diff --git a/.env.example b/.env.example index f163e3b..2d29bdb 100644 --- a/.env.example +++ b/.env.example @@ -55,7 +55,7 @@ OPENROUTER_API_KEY=your_openrouter_api_key_here # Optional: Default model to use # Options: 'auto' (Claude picks best model), 'pro', 'flash', 'o3', 'o3-mini', 'o4-mini', 'o4-mini-high', -# 'gpt-5.1', 'gpt-5.1-codex', 'gpt-5.1-codex-mini', 'gpt-5', 'gpt-5-mini', 'grok', +# 'gpt-5.2', 'gpt-5.1-codex', 'gpt-5.1-codex-mini', 'gpt-5', 'gpt-5-mini', 'grok', # 'opus-4.1', 'sonnet-4.1', or any DIAL model if DIAL is configured # When set to 'auto', Claude will select the best model for each task # Defaults to 'auto' if not specified @@ -80,7 +80,8 @@ DEFAULT_THINKING_MODE_THINKDEEP=high # If you want to disable a provider entirely, don't set its API key # # Supported OpenAI models: -# - gpt-5.1 (400K context, 128K output, reasoning tokens, streaming enabled) +# - gpt-5.2 (400K context, 128K output, reasoning tokens, streaming enabled) +# - gpt-5.2-pro (400K context, 272K output, highest reasoning quality, Responses API only) # - gpt-5.1-codex (400K context, 128K output, coding specialization, Responses API only) # - gpt-5.1-codex-mini (400K context, 128K output, cost-efficient Codex with streaming) # - gpt-5 (400K context, 128K output, reasoning tokens) @@ -126,7 +127,7 @@ DEFAULT_THINKING_MODE_THINKDEEP=high # # Examples: # OPENAI_ALLOWED_MODELS=o3-mini,o4-mini,mini # Only allow mini models (cost control) -# OPENAI_ALLOWED_MODELS=gpt-5.1,gpt-5.1-codex # Pin to GPT-5.1 family +# OPENAI_ALLOWED_MODELS=gpt-5.2,gpt-5.1-codex # Pin to flagship GPT-5 family # GOOGLE_ALLOWED_MODELS=flash # Only allow Flash (fast responses) # XAI_ALLOWED_MODELS=grok-3 # Only allow standard GROK (not fast variant) # OPENAI_ALLOWED_MODELS=o4-mini # Single model standardization diff --git a/README.md b/README.md index e4bc45f..0d87881 100644 --- a/README.md +++ b/README.md @@ -128,7 +128,7 @@ and review into consideration to aid with its final pre-commit review. For best results when using [Claude Code](https://claude.ai/code): - **Sonnet 4.5** - All agentic work and orchestration -- **Gemini 3.0 Pro** OR **GPT-5-Pro** - Deep thinking, additional code reviews, debugging and validations, pre-commit analysis +- **Gemini 3.0 Pro** OR **GPT-5.2-Pro** - Deep thinking, additional code reviews, debugging and validations, pre-commit analysis
@@ -137,7 +137,7 @@ For best results when using [Claude Code](https://claude.ai/code): For best results when using [Codex CLI](https://developers.openai.com/codex/cli): - **GPT-5 Codex Medium** - All agentic work and orchestration -- **Gemini 3.0 Pro** OR **GPT-5-Pro** - Deep thinking, additional code reviews, debugging and validations, pre-commit analysis +- **Gemini 3.0 Pro** OR **GPT-5.2-Pro** - Deep thinking, additional code reviews, debugging and validations, pre-commit analysis
## Quick Start (5 minutes) @@ -208,7 +208,7 @@ PAL activates any provider that has credentials in your `.env`. See `.env.exampl **Collaboration & Planning** *(Enabled by default)* - **[`clink`](docs/tools/clink.md)** - Bridge requests to external AI CLIs (Gemini planner, codereviewer, etc.) -- **[`chat`](docs/tools/chat.md)** - Brainstorm ideas, get second opinions, validate approaches. With capable models (GPT-5 Pro, Gemini 3.0 Pro), generates complete code / implementation +- **[`chat`](docs/tools/chat.md)** - Brainstorm ideas, get second opinions, validate approaches. With capable models (GPT-5.2 Pro, Gemini 3.0 Pro), generates complete code / implementation - **[`thinkdeep`](docs/tools/thinkdeep.md)** - Extended reasoning, edge case analysis, alternative perspectives - **[`planner`](docs/tools/planner.md)** - Break down complex projects into structured, actionable plans - **[`consensus`](docs/tools/consensus.md)** - Get expert opinions from multiple AI models with stance steering diff --git a/conf/gemini_models.json b/conf/gemini_models.json index fed3747..05372e3 100644 --- a/conf/gemini_models.json +++ b/conf/gemini_models.json @@ -17,7 +17,7 @@ "max_image_size_mb": "Maximum total size in MB for all images combined (capped at 40MB max for custom models)", "supports_temperature": "Whether the model accepts temperature parameter in API calls (set to false for O3/O4 reasoning models)", "temperature_constraint": "Type of temperature constraint: 'fixed' (fixed value), 'range' (continuous range), 'discrete' (specific values), or omit for default range", - "use_openai_response_api": "Set to true when the model must use the /responses endpoint (reasoning models like GPT-5 Pro). Leave false/omit for standard chat completions.", + "use_openai_response_api": "Set to true when the model must use the /responses endpoint (reasoning models like GPT-5.2 Pro). Leave false/omit for standard chat completions.", "default_reasoning_effort": "Default reasoning effort level for models that support it (e.g., 'low', 'medium', 'high'). Omit if not applicable.", "description": "Human-readable description of the model", "intelligence_score": "1-20 human rating used as the primary signal for auto-mode model ordering", diff --git a/conf/openai_models.json b/conf/openai_models.json index 52e86a3..327cfd1 100644 --- a/conf/openai_models.json +++ b/conf/openai_models.json @@ -17,7 +17,7 @@ "max_image_size_mb": "Maximum total size in MB for all images combined (capped at 40MB max for custom models)", "supports_temperature": "Whether the model accepts temperature parameter in API calls (set to false for O3/O4 reasoning models)", "temperature_constraint": "Type of temperature constraint: 'fixed' (fixed value), 'range' (continuous range), 'discrete' (specific values), or omit for default range", - "use_openai_response_api": "Set to true when the model must use the /responses endpoint (reasoning models like GPT-5 Pro). Leave false/omit for standard chat completions.", + "use_openai_response_api": "Set to true when the model must use the /responses endpoint (reasoning models like GPT-5.2 Pro). Leave false/omit for standard chat completions.", "default_reasoning_effort": "Default reasoning effort level for models that support it (e.g., 'low', 'medium', 'high'). Omit if not applicable.", "description": "Human-readable description of the model", "intelligence_score": "1-20 human rating used as the primary signal for auto-mode model ordering", @@ -47,14 +47,16 @@ "temperature_constraint": "fixed" }, { - "model_name": "gpt-5-pro", - "friendly_name": "OpenAI (GPT-5 Pro)", + "model_name": "gpt-5.2-pro", + "friendly_name": "OpenAI (GPT-5.2 Pro)", "aliases": [ + "gpt5.2-pro", + "gpt5.2pro", "gpt5pro", "gpt5-pro" ], "intelligence_score": 18, - "description": "GPT-5 Pro (400K context, 272K output) - Very advanced, reasoning model", + "description": "GPT-5.2 Pro (400K context, 272K output) - Very advanced, reasoning model", "context_window": 400000, "max_output_tokens": 272000, "supports_extended_thinking": true, @@ -234,15 +236,18 @@ "use_openai_response_api": true }, { - "model_name": "gpt-5.1", - "friendly_name": "OpenAI (GPT-5.1)", + "model_name": "gpt-5.2", + "friendly_name": "OpenAI (GPT-5.2)", "aliases": [ + "gpt5.2", + "gpt-5.2", + "5.2", "gpt5.1", "gpt-5.1", "5.1" ], "intelligence_score": 18, - "description": "GPT-5.1 (400K context, 128K output) - Flagship reasoning model with configurable thinking effort and vision support.", + "description": "GPT-5.2 (400K context, 128K output) - Flagship reasoning model with configurable thinking effort and vision support.", "context_window": 400000, "max_output_tokens": 128000, "supports_extended_thinking": true, diff --git a/conf/openrouter_models.json b/conf/openrouter_models.json index 8270dc0..92645e4 100644 --- a/conf/openrouter_models.json +++ b/conf/openrouter_models.json @@ -16,7 +16,7 @@ "max_image_size_mb": "Maximum total size in MB for all images combined (capped at 40MB max for custom models)", "supports_temperature": "Whether the model accepts temperature parameter in API calls (set to false for O3/O4 reasoning models)", "temperature_constraint": "Type of temperature constraint: 'fixed' (fixed value), 'range' (continuous range), 'discrete' (specific values), or omit for default range", - "use_openai_response_api": "Set to true when the model must use the /responses endpoint (reasoning models like GPT-5 Pro). Leave false/omit for standard chat completions.", + "use_openai_response_api": "Set to true when the model must use the /responses endpoint (reasoning models like GPT-5.2 Pro). Leave false/omit for standard chat completions.", "default_reasoning_effort": "Default reasoning effort level for models that support it (e.g., 'low', 'medium', 'high'). Omit if not applicable.", "description": "Human-readable description of the model", "intelligence_score": "1-20 human rating used as the primary signal for auto-mode model ordering", @@ -315,8 +315,10 @@ "intelligence_score": 16 }, { - "model_name": "openai/gpt-5-pro", + "model_name": "openai/gpt-5.2-pro", "aliases": [ + "gpt5.2-pro", + "gpt5.2pro", "gpt5pro" ], "context_window": 400000, @@ -331,7 +333,7 @@ "use_openai_response_api": true, "default_reasoning_effort": "high", "allow_code_generation": true, - "description": "GPT-5 Pro - Advanced reasoning model with highest quality responses (text+image input, text output only)", + "description": "GPT-5.2 Pro - Advanced reasoning model with highest quality responses (text+image input, text output only)", "intelligence_score": 18 }, { @@ -385,8 +387,11 @@ "intelligence_score": 8 }, { - "model_name": "openai/gpt-5.1", + "model_name": "openai/gpt-5.2", "aliases": [ + "gpt5.2", + "gpt-5.2", + "5.2", "gpt5.1", "gpt-5.1", "5.1" @@ -402,7 +407,7 @@ "temperature_constraint": "fixed", "default_reasoning_effort": "medium", "allow_code_generation": true, - "description": "GPT-5.1 (400K context, 128K output) - Flagship reasoning model with configurable thinking effort and vision support", + "description": "GPT-5.2 (400K context, 128K output) - Flagship reasoning model with configurable thinking effort and vision support", "intelligence_score": 18 }, { diff --git a/conf/xai_models.json b/conf/xai_models.json index 7d65fe9..243ea72 100644 --- a/conf/xai_models.json +++ b/conf/xai_models.json @@ -17,7 +17,7 @@ "max_image_size_mb": "Maximum total size in MB for all images combined (capped at 40MB max for custom models)", "supports_temperature": "Whether the model accepts temperature parameter in API calls (set to false for O3/O4 reasoning models)", "temperature_constraint": "Type of temperature constraint: 'fixed' (fixed value), 'range' (continuous range), 'discrete' (specific values), or omit for default range", - "use_openai_response_api": "Set to true when the model