Skip to content

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.

fix(deck): replace shut-down gemini-3-pro-preview with gemini-3.1-pro (#963)

Louis Choquelac59514fc221
diff --git a/.pipelex-dev/test_profiles.toml b/.pipelex-dev/test_profiles.toml
index dbe7cadff..21feb717e 100644
--- a/.pipelex-dev/test_profiles.toml
+++ b/.pipelex-dev/test_profiles.toml
@@ -87,7 +87,6 @@ google = [
"gemini-2.5-flash",
"gemini-2.5-flash-lite",
"gemini-2.5-pro",
- "gemini-3.0-pro",
"gemini-3.0-flash",
"gemini-3.1-flash-lite",
"gemini-3.1-pro",
diff --git a/.pipelex/inference/backends/google.toml b/.pipelex/inference/backends/google.toml
index 9651f7c0d..07845aa69 100644
--- a/.pipelex/inference/backends/google.toml
+++ b/.pipelex/inference/backends/google.toml
@@ -8,7 +8,7 @@
#
# Configuration structure:
# - Each model is defined in its own section with the model name as the header
-# - Headers with dots must be quoted (e.g., ["gemini-3.0-pro"])
+# - Headers with dots must be quoted (e.g., ["gemini-3.1-pro"])
# - Model costs are in USD per million tokens (input/output)
#
# Documentation: https://docs.pipelex.com
@@ -54,14 +54,6 @@ max_prompt_images = 3000
costs = { input = 0.10, output = 0.40 }
# --- Gemini 3.0 Series ----------------------------------------
-["gemini-3.0-pro"]
-model_id = "gemini-3-pro-preview"
-inputs = ["text", "images", "pdf"]
-outputs = ["text", "structured"]
-max_prompt_images = 3000
-costs = { input = 2, output = 12.0 }
-thinking_mode = "adaptive"
-
["gemini-3.0-flash"]
model_id = "gemini-3-flash-preview"
inputs = ["text", "images", "pdf"]
diff --git a/.pipelex/inference/backends/openrouter.toml b/.pipelex/inference/backends/openrouter.toml
index 6256bb13c..48fe657c5 100644
--- a/.pipelex/inference/backends/openrouter.toml
+++ b/.pipelex/inference/backends/openrouter.toml
@@ -538,12 +538,6 @@ inputs = ["text", "images", "pdf", "audio", "video"]
outputs = ["text", "structured"]
costs = { input = 0.5, output = 3 }
-["google/gemini-3-pro-preview"]
-max_tokens = 1048576
-inputs = ["text", "images", "pdf", "audio", "video"]
-outputs = ["text", "structured"]
-costs = { input = 2, output = 12 }
-
["google/gemini-3.1-pro-preview"]
max_tokens = 1048576
inputs = ["audio", "pdf", "images", "text", "video"]
diff --git a/.pipelex/inference/backends/pipelex_gateway_models.md b/.pipelex/inference/backends/pipelex_gateway_models.md
index 24cd549c1..667ebdd74 100644
--- a/.pipelex/inference/backends/pipelex_gateway_models.md
+++ b/.pipelex/inference/backends/pipelex_gateway_models.md
@@ -141,14 +141,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
</tr>
<tr>
-<td>gemini-3.0-pro</td>
-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
-<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
-<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
-</tr>
-<tr>
<td>gemini-3.1-flash-lite</td>
<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
@@ -614,6 +606,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
> **AUTO-GENERATED FILE** - Do not edit manually.
-> Last updated: 2026-05-28T20:52:54Z
+> Last updated: 2026-06-04T11:47:03Z
>
> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.
\ No newline at end of file
diff --git a/.pipelex/inference/backends/pipelex_gateway_models_plain.md b/.pipelex/inference/backends/pipelex_gateway_models_plain.md
index 99958be8e..ffee9b0c4 100644
--- a/.pipelex/inference/backends/pipelex_gateway_models_plain.md
+++ b/.pipelex/inference/backends/pipelex_gateway_models_plain.md
@@ -52,9 +52,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
- **gemini-3.0-flash**
- inputs: text, images, pdf
- outputs: text, structured
-- **gemini-3.0-pro**
- - inputs: text, images, pdf
- - outputs: text, structured
- **gemini-3.1-flash-lite**
- inputs: text, images, pdf
- outputs: text, structured
@@ -229,6 +226,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
> **AUTO-GENERATED FILE** - Do not edit manually.
-> Last updated: 2026-05-28T20:52:54Z
+> Last updated: 2026-06-04T11:47:03Z
>
> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.
