Lightpanda: the headless browser designed for AI and automation
agent: drop the OrcaRouter provider
Adrià Arrufata6df7b04d0da
diff --git a/README.md b/README.mdindex c06432927..b315d50db 100644--- a/README.md+++ b/README.md@@ -181,9 +181,8 @@ you can prototype with the LLM and ship the output to production without amodel at runtime.It supports Anthropic, OpenAI, Gemini, Google Vertex AI, Mistral, Hugging-Face, the multi-lab gateways [Vercel AI Gateway](https://vercel.com/ai-gateway),-[OpenRouter](https://openrouter.ai) and [OrcaRouter](https://orcarouter.ai)-(one key for hundreds of models), any OpenAI-compatible endpoint via+Face, the multi-lab gateways [Vercel AI Gateway](https://vercel.com/ai-gateway)+and [OpenRouter](https://openrouter.ai) (one key for hundreds of models), any OpenAI-compatible endpoint via`OPENAI_BASE_URL`, and local models via Ollama or llama.cpp. You can also runwithout an LLM using `--no-llm`, which drops you into the REPL. See the[agent documentation](https://lightpanda.io/docs/usage/agent) for the fulldiff --git a/build.zig.zon b/build.zig.zonindex fbcf8a358..61b3b6d82 100644--- a/build.zig.zon+++ b/build.zig.zon@@ -36,8 +36,8 @@.hash = "sqlite3-3.53.2-DMxLWuAOAAA_Px0arJOIOaP4AKEu5prbsQgPMA35W1zz",},.zenai = .{- .url = "git+https://github.com/lightpanda-io/zenai.git#43658858f6c677b107a0f4fb76dc92e5ac97d3a4",- .hash = "zenai-0.0.0-iOY_VKquBgBT36nAFRpM4tQki3JNZgFvTwQY6Pz-wiQx",+ .url = "git+https://github.com/lightpanda-io/zenai.git#b3386fde741d3d9f76674e4706ac1db27923c855",+ .hash = "zenai-0.0.0-iOY_VJEhBwBj9qGuHOtw1TdQw0aiIbOZhXlybkSqhXKs",},.isocline = .{.url = "git+https://github.com/arrufat/isocline#4a99434bee4a5ed04c1639514224d48cd55e1405",diff --git a/src/agent/settings.zig b/src/agent/settings.zigindex 8c6d00b9e..817d6ca78 100644--- a/src/agent/settings.zig+++ b/src/agent/settings.zig@@ -31,7 +31,7 @@ const string = @import("../string.zig");const auth = @import("auth/auth.zig");const Candidate = zenai.provider.Candidate;-pub const api_keys_hint = "ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, HF_TOKEN, AI_GATEWAY_API_KEY, MISTRAL_API_KEY, OPENROUTER_API_KEY, or ORCAROUTER_API_KEY (Vertex AI: VERTEX_API_KEY, or GOOGLE_CLOUD_PROJECT via gcloud; Codex: a ChatGPT subscription via /provider codex)";+pub const api_keys_hint = "ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, HF_TOKEN, AI_GATEWAY_API_KEY, MISTRAL_API_KEY, or OPENROUTER_API_KEY (Vertex AI: VERTEX_API_KEY, or GOOGLE_CLOUD_PROJECT via gcloud; Codex: a ChatGPT subscription via /provider codex)";/// Determine which provider to use and read its env key. Returns null/// only when no `--provider` was given AND no env key exists (the callerdiff --git a/src/help.zon b/src/help.zonindex 85a0c78c8..91f19b734 100644--- a/src/help.zon+++ b/src/help.zon@@ -266,8 +266,8 @@\\ The AI provider. When omitted, lightpanda auto-detects an API\\ key from your environment (ANTHROPIC_API_KEY, OPENAI_API_KEY,\\ GOOGLE_API_KEY/GEMINI_API_KEY, HF_TOKEN, AI_GATEWAY_API_KEY,- \\ MISTRAL_API_KEY, OPENROUTER_API_KEY, ORCAROUTER_API_KEY,- \\ VERTEX_API_KEY). With exactly one key set:+ \\ MISTRAL_API_KEY, OPENROUTER_API_KEY, VERTEX_API_KEY). With+ \\ exactly one key set:\\ that provider is used. With multiple keys on a TTY: you'll be\\ prompted to pick; in non-interactive contexts, pass --provider\\ explicitly. With no keys set: falls back to the basic REPL@@ -288,8 +288,8 @@\\ subscription (OAuth) instead of an API key.\\\\ Allowed values: "anthropic", "openai", "gemini", "huggingface",- \\ "vercel", "mistral", "openrouter", "orcarouter",- \\ "ollama", "llama_cpp", "vertex", "codex",+ \\ "vercel", "mistral", "openrouter", "ollama",+ \\ "llama_cpp", "vertex", "codex",\\ "openai_compatible".\\ In the REPL, use /provider to list and change providers.\\ --save <PATH>