: centralize protocol message/tool/response types in protocoltypes and keep compatibility aliases in providers and protocol packages.

Phase 1: preserve HTTPProvider constructor compatibility and route Anthropic api_base through factory auth/provider constructors with base URL normalization.

Phase 2: expand provider routing/auth tests (deepseek/nvidia/shengsuanyun, codex/claude oauth/codex-cli) and add openai_compat + anthropic coverage for proxy transport, model normalization, numeric option coercion, token-source refresh, and base URL behavior.

Phase 3: apply gofmt and validate with Dockerized tests (go test ./pkg/providers/... ./pkg/migrate and go test ./...).
2026-02-17 11:13:10 -05:00
Jared Mahotiere e3c246a36f Merge origin/main into refactor/provider-protocol-122 2026-02-17 09:28:56 -05:00
Jared Mahotiere a6e885bb47 refactor(providers): extract protocol factory and openai-compat transport 2026-02-15 08:04:07 -05:00