From d7f6dadbea08333bd6667c04cce2010673ad3415 Mon Sep 17 00:00:00 2001 From: ceverson70 <77007231+ceverson70@users.noreply.github.com> Date: Tue, 21 Jul 2026 12:05:09 -0400 Subject: [PATCH] feat(vertex): add validated Gemini model catalog for /model picker MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a "vertex" key to _PROVIDER_MODELS with 6 Gemini 3.x models that were validated live against the Vertex AI OpenAI-compatible endpoint (aiplatform.googleapis.com, global region, project antse-tooling) on 2026-07-21. All entries returned HTTP 200; 8 other candidates (e.g. gemini-3.1-flash, gemini-3-pro-preview) returned 404 and were excluded. Validated models (google/ prefix required by Vertex endpoint): - google/gemini-3.5-flash (frontier Flash, agentic) - google/gemini-3.6-flash (newer incremental over 3.5) - google/gemini-3.5-flash-lite (lighter/cheaper 3.5 variant) - google/gemini-3.1-pro-preview (3.1 Pro preview) - google/gemini-3-flash-preview (3.0 Flash preview) - google/gemini-3.1-flash-lite (most cost-efficient 3.x model) Context lengths are covered by the existing "gemini" prefix entry (1_048_576) in agent/model_metadata.py DEFAULT_CONTEXT_LENGTHS — no additional entries needed. Co-Authored-By: Claude Sonnet 4.6 (1M context) --- hermes_cli/models.py | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/hermes_cli/models.py b/hermes_cli/models.py index 5556da9fdbc..3a8107ed1b4 100644 --- a/hermes_cli/models.py +++ b/hermes_cli/models.py @@ -575,6 +575,19 @@ _PROVIDER_MODELS: dict[str, list[str]] = { "deepseek/deepseek-r1-0528", "qwen/qwen3-235b-a22b-fp8", ], + # Google Vertex AI — OpenAI-compatible endpoint + # (aiplatform.googleapis.com/v1beta1/projects//locations/global/endpoints/openapi) + # IDs must use the "google/" prefix exactly as returned by the API. + # All entries below have been validated live against the antse-tooling GCP + # project (global region) and returned HTTP 200 as of 2026-07-21. + "vertex": [ + "google/gemini-3.5-flash", # frontier Flash; strong agentic + coding + "google/gemini-3.6-flash", # incremental over 3.5-flash (newer) + "google/gemini-3.5-flash-lite", # lighter/cheaper 3.5 Flash variant + "google/gemini-3.1-pro-preview", # 3.1 Pro preview + "google/gemini-3-flash-preview", # 3.0 Flash preview + "google/gemini-3.1-flash-lite", # most cost-efficient Gemini 3.x + ], } # ---------------------------------------------------------------------------