\ No newline at end of file
diff --git a/.pipelex/inference/backends/portkey.toml b/.pipelex/inference/backends/portkey.toml
index d91a1da80..796de3a90 100644
--- a/.pipelex/inference/backends/portkey.toml
+++ b/.pipelex/inference/backends/portkey.toml
@@ -286,8 +286,8 @@ thinking_mode = "manual"
prompting_target = "gemini"
x-portkey-provider = "@google"
-["gemini-3.0-pro"]
-model_id = "gemini-3-pro-preview"
+["gemini-3.1-pro"]
+model_id = "gemini-3.1-pro-preview"
inputs = ["text", "images", "pdf"]
outputs = ["text", "structured"]
max_prompt_images = 3000
@@ -296,7 +296,7 @@ thinking_mode = "adaptive"
prompting_target = "gemini"
x-portkey-provider = "@google"
-["gemini-3.0-flash-preview"]
+["gemini-3.0-flash"]
model_id = "gemini-3-flash-preview"
inputs = ["text", "images", "pdf"]
outputs = ["text", "structured"]
diff --git a/.pipelex/inference/deck/x_custom_llm_deck.toml b/.pipelex/inference/deck/x_custom_llm_deck.toml
index eb4748074..b3adf6d9c 100644
--- a/.pipelex/inference/deck/x_custom_llm_deck.toml
+++ b/.pipelex/inference/deck/x_custom_llm_deck.toml
@@ -34,21 +34,21 @@ for_object = "disabled"
#
# Example (uncomment to use):
# [llm.waterfalls]
-# premium-llm = ["claude-4.5-opus", "gemini-3.0-pro", "gpt-5.2", "grok-4"]
+# premium-llm = ["claude-4.5-opus", "gemini-3.1-pro", "gpt-5.2", "grok-4"]
# premium-llm-vision = [
# "claude-4.5-opus",
-# "gemini-3.0-pro",
+# "gemini-3.1-pro",
# "gpt-5.2",
# "grok-4-fast-reasoning",
# ]
# premium-llm-structured = [
# "claude-4.5-opus",
-# "gemini-3.0-pro",
+# "gemini-3.1-pro",
# "gpt-5.2",
# "grok-4",
# ]
# large-context-llm-code = [
-# "gemini-3.0-pro",
+# "gemini-3.1-pro",
# "claude-4.5-opus",
# "gpt-5.2",
# "grok-4-fast-reasoning",
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 127c04d51..c663470bc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -23,6 +23,8 @@
### Changed
+- **Gemini deck: `gemini-3.0-pro` removed — Google shut down the underlying `gemini-3-pro-preview`.** Use `gemini-3.1-pro` (→ `gemini-3.1-pro-preview`) instead; it was already in the deck and is now also registered on the `portkey` backend for parity with `google`. The dead `gemini-3.0-pro` handle is dropped from the `google`, `portkey`, and `openrouter` backends and from the test-profile collections. `gemini-3.0-flash` and the `nano-banana-pro` image model (`gemini-3-pro-image-preview`) are unaffected. Anyone referencing `gemini-3.0-pro` must switch to `gemini-3.1-pro` (or the `gemini-pro-latest` alias). The Pipelex Gateway lists models from its own remote config — drop `gemini-3.0-pro` there separately.
+
- **`validate_bundle`, `validate_bundles_from_directory`, and `BundleValidator.validate_pipes` / `acquire_and_validate` now accept `allow_signatures: bool = False`.** Strict by default. The same flag is threaded through `pipelex/cli/commands/validate/_validate_core.py` (the CLI entry point) and `pipelex/cli/agent_cli/commands/validate/_validate_core.py` (the agent CLI), both strict by default. `ValidateBundleError` gained a `signature_check_error: SignaturesNotAllowedError | None` field so callers (and the CLI error renderer) can show the signature dep chain when validation fails on a signature.
- **Dry-run and validation consolidated into `BundleValidator`; the standalone `pipelex/pipe_run/dry_run.py` is removed.** The free functions `dry_run_pipe` / `dry_run_pipes` and the modules `pipelex/pipe_run/dry_run.py`, `dry_run_with_graph.py`, and `dry_pipe_router.py` are gone. Their work now lives in `BundleValidator` (`pipelex/pipeline/bundle_validator.py`) with two lifecycles — `acquire_and_validate` (opens a fresh library, sweeps every pipe, owns teardown; the standalone `validate --all` path) and `validate_pipes` (the inner sweep against an already-open library, called by `validate_bundle`) — and the library/job setup steps are extracted into `pipelex/pipeline/execution_seams.py` (`acquire_library`, `prepare_pipe_job`). The mock-minting and stuff-spec converters (`convert_to_working_memory_format`, `convert_stuff_spec_to_typed_named`) moved onto `WorkingMemoryFactory` as classmethods. No behavior change — validation ordering (wiring pass → signature pre-pass → per-pipe dry-run sweep) and outputs are preserved; only the import surface moved. Callers importing from `pipelex.pipe_run.dry_run` must switch to `BundleValidator` / `WorkingMemoryFactory`.
