Case: 20260426T062915Z__gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file
TIMEOUT Trajectory: clean | Invoked: no | Match: 0%
gptme --non-interactive --no-confirm --name gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file-warmup --system short --workspace /work/results/runs/20260426T062915Z/cases/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file/workspace-warmup --tools shell --tool-format tool -m local/gemma4:e4b 'Use the shell tool. Read search-response.json and required-token.txt from the current workspace. From results in search-response.json, select the item with highest score among snippets that contain the exact required token. Write search-result.json in the current workspace as JSON with exactly these keys: - query - selected_id - selected_url - selected_score If successful, reply only DONE. If command execution fails, reply only FAIL. '
gptme --non-interactive --no-confirm --name gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file-measured --system short --workspace /work/results/runs/20260426T062915Z/cases/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file/workspace --tools shell --tool-format tool -m local/gemma4:e4b 'Use the shell tool. Read search-response.json and required-token.txt from the current workspace. From results in search-response.json, select the item with highest score among snippets that contain the exact required token. Write search-result.json in the current workspace as JSON with exactly these keys: - query - selected_id - selected_url - selected_score If successful, reply only DONE. If command execution fails, reply only FAIL. '
Consistency: consistent
Use the shell tool. Read search-response.json and required-token.txt from the current workspace. From results in search-response.json, select the item with highest score among snippets that contain the exact required token. Write search-result.json in the current workspace as JSON with exactly these keys: - query - selected_id - selected_url - selected_score If successful, reply only DONE. If command execution fails, reply only FAIL.
{"query": "weekly plan static fixture checkbox", "selected_id": "doc-static-top", "selected_score": 0.98, "selected_url": "https://kb.example/static-top"}
MISSING_FILE
--- expected
+++ observed
@@ -1 +1 @@
-{"query": "weekly plan static fixture checkbox", "selected_id": "doc-static-top", "selected_score": 0.98, "selected_url": "https://kb.example/static-top"}
+MISSING_FILE
No structured session transcript found.
[gripprobe] process_started_at=2026-04-26T06:29:17+00:00
[06:29:18] Created config file at /work/results/runs/20260426T062915Z/cases/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file/runtime/gptme/warmup/home/.config/gptme/config.toml
[06:29:19] WARNING Skipping all confirmation prompts. cli.py:265
[06:29:19] Using model: local/gemma4:e4b
Using logdir: /work/results/runs/20260426T062915Z/cases/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file/runtime/gptme/warmup/state/gptme-logs/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file-warmup
Using workspace: /work/results/runs/20260426T062915Z/cases/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file/workspace-warmup
Skipped 2 hidden system messages, show with --show-hidden
--- ^^^ past messages ^^^ ---
User:
Use the shell tool.
Read search-response.json and required-token.txt from the current workspace.
From results in search-response.json, select the item with highest score among snippets that contain the exact required token.
Write search-result.json in the current workspace as JSON with exactly these keys:
- query
- selected_id
- selected_url
- selected_score
If successful, reply only DONE.
If command execution fails, reply only FAIL.
````search-response.json
{"query": "weekly plan static fixture checkbox", "results": [{"id": "doc-intro", "title": "Markdown planning intro", "url": "https://kb.example/intro", "snippet": "Basic markdown checklist examples.", "score": 0.72, "lang": "en"}, {"id": "doc-static-top", "title": "Weekly
planning with checkboxes", "url": "https://kb.example/static-top", "snippet": "Actionable template. Required token: static-token-abc123.", "score": 0.98, "lang": "en"}, {"id": "doc-static-alt", "title": "Alternate planning approach", "url": "https://kb.example/static-alt",
"snippet": "Also mentions token static-token-abc123, but less relevant.", "score": 0.91, "lang": "en"}, {"id": "doc-noise", "title": "General productivity", "url": "https://kb.example/noise", "snippet": "Time-blocking article.", "score": 0.44, "lang": "en"}], "total": 4,
"returned": 4, "error": ""}
````
````required-token.txt
static-token-abc123
````
````search-response.json
{"query": "weekly plan static fixture checkbox", "results": [{"id": "doc-intro", "title": "Markdown planning intro", "url": "https://kb.example/intro", "snippet": "Basic markdown checklist examples.", "score": 0.72, "lang": "en"}, {"id": "doc-static-top", "title": "Weekly
planning with checkboxes", "url": "https://kb.example/static-top", "snippet": "Actionable template. Required token: static-token-abc123.", "score": 0.98, "lang": "en"}, {"id": "doc-static-alt", "title": "Alternate planning approach", "url": "https://kb.example/static-alt",
"snippet": "Also mentions token static-token-abc123, but less relevant.", "score": 0.91, "lang": "en"}, {"id": "doc-noise", "title": "General productivity", "url": "https://kb.example/noise", "snippet": "Time-blocking article.", "score": 0.44, "lang": "en"}], "total": 4,
"returned": 4, "error": ""}
````
Assistant: Thinking...
Assistant:
<think>
<think>
The user wants me to process three files: `search-response.json`, `required-token.txt`, and `search-response.json` (which seems to be a duplicate of the first one, but I will treat it as the input data).
