llm-gemini 0.23__tar.gz → 0.25__tar.gz

{llm_gemini-0.23 → llm_gemini-0.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llm-gemini
-Version: 0.23
+Version: 0.25
 Summary: LLM plugin to access Google's Gemini family of models
 Author: Simon Willison
 License-Expression: Apache-2.0
@@ -77,7 +77,7 @@ to_output = []
 NOTES = {
     "gemini/gemini-2.5-pro": "Gemini 2.5 Pro",
     "gemini/gemini-2.5-flash": "Gemini 2.5 Flash",
-    "gemini/gemini-2.5-flash-lite-preview-06-17": "Gemini 2.5 Lite Preview",
+    "gemini/gemini-2.5-flash-lite": "Gemini 2.5 Flash Lite",
     "gemini/gemini-2.5-flash-preview-05-20": "Gemini 2.5 Flash preview (priced differently from 2.5 Flash)",
     "gemini/gemini-2.0-flash-thinking-exp-01-21": "Experimental \"thinking\" model from January 2025",
     "gemini/gemini-1.5-flash-8b-latest": "The least expensive model",
@@ -93,9 +93,9 @@ for line in lines:
     )
 cog.out("\n".join(to_output))
 ]]] -->
+- `gemini/gemini-2.5-flash-lite`: Gemini 2.5 Flash Lite
 - `gemini/gemini-2.5-pro`: Gemini 2.5 Pro
 - `gemini/gemini-2.5-flash`: Gemini 2.5 Flash
-- `gemini/gemini-2.5-flash-lite-preview-06-17`: Gemini 2.5 Lite Preview
 - `gemini/gemini-2.5-pro-preview-06-05`
 - `gemini/gemini-2.5-flash-preview-05-20`: Gemini 2.5 Flash preview (priced differently from 2.5 Flash)
 - `gemini/gemini-2.5-pro-preview-05-06`
@@ -197,6 +197,27 @@ llm -m gemini-2.0-flash -o google_search 1 \
 
 Use `llm logs -c --json` after running a prompt to see the full JSON response, which includes [additional information](https://github.com/simonw/llm-gemini/pull/29#issuecomment-2606201877) about grounded results.
 
+### URL context
+
+Gemini models support a [URL context](https://ai.google.dev/gemini-api/docs/url-context) tool which, when enabled, allows the models to fetch additional content from URLs as part of their execution.
+
+You can enable that with the `-o url_context 1` option - for example:
+
+```bash
+llm -m gemini-2.5-flash -o url_context 1 'Latest headline on simonwillison.net'
+```
+Extra tokens introduced by this tool will be charged as input tokens. Use `--usage` to see details of those:
+```bash
+llm -m gemini-2.5-flash -o url_context 1 --usage \
+  'Latest headline on simonwillison.net'
+```
+Outputs:
+```
+The latest headline on simonwillison.net as of August 17, 2025, is "TIL: Running a gpt-oss eval suite against LM Studio on a Mac.".
+Token usage: 9,613 input, 87 output, {"candidatesTokenCount": 57, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}], "toolUsePromptTokenCount": 9603, "toolUsePromptTokensDetails": [{"modality": "TEXT", "tokenCount": 9603}], "thoughtsTokenCount": 30}
+```
+The `"toolUsePromptTokenCount"` key shows how many tokens were used for that URL context.
+
 ### Chat
 
 To chat interactively with the model, run `llm chat`:

{llm_gemini-0.23 → llm_gemini-0.25}/README.md

@@ -54,7 +54,7 @@ to_output = []
 NOTES = {
     "gemini/gemini-2.5-pro": "Gemini 2.5 Pro",
     "gemini/gemini-2.5-flash": "Gemini 2.5 Flash",
-    "gemini/gemini-2.5-flash-lite-preview-06-17": "Gemini 2.5 Lite Preview",
+    "gemini/gemini-2.5-flash-lite": "Gemini 2.5 Flash Lite",
     "gemini/gemini-2.5-flash-preview-05-20": "Gemini 2.5 Flash preview (priced differently from 2.5 Flash)",
     "gemini/gemini-2.0-flash-thinking-exp-01-21": "Experimental \"thinking\" model from January 2025",
     "gemini/gemini-1.5-flash-8b-latest": "The least expensive model",
@@ -70,9 +70,9 @@ for line in lines:
     )
 cog.out("\n".join(to_output))
 ]]] -->
+- `gemini/gemini-2.5-flash-lite`: Gemini 2.5 Flash Lite
 - `gemini/gemini-2.5-pro`: Gemini 2.5 Pro
 - `gemini/gemini-2.5-flash`: Gemini 2.5 Flash
-- `gemini/gemini-2.5-flash-lite-preview-06-17`: Gemini 2.5 Lite Preview
 - `gemini/gemini-2.5-pro-preview-06-05`
 - `gemini/gemini-2.5-flash-preview-05-20`: Gemini 2.5 Flash preview (priced differently from 2.5 Flash)
 - `gemini/gemini-2.5-pro-preview-05-06`
@@ -174,6 +174,27 @@ llm -m gemini-2.0-flash -o google_search 1 \
 