diff --git a/docs/configuration/config-technical/inference-backend-config.md b/docs/configuration/config-technical/inference-backend-config.md
index 19ee809a8..03aa1732d 100644
--- a/docs/configuration/config-technical/inference-backend-config.md
+++ b/docs/configuration/config-technical/inference-backend-config.md
@@ -436,7 +436,7 @@ Define user-friendly names that map to model names. Aliases are defined in the d
# Simple aliases map to a single model
best-claude = "claude-4.5-opus"
best-gpt = "gpt-5.2"
-best-gemini = "gemini-3.0-pro"
+best-gemini = "gemini-3.1-pro"
# Default aliases (used in presets)
default-general = "claude-4.5-sonnet"
@@ -580,7 +580,7 @@ for_object = "@my-custom-alias"
# Add custom waterfalls - lists of models tried in order
[llm.waterfalls]
-premium-llm = ["claude-4.5-opus", "gemini-3.0-pro", "gpt-5.2"]
+premium-llm = ["claude-4.5-opus", "gemini-3.1-pro", "gpt-5.2"]
small-llm = ["gemini-2.5-flash-lite", "gpt-4o-mini", "claude-3-haiku"]
```
@@ -594,7 +594,7 @@ document_extractor = ["azure-document-intelligence", "mistral-document-ai-2505"]
When using waterfalls in `.mthds` files, prefix them with `~`:
```toml
-model = "~premium-llm" # Will try claude-4.5-opus, then gemini-3.0-pro, then gpt-5.2
+model = "~premium-llm" # Will try claude-4.5-opus, then gemini-3.1-pro, then gpt-5.2
model = "~small-llm" # Will try gemini-2.5-flash-lite, then gpt-4o-mini, etc.
```
diff --git a/docs/under-the-hood/reasoning-controls.md b/docs/under-the-hood/reasoning-controls.md
index e15b181e5..fc867a64b 100644
--- a/docs/under-the-hood/reasoning-controls.md
+++ b/docs/under-the-hood/reasoning-controls.md
@@ -78,13 +78,13 @@ Effort is translated to a `thinking_budget` token count:
model = { model = "gemini-2.5-pro", temperature = 0.3, reasoning_effort = "medium" }
```
-**Gemini 3.0 Pro — adaptive mode**
+**Gemini 3.1 Pro — adaptive mode**
Effort maps to a `ThinkingLevel` enum sent to the Google SDK:
```toml
# Adaptive: effort "high" -> ThinkingLevel.HIGH
-model = { model = "gemini-3.0-pro", temperature = 0.3, reasoning_effort = "high" }
+model = { model = "gemini-3.1-pro", temperature = 0.3, reasoning_effort = "high" }
```
**GPT-5.2 — manual mode**
@@ -380,7 +380,7 @@ thinking_mode = "manual"
thinking_mode = "adaptive"
# Google Gemini 3 with adaptive reasoning
-["gemini-3.0-pro"]
+["gemini-3.1-pro"]
thinking_mode = "adaptive"
# Model without reasoning (or inherited from defaults)
diff --git a/pipelex/kit/configs/inference/backends/google.toml b/pipelex/kit/configs/inference/backends/google.toml
index 9651f7c0d..07845aa69 100644
--- a/pipelex/kit/configs/inference/backends/google.toml
+++ b/pipelex/kit/configs/inference/backends/google.toml
@@ -8,7 +8,7 @@
#
# Configuration structure:
# - Each model is defined in its own section with the model name as the header
-# - Headers with dots must be quoted (e.g., ["gemini-3.0-pro"])
+# - Headers with dots must be quoted (e.g., ["gemini-3.1-pro"])
# - Model costs are in USD per million tokens (input/output)
#
# Documentation: https://docs.pipelex.com
@@ -54,14 +54,6 @@ max_prompt_images = 3000
costs = { input = 0.10, output = 0.40 }
# --- Gemini 3.0 Series ----------------------------------------
-["gemini-3.0-pro"]
-model_id = "gemini-3-pro-preview"
-inputs = ["text", "images", "pdf"]
-outputs = ["text", "structured"]
-max_prompt_images = 3000
-costs = { input = 2, output = 12.0 }
-thinking_mode = "adaptive"
-
["gemini-3.0-flash"]
model_id = "gemini-3-flash-preview"
inputs = ["text", "images", "pdf"]
diff --git a/pipelex/kit/configs/inference/backends/openrouter.toml b/pipelex/kit/configs/inference/backends/openrouter.toml
index 6256bb13c..48fe657c5 100644
--- a/pipelex/kit/configs/inference/backends/openrouter.toml
+++ b/pipelex/kit/configs/inference/backends/openrouter.toml
@@ -538,12 +538,6 @@ inputs = ["text", "images", "pdf", "audio", "video"]
outputs = ["text", "structured"]
costs = { input = 0.5, output = 3 }
-["google/gemini-3-pro-preview"]
-max_tokens = 1048576
-inputs = ["text", "images", "pdf", "audio", "video"]
-outputs = ["text", "structured"]
-costs = { input = 2, output = 12 }
-
["google/gemini-3.1-pro-preview"]
max_tokens = 1048576
inputs = ["audio", "pdf", "images", "text", "video"]
diff --git a/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md b/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md
index 24cd549c1..667ebdd74 100644
--- a/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md
+++ b/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md
@@ -141,14 +141,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
</tr>
<tr>
-<td>gemini-3.0-pro</td>
-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
-<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
-<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
-</tr>
-<tr>
<td>gemini-3.1-flash-lite</td>
<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
@@ -614,6 +606,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
> **AUTO-GENERATED FILE** - Do not edit manually.