must use the /responses endpoint (reasoning models like GPT-5 Pro). Leave false/omit for standard chat completions.", + "use_openai_response_api": "Set to true when the model must use the /responses endpoint (reasoning models like GPT-5.2 Pro). Leave false/omit for standard chat completions.", "default_reasoning_effort": "Default reasoning effort level for models that support it (e.g., 'low', 'medium', 'high'). Omit if not applicable.", "description": "Human-readable description of the model", "intelligence_score": "1-20 human rating used as the primary signal for auto-mode model ordering" diff --git a/docs/advanced-usage.md b/docs/advanced-usage.md index 0ebd942..30a171c 100644 --- a/docs/advanced-usage.md +++ b/docs/advanced-usage.md @@ -41,7 +41,7 @@ Regardless of your default configuration, you can specify models per request: | **`o3-mini`** | OpenAI | 200K tokens | Balanced speed/quality | Moderate complexity tasks | | **`o4-mini`** | OpenAI | 200K tokens | Latest reasoning model | Optimized for shorter contexts | | **`gpt4.1`** | OpenAI | 1M tokens | Latest GPT-4 with extended context | Large codebase analysis, comprehensive reviews | -| **`gpt5.1`** (GPT-5.1) | OpenAI | 400K tokens | Flagship reasoning model with configurable thinking effort | Complex problems, balanced agent/coding flows | +| **`gpt5.2`** (GPT-5.2) | OpenAI | 400K tokens | Flagship reasoning model with configurable thinking effort | Complex problems, balanced agent/coding flows | | **`gpt5.1-codex`** (GPT-5.1 Codex) | OpenAI | 400K tokens | Agentic coding specialization (Responses API) | Advanced coding tasks, structured code generation | | **`gpt5.1-codex-mini`** (GPT-5.1 Codex mini) | OpenAI | 400K tokens | Cost-efficient Codex variant with streaming | Balanced coding tasks, cost-conscious development | | **`gpt5`** (GPT-5) | OpenAI | 400K tokens | Advanced model with reasoning support | Complex problems requiring advanced reasoning | @@ -64,8 +64,8 @@ cloud models (expensive/powerful) AND local models (free/private) in the same co - **Flash Lite 2.0**: Text-only lightweight model (no thinking support) - **O3/O4 Models**: Excellent reasoning, systematic analysis, 200K context - **GPT-4.1**: Extended context window (1M tokens), general capabilities -- **GPT-5.1 Series**: Latest flagship reasoning models, 400K context - - **GPT-5.1**: Flagship model with configurable thinking effort and vision +- **GPT-5.2 Series**: Latest flagship reasoning models, 400K context + - **GPT-5.2**: Flagship model with configurable thinking effort and vision - **GPT-5.1 Codex**: Agentic coding specialization (Responses API, non-streaming) - **GPT-5.1 Codex mini**: Cost-efficient Codex variant with streaming support - **GPT-5 Series**: Advanced reasoning models, 400K context @@ -168,7 +168,7 @@ All tools that work with files support **both individual files and entire direct **`analyze`** - Analyze files or directories - `files`: List of file paths or directories (required) - `question`: What to analyze (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `analysis_type`: architecture|performance|security|quality|general - `output_format`: summary|detailed|actionable - `thinking_mode`: minimal|low|medium|high|max (default: medium, Gemini only) @@ -183,7 +183,7 @@ All tools that work with files support **both individual files and entire direct **`codereview`** - Review code files or directories - `files`: List of file paths or directories (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `review_type`: full|security|performance|quick - `focus_on`: Specific aspects to focus on - `standards`: Coding standards to enforce @@ -199,7 +199,7 @@ All tools that work with files support **both individual files and entire direct **`debug`** - Debug with file context - `error_description`: Description of the issue (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `error_context`: Stack trace or logs - `files`: Files or directories related to the issue - `runtime_info`: Environment details @@ -215,7 +215,7 @@ All tools that work with files support **both individual files and entire direct **`thinkdeep`** - Extended analysis with file context - `current_analysis`: Your current thinking (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `problem_context`: Additional context - `focus_areas`: Specific aspects to focus on - `files`: Files or directories for context @@ -231,7 +231,7 @@ All tools that work with files support **both individual files and entire direct **`testgen`** - Comprehensive test generation with edge case coverage - `files`: Code files or directories to generate tests for (required) - `prompt`: Description of what to test, testing objectives, and scope (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `test_examples`: Optional existing test files as style/pattern reference - `thinking_mode`: minimal|low|medium|high|max (default: medium, Gemini only) @@ -246,7 +246,7 @@ All tools that work with files support **both individual files and entire direct - `files`: Code files or directories to analyze for refactoring opportunities (required) - `prompt`: Description of refactoring goals, context, and specific areas of focus (required) - `refactor_type`: codesmells|decompose|modernize|organization (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `focus_areas`: Specific areas to focus on (e.g., 'performance', 'readability', 'maintainability', 'security') - `style_guide_examples`: Optional existing code files to use as style/pattern reference - `thinking_mode`: minimal|low|medium|high|max (default: medium, Gemini only) diff --git a/docs/configuration.md b/docs/configuration.md index 204c203..0f4ecea 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -63,7 +63,7 @@ CUSTOM_MODEL_NAME=llama3.2 # Default model **Default Model Selection:** ```env -# Options: 'auto', 'pro', 'flash', 'gpt5.1', 'gpt5.1-codex', 'gpt5.1-codex-mini', 'o3', 'o3-mini', 'o4-mini', etc. +# Options: 'auto', 'pro', 'flash', 'gpt5.2', 'gpt5.1-codex', 'gpt5.1-codex-mini', 'o3', 'o3-mini', 'o4-mini', etc. DEFAULT_MODEL=auto # Claude picks best model for each task (recommended) ``` @@ -81,13 +81,13 @@ DEFAULT_MODEL=auto # Claude picks best model for each task (recommended) | Provider | Canonical Models | Notable Aliases | |----------|-----------------|-----------------| - | OpenAI | `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5`, `gpt-5-pro`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5-codex`, `gpt-4.1`, `o3`, `o3-mini`, `o3-pro`, `o4-mini` | `gpt5.1`, `gpt-5.1`, `5.1`, `gpt5.1-codex`, `codex-5.1`, `codex-mini`, `gpt5`, `gpt5pro`, `mini`, `nano`, `codex`, `o3mini`, `o3pro`, `o4mini` | + | OpenAI | `gpt-5.2`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5`, `gpt-5.2-pro`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5-codex`, `gpt-4.1`, `o3`, `o3-mini`, `o3-pro`, `o4-mini` | `gpt5.2`, `gpt-5.2`, `5.2`, `gpt5.1-codex`, `codex-5.1`, `codex-mini`, `gpt5`, `gpt5pro`, `mini`, `nano`, `codex`, `o3mini`, `o3pro`, `o4mini` | | Gemini | `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.0-flash`, `gemini-2.0-flash-lite` | `pro`, `gemini-pro`, `flash`, `flash-2.0`, `flashlite` | | X.AI | `grok-4`, `grok-3`, `grok-3-fast` | `grok`, `grok4`, `grok3`, `grok3fast`, `grokfast` | | OpenRouter | See `conf/openrouter_models.json` for the continually evolving catalogue | e.g., `opus`, `sonnet`, `flash`, `pro`, `mistral` | | Custom | User-managed entries such as `llama3.2` | Define your own aliases per entry | - Latest OpenAI entries (`gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`) mirror the official model cards released on November 13, 2025: all three expose 400K-token contexts with 128K-token outputs, reasoning-token support, and multimodal inputs. `gpt-5.1-codex` is Responses-only with streaming disabled, while the base `gpt-5.1` and Codex mini support streaming along with full code-generation flags. Update your manifests if you run custom deployments so these capability bits stay accurate. + Latest OpenAI entries (`gpt-5.2`, `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2-pro`) expose 400K-token contexts with large outputs, reasoning-token support, and multimodal inputs. `gpt-5.1-codex` and `gpt-5.2-pro` are Responses-only with streaming disabled, while the base `gpt-5.2` and Codex mini support streaming along with full code-generation flags. Update your manifests if you run custom deployments so these capability bits stay accurate. > **Tip:** Copy the JSON file you need, customise it, and point the corresponding `*_MODELS_CONFIG_PATH` environment variable to your version. This lets you enable or disable capabilities (JSON mode, function calling, temperature support, code generation) without editing Python. @@ -107,7 +107,7 @@ The `allow_code_generation` capability enables models to generate complete, prod **When to Enable:** -- **Enable for**: Models MORE capable than your primary CLI's model (e.g., GPT-5.1 Codex, GPT-5 Pro, GPT-5.1 when using Claude Code with Sonnet 4.5) +- **Enable for**: Models MORE capable than your primary CLI's model (e.g., GPT-5.1 Codex, GPT-5.2 Pro, GPT-5.2 when using Claude Code with Sonnet 4.5) - **Purpose**: Get complete implementations from a more powerful reasoning model that your primary CLI can then review and apply - **Use case**: Large-scale implementations, major refactoring, complete module creation @@ -132,7 +132,7 @@ The `allow_code_generation` capability enables models to generate complete, prod ... }, { - "model_name": "gpt-5-pro", + "model_name": "gpt-5.2-pro", "allow_code_generation": true, "intelligence_score": 19, ... @@ -142,8 +142,8 @@ The `allow_code_generation` capability enables models to generate complete, prod ``` **Typical Workflow:** -1. You ask your AI agent to implement a complex new feature using `chat` with a higher-reasoning model such as **gpt-5-pro** -2. GPT-5-Pro generates structured implementation and shares the complete implementation with PAL +1. You ask your AI agent to implement a complex new feature using `chat` with a higher-reasoning model such as **gpt-5.2-pro** +2. GPT-5.2-Pro generates structured implementation and shares the complete implementation with PAL 3. PAL saves the code to `pal_generated.code` and asks AI agent to implement the plan 4. AI agent continues from the previous context, reads the file, applies the implementation @@ -198,7 +198,7 @@ OPENAI_ALLOWED_MODELS=o4-mini GOOGLE_ALLOWED_MODELS=flash # High-performance setup -OPENAI_ALLOWED_MODELS=gpt-5.1-codex,gpt-5.1 +OPENAI_ALLOWED_MODELS=gpt-5.1-codex,gpt-5.2 GOOGLE_ALLOWED_MODELS=pro # Single model standardization diff --git a/docs/custom_models.md b/docs/custom_models.md