llm-gemini 0.24__tar.gz → 0.25__tar.gz

{llm_gemini-0.24 → llm_gemini-0.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llm-gemini
-Version: 0.24
+Version: 0.25
 Summary: LLM plugin to access Google's Gemini family of models
 Author: Simon Willison
 License-Expression: Apache-2.0
@@ -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-0.24 → llm_gemini-0.25}/README.md

@@ -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-0.24 → llm_gemini-0.25}/llm_gemini.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llm-gemini
-Version: 0.24
+Version: 0.25
 Summary: LLM plugin to access Google's Gemini family of models
 Author: Simon Willison
 License-Expression: Apache-2.0
@@ -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-0.24 → llm_gemini-0.25}/llm_gemini.py

@@ -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(
@@ -404,6 +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(
                 {
@@ -489,6 +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-0.24 → llm_gemini-0.25}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "llm-gemini"
-version = "0.24"
+version = "0.25"
 description = "LLM plugin to access Google's Gemini family of models"
 readme = "README.md"
 authors = [{name = "Simon Willison"}]