Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.
feature/Add-models · L-260920-1feb2b (#1218)
Louis Choquel9f55e30027aa
diff --git a/.pipelex-dev/test_profiles.toml b/.pipelex-dev/test_profiles.tomlindex 18d88873a..7d0ffd4c6 100644--- a/.pipelex-dev/test_profiles.toml+++ b/.pipelex-dev/test_profiles.toml@@ -187,6 +187,10 @@ openai = ["gpt-5.4-mini","gpt-5.4-nano","gpt-5.5",+ "gpt-5.6-sol",+ "gpt-5.6-terra",+ "gpt-5.6-luna",+ "gpt-6-astra",]# --- OpenAI OSS Models ---diff --git a/.pipelex/inference/backends/azure_openai.toml b/.pipelex/inference/backends/azure_openai.tomlindex 5258545b0..db9a0c183 100644--- a/.pipelex/inference/backends/azure_openai.toml+++ b/.pipelex/inference/backends/azure_openai.toml@@ -225,6 +225,40 @@ costs = { input = 5.0, output = 30.0 }valued_constraints = { fixed_temperature = 1 }thinking_mode = "manual"+# --- GPT-5.6 Series -----------------------------------------------------------+["gpt-5.6-sol"]+model_id = "gpt-5.6-sol-2026-07-09"+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 4.0, output = 20.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++["gpt-5.6-terra"]+model_id = "gpt-5.6-terra-2026-07-09"+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 2.0, output = 12.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++["gpt-5.6-luna"]+model_id = "gpt-5.6-luna-2026-07-09"+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 0.2, output = 1.2 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++# --- GPT-6 Series -------------------------------------------------------------+["gpt-6-astra"]+model_id = "gpt-6-astra-2026-09-03"+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 10.0, output = 50.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"+################################################################################# IMAGE GENERATION MODELS################################################################################diff --git a/.pipelex/inference/backends/openai.toml b/.pipelex/inference/backends/openai.tomlindex 12684a75d..ef2ee7ccf 100644--- a/.pipelex/inference/backends/openai.toml+++ b/.pipelex/inference/backends/openai.toml@@ -244,6 +244,36 @@ costs = { input = 5.0, output = 30.0 }valued_constraints = { fixed_temperature = 1 }thinking_mode = "manual"+# --- GPT-5.6 Series -----------------------------------------------------------+["gpt-5.6-sol"]+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 4.0, output = 20.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++["gpt-5.6-terra"]+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 2.0, output = 12.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++["gpt-5.6-luna"]+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 0.2, output = 1.2 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++# --- GPT-6 Series -------------------------------------------------------------+["gpt-6-astra"]+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 10.0, output = 50.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"+################################################################################# IMAGE GENERATION MODELS################################################################################diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 3974d7343..3bcc0e93f 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -2,6 +2,10 @@## [Unreleased]+### Added++- **The GPT-5.6 series and GPT-6 Astra are served on OpenAI, Azure OpenAI, the Pipelex Gateway and Pipelex Manifold**: `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna` and `gpt-6-astra` are registered on the two direct backends and, through the remote config, on both hosted routing profiles. All four take text, images and PDF, produce text and structured output, and reason under `thinking_mode = "manual"` with a fixed temperature of 1. The Azure entries carry the dated deployment ids the hosted profiles also use as their wire model ids.+### Changed- **`add-model` skill follows the model's nearest sibling**: the skill derives which backend TOMLs, test collection and deck entries a new model belongs in from the model it succeeds, instead of a fixed provider-to-backend table, and checks each backend actually serves the model. It takes the model's facts from the provider's own documentation with OpenRouter as a cross-check, hands the live tests to `/test-model` with a test class per declared capability, and adds the deck and changelog steps and `make ugm` once the gateway catalog carries the model.diff --git a/pipelex/kit/configs/inference/backends/azure_openai.toml b/pipelex/kit/configs/inference/backends/azure_openai.tomlindex 5258545b0..db9a0c183 100644--- a/pipelex/kit/configs/inference/backends/azure_openai.toml+++ b/pipelex/kit/configs/inference/backends/azure_openai.toml@@ -225,6 +225,40 @@ costs = { input = 5.0, output = 30.0 }valued_constraints = { fixed_temperature = 1 }thinking_mode = "manual"+# --- GPT-5.6 Series -----------------------------------------------------------+["gpt-5.6-sol"]+model_id = "gpt-5.6-sol-2026-07-09"+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 4.0, output = 20.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++["gpt-5.6-terra"]+model_id = "gpt-5.6-terra-2026-07-09"+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 2.0, output = 12.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++["gpt-5.6-luna"]+model_id = "gpt-5.6-luna-2026-07-09"+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 0.2, output = 1.2 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++# --- GPT-6 Series -------------------------------------------------------------+["gpt-6-astra"]+model_id = "gpt-6-astra-2026-09-03"+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 10.0, output = 50.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"+################################################################################# IMAGE GENERATION MODELS################################################################################diff --git a/pipelex/kit/configs/inference/backends/openai.toml b/pipelex/kit/configs/inference/backends/openai.tomlindex 12684a75d..ef2ee7ccf 100644--- a/pipelex/kit/configs/inference/backends/openai.toml+++ b/pipelex/kit/configs/inference/backends/openai.toml@@ -244,6 +244,36 @@ costs = { input = 5.0, output = 30.0 }valued_constraints = { fixed_temperature = 1 }thinking_mode = "manual"+# --- GPT-5.6 Series -----------------------------------------------------------+["gpt-5.6-sol"]+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 4.0, output = 20.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++["gpt-5.6-terra"]+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 2.0, output = 12.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++["gpt-5.6-luna"]+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 0.2, output = 1.2 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"++# --- GPT-6 Series -------------------------------------------------------------+["gpt-6-astra"]+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+costs = { input = 10.0, output = 50.0 }+valued_constraints = { fixed_temperature = 1 }+thinking_mode = "manual"+################################################################################# IMAGE GENERATION MODELS################################################################################