index 8c9a667..bee1c8b 100644 --- a/docs/custom_models.md +++ b/docs/custom_models.md @@ -61,7 +61,7 @@ The curated defaults in `conf/openrouter_models.json` include popular entries su | `llama3` | `meta-llama/llama-3-70b` | Large open-weight text model | | `deepseek-r1` | `deepseek/deepseek-r1-0528` | DeepSeek reasoning model | | `perplexity` | `perplexity/llama-3-sonar-large-32k-online` | Search-augmented model | -| `gpt5.1`, `gpt-5.1`, `5.1` | `openai/gpt-5.1` | Flagship GPT-5.1 with reasoning and vision | +| `gpt5.2`, `gpt-5.2`, `5.2` | `openai/gpt-5.2` | Flagship GPT-5.2 with reasoning and vision | | `gpt5.1-codex`, `codex-5.1` | `openai/gpt-5.1-codex` | Agentic coding specialization (Responses API) | | `codex-mini`, `gpt5.1-codex-mini` | `openai/gpt-5.1-codex-mini` | Cost-efficient Codex variant with streaming | @@ -77,21 +77,21 @@ View the baseline OpenRouter catalogue in [`conf/openrouter_models.json`](conf/o Native catalogues (`conf/openai_models.json`, `conf/gemini_models.json`, `conf/xai_models.json`, `conf/dial_models.json`) follow the same schema. Updating those files lets you: -- Expose new aliases (e.g., map `enterprise-pro` to `gpt-5-pro`) +- Expose new aliases (e.g., map `enterprise-pro` to `gpt-5.2-pro`) - Advertise support for JSON mode or vision if the upstream provider adds it - Adjust token limits when providers increase context windows ### Latest OpenAI releases -OpenAI's November 13, 2025 drop introduced `gpt-5.1`, `gpt-5.1-codex`, and `gpt-5.1-codex-mini`, all of which now ship in `conf/openai_models.json`: +OpenAI's November 13, 2025 drop introduced `gpt-5.1-codex` and `gpt-5.1-codex-mini`, while the flagship base model is now `gpt-5.2`. All of these ship in `conf/openai_models.json`: | Model | Highlights | Notes | |-------|------------|-------| -| `gpt-5.1` | 400K context, 128K output, multimodal IO, configurable reasoning effort | Streaming enabled; use for balanced agent/coding flows | +| `gpt-5.2` | 400K context, 128K output, multimodal IO, configurable reasoning effort | Streaming enabled; use for balanced agent/coding flows | | `gpt-5.1-codex` | Responses-only agentic coding version of GPT-5.1 | Streaming disabled; `use_openai_response_api=true`; `allow_code_generation=true` | | `gpt-5.1-codex-mini` | Cost-efficient Codex variant | Streaming enabled, retains 400K context and code-generation flag | -These entries include pricing-friendly aliases (`gpt5.1`, `codex-5.1`, `codex-mini`) plus updated capability flags (`supports_extended_thinking`, `allow_code_generation`). Copy the manifest if you operate custom deployment names so downstream providers inherit the same metadata. +These entries include pricing-friendly aliases (`gpt5.2`, `codex-5.1`, `codex-mini`) plus updated capability flags (`supports_extended_thinking`, `allow_code_generation`). Copy the manifest if you operate custom deployment names so downstream providers inherit the same metadata. Because providers load the manifests on import, you can tweak capabilities without touching Python. Restart the server after editing the JSON files so changes are picked up. diff --git a/docs/getting-started.md b/docs/getting-started.md index 5a9a874..8a81c17 100644 --- a/docs/getting-started.md +++ b/docs/getting-started.md @@ -29,7 +29,7 @@ You need at least one API key. Choose based on your needs: **OpenAI:** - Visit [OpenAI Platform](https://platform.openai.com/api-keys) -- Generate an API key for GPT-5.1, GPT-5.1-Codex, GPT-5, O3 access +- Generate an API key for GPT-5.2, GPT-5.1-Codex, GPT-5, O3 access **X.AI (Grok):** - Visit [X.AI Console](https://console.x.ai/) @@ -287,7 +287,7 @@ Add your API keys (at least one required): ```env # Choose your providers (at least one required) GEMINI_API_KEY=your-gemini-api-key-here # For Gemini models -OPENAI_API_KEY=your-openai-api-key-here # For GPT-5.1, GPT-5.1-Codex, O3 +OPENAI_API_KEY=your-openai-api-key-here # For GPT-5.2, GPT-5.1-Codex, O3 XAI_API_KEY=your-xai-api-key-here # For Grok models OPENROUTER_API_KEY=your-openrouter-key # For multiple models @@ -514,7 +514,7 @@ DEFAULT_MODEL=auto GEMINI_API_KEY=your-key OPENAI_API_KEY=your-key GOOGLE_ALLOWED_MODELS=pro -OPENAI_ALLOWED_MODELS=gpt-5.1-codex,gpt-5.1 +OPENAI_ALLOWED_MODELS=gpt-5.1-codex,gpt-5.2 ``` ### Local-First Setup diff --git a/docs/model_ranking.md b/docs/model_ranking.md index 5b5dc1b..785ef2e 100644 --- a/docs/model_ranking.md +++ b/docs/model_ranking.md @@ -39,7 +39,7 @@ A straightforward rubric that mirrors typical provider tiers: | Intelligence | Guidance | |--------------|-------------------------------------------------------------------------------------------| -| 18–19 | Frontier reasoning models (Gemini 3.0 Pro, Gemini 2.5 Pro, GPT‑5.1 Codex, GPT‑5.1, GPT‑5) | +| 18–19 | Frontier reasoning models (Gemini 3.0 Pro, Gemini 2.5 Pro, GPT‑5.1 Codex, GPT‑5.2 Pro, GPT‑5.2, GPT‑5) | | 15–17 | Strong general models with large context (O3 Pro, DeepSeek R1) | | 12–14 | Balanced assistants (Claude Opus/Sonnet, Mistral Large) | | 9–11 | Fast distillations (Gemini Flash, GPT-5 Mini, Mistral medium) | diff --git a/docs/tools/analyze.md b/docs/tools/analyze.md index 92e872d..6b5cdbc 100644 --- a/docs/tools/analyze.md +++ b/docs/tools/analyze.md @@ -64,7 +64,7 @@ This workflow ensures methodical analysis before expert insights, resulting in d **Initial Configuration (used in step 1):** - `prompt`: What to analyze or look for (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `analysis_type`: architecture|performance|security|quality|general (default: general) - `output_format`: summary|detailed|actionable (default: detailed) - `temperature`: Temperature for analysis (0-1, default 0.2) diff --git a/docs/tools/chat.md b/docs/tools/chat.md index e117d72..a6365b0 100644 --- a/docs/tools/chat.md +++ b/docs/tools/chat.md @@ -39,7 +39,7 @@ word verdict in the end. - **Collaborative thinking partner** for your analysis and planning - **Get second opinions** on your designs and approaches - **Brainstorm solutions** and explore alternatives together -- **Structured code generation**: When using GPT-5.1 or Gemini 3.0 / 2.5 Pro, get complete, production-ready implementations saved to `pal_generated.code` for your CLI to review and apply +- **Structured code generation**: When using GPT-5.2 or Gemini 3.0 / 2.5 Pro, get complete, production-ready implementations saved to `pal_generated.code` for your CLI to review and apply - **Validate your checklists** and implementation plans - **General development questions** and explanations - **Technology comparisons** and best practices @@ -52,7 +52,7 @@ word verdict in the end. ## Tool Parameters - `prompt`: Your question or discussion topic (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `absolute_file_paths`: Optional absolute file or directory paths for additional context - `images`: Optional images for visual context (absolute paths) - `working_directory_absolute_path`: **Required** - Absolute path to an existing directory where generated code artifacts will be saved @@ -62,11 +62,11 @@ word verdict in the end. ## Structured Code Generation -When using advanced reasoning models like **GPT-5 Pro** or **Gemini 3.0 Pro**, the chat tool can generate complete, production-ready code implementations in a structured format. +When using advanced reasoning models like **GPT-5.2 Pro** or **Gemini 3.0 Pro**, the chat tool can generate complete, production-ready code implementations in a structured format. ### How It Works -1. You ask your AI agent to implement a complex new feature using `chat` with a higher-reasoning model such as **GPT-5 Pro** or **Gemini 3.0 Pro** +1. You ask your AI agent to implement a complex new feature using `chat` with a higher-reasoning model such as **GPT-5.2 Pro** or **Gemini 3.0 Pro** 2. The model generates structured implementation and shares the complete implementation with PAL 3. PAL saves the code to `pal_generated.code` and asks AI agent to implement the plan 4. AI agent continues from the previous context, reads the file, applies the implementation @@ -85,7 +85,7 @@ For minor changes (small tweaks, bug fixes, algorithm improvements), the model r ### Example Usage ``` -chat with gpt-5-pro and ask it to make me a standalone, classic version of the +chat with gpt-5.2-pro and ask it to make me a standalone, classic version of the Pacman game using pygame that I can run from the commandline. Give me a single script to execute in the end with any / all dependencies setup for me. Do everything using pygame, we have no external resources / images / audio at diff --git a/docs/tools/codereview.md b/docs/tools/codereview.md index b373a69..9bdebd4 100644 --- a/docs/tools/codereview.md +++ b/docs/tools/codereview.md @@ -79,7 +79,7 @@ The above prompt will simultaneously run two separate `codereview` tools with tw **Initial Review Configuration (used in step 1):** - `prompt`: User's summary of what the code does, expected behavior, constraints, and review objectives (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `review_type`: full|security|performance|quick (default: full) - `focus_on`: Specific aspects to focus on (e.g., "security vulnerabilities", "performance bottlenecks") - `standards`: Coding standards to enforce (e.g., "PEP8", "ESLint", "Google Style Guide") diff --git a/docs/tools/debug.md b/docs/tools/debug.md index 6e8a95a..d44eb8f 100644 --- a/docs/tools/debug.md +++ b/docs/tools/debug.md @@ -72,7 +72,7 @@ This structured approach ensures Claude performs methodical groundwork before ex - `images`: Visual debugging materials (error screenshots, logs, etc.) **Model Selection:** -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `thinking_mode`: minimal|low|medium|high|max (default: medium, Gemini only) - `use_assistant_model`: Whether to use expert analysis phase (default: true, set to false to use Claude only) diff --git a/docs/tools/precommit.md b/docs/tools/precommit.md index a84e680..e6b2b6a 100644 --- a/docs/tools/precommit.md +++ b/docs/tools/precommit.md @@ -140,7 +140,7 @@ Use pal and perform a thorough precommit ensuring there aren't any new regressio **Initial Configuration (used in step 1):** - `path`: Starting directory to search for repos (REQUIRED for step 1, must be absolute path) - `prompt`: The original user request description for the changes (required for context) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `compare_to`: Compare against a branch/tag instead of local changes (optional) - `severity_filter`: critical|high|medium|low|all (default: all) - `include_staged`: Include staged changes in the review (default: true) diff --git a/docs/tools/refactor.md b/docs/tools/refactor.md