Commit graph

12 commits

Author SHA1 Message Date
Chummy
178bb108da
fix(gemini): correct Gemini CLI OAuth cloudcode payload/response handling (#1040)
* fix(gemini): align OAuth cloudcode payload and response parsing

* docs(gemini): document OAuth vs API key endpoint behavior
2026-02-19 23:27:00 -05:00
Aleksandr Prilipko
1b57be7223 fix(provider): implement chat_with_history for OpenAI Codex and Gemini
Both providers only implemented chat_with_system, so the default
chat_with_history trait method was discarding all conversation history
except the last user message. This caused the Telegram bot to lose
context between messages.

Changes:
- OpenAiCodexProvider: extract send_responses_request helper, add
  chat_with_history that maps full ChatMessage history to ResponsesInput
- GeminiProvider: extract send_generate_content helper, add
  chat_with_history that maps ChatMessage history to Gemini Content
  (with assistant→model role mapping)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 19:04:02 +08:00
Chummy
ce104bed45 feat(proxy): add scoped proxy configuration and docs runbooks
- add scope-aware proxy schema and runtime wiring for providers/channels/tools

- add agent callable proxy_config tool for fast proxy setup

- standardize docs system with index, template, and playbooks
2026-02-18 22:10:42 +08:00
Chummy
c70d9b181d test: stabilize cron shell output capture and gemini warmup noop 2026-02-18 19:26:07 +08:00
Edvard
1336c2f03e feat(providers): add warmup() for OpenAI, Anthropic, Gemini, Compatible, GLM
All five providers have HTTP clients but did not implement warmup(),
relying on the trait default no-op. This adds lightweight warmup calls
to establish TLS + HTTP/2 connection pools on startup, reducing
first-request latency. Each warmup is skipped when credentials are
absent, matching the OpenRouter pattern.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-18 14:35:03 +08:00
Chummy
9e9a4a53ab style(gemini): apply rustfmt to oauth endpoint patch 2026-02-18 10:25:15 +08:00
KNIGHTABDO
1d8e57d388 fix(gemini): route OAuth tokens to cloudcode-pa.googleapis.com
Gemini CLI OAuth tokens are scoped for Google's internal Code Assist
API at cloudcode-pa.googleapis.com/v1internal, not the public
generativelanguage.googleapis.com/v1beta endpoint.

This commit:
- Routes OAuth requests to the correct internal endpoint
- Wraps the request payload with model metadata (internal API format)
- Keeps API key auth unchanged on the public endpoint

Fixes #578
2026-02-18 10:25:15 +08:00
mai1015
b341fdb368 feat: add agent structure and improve tooling for provider 2026-02-17 01:01:56 +08:00
chumyin
3b4a4de457 refactor(provider): unify Provider responses with ChatResponse
- Switch Provider trait methods to return structured ChatResponse
- Map OpenAI-compatible tool_calls into shared ToolCall type
- Update reliable/router wrappers and provider tests for new interface
- Make agent loop prefer structured tool calls with text fallback parsing
- Adapt gateway replies to structured responses with safe tool-call fallback
2026-02-16 19:16:22 +08:00
Edvard Schøyen
49bb20f961
fix(providers): use Bearer auth for Gemini CLI OAuth tokens
* fix(providers): use Bearer auth for Gemini CLI OAuth tokens

When credentials come from ~/.gemini/oauth_creds.json (Gemini CLI),
send them as Authorization: Bearer header instead of ?key= query
parameter. API keys from env vars or config continue using ?key=.

Fixes #194

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor(gemini): harden OAuth bearer auth flow and tests

* fix(gemini): granular auth source tracking and review fixes

Build on chumyin's auth model refactor with:
- Expand GeminiAuth to 4 variants (ExplicitKey/EnvGeminiKey/EnvGoogleKey/
  OAuthToken) so auth_source() uses stored discriminant without re-reading
  env vars at call time
- Add is_api_key()/credential() helpers on the enum
- Upgrade expired OAuth token log from debug to warn
- Add tests: provider_rejects_empty_key, auth_source_explicit_key,
  auth_source_none_without_credentials

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* style: apply rustfmt to fix CI lint failures

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: root <root@instance-20220913-1738.vcn09131738.oraclevcn.com>
Co-authored-by: argenis de la rosa <theonlyhennygod@gmail.com>
2026-02-15 14:32:33 -05:00
argenis de la rosa
a310e178db fix: add missing port/host fields to GatewayConfig and apply_env_overrides method
- Add port and host fields to GatewayConfig struct
- Add default_gateway_port() and default_gateway_host() functions
- Add apply_env_overrides() method to Config for env var support
- Fix test to include new GatewayConfig fields

All tests pass.
2026-02-14 16:05:13 -05:00
argenis de la rosa
3bb5deff37 feat: add Google Gemini provider with CLI token reuse support
- Add src/providers/gemini.rs with support for:
  - Direct API key (GEMINI_API_KEY env var or config)
  - Gemini CLI OAuth token reuse (~/.gemini/oauth_creds.json)
  - GOOGLE_API_KEY environment variable fallback
- Register gemini provider in src/providers/mod.rs with aliases: gemini, google, google-gemini
- Add Gemini to onboarding wizard with:
  - Auto-detection of existing Gemini CLI credentials
  - Model selection (gemini-2.0-flash, gemini-1.5-pro, etc.)
  - API key URL and env var guidance
- Add comprehensive tests for Gemini provider
- Fix pre-existing clippy warnings in email_channel.rs and whatsapp.rs

Closes #XX (Gemini CLI token reuse feature request)
2026-02-14 14:58:19 -05:00