V0.87.0

HISTORY.md

@@ -1,5 +1,26 @@
 # Release history
 
+### Aider v0.86.0
+
+- Expanded GPT-5 model support across family variants and providers (OpenAI, Azure, OpenRouter), including dated and chat/mini/nano variants.
+- Aider wrote 88% of the code in this release.
+
+### Aider v0.85.5
+
+- Enforced diff edit format for GPT-5 models.
+- Added support for the reasoning_effort setting for GPT-5 models.
+- Fixed model detection to correctly apply GPT-5 settings to versioned names (gpt-5 and gpt-5-2025-08-07).
+
+### Aider v0.85.4
+
+- Added support for openai/gpt-5
+- Fixed analytics to support the latest PostHog SDK event-capture API.
+- Disabled temperature when using GPT-5 models for more deterministic outputs.
+
+### Aider v0.85.3
+
+- Bumped dependencies to pick up latest litellm==1.75.0.
+
 ### Aider v0.85.2
 
 - Added support for Grok-4 via `xai/grok-4` and `openrouter/x-ai/grok-4` model names.

README.md

@@ -27,13 +27,13 @@ cog.out(text)
   <a href="https://github.com/Aider-AI/aider/stargazers"><img alt="GitHub Stars" title="Total number of GitHub stars the Aider project has received"
 src="https://img.shields.io/github/stars/Aider-AI/aider?style=flat-square&logo=github&color=f1c40f&labelColor=555555"/></a>
   <a href="https://pypi.org/project/aider-chat/"><img alt="PyPI Downloads" title="Total number of installations via pip from PyPI"
-src="https://img.shields.io/badge/📦%20Installs-2.8M-2ecc71?style=flat-square&labelColor=555555"/></a>
+src="https://img.shields.io/badge/📦%20Installs-3.0M-2ecc71?style=flat-square&labelColor=555555"/></a>
   <img alt="Tokens per week" title="Number of tokens processed weekly by Aider users"
 src="https://img.shields.io/badge/📈%20Tokens%2Fweek-15B-3498db?style=flat-square&labelColor=555555"/>
   <a href="https://openrouter.ai/#options-menu"><img alt="OpenRouter Ranking" title="Aider's ranking among applications on the OpenRouter platform"
 src="https://img.shields.io/badge/🏆%20OpenRouter-Top%2020-9b59b6?style=flat-square&labelColor=555555"/></a>
   <a href="https://aider.chat/HISTORY.html"><img alt="Singularity" title="Percentage of the new code in Aider's last release written by Aider itself"
-src="https://img.shields.io/badge/🔄%20Singularity-21%25-e74c3c?style=flat-square&labelColor=555555"/></a>
+src="https://img.shields.io/badge/🔄%20Singularity-88%25-e74c3c?style=flat-square&labelColor=555555"/></a>
 <!--[[[end]]]-->  
 </p>
 

aider/__init__.py

@@ -1,6 +1,6 @@
 from packaging import version
 
-__version__ = "0.86.2.dev"
+__version__ = "0.87.0.dev"
 safe_version = __version__
 
 try:

aider/analytics.py

@@ -237,7 +237,7 @@ def event(self, event_name, main_model=None, **kwargs):
                 self.mp = None  # Disable mixpanel on connection errors
 
         if self.ph:
-            self.ph.capture(self.user_id, event_name, dict(properties))
+            self.ph.capture(event_name, distinct_id=self.user_id, properties=dict(properties))
 
         if self.logfile:
             log_entry = {

aider/commands.py

@@ -196,14 +196,11 @@ def cmd_chat_mode(self, args):
         elif ef == "ask":
             summarize_from_coder = False
 
-        try:
-            raise SwitchCoder(
-                edit_format=edit_format,
-                summarize_from_coder=summarize_from_coder,
-            )
 
-        except Exception as e:
-            raise e.with_traceback(None)
+        raise SwitchCoder(
+            edit_format=edit_format,
+            summarize_from_coder=summarize_from_coder,
+        )
 
     def completions_model(self):
         models = litellm.model_cost.keys()
@@ -1395,6 +1392,7 @@ def _generic_chat_command(self, args, edit_format, placeholder=None):
             from_coder=self.coder,
             edit_format=edit_format,
             summarize_from_coder=False,
+            num_cache_warming_pings=0,
         )
 
         user_msg = args

aider/main.py

@@ -1184,6 +1184,9 @@ def get_io(pretty):
             if "show_announcements" in kwargs:
                 del kwargs["show_announcements"]
 
+            # Disable cache warming for the new coder
+            kwargs["num_cache_warming_pings"] = 0
+
             coder = Coder.create(**kwargs)
 
             if switch.kwargs.get("show_announcements") is not False:

aider/models.py

@@ -94,6 +94,7 @@
     # Other models
     "deepseek": "deepseek/deepseek-chat",
     "flash": "gemini/gemini-2.5-flash",
+    "flash-lite": "gemini/gemini-2.5-flash-lite",
     "quasar": "openrouter/openrouter/quasar-alpha",
     "r1": "deepseek/deepseek-reasoner",
     "gemini-2.5-pro": "gemini/gemini-2.5-pro",
@@ -436,6 +437,14 @@ def apply_generic_model_settings(self, model):
             self.examples_as_sys_msg = False
             return  # <--
 