index 59b930e..999c275 100644 --- a/docs/tools/refactor.md +++ b/docs/tools/refactor.md @@ -102,7 +102,7 @@ This results in Claude first performing its own expert analysis, encouraging it **Initial Configuration (used in step 1):** - `prompt`: Description of refactoring goals, context, and specific areas of focus (required) - `refactor_type`: codesmells|decompose|modernize|organization (default: codesmells) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `focus_areas`: Specific areas to focus on (e.g., 'performance', 'readability', 'maintainability', 'security') - `style_guide_examples`: Optional existing code files to use as style/pattern reference (absolute paths) - `thinking_mode`: minimal|low|medium|high|max (default: medium, Gemini only) diff --git a/docs/tools/secaudit.md b/docs/tools/secaudit.md index 7f4c3cb..e91c48a 100644 --- a/docs/tools/secaudit.md +++ b/docs/tools/secaudit.md @@ -85,7 +85,7 @@ security remediation plan using planner - `images`: Architecture diagrams, security documentation, or visual references **Initial Security Configuration (used in step 1):** -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `security_scope`: Application context, technology stack, and security boundary definition (required) - `threat_level`: low|medium|high|critical (default: medium) - determines assessment depth and urgency - `compliance_requirements`: List of compliance frameworks to assess against (e.g., ["PCI DSS", "SOC2"]) diff --git a/docs/tools/testgen.md b/docs/tools/testgen.md index a99448c..777d0fa 100644 --- a/docs/tools/testgen.md +++ b/docs/tools/testgen.md @@ -69,7 +69,7 @@ Test generation excels with extended reasoning models like Gemini Pro or O3, whi **Initial Configuration (used in step 1):** - `prompt`: Description of what to test, testing objectives, and specific scope/focus areas (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `test_examples`: Optional existing test files or directories to use as style/pattern reference (absolute paths) - `thinking_mode`: minimal|low|medium|high|max (default: medium, Gemini only) - `use_assistant_model`: Whether to use expert test generation phase (default: true, set to false to use Claude only) diff --git a/docs/tools/thinkdeep.md b/docs/tools/thinkdeep.md index 9a5f2c4..492e3de 100644 --- a/docs/tools/thinkdeep.md +++ b/docs/tools/thinkdeep.md @@ -30,7 +30,7 @@ with the best architecture for my project ## Tool Parameters - `prompt`: Your current thinking/analysis to extend and validate (required) -- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.1|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) +- `model`: auto|pro|flash|flash-2.0|flashlite|o3|o3-mini|o4-mini|gpt4.1|gpt5.2|gpt5.1-codex|gpt5.1-codex-mini|gpt5|gpt5-mini|gpt5-nano (default: server default) - `problem_context`: Additional context about the problem or goal - `focus_areas`: Specific aspects to focus on (architecture, performance, security, etc.) - `files`: Optional file paths or directories for additional context (absolute paths) diff --git a/providers/openai.py b/providers/openai.py index 7acb19c..2f96f5f 100644 --- a/providers/openai.py +++ b/providers/openai.py @@ -119,9 +119,9 @@ class OpenAIModelProvider(RegistryBackedProviderMixin, OpenAICompatibleProvider) preferred = find_first( [ "gpt-5.1-codex", - "gpt-5.1", + "gpt-5.2", "gpt-5-codex", - "gpt-5-pro", + "gpt-5.2-pro", "o3-pro", "gpt-5", "o3", @@ -131,10 +131,10 @@ class OpenAIModelProvider(RegistryBackedProviderMixin, OpenAICompatibleProvider) elif category == ToolModelCategory.FAST_RESPONSE: # Prefer fast, cost-efficient models - # GPT-5.1 models for speed, GPT-5.1-Codex after (premium pricing but cached) + # GPT-5.2 models for speed, GPT-5.1-Codex after (premium pricing but cached) preferred = find_first( [ - "gpt-5.1", + "gpt-5.2", "gpt-5.1-codex-mini", "gpt-5", "gpt-5-mini", @@ -147,14 +147,14 @@ class OpenAIModelProvider(RegistryBackedProviderMixin, OpenAICompatibleProvider) else: # BALANCED or default # Prefer balanced performance/cost models - # Include GPT-5.1 family for latest capabilities + # Include GPT-5.2 family for latest capabilities preferred = find_first( [ - "gpt-5.1", + "gpt-5.2", "gpt-5.1-codex", "gpt-5", "gpt-5-codex", - "gpt-5-pro", + "gpt-5.2-pro", "gpt-5-mini", "o4-mini", "o3-mini", diff --git a/tests/CASSETTE_MAINTENANCE.md b/tests/CASSETTE_MAINTENANCE.md index cb2c57c..9d3ebf9 100644 --- a/tests/CASSETTE_MAINTENANCE.md +++ b/tests/CASSETTE_MAINTENANCE.md @@ -228,10 +228,10 @@ Some integration tests maintain cassettes for multiple model variants to ensure ### Consensus Tool Cassettes -The `test_consensus_integration.py` test uses parameterized fixtures to test both `gpt-5` and `gpt-5.1` models: +The `test_consensus_integration.py` test uses parameterized fixtures to test both `gpt-5` and `gpt-5.2` models: - `tests/openai_cassettes/consensus_step1_gpt5_for.json` - Cassette for gpt-5 model -- `tests/openai_cassettes/consensus_step1_gpt51_for.json` - Cassette for gpt-5.1 model +- `tests/openai_cassettes/consensus_step1_gpt52_for.json` - Cassette for gpt-5.2 model **When updating consensus cassettes:** @@ -249,9 +249,9 @@ rm tests/openai_cassettes/consensus_step1_gpt5_for.json # Run the test with real API key (it will record for gpt-5) OPENAI_API_KEY="your-real-key" python -m pytest tests/test_consensus_integration.py::test_consensus_multi_model_consultations[gpt-5] -v -# Or for gpt-5.1 -rm tests/openai_cassettes/consensus_step1_gpt51_for.json -OPENAI_API_KEY="your-real-key" python -m pytest tests/test_consensus_integration.py::test_consensus_multi_model_consultations[gpt-5.1] -v +# Or for gpt-5.2 +rm tests/openai_cassettes/consensus_step1_gpt52_for.json +OPENAI_API_KEY="your-real-key" python -m pytest tests/test_consensus_integration.py::test_consensus_multi_model_consultations[gpt-5.2] -v ``` This dual-coverage approach ensures that both model families continue to work correctly as the codebase evolves. diff --git a/tests/gemini_cassettes/consensus/step2_gemini25_flash_against/mldev.json b/tests/gemini_cassettes/consensus/step2_gemini25_flash_against/mldev.json index f0d8fea..bcb1a90 100644 --- a/tests/gemini_cassettes/consensus/step2_gemini25_flash_against/mldev.json +++ b/tests/gemini_cassettes/consensus/step2_gemini25_flash_against/mldev.json @@ -38,12 +38,12 @@ "content-type": "application/json; charset=UTF-8", "vary": "Origin, X-Origin, Referer", "content-encoding": "gzip", - "date": "Sat, 04 Oct 2025 06:26:00 GMT", + "date": "Thu, 11 Dec 2025 19:08:00 GMT", "server": "scaffolding on HTTPServer2", "x-xss-protection": "0", "x-frame-options": "SAMEORIGIN", "x-content-type-options": "nosniff", - "server-timing": "gfet4t7; dur=20597", + "server-timing": "gfet4t7; dur=15067", "alt-svc": "h3=\":443\"; ma=2592000,h3-29=\":443\"; ma=2592000", "transfer-encoding": "chunked" }, @@ -54,7 +54,7 @@ "content": { "parts": [ { - "text": "## Verdict\nFor strategic adoption and new development, **SwiftUI** is the unequivocal recommendation.\n\n## Analysis\n\n1. **TECHNICAL FEASIBILITY**\n Both SwiftUI and UIKit are technically feasible and robust frameworks for building iOS applications. UIKit is a mature, imperative framework that has been the cornerstone of iOS development for over a decade. SwiftUI is Apple's modern, declarative framework, designed to simplify UI development across all Apple platforms. Both are actively maintained, but SwiftUI represents Apple's future direction.\n\n2. **PROJECT SUITABILITY**\n For new projects or significant new feature development within existing applications, SwiftUI offers superior project suitability. Its declarative nature aligns better with modern reactive programming paradigms and allows for more concise, readable code. While UIKit remains essential for maintaining legacy codebases or integrating highly specialized, low-level custom controls, SwiftUI's interoperability with UIKit (via `UIHostingController` and `UIViewRepresentable`) allows for a gradual migration or hybrid approach, making it suitable even for projects with existing UIKit components.\n\n3. **USER VALUE ASSESSMENT**\n Both frameworks can deliver exceptional user experiences. However, SwiftUI's design facilitates faster iteration and development cycles, potentially leading to quicker delivery of new features and improvements to users. Its declarative syntax often results in fewer bugs related to UI state management, indirectly enhancing user value through a more stable and polished application. SwiftUI also inherently supports platform consistency and adaptability (e.g., Dark Mode, Dynamic Type, accessibility) with less effort.\n\n4. **IMPLEMENTATION COMPLEXITY**\n SwiftUI generally reduces implementation complexity, especially for common UI patterns and reactive data flows. It significantly cuts down on boilerplate code compared to UIKit, particularly when dealing with layout, state management, and animations. While there can be a learning curve for developers accustomed to UIKit's imperative style, the long-term benefits in terms of code simplicity and maintainability outweigh this initial investment. UIKit can become complex quickly for dynamic UIs requiring extensive manual view lifecycle management.\n\n5. **ALTERNATIVE APPROACHES**\n The primary alternative is UIKit. While UIKit offers granular control and a vast ecosystem of existing libraries and patterns, it often requires more verbose code and a more imperative approach to UI construction and state management. For new development, choosing UIKit would mean opting for an older paradigm that is less aligned with Apple's strategic direction and potentially incurring higher long-term maintenance costs.\n\n6. **INDUSTRY PERSPECTIVE**\n The industry is steadily shifting towards SwiftUI. Apple actively promotes SwiftUI as the preferred framework for new development, and its capabilities are expanding with each OS release. While a significant portion of existing apps still rely on UIKit, new projects and major feature rewrites increasingly adopt SwiftUI. Many third-party libraries and frameworks are also adding SwiftUI support, indicating a clear trend.\n\n7. **LONG-TERM IMPLICATIONS**\n Adopting SwiftUI offers significant long-term advantages. It aligns with Apple's vision for a unified UI framework across all its platforms (iOS, macOS, watchOS, tvOS, visionOS), reducing the learning curve for multi-platform development. It generally leads to more maintainable code, less technical debt, and better scalability for future features. Investing in SwiftUI now positions a project for easier adoption of future Apple technologies and OS enhancements.