 Use `llm logs -c --json` after running a prompt to see the full JSON response, which includes [additional information](https://github.com/simonw/llm-gemini/pull/29#issuecomment-2606201877) about grounded results.
 
+### URL context
+
+Gemini models support a [URL context](https://ai.google.dev/gemini-api/docs/url-context) tool which, when enabled, allows the models to fetch additional content from URLs as part of their execution.
+
+You can enable that with the `-o url_context 1` option - for example:
+
+```bash
+llm -m gemini-2.5-flash -o url_context 1 'Latest headline on simonwillison.net'
+```
+Extra tokens introduced by this tool will be charged as input tokens. Use `--usage` to see details of those:
+```bash
+llm -m gemini-2.5-flash -o url_context 1 --usage \
+  'Latest headline on simonwillison.net'
+```
+Outputs:
+```
+The latest headline on simonwillison.net as of August 17, 2025, is "TIL: Running a gpt-oss eval suite against LM Studio on a Mac.".
+Token usage: 9,613 input, 87 output, {"candidatesTokenCount": 57, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}], "toolUsePromptTokenCount": 9603, "toolUsePromptTokensDetails": [{"modality": "TEXT", "tokenCount": 9603}], "thoughtsTokenCount": 30}
+```
+The `"toolUsePromptTokenCount"` key shows how many tokens were used for that URL context.
+
 ### Chat
 
 To chat interactively with the model, run `llm chat`:

{llm_gemini-0.23 → llm_gemini-0.25}/llm_gemini.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llm-gemini
-Version: 0.23
+Version: 0.25
 Summary: LLM plugin to access Google's Gemini family of models
 Author: Simon Willison
 License-Expression: Apache-2.0
@@ -77,7 +77,7 @@ to_output = []
 NOTES = {
     "gemini/gemini-2.5-pro": "Gemini 2.5 Pro",
     "gemini/gemini-2.5-flash": "Gemini 2.5 Flash",
-    "gemini/gemini-2.5-flash-lite-preview-06-17": "Gemini 2.5 Lite Preview",
+    "gemini/gemini-2.5-flash-lite": "Gemini 2.5 Flash Lite",
     "gemini/gemini-2.5-flash-preview-05-20": "Gemini 2.5 Flash preview (priced differently from 2.5 Flash)",
     "gemini/gemini-2.0-flash-thinking-exp-01-21": "Experimental \"thinking\" model from January 2025",
     "gemini/gemini-1.5-flash-8b-latest": "The least expensive model",
@@ -93,9 +93,9 @@ for line in lines:
     )
 cog.out("\n".join(to_output))
 ]]] -->
+- `gemini/gemini-2.5-flash-lite`: Gemini 2.5 Flash Lite
 - `gemini/gemini-2.5-pro`: Gemini 2.5 Pro
 - `gemini/gemini-2.5-flash`: Gemini 2.5 Flash
-- `gemini/gemini-2.5-flash-lite-preview-06-17`: Gemini 2.5 Lite Preview
 - `gemini/gemini-2.5-pro-preview-06-05`
 - `gemini/gemini-2.5-flash-preview-05-20`: Gemini 2.5 Flash preview (priced differently from 2.5 Flash)
 - `gemini/gemini-2.5-pro-preview-05-06`
@@ -197,6 +197,27 @@ llm -m gemini-2.0-flash -o google_search 1 \
 
 Use `llm logs -c --json` after running a prompt to see the full JSON response, which includes [additional information](https://github.com/simonw/llm-gemini/pull/29#issuecomment-2606201877) about grounded results.
 