+        last_segment = model.split("/")[-1]
+        if last_segment in ("gpt-5", "gpt-5-2025-08-07"):
+            self.use_temperature = False
+            self.edit_format = "diff"
+            if "reasoning_effort" not in self.accepts_settings:
+                self.accepts_settings.append("reasoning_effort")
+            return  # <--
+
         if "/o1-mini" in model:
             self.use_repo_map = True
             self.use_temperature = False
@@ -1012,7 +1021,15 @@ def send_completion(self, messages, functions, stream, temperature=None, tools=N
 
             self.github_copilot_token_to_open_ai_key(kwargs["extra_headers"])
 
-        res = litellm.completion(**kwargs)
+
+        try:
+            res = litellm.completion(**kwargs)
+        except Exception as err:
+            res = "Model API Response Error. Please retry the previous request"
+
+            if self.verbose:
+                print(f"LiteLLM API Error: {str(err)}")
+
         return hash_object, res
 
     def simple_send_with_retries(self, messages):

aider/resources/model-settings.yml

@@ -1819,3 +1819,196 @@
   editor_edit_format: editor-diff
   accepts_settings: ["thinking_tokens"]
 
+# GPT-5 family
+- name: gpt-5
+  edit_format: diff
+  weak_model_name: gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: gpt-5-2025-08-07
+  edit_format: diff
+  weak_model_name: gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: gpt-5-mini
+  edit_format: diff
+  weak_model_name: gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: gpt-5-mini-2025-08-07
+  edit_format: diff
+  weak_model_name: gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: gpt-5-nano
+  edit_format: diff
+  weak_model_name: gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: gpt-5-nano-2025-08-07
+  edit_format: diff
+  weak_model_name: gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: gpt-5-chat
+  edit_format: diff
+  weak_model_name: gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: gpt-5-chat-latest
+  edit_format: diff
+  weak_model_name: gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: azure/gpt-5
+  edit_format: diff
+  weak_model_name: azure/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: azure/gpt-5-2025-08-07
+  edit_format: diff
+  weak_model_name: azure/gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: azure/gpt-5-mini
+  edit_format: diff
+  weak_model_name: azure/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: azure/gpt-5-mini-2025-08-07
+  edit_format: diff
+  weak_model_name: azure/gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: azure/gpt-5-nano
+  edit_format: diff
+  weak_model_name: azure/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: azure/gpt-5-nano-2025-08-07
+  edit_format: diff
+  weak_model_name: azure/gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: azure/gpt-5-chat
+  edit_format: diff
+  weak_model_name: azure/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: azure/gpt-5-chat-latest
+  edit_format: diff
+  weak_model_name: azure/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openai/gpt-5
+  edit_format: diff
+  weak_model_name: openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openai/gpt-5-2025-08-07
+  edit_format: diff
+  weak_model_name: openai/gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: openai/gpt-5-mini
+  edit_format: diff
+  weak_model_name: openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openai/gpt-5-mini-2025-08-07
+  edit_format: diff
+  weak_model_name: openai/gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: openai/gpt-5-nano
+  edit_format: diff
+  weak_model_name: openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openai/gpt-5-nano-2025-08-07
+  edit_format: diff
+  weak_model_name: openai/gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: openai/gpt-5-chat
+  edit_format: diff
+  weak_model_name: openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openai/gpt-5-chat-latest
+  edit_format: diff
+  weak_model_name: openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openrouter/openai/gpt-5
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openrouter/openai/gpt-5-2025-08-07
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: openrouter/openai/gpt-5-mini
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openrouter/openai/gpt-5-mini-2025-08-07
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: openrouter/openai/gpt-5-nano
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openrouter/openai/gpt-5-nano-2025-08-07
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-5-nano-2025-08-07
+  use_repo_map: true
+  use_temperature: false
+
+- name: openrouter/openai/gpt-5-chat
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+
+- name: openrouter/openai/gpt-5-chat-latest
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-5-nano
+  use_repo_map: true
+  use_temperature: false
+

aider/website/HISTORY.md

@@ -24,6 +24,27 @@ cog.out(text)
 ]]]-->
 
 
+### Aider v0.86.0
+
+- Expanded GPT-5 model support across family variants and providers (OpenAI, Azure, OpenRouter), including dated and chat/mini/nano variants.
+- Aider wrote 88% of the code in this release.
+
+### Aider v0.85.5
+
+- Enforced diff edit format for GPT-5 models.
+- Added support for the reasoning_effort setting for GPT-5 models.
+- Fixed model detection to correctly apply GPT-5 settings to versioned names (gpt-5 and gpt-5-2025-08-07).
+
+### Aider v0.85.4
+
+- Added support for openai/gpt-5
+- Fixed analytics to support the latest PostHog SDK event-capture API.
+- Disabled temperature when using GPT-5 models for more deterministic outputs.
+
+### Aider v0.85.3
+
+- Bumped dependencies to pick up latest litellm==1.75.0.
+
 ### Aider v0.85.2
 
 - Added support for Grok-4 via `xai/grok-4` and `openrouter/x-ai/grok-4` model names.