-> Last updated: 2026-05-28T20:52:54Z
+> Last updated: 2026-06-04T11:47:03Z
>
> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.
\ No newline at end of file
diff --git a/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md b/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md
index 99958be8e..ffee9b0c4 100644
--- a/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md
+++ b/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md
@@ -52,9 +52,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
- **gemini-3.0-flash**
- inputs: text, images, pdf
- outputs: text, structured
-- **gemini-3.0-pro**
- - inputs: text, images, pdf
- - outputs: text, structured
- **gemini-3.1-flash-lite**
- inputs: text, images, pdf
- outputs: text, structured
@@ -229,6 +226,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
> **AUTO-GENERATED FILE** - Do not edit manually.
-> Last updated: 2026-05-28T20:52:54Z
+> Last updated: 2026-06-04T11:47:03Z
>
> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.
\ No newline at end of file
diff --git a/pipelex/kit/configs/inference/backends/portkey.toml b/pipelex/kit/configs/inference/backends/portkey.toml
index d91a1da80..796de3a90 100644
--- a/pipelex/kit/configs/inference/backends/portkey.toml
+++ b/pipelex/kit/configs/inference/backends/portkey.toml
@@ -286,8 +286,8 @@ thinking_mode = "manual"
prompting_target = "gemini"
x-portkey-provider = "@google"
-["gemini-3.0-pro"]
-model_id = "gemini-3-pro-preview"
+["gemini-3.1-pro"]
+model_id = "gemini-3.1-pro-preview"
inputs = ["text", "images", "pdf"]
outputs = ["text", "structured"]
max_prompt_images = 3000
@@ -296,7 +296,7 @@ thinking_mode = "adaptive"
prompting_target = "gemini"
x-portkey-provider = "@google"
-["gemini-3.0-flash-preview"]
+["gemini-3.0-flash"]
model_id = "gemini-3-flash-preview"
inputs = ["text", "images", "pdf"]
outputs = ["text", "structured"]
diff --git a/pipelex/kit/configs/inference/deck/x_custom_llm_deck.toml b/pipelex/kit/configs/inference/deck/x_custom_llm_deck.toml
index 0b964ef3d..5ad13b82b 100644
--- a/pipelex/kit/configs/inference/deck/x_custom_llm_deck.toml
+++ b/pipelex/kit/configs/inference/deck/x_custom_llm_deck.toml
@@ -35,21 +35,21 @@ for_object = "disabled"
# Example (uncomment to use):
# [llm.waterfalls]
-# premium-llm = ["claude-4.5-opus", "gemini-3.0-pro", "gpt-5.2", "grok-4"]
+# premium-llm = ["claude-4.5-opus", "gemini-3.1-pro", "gpt-5.2", "grok-4"]
# premium-llm-vision = [
# "claude-4.5-opus",
-# "gemini-3.0-pro",
+# "gemini-3.1-pro",
# "gpt-5.2",
# "grok-4-fast-reasoning",
# ]
# premium-llm-structured = [
# "claude-4.5-opus",
-# "gemini-3.0-pro",
+# "gemini-3.1-pro",
# "gpt-5.2",
# "grok-4",
# ]
# large-context-llm-code = [
-# "gemini-3.0-pro",
+# "gemini-3.1-pro",
# "claude-4.5-opus",
# "gpt-5.2",
# "grok-4-fast-reasoning",