+### URL context
+
+Gemini models support a [URL context](https://ai.google.dev/gemini-api/docs/url-context) tool which, when enabled, allows the models to fetch additional content from URLs as part of their execution.
+
+You can enable that with the `-o url_context 1` option - for example:
+
+```bash
+llm -m gemini-2.5-flash -o url_context 1 'Latest headline on simonwillison.net'
+```
+Extra tokens introduced by this tool will be charged as input tokens. Use `--usage` to see details of those:
+```bash
+llm -m gemini-2.5-flash -o url_context 1 --usage \
+  'Latest headline on simonwillison.net'
+```
+Outputs:
+```
+The latest headline on simonwillison.net as of August 17, 2025, is "TIL: Running a gpt-oss eval suite against LM Studio on a Mac.".
+Token usage: 9,613 input, 87 output, {"candidatesTokenCount": 57, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}], "toolUsePromptTokenCount": 9603, "toolUsePromptTokensDetails": [{"modality": "TEXT", "tokenCount": 9603}], "thoughtsTokenCount": 30}
+```
+The `"toolUsePromptTokenCount"` key shows how many tokens were used for that URL context.
+
 ### Chat
 
 To chat interactively with the model, run `llm chat`:

{llm_gemini-0.23 → llm_gemini-0.25}/llm_gemini.py

@@ -44,7 +44,7 @@ GOOGLE_SEARCH_MODELS = {
     "gemini-2.5-pro-preview-06-05",
     "gemini-2.5-pro",
     "gemini-2.5-flash",
-    "gemini-2.5-flash-lite-preview-06-17",
+    "gemini-2.5-flash-lite",
 }
 
 # Older Google models used google_search_retrieval instead of google_search
@@ -69,7 +69,7 @@ THINKING_BUDGET_MODELS = {
     "gemini-2.5-pro-preview-06-05",
     "gemini-2.5-pro",
     "gemini-2.5-flash",
-    "gemini-2.5-flash-lite-preview-06-17",
+    "gemini-2.5-flash-lite",
 }
 
 NO_VISION_MODELS = {"gemma-3-1b-it", "gemma-3n-e4b-it"}
@@ -152,10 +152,10 @@ def register_models(register):
         "gemini-2.5-flash-preview-05-20",
         # 5th June 2025:
         "gemini-2.5-pro-preview-06-05",
-        # 17th June 2025:
-        "gemini-2.5-flash-lite-preview-06-17",
         "gemini-2.5-flash",
         "gemini-2.5-pro",
+        # 22nd July 2025:
+        "gemini-2.5-flash-lite",
     ):
         can_google_search = model_id in GOOGLE_SEARCH_MODELS
         can_thinking_budget = model_id in THINKING_BUDGET_MODELS
@@ -272,6 +272,13 @@ class _SharedGemini:
             ),
             default=None,
         )
+        url_context: Optional[bool] = Field(
+            description=(
+                "Enable the URL context tool so the model can fetch content "
+                "from URLs mentioned in the prompt"
+            ),
+            default=None,
+        )
 
     class OptionsWithGoogleSearch(Options):
         google_search: Optional[bool] = Field(
@@ -339,8 +346,7 @@ class _SharedGemini:
                 messages.append({"role": "user", "parts": parts})
                 model_parts = []
                 response_text = response.text_or_raise()
-                if response_text:
-                    model_parts.append({"text": response_text})
+                model_parts.append({"text": response_text})
                 tool_calls = response.tool_calls_or_raise()
                 if tool_calls:
                     model_parts.extend(
@@ -405,6 +411,8 @@ class _SharedGemini:
                 else "google_search"
             )
             tools.append({tool_name: {}})
+        if prompt.options and prompt.options.url_context:
+            tools.append({"url_context": {}})
         if prompt.tools:
             tools.append(
                 {
@@ -490,6 +498,12 @@ class _SharedGemini:
             candidates_token_count = usage.get("candidatesTokenCount") or 0
             thoughts_token_count = usage.get("thoughtsTokenCount") or 0
             output_tokens = candidates_token_count + thoughts_token_count
+            tool_token_count = usage.get("toolUsePromptTokenCount") or 0
+            if tool_token_count:
+                if input_tokens is None:
+                    input_tokens = tool_token_count
+                else:
+                    input_tokens += tool_token_count
             usage.pop("totalTokenCount", None)
             if input_tokens is not None:
                 response.set_usage(

{llm_gemini-0.23 → llm_gemini-0.25}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "llm-gemini"
-version = "0.23"
+version = "0.25"
 description = "LLM plugin to access Google's Gemini family of models"
 readme = "README.md"
 authors = [{name = "Simon Willison"}]