\n\n## Confidence Score\n9/10 - High confidence in recommending SwiftUI for new adoption, driven by Apple's clear strategic direction, significant developer experience improvements, and growing industry adoption. The remaining 10% uncertainty relates to highly niche use cases requiring deep UIKit customization or strict legacy OS version support, which are not specified in the prompt.\n\n## Key Takeaways\n* **Strategic Alignment:** SwiftUI is Apple's future-proof UI framework, offering better alignment with upcoming OS features and multi-platform development.\n* **Developer Productivity:** It significantly enhances developer productivity and reduces boilerplate code, leading to faster feature delivery and improved maintainability.\n* **Hybrid Approach Viability:** For existing UIKit codebases, a hybrid approach allows for gradual adoption of SwiftUI for new features without a full rewrite.\n* **Minimum OS Version:** Consider the minimum OS version requirement; SwiftUI's full capabilities are best utilized on recent iOS versions (e.g., iOS 15+)." + "text": "## Verdict\nAdopting SwiftUI for new development or significant feature builds is the most strategic long-term direction, despite initial learning curves and some existing ecosystem limitations.\n\n## Analysis\n\n### 1. TECHNICAL FEASIBILITY\nBoth SwiftUI and UIKit are technically feasible and robust frameworks for building iOS applications. UIKit, being the older and more mature framework, offers unparalleled stability and a vast ecosystem of third-party libraries. SwiftUI, while newer, is fully capable of building complex UIs and is Apple's declared future for UI development across all its platforms. The primary technical dependencies for SwiftUI are Swift and Xcode, along with a minimum deployment target of iOS 13 (though iOS 15+ is recommended for a smoother experience).\n\n### 2. PROJECT SUITABILITY\nFor greenfield projects or new modules within existing applications, SwiftUI offers superior project suitability. It integrates seamlessly with modern Swift language features, leverages declarative programming paradigms, and promotes a more component-based architecture. For existing UIKit-heavy projects, adopting SwiftUI for new features is suitable, as the frameworks can coexist and interoperate through `UIViewRepresentable` and `UIViewControllerRepresentable`. However, a full migration of an existing, large UIKit codebase to SwiftUI is a massive undertaking, often not justified unless there's a strong business case for a complete rewrite.\n\n### 3. USER VALUE ASSESSMENT\nThe choice between SwiftUI and UIKit doesn't directly impact the end-user experience from a functional perspective; both can deliver high-quality interfaces. However, SwiftUI's declarative nature often leads to faster development cycles and easier iteration, which can indirectly translate to more features, quicker bug fixes, and a more polished product delivered to users over time. Its multi-platform capabilities also allow for more consistent experiences across Apple's device ecosystem with less effort.\n\n### 4. IMPLEMENTATION COMPLEXITY\nImplementing with SwiftUI introduces a learning curve for teams accustomed to imperative UIKit. Concepts like state management (`@State`, `@Binding`, `@ObservedObject`, `@StateObject`, `@EnvironmentObject`) require a shift in mindset. While SwiftUI often reduces boilerplate code and simplifies common UI tasks, achieving highly custom layouts or integrating specific legacy UIKit components can sometimes be more complex due to the need for representable wrappers. Debugging can also feel less mature compared to UIKit's well-established tooling. Conversely, UIKit, while verbose, has predictable patterns and extensive community resources.\n\n### 5. ALTERNATIVE APPROACHES\nWhile UIKit is the immediate alternative, for native iOS development, there are no other first-party Apple UI frameworks. Third-party cross-platform frameworks (e.g., React Native, Flutter) exist, but they introduce their own set of trade-offs regarding native look-and-feel, performance, and dependency on non-Apple ecosystems. Sticking to native development for iOS offers the best performance, user experience, and access to the latest platform features.\n\n### 6. INDUSTRY PERSPECTIVE\nThe industry is undeniably shifting towards SwiftUI. Apple continues to heavily invest in SwiftUI, adding new features and improving performance with each OS release. Many new applications and significant updates from established companies are leveraging SwiftUI, especially for components that benefit from its declarative nature and multi-platform reach. UIKit remains indispensable for maintaining legacy applications and for specific, highly customized UI components where SwiftUI's abstractions might be limiting.\n\n### 7. LONG-TERM IMPLICATIONS\nAdopting SwiftUI aligns with Apple's long-term vision, ensuring better future compatibility, reduced technical debt for new features, and easier adoption of new platform capabilities. Its declarative nature generally leads to more readable and maintainable codebases over time. The multi-platform story with SwiftUI for macOS, watchOS, and tvOS is a significant long-term advantage, reducing development effort for cross-device experiences. Continuing solely with UIKit for new development increases the risk of accumulating technical debt and missing out on future productivity gains.\n\n## Confidence Score\n9/10 - High confidence based on extensive industry observations, Apple's clear strategic direction, and practical experience with both frameworks across various project scales. The remaining uncertainty relates to specific project constraints not provided, such as required iOS target versions or existing team expertise levels.\n\n## Key Takeaways\n* **Embrace SwiftUI for new development:** Prioritize SwiftUI for all new features and greenfield projects to capitalize on future productivity and maintainability benefits.\n* **Plan for interoperability:** Design new SwiftUI components to integrate seamlessly with existing UIKit code where necessary, utilizing `UIViewRepresentable` and `UIViewControllerRepresentable`.\n* **Invest in team training:** Allocate resources for team members to upskill in SwiftUI's declarative paradigm and state management best practices.\n* **Assess minimum OS compatibility:** Be mindful of SwiftUI's minimum iOS 13 deployment target (iOS 15+ for richer features) and ensure it aligns with user base requirements.\n* **Strategic migration for legacy:** For existing UIKit apps, consider a phased migration strategy, starting with isolated components or entire new features in SwiftUI rather than a full rewrite." } ], "role": "model" @@ -65,18 +65,18 @@ ], "usageMetadata": { "promptTokenCount": 1404, - "candidatesTokenCount": 884, - "totalTokenCount": 4171, + "candidatesTokenCount": 1034, + "totalTokenCount": 3703, "promptTokensDetails": [ { "modality": "TEXT", "tokenCount": 1404 } ], - "thoughtsTokenCount": 1883 + "thoughtsTokenCount": 1265 }, "modelVersion": "gemini-2.5-flash", - "responseId": "-L3gaPHDJ5GzkdUP1YWsyQE" + "responseId": "kBY7aeSaMs6JkdUP4OHz0AE" } ], "byte_segments": [], @@ -87,12 +87,12 @@ "content-type": "application/json; charset=UTF-8", "vary": "Origin, X-Origin, Referer", "content-encoding": "gzip", - "date": "Sat, 04 Oct 2025 06:26:00 GMT", + "date": "Thu, 11 Dec 2025 19:08:00 GMT", "server": "scaffolding on HTTPServer2", "x-xss-protection": "0", "x-frame-options": "SAMEORIGIN", "x-content-type-options": "nosniff", - "server-timing": "gfet4t7; dur=20597", + "server-timing": "gfet4t7; dur=15067", "alt-svc": "h3=\":443\"; ma=2592000,h3-29=\":443\"; ma=2592000", "transfer-encoding": "chunked" } @@ -102,7 +102,7 @@ "content": { "parts": [ { - "text": "## Verdict\nFor strategic adoption and new development, **SwiftUI** is the unequivocal recommendation.\n\n## Analysis\n\n1. **TECHNICAL FEASIBILITY**\n Both SwiftUI and UIKit are technically feasible and robust frameworks for building iOS applications. UIKit is a mature, imperative framework that has been the cornerstone of iOS development for over a decade. SwiftUI is Apple's modern, declarative framework, designed to simplify UI development across all Apple platforms. Both are actively maintained, but SwiftUI represents Apple's future direction.\n\n2. **PROJECT SUITABILITY**\n For new projects or significant new feature development within existing applications, SwiftUI offers superior project suitability. Its declarative nature aligns better with modern reactive programming paradigms and allows for more concise, readable code. While UIKit remains essential for maintaining legacy codebases or integrating highly specialized, low-level custom controls, SwiftUI's interoperability with UIKit (via `UIHostingController` and `UIViewRepresentable`) allows for a gradual migration or hybrid approach, making it suitable even for projects with existing UIKit components.\n\n3. **USER VALUE ASSESSMENT**\n Both frameworks can deliver exceptional user experiences. However, SwiftUI's design facilitates faster iteration and development cycles, potentially leading to quicker delivery of new features and improvements to users. Its declarative syntax often results in fewer bugs related to UI state management, indirectly enhancing user value through a more stable and polished application. SwiftUI also inherently supports platform consistency and adaptability (e.g., Dark Mode, Dynamic Type, accessibility) with less effort.\n\n4. **IMPLEMENTATION COMPLEXITY**\n SwiftUI generally reduces implementation complexity, especially for common UI patterns and reactive data flows. It significantly cuts down on boilerplate code compared to UIKit, particularly when dealing with layout, state management, and animations. While there can be a learning curve for developers accustomed to UIKit's imperative style, the long-term benefits in terms of code simplicity and maintainability outweigh this initial investment. UIKit can become complex quickly for dynamic UIs requiring extensive manual view lifecycle management.\n\n5. **ALTERNATIVE APPROACHES**\n The primary alternative is UIKit. While UIKit offers granular control and a vast ecosystem of existing libraries and patterns, it often requires more verbose code and a more imperative approach to UI construction and state management. For new development, choosing UIKit would mean opting for an older paradigm that is less aligned with Apple's strategic direction and potentially incurring higher long-term maintenance costs.