Conversation
…-5-1; thinking-off per model (omit / between_tools), effort kept, forced tool_choice rejected locally
…explicit cache, cache-write prices); no gpt-6-terra in OpenAI's model list
…e thinking_level per model
…s takes the thinking-off route
…e-5-1, gpt-6.1-sol, gpt-6-luna, gemini-3.8-flash, gemini-3.5-flash-lite
There was a problem hiding this comment.
Copilot review overview
🟡 Changes recommended
Gemini token-budget handling is incompatible with the new models, and Anthropic cache-write pricing mismatches the default TTL.
Review effort: Balanced
Findings: 2
Open (2)
What changed in this PR
Adds newly released OpenAI, Gemini, and Anthropic models with provider-specific reasoning, caching, pricing, and structured-output behavior.
Changes:
- Registers new models and capabilities across three providers.
- Adds reasoning/thinking validation and Anthropic thinking-mode translation.
- Expands unit, live smoke, caching, and documentation coverage.
| File | Description |
|---|---|
symai/backend/engines/neurosymbolic/openai/models.py |
Adds GPT-6.1 Sol and GPT-6 Luna specifications. |
symai/backend/engines/neurosymbolic/google/models.py |
Adds Gemini 3.5 Flash-Lite and 3.8 Flash specifications. |
symai/backend/engines/neurosymbolic/google/engine.py |
Validates model-specific thinking levels. |
symai/backend/engines/neurosymbolic/anthropic/models.py |
Adds Claude 5.x specifications and thinking-off behavior. |
symai/backend/engines/neurosymbolic/anthropic/engine.py |
Handles adaptive thinking and output configuration merging. |
tests/engines/neurosymbolic/interface.py |
Updates shared unsupported-cache behavior tests. |
tests/engines/neurosymbolic/test_openai.py |
Tests new OpenAI models and live requests. |
tests/engines/neurosymbolic/test_google.py |
Tests new Gemini models and thinking levels. |
tests/engines/neurosymbolic/test_anthropic.py |
Tests new Claude models and thinking behavior. |
docs/source/ENGINES/neurosymbolic_engine.md |
Documents newly supported models and controls. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
Comment on lines
+54
to
+56
| # NOTE: cache_write is the 5-minute TTL rate (1.25x input); a 1h TTL write, | ||
| # the engine's default cache_control, bills 2x input. | ||
| pricing=ModelPricing(input=10.00, output=50.00, cached_input=0.25, cache_write=12.50), |
| if isinstance(thinking, dict) and self.is_reasoning_model(): | ||
| thinking_config = {"includeThoughts": True} | ||
| if "thinking_level" in thinking: | ||
| self._validate_thinking_level(model, thinking["thinking_level"], spec) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.