\n\n6. **INDUSTRY PERSPECTIVE**\n The industry is steadily shifting towards SwiftUI. Apple actively promotes SwiftUI as the preferred framework for new development, and its capabilities are expanding with each OS release. While a significant portion of existing apps still rely on UIKit, new projects and major feature rewrites increasingly adopt SwiftUI. Many third-party libraries and frameworks are also adding SwiftUI support, indicating a clear trend.\n\n7. **LONG-TERM IMPLICATIONS**\n Adopting SwiftUI offers significant long-term advantages. It aligns with Apple's vision for a unified UI framework across all its platforms (iOS, macOS, watchOS, tvOS, visionOS), reducing the learning curve for multi-platform development. It generally leads to more maintainable code, less technical debt, and better scalability for future features. Investing in SwiftUI now positions a project for easier adoption of future Apple technologies and OS enhancements.\n\n## Confidence Score\n9/10 - High confidence in recommending SwiftUI for new adoption, driven by Apple's clear strategic direction, significant developer experience improvements, and growing industry adoption. The remaining 10% uncertainty relates to highly niche use cases requiring deep UIKit customization or strict legacy OS version support, which are not specified in the prompt.\n\n## Key Takeaways\n* **Strategic Alignment:** SwiftUI is Apple's future-proof UI framework, offering better alignment with upcoming OS features and multi-platform development.\n* **Developer Productivity:** It significantly enhances developer productivity and reduces boilerplate code, leading to faster feature delivery and improved maintainability.\n* **Hybrid Approach Viability:** For existing UIKit codebases, a hybrid approach allows for gradual adoption of SwiftUI for new features without a full rewrite.\n* **Minimum OS Version:** Consider the minimum OS version requirement; SwiftUI's full capabilities are best utilized on recent iOS versions (e.g., iOS 15+)." + "text": "## Verdict\nAdopting SwiftUI for new development or significant feature builds is the most strategic long-term direction, despite initial learning curves and some existing ecosystem limitations.\n\n## Analysis\n\n### 1. TECHNICAL FEASIBILITY\nBoth SwiftUI and UIKit are technically feasible and robust frameworks for building iOS applications. UIKit, being the older and more mature framework, offers unparalleled stability and a vast ecosystem of third-party libraries. SwiftUI, while newer, is fully capable of building complex UIs and is Apple's declared future for UI development across all its platforms. The primary technical dependencies for SwiftUI are Swift and Xcode, along with a minimum deployment target of iOS 13 (though iOS 15+ is recommended for a smoother experience).\n\n### 2. PROJECT SUITABILITY\nFor greenfield projects or new modules within existing applications, SwiftUI offers superior project suitability. It integrates seamlessly with modern Swift language features, leverages declarative programming paradigms, and promotes a more component-based architecture. For existing UIKit-heavy projects, adopting SwiftUI for new features is suitable, as the frameworks can coexist and interoperate through `UIViewRepresentable` and `UIViewControllerRepresentable`. However, a full migration of an existing, large UIKit codebase to SwiftUI is a massive undertaking, often not justified unless there's a strong business case for a complete rewrite.\n\n### 3. USER VALUE ASSESSMENT\nThe choice between SwiftUI and UIKit doesn't directly impact the end-user experience from a functional perspective; both can deliver high-quality interfaces. However, SwiftUI's declarative nature often leads to faster development cycles and easier iteration, which can indirectly translate to more features, quicker bug fixes, and a more polished product delivered to users over time. Its multi-platform capabilities also allow for more consistent experiences across Apple's device ecosystem with less effort.\n\n### 4. IMPLEMENTATION COMPLEXITY\nImplementing with SwiftUI introduces a learning curve for teams accustomed to imperative UIKit. Concepts like state management (`@State`, `@Binding`, `@ObservedObject`, `@StateObject`, `@EnvironmentObject`) require a shift in mindset. While SwiftUI often reduces boilerplate code and simplifies common UI tasks, achieving highly custom layouts or integrating specific legacy UIKit components can sometimes be more complex due to the need for representable wrappers. Debugging can also feel less mature compared to UIKit's well-established tooling. Conversely, UIKit, while verbose, has predictable patterns and extensive community resources.\n\n### 5. ALTERNATIVE APPROACHES\nWhile UIKit is the immediate alternative, for native iOS development, there are no other first-party Apple UI frameworks. Third-party cross-platform frameworks (e.g., React Native, Flutter) exist, but they introduce their own set of trade-offs regarding native look-and-feel, performance, and dependency on non-Apple ecosystems. Sticking to native development for iOS offers the best performance, user experience, and access to the latest platform features.\n\n### 6. INDUSTRY PERSPECTIVE\nThe industry is undeniably shifting towards SwiftUI. Apple continues to heavily invest in SwiftUI, adding new features and improving performance with each OS release. Many new applications and significant updates from established companies are leveraging SwiftUI, especially for components that benefit from its declarative nature and multi-platform reach. UIKit remains indispensable for maintaining legacy applications and for specific, highly customized UI components where SwiftUI's abstractions might be limiting.\n\n### 7. LONG-TERM IMPLICATIONS\nAdopting SwiftUI aligns with Apple's long-term vision, ensuring better future compatibility, reduced technical debt for new features, and easier adoption of new platform capabilities. Its declarative nature generally leads to more readable and maintainable codebases over time. The multi-platform story with SwiftUI for macOS, watchOS, and tvOS is a significant long-term advantage, reducing development effort for cross-device experiences. Continuing solely with UIKit for new development increases the risk of accumulating technical debt and missing out on future productivity gains.\n\n## Confidence Score\n9/10 - High confidence based on extensive industry observations, Apple's clear strategic direction, and practical experience with both frameworks across various project scales. The remaining uncertainty relates to specific project constraints not provided, such as required iOS target versions or existing team expertise levels.\n\n## Key Takeaways\n* **Embrace SwiftUI for new development:** Prioritize SwiftUI for all new features and greenfield projects to capitalize on future productivity and maintainability benefits.\n* **Plan for interoperability:** Design new SwiftUI components to integrate seamlessly with existing UIKit code where necessary, utilizing `UIViewRepresentable` and `UIViewControllerRepresentable`.\n* **Invest in team training:** Allocate resources for team members to upskill in SwiftUI's declarative paradigm and state management best practices.\n* **Assess minimum OS compatibility:** Be mindful of SwiftUI's minimum iOS 13 deployment target (iOS 15+ for richer features) and ensure it aligns with user base requirements.\n* **Strategic migration for legacy:** For existing UIKit apps, consider a phased migration strategy, starting with isolated components or entire new features in SwiftUI rather than a full rewrite." } ], "role": "model" @@ -112,9 +112,9 @@ } ], "model_version": "gemini-2.5-flash", - "response_id": "-L3gaPHDJ5GzkdUP1YWsyQE", + "response_id": "kBY7aeSaMs6JkdUP4OHz0AE", "usage_metadata": { - "candidates_token_count": 884, + "candidates_token_count": 1034, "prompt_token_count": 1404, "prompt_tokens_details": [ { @@ -122,8 +122,8 @@ "token_count": 1404 } ], - "thoughts_token_count": 1883, - "total_token_count": 4171 + "thoughts_token_count": 1265, + "total_token_count": 3703 } } ] diff --git a/tests/openai_cassettes/consensus_step1_gpt52_for.json b/tests/openai_cassettes/consensus_step1_gpt52_for.json new file mode 100644 index 0000000..46d7be5 --- /dev/null +++ b/tests/openai_cassettes/consensus_step1_gpt52_for.json @@ -0,0 +1,82 @@ +{ + "interactions": [ + { + "request": { + "content": { + "messages": [ + { + "content": "\nROLE\nYou are an expert technical consultant providing consensus analysis on proposals, plans, and ideas. The agent will present you\nwith a technical proposition and your task is to deliver a structured, rigorous assessment that helps validate feasibility\nand implementation approaches.\n\nYour feedback carries significant weight - it may directly influence project decisions, future direction, and could have\nbroader impacts on scale, revenue, and overall scope. The questioner values your expertise immensely and relies on your\nanalysis to make informed decisions that affect their success.\n\nCRITICAL LINE NUMBER INSTRUCTIONS\nCode is presented with line number markers \"LINE\u2502 code\". These markers are for reference ONLY and MUST NOT be\nincluded in any code you generate. Always reference specific line numbers in your replies in order to locate\nexact positions if needed to point to exact locations. Include a very short code excerpt alongside for clarity.\nInclude context_start_text and context_end_text as backup references. Never include \"LINE\u2502\" markers in generated code\nsnippets.\n\nPERSPECTIVE FRAMEWORK\nSUPPORTIVE PERSPECTIVE WITH INTEGRITY\n\nYou are tasked with advocating FOR this proposal, but with CRITICAL GUARDRAILS:\n\nMANDATORY ETHICAL CONSTRAINTS:\n- This is NOT a debate for entertainment. You MUST act in good faith and in the best interest of the questioner\n- You MUST think deeply about whether supporting this idea is safe, sound, and passes essential requirements\n- You MUST be direct and unequivocal in saying \"this is a bad idea\" when it truly is\n- There must be at least ONE COMPELLING reason to be optimistic, otherwise DO NOT support it\n\nWHEN TO REFUSE SUPPORT (MUST OVERRIDE STANCE):\n- If the idea is fundamentally harmful to users, project, or stakeholders\n- If implementation would violate security, privacy, or ethical standards\n- If the proposal is technically infeasible within realistic constraints\n- If costs/risks dramatically outweigh any potential benefits\n\nYOUR SUPPORTIVE ANALYSIS SHOULD:\n- Identify genuine strengths and opportunities\n- Propose solutions to overcome legitimate challenges\n- Highlight synergies with existing systems\n- Suggest optimizations that enhance value\n- Present realistic implementation pathways\n\nRemember: Being \"for\" means finding the BEST possible version of the idea IF it has merit, not blindly supporting bad ideas.\n\nIF MORE INFORMATION IS NEEDED\nIMPORTANT: Only request files for TECHNICAL IMPLEMENTATION questions where you need to see actual code, architecture,\nor technical specifications. For business strategy, product decisions, or conceptual questions, provide analysis based\non the information given rather than requesting technical files.\n\nIf you need additional technical context (e.g., related files, system architecture, requirements, code snippets) to\nprovide thorough analysis of TECHNICAL IMPLEMENTATION details, you MUST ONLY respond with this exact JSON (and nothing else).\nDo NOT ask for the same file you've been provided unless for some reason its content is missing or incomplete:\n{\n \"status\": \"files_required_to_continue\",\n \"mandatory_instructions\": \"\",\n \"files_needed\": [\"[file name here]\", \"[or some folder/]\"]\n}\n\nFor business strategy, product planning, or conceptual questions, proceed with analysis using your expertise and the\ncontext provided, even if specific technical details are not available.\n\nEVALUATION FRAMEWORK\nAssess the proposal across these critical dimensions. Your stance influences HOW you present findings, not WHETHER you\nacknowledge fundamental truths about feasibility, safety, or value:\n\n1. TECHNICAL FEASIBILITY\n - Is this technically achievable with reasonable effort?\n - What are the core technical dependencies and requirements?\n - Are there any fundamental technical blockers?\n\n2. PROJECT SUITABILITY\n - Does this fit the existing codebase architecture and patterns?\n - Is it compatible with current technology stack and constraints?\n - How well does it align with the project's technical direction?\n\n3. USER VALUE ASSESSMENT\n - Will users actually want and use this feature?\n - What concrete benefits does this provide?\n - How does this compare to alternative solutions?\n\n4. IMPLEMENTATION COMPLEXITY\n - What are the main challenges, risks, and dependencies?\n - What is the estimated effort and timeline?\n - What expertise and resources are required?\n\n5. ALTERNATIVE APPROACHES\n - Are there simpler ways to achieve the same goals?\n - What are the trade-offs between different approaches?\n - Should we consider a different strategy entirely?\n\n6. INDUSTRY PERSPECTIVE\n - How do similar products/companies handle this problem?\n - What are current best practices and emerging patterns?\n - Are there proven solutions or cautionary tales?\n\n7. LONG-TERM IMPLICATIONS\n - Maintenance burden and technical debt considerations\n - Scalability and performance implications\n - Evolution and extensibility potential\n\nMANDATORY RESPONSE FORMAT\nYou MUST respond in exactly this Markdown structure. Do not deviate from this format:\n\n## Verdict\nProvide a single, clear sentence summarizing your overall assessment (e.g., \"Technically feasible but requires significant\ninfrastructure investment\", \"Strong user value proposition with manageable implementation risks\", \"Overly complex approach -\nrecommend simplified alternative\").\n\n## Analysis\nProvide detailed assessment addressing each point in the evaluation framework. Use clear reasoning and specific examples.\nBe thorough but concise. Address both strengths and weaknesses objectively.\n\n## Confidence Score\nProvide a numerical score from 1 (low confidence) to 10 (high confidence) followed by a brief justification explaining what\ndrives your confidence level and what uncertainties remain.\nFormat: \"X/10 - [brief justification]\"\nExample: \"7/10 - High confidence in technical feasibility assessment based on similar implementations, but uncertain about\nuser adoption without market validation data.\"\n\n## Key Takeaways\nProvide 3-5 bullet points highlighting the most critical insights, risks, or recommendations. These should be actionable\nand specific.\n\nQUALITY STANDARDS\n- Ground all insights in the current project's scope and constraints\n- Be honest about limitations and uncertainties\n- Focus on practical, implementable solutions rather than theoretical possibilities\n- Provide specific, actionable guidance rather than generic advice\n- Balance optimism with realistic risk assessment\n- Reference concrete examples and precedents when possible\n\nREMINDERS\n- Your assessment will be synthesized with other expert opinions by the agent\n- Aim to provide unique insights that complement other perspectives\n- If files are provided, reference specific technical details in your analysis\n- Maintain professional objectivity while being decisive in your recommendations\n- Keep your response concise - your entire reply must not exceed 850 tokens to ensure transport compatibility\n- CRITICAL: Your stance does NOT override your responsibility to provide truthful, ethical, and beneficial guidance\n- Bad ideas must be called out regardless of stance; good ideas must be acknowledged regardless of stance\n", + "role": "system" + }, + { + "content": "Evaluate SwiftUI vs UIKit adoption and recommend ONE word (SwiftUI or UIKit).", + "role": "user" + } + ], + "model": "gpt-5.2", + "stream": false, + "temperature": 1.0 + }, + "headers": { + "accept": "application/json", + "accept-encoding": "gzip, deflate", + "authorization": "Bearer SANITIZED", + "connection": "keep-alive", + "content-length": "7618", + "content-type": "application/json", + "host": "api.openai.com", + "user-agent": "OpenAI/Python 2.8.1", + "x-stainless-arch": "arm64", + "x-stainless-async": "false", + "x-stainless-lang": "python", + "x-stainless-os": "MacOS", + "x-stainless-package-version": "2.8.1", + "x-stainless-read-timeout": "900.0", + "x-stainless-retry-count": "0", + "x-stainless-runtime": "CPython", + "x-stainless-runtime-version": "3.12.11" + }, + "method": "POST", + "path": "/v1/chat/completions", + "url": "https://api.openai.com/v1/chat/completions" + }, + "response": { + "content": { + "data": "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", + "encoding": "base64", + "size": 4026 + }, + "headers": { + "access-control-expose-headers": "X-Request-ID", + "alt-svc": "h3=\":443\"; ma=86400", + "cf-cache-status": "DYNAMIC", + "cf-ray": "9ac743fe2a54653a-LHR", + "connection": "keep-alive", + "content-encoding": "gzip", + "content-type": "application/json", + "date": "Thu, 11 Dec 2025 19:07:45 GMT", + "openai-organization": "beehive-innovations-fze", + "openai-processing-ms": "12197", + "openai-project": "proj_QP57xBVPOlWpp0vuJEPGwXK3", + "openai-version": "2020-10-01", + "server": "cloudflare", + "set-cookie": "__cf_bm=YSi1fGMajsMcw8oJQVFHSnTi5FuoVpyCfYIaa0wtlxA-(XXX) XXX-XXXX-0.0.0.0-xWUJHJUqXYkTgY_mTSOGnwyLR8xWGzn.c5XN64I5gBtxULpaWypKynzKkgQIpYLeZpZJzXDgMOPKOQgfeOykrOVON_fC.XS6beQpui4Im4Y; path=/; expires=Thu, 11-Dec-25 19:37:45 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None, _cfuvid=EriAVAchI2yhzaRh8mdujjhdIuwS6S.GY7w6lETIknI-176(XXX) XXX-XXXX-0.0.0.0-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None", + "strict-transport-security": "max-age=31536000; includeSubDomains; preload", + "transfer-encoding": "chunked", + "x-content-type-options": "nosniff", + "x-envoy-upstream-service-time": "12214", + "x-openai-proxy-wasm": "v0.1", + "x-ratelimit-limit-requests": "500", + "x-ratelimit-limit-tokens": "500000", + "x-ratelimit-remaining-requests": "499", + "x-ratelimit-remaining-tokens": "498166", + "x-ratelimit-reset-requests": "120ms", + "x-ratelimit-reset-tokens": "220ms", + "x-request-id": "req_ee4f839bce394f37855e555a78dc48e4" + }, + "reason_phrase": "OK", + "status_code": 200 + } + } + ] +} \ No newline at end of file diff --git a/tests/test_auto_mode_comprehensive.py b/tests/test_auto_mode_comprehensive.py index 69365e7..523d864 100644 --- a/tests/test_auto_mode_comprehensive.py +++ b/tests/test_auto_mode_comprehensive.py @@ -95,8 +95,8 @@ class TestAutoModeComprehensive: }, { "EXTENDED_REASONING": "gpt-5.1-codex", # GPT-5.1 Codex prioritized for coding tasks - "FAST_RESPONSE": "gpt-5.1", # Prefer gpt-5.1 for speed - "BALANCED": "gpt-5.1", # Prefer gpt-5.1 for balanced + "FAST_RESPONSE": "gpt-5.2", # Prefer gpt-5.2 for speed + "BALANCED": "gpt-5.2", # Prefer gpt-5.2 for balanced }, ), # Only X.AI API available diff --git a/tests/test_auto_mode_model_listing.py b/tests/test_auto_mode_model_listing.py index ab99019..5f1ae15 100644 --- a/tests/test_auto_mode_model_listing.py +++ b/tests/test_auto_mode_model_listing.py @@ -83,7 +83,7 @@ def test_error_listing_respects_env_restrictions(monkeypatch, reset_registry): pass monkeypatch.setenv("GOOGLE_ALLOWED_MODELS", "gemini-2.5-pro") - monkeypatch.setenv("OPENAI_ALLOWED_MODELS", "gpt-5.1") + monkeypatch.setenv("OPENAI_ALLOWED_MODELS", "gpt-5.2") monkeypatch.setenv("OPENROUTER_ALLOWED_MODELS", "gpt5nano") monkeypatch.setenv("XAI_ALLOWED_MODELS", "") @@ -104,7 +104,7 @@ def test_error_listing_respects_env_restrictions(monkeypatch, reset_registry): ("OPENAI_API_KEY", "test-openai"), ("OPENROUTER_API_KEY", "test-openrouter"), ("GOOGLE_ALLOWED_MODELS", "gemini-2.5-pro"), - ("OPENAI_ALLOWED_MODELS", "gpt-5.1"), + ("OPENAI_ALLOWED_MODELS", "gpt-5.2"), ("OPENROUTER_ALLOWED_MODELS", "gpt5nano"), ("XAI_ALLOWED_MODELS", ""), ): @@ -139,7 +139,7 @@ def test_error_listing_respects_env_restrictions(monkeypatch, reset_registry): assert payload["status"] == "error" available_models = _extract_available_models(payload["content"]) - assert set(available_models) == {"gemini-2.5-pro", "gpt-5.1", "gpt5nano", "openai/gpt-5-nano"} + assert set(available_models) == {"gemini-2.5-pro", "gpt-5.2", "gpt5nano", "openai/gpt-5-nano"} @pytest.mark.no_mock_provider @@ -225,6 +225,6 @@ def test_error_listing_without_restrictions_shows_full_catalog(monkeypatch, rese available_models = _extract_available_models(payload["content"]) assert "gemini-2.5-pro" in available_models - assert any(model in available_models for model in {"gpt-5.1", "gpt-5"}) + assert any(model in available_models for model in {"gpt-5.2", "gpt-5"}) assert "grok-4" in available_models assert len(available_models) >= 5 diff --git a/tests/test_auto_mode_provider_selection.py b/tests/test_auto_mode_provider_selection.py index c60d446..9268489 100644 --- a/tests/test_auto_mode_provider_selection.py +++ b/tests/test_auto_mode_provider_selection.py @@ -99,8 +99,8 @@ class TestAutoModeProviderSelection: # Should select appropriate OpenAI models based on new preference order assert extended_reasoning == "gpt-5.1-codex" # GPT-5.1 Codex prioritized for extended reasoning - assert fast_response == "gpt-5.1" # gpt-5.1 comes first in fast response preference - assert balanced == "gpt-5.1" # gpt-5.1 for balanced + assert fast_response == "gpt-5.2" # gpt-5.2 comes first in fast response preference + assert balanced == "gpt-5.2" # gpt-5.2 for balanced finally: # Restore original environment diff --git a/tests/test_consensus_integration.py b/tests/test_consensus_integration.py index b1e6094..58a1ba7 100644 --- a/tests/test_consensus_integration.py +++ b/tests/test_consensus_integration.py @@ -20,7 +20,7 @@ CASSETTE_DIR.mkdir(exist_ok=True) # Mapping of OpenAI model names to their cassette files CONSENSUS_CASSETTES = { "gpt-5": CASSETTE_DIR / "consensus_step1_gpt5_for.json", - "gpt-5.1": CASSETTE_DIR / "consensus_step1_gpt51_for.json", + "gpt-5.2": CASSETTE_DIR / "consensus_step1_gpt52_for.json", } GEMINI_REPLAY_DIR = Path(__file__).parent / "gemini_cassettes" @@ -32,11 +32,11 @@ GEMINI_REPLAY_PATH = GEMINI_REPLAY_DIR / "consensus" / "step2_gemini25_flash_aga @pytest.mark.integration @pytest.mark.asyncio @pytest.mark.no_mock_provider -@pytest.mark.parametrize("openai_model", ["gpt-5", "gpt-5.1"]) +@pytest.mark.parametrize("openai_model", ["gpt-5", "gpt-5.2"]) async def test_consensus_multi_model_consultations(monkeypatch, openai_model): """Exercise ConsensusTool against OpenAI model (supporting) and gemini-2.5-flash (critical). - Tests both gpt-5 and gpt-5.1 to ensure regression coverage for both model families. + Tests both gpt-5 and gpt-5.2 to ensure regression coverage for both model families. """ # Get the cassette path for this model diff --git a/tests/test_intelligent_fallback.py b/tests/test_intelligent_fallback.py index d2736c4..fe552a0 100644 --- a/tests/test_intelligent_fallback.py +++ b/tests/test_intelligent_fallback.py @@ -37,14 +37,14 @@ class TestIntelligentFallback: @patch.dict(os.environ, {"OPENAI_API_KEY": "sk-test-key", "GEMINI_API_KEY": ""}, clear=False) def test_prefers_openai_o3_mini_when_available(self): - """Test that gpt-5.1 is preferred when OpenAI API key is available (based on new preference order)""" + """Test that gpt-5.2 is preferred when OpenAI API key is available (based on new preference order)""" # Register only OpenAI provider for this test from providers.openai import OpenAIModelProvider ModelProviderRegistry.register_provider(ProviderType.OPENAI, OpenAIModelProvider) fallback_model = ModelProviderRegistry.get_preferred_fallback_model() - assert fallback_model == "gpt-5.1" # Based on new preference order: gpt-5.1 before o4-mini + assert fallback_model == "gpt-5.2" # Based on new preference order: gpt-5.2 before o4-mini @patch.dict(os.environ, {"OPENAI_API_KEY": "", "GEMINI_API_KEY": "test-gemini-key"}, clear=False) def test_prefers_gemini_flash_when_openai_unavailable(self): @@ -147,8 +147,8 @@ class TestIntelligentFallback: history, tokens = build_conversation_history(context, model_context=None) - # Verify that ModelContext was called with gpt-5.1 (the intelligent fallback based on new preference order) - mock_context_class.assert_called_once_with("gpt-5.1") + # Verify that ModelContext was called with gpt-5.2 (the intelligent fallback based on new preference order) + mock_context_class.assert_called_once_with("gpt-5.2") def test_auto_mode_with_gemini_only(self): """Test auto mode behavior when only Gemini API key is available""" diff --git a/tests/test_openai_provider.py b/tests/test_openai_provider.py index 764143c..66faf58 100644 --- a/tests/test_openai_provider.py +++ b/tests/test_openai_provider.py @@ -50,7 +50,7 @@ class TestOpenAIProvider: assert provider.validate_model_name("o4-mini") is True assert provider.validate_model_name("gpt-5") is True assert provider.validate_model_name("gpt-5-mini") is True - assert provider.validate_model_name("gpt-5.1") is True + assert provider.validate_model_name("gpt-5.2") is True assert provider.validate_model_name("gpt-5.1-codex") is True assert provider.validate_model_name("gpt-5.1-codex-mini") is True @@ -62,6 +62,7 @@ class TestOpenAIProvider: assert provider.validate_model_name("gpt5") is True assert provider.validate_model_name("gpt5-mini") is True assert provider.validate_model_name("gpt5mini") is True + assert provider.validate_model_name("gpt5.2") is True assert provider.validate_model_name("gpt5.1") is True assert provider.validate_model_name("gpt5.1-codex") is True assert provider.validate_model_name("codex-mini") is True @@ -83,7 +84,8 @@ class TestOpenAIProvider: assert provider._resolve_model_name("gpt5") == "gpt-5" assert provider._resolve_model_name("gpt5-mini") == "gpt-5-mini" assert provider._resolve_model_name("gpt5mini") == "gpt-5-mini" - assert provider._resolve_model_name("gpt5.1") == "gpt-5.1" + assert provider._resolve_model_name("gpt5.2") == "gpt-5.2" + assert provider._resolve_model_name("gpt5.1") == "gpt-5.2" assert provider._resolve_model_name("gpt5.1-codex") == "gpt-5.1-codex" assert provider._resolve_model_name("codex-mini") == "gpt-5.1-codex-mini" @@ -95,7 +97,8 @@ class TestOpenAIProvider: assert provider._resolve_model_name("o4-mini") == "o4-mini" assert provider._resolve_model_name("gpt-5") == "gpt-5" assert provider._resolve_model_name("gpt-5-mini") == "gpt-5-mini" - assert provider._resolve_model_name("gpt-5.1") == "gpt-5.1" + assert provider._resolve_model_name("gpt-5.2") == "gpt-5.2" + assert provider._resolve_model_name("gpt-5.1") == "gpt-5.2" assert provider._resolve_model_name("gpt-5.1-codex") == "gpt-5.1-codex" assert provider._resolve_model_name("gpt-5.1-codex-mini") == "gpt-5.1-codex-mini" @@ -158,12 +161,12 @@ class TestOpenAIProvider: assert capabilities.supports_function_calling is True assert capabilities.supports_temperature is True - def test_get_capabilities_gpt51(self): - """Test GPT-5.1 capabilities reflect new metadata.""" + def test_get_capabilities_gpt52(self): + """Test GPT-5.2 capabilities reflect new metadata.""" provider = OpenAIModelProvider("test-key") - capabilities = provider.get_capabilities("gpt-5.1") - assert capabilities.model_name == "gpt-5.1" + capabilities = provider.get_capabilities("gpt-5.2") + assert capabilities.model_name == "gpt-5.2" assert capabilities.supports_streaming is True assert capabilities.supports_function_calling is True assert capabilities.supports_json_mode is True diff --git a/tests/test_per_tool_model_defaults.py b/tests/test_per_tool_model_defaults.py index f5e71a7..3da4e30 100644 --- a/tests/test_per_tool_model_defaults.py +++ b/tests/test_per_tool_model_defaults.py @@ -133,8 +133,8 @@ class TestModelSelection: ModelProviderRegistry.register_provider(ProviderType.OPENAI, OpenAIModelProvider) model = ModelProviderRegistry.get_preferred_fallback_model(ToolModelCategory.FAST_RESPONSE) - # OpenAI now prefers gpt-5.1 for fast response (based on our new preference order) - assert model == "gpt-5.1" + # OpenAI now prefers gpt-5.2 for fast response (based on our new preference order) + assert model == "gpt-5.2" def test_fast_response_with_gemini_only(self): """Test FAST_RESPONSE prefers flash when only Gemini is available.""" @@ -167,8 +167,8 @@ class TestModelSelection: ModelProviderRegistry.register_provider(ProviderType.OPENAI, OpenAIModelProvider) model = ModelProviderRegistry.get_preferred_fallback_model(ToolModelCategory.BALANCED) - # OpenAI prefers gpt-5.1 for balanced (based on our new preference order) - assert model == "gpt-5.1" + # OpenAI prefers gpt-5.2 for balanced (based on our new preference order) + assert model == "gpt-5.2" def test_no_category_uses_balanced_logic(self): """Test that no category specified uses balanced logic.""" @@ -209,7 +209,7 @@ class TestFlexibleModelSelection: "env": {"OPENAI_API_KEY": "test-key"}, "provider_type": ProviderType.OPENAI, "category": ToolModelCategory.FAST_RESPONSE, - "expected": "gpt-5.1", # Based on new preference order + "expected": "gpt-5.2", # Based on new preference order }, ] diff --git a/tests/test_providers.py b/tests/test_providers.py index 3dfa597..4679f4e 100644 --- a/tests/test_providers.py +++ b/tests/test_providers.py @@ -209,7 +209,7 @@ class TestOpenAIProvider: assert provider.validate_model_name("o4-mini") assert provider.validate_model_name("o4mini") assert provider.validate_model_name("o4-mini") - assert provider.validate_model_name("gpt-5.1") + assert provider.validate_model_name("gpt-5.2") assert provider.validate_model_name("gpt-5.1-codex") assert provider.validate_model_name("gpt-5.1-codex-mini") assert not provider.validate_model_name("gpt-4o") @@ -223,11 +223,11 @@ class TestOpenAIProvider: for alias in aliases: assert not provider.get_capabilities(alias).supports_extended_thinking - def test_gpt51_family_capabilities(self): - """Ensure GPT-5.1 family exposes correct capability flags.""" + def test_gpt52_family_capabilities(self): + """Ensure GPT-5.2 base model exposes correct capability flags.""" provider = OpenAIModelProvider(api_key="test-key") - base = provider.get_capabilities("gpt-5.1") + base = provider.get_capabilities("gpt-5.2") assert base.supports_streaming assert base.allow_code_generation diff --git a/tests/test_supported_models_aliases.py b/tests/test_supported_models_aliases.py index 3cebe19..8b4dd84 100644 --- a/tests/test_supported_models_aliases.py +++ b/tests/test_supported_models_aliases.py @@ -54,7 +54,7 @@ class TestSupportedModelsAliases: assert "o3mini" in provider.MODEL_CAPABILITIES["o3-mini"].aliases assert "o3pro" in provider.MODEL_CAPABILITIES["o3-pro"].aliases assert "gpt4.1" in provider.MODEL_CAPABILITIES["gpt-4.1"].aliases - assert "gpt5.1" in provider.MODEL_CAPABILITIES["gpt-5.1"].aliases + assert "gpt5.2" in provider.MODEL_CAPABILITIES["gpt-5.2"].aliases assert "gpt5.1-codex" in provider.MODEL_CAPABILITIES["gpt-5.1-codex"].aliases assert "codex-mini" in provider.MODEL_CAPABILITIES["gpt-5.1-codex-mini"].aliases @@ -64,14 +64,15 @@ class TestSupportedModelsAliases: assert provider._resolve_model_name("o3pro") == "o3-pro" # o3pro resolves to o3-pro assert provider._resolve_model_name("o4mini") == "o4-mini" assert provider._resolve_model_name("gpt4.1") == "gpt-4.1" # gpt4.1 resolves to gpt-4.1 - assert provider._resolve_model_name("gpt5.1") == "gpt-5.1" + assert provider._resolve_model_name("gpt5.2") == "gpt-5.2" + assert provider._resolve_model_name("gpt5.1") == "gpt-5.2" assert provider._resolve_model_name("gpt5.1-codex") == "gpt-5.1-codex" assert provider._resolve_model_name("codex-mini") == "gpt-5.1-codex-mini" # Test case insensitive resolution assert provider._resolve_model_name("Mini") == "gpt-5-mini" # mini -> gpt-5-mini now assert provider._resolve_model_name("O3MINI") == "o3-mini" - assert provider._resolve_model_name("Gpt5.1") == "gpt-5.1" + assert provider._resolve_model_name("Gpt5.1") == "gpt-5.2" def test_xai_provider_aliases(self): """Test XAI provider's alias structure."""