The goal is to:
1. Read `search-response.json` and `required-token.txt`.
2. From the results in `search-response.json`, select the item with the highest score among snippets that contain the exact required token.
3. Write the result to `search-result.json` with exactly these keys: `query`, `selected_id`, `selected_url`, `selected_score`.
4. If successful, reply only `DONE`.
5. If command execution fails, reply only `FAIL`.
I will use the `shell` tool to perform these steps, likely involving `jq` or a combination of shell scripting tools to handle JSON and text processing.
**Step 1: Read the files.**
I have the content provided in the prompt, but I need to assume they are available in the current workspace. I will use `cat` to read them first to confirm their content structure, although the prompt already provided them.
**Step 2: Extract the required token.**
The token is in `required-token.txt`.
**Step 3: Filter and select the best result.**
I need to iterate through the `results` array in `search-response.json`.
For each result:
a. Check if the `snippet` contains the exact token from `required-token.txt`.
b. If it does, keep track of the result with the maximum `score`.
**Step 4: Construct the output JSON.**
The final JSON must contain:
- `query`: From `search-response.json`.
- `selected_id`: The ID of the best result.
- `selected_url`: The URL of the best result.
- `selected_score`: The score of the best result.
Let's analyze the provided data:
`search-response.json`:
- `query`: "weekly plan static fixture checkbox"
- `results`:
1. `id`: "doc-intro", `snippet`: "Basic markdown checklist examples.", `score`: 0.72
2. `id`: "doc-static-top", `snippet`: "Actionable template. Required token: static-token-abc123.", `score`: 0.98
3. `id`: "doc-static-alt", `snippet`: "Also mentions token static-token-abc123, but less relevant.", `score`: 0.91
4. `id`: "doc-noise", `snippet`: "Time-blocking article.", `score`: 0.44
- `required-token.txt`: "static-token-abc123"
Filtering based on token "static-token-abc123":
1. doc-intro: No match.
2. doc-static-top: Match. Score: 0.98.
3. doc-static-alt: Match. Score: 0.91.
4. doc-noise: No match.
The highest score among matching snippets is 0.98, corresponding to `doc-static-top`.
Selected data:
- `query`: "weekly plan static fixture checkbox"
- `selected_id`: "doc-static-top"
- `selected_url`: "https://kb.example/static-top"
- `selected_score`: 0.98
I will use `jq` and shell scripting to automate this process. Since the input files are provided in the prompt, I will assume they are written to the filesystem for the shell commands to work.
I will write a script that reads the files, processes the JSON, and outputs the final JSON structure.
Since I cannot assume the files are physically present, I must first write them using the shell tool if they are not already there, or assume the environment setup handles this. Given the prompt structure, I will assume I need to write the content to files first, then process them.
Let's start by writing the files.
</think>
</think>
<thinking>
<thinking>
The user wants me to process two input files, `search-response.json` and `required-token.txt`, to find the best search result based on a required token and highest score. The output must be a JSON file named `search-result.json` with specific keys.
I will follow these steps:
1. Write the provided content into the respective files (`search-response.json` and `required-token.txt`) using the `shell` tool.
2. Use a combination of shell tools (like `jq` and `grep` or `awk`) to:
a. Read the required token from `required-token.txt`.
b. Parse `search-response.json`.
c. Filter results where the `snippet` contains the token.
d. Select the result with the maximum `score`.
e. Construct the final JSON object.
3. Write the resulting JSON to `search-result.json`.
4. Finally, reply with "DONE".
Since the input files are provided in the prompt, I must ensure they exist before processing. I will use `echo` and redirection for this.
</thinking>
</thinking>
[gripprobe] process_finished_at=2026-04-26T06:31:17+00:00 exit_code=124 timeout=true
[gripprobe] process_started_at=2026-04-26T06:29:17+00:00 [gripprobe] process_finished_at=2026-04-26T06:31:17+00:00 exit_code=124 timeout=true
[gripprobe] process_started_at=2026-04-26T06:31:17+00:00
[06:31:18] Created config file at /work/results/runs/20260426T062915Z/cases/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file/runtime/gptme/measured/home/.config/gptme/config.toml
[06:31:18] WARNING Skipping all confirmation prompts. cli.py:265
Using model: local/gemma4:e4b
[06:31:19] Using logdir: /work/results/runs/20260426T062915Z/cases/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file/runtime/gptme/measured/state/gptme-logs/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file-measured
Using workspace: /work/results/runs/20260426T062915Z/cases/gptme__local_gemma4_e4b__ollama__tool__json_rank_from_file/workspace
Skipped 2 hidden system messages, show with --show-hidden
--- ^^^ past messages ^^^ ---
User:
Use the shell tool.
Read search-response.json and required-token.txt from the current workspace.
From results in search-response.json, select the item with highest score among snippets that contain the exact required token.
Write search-result.json in the current workspace as JSON with exactly these keys:
- query
- selected_id
- selected_url
- selected_score
If successful, reply only DONE.
If command execution fails, reply only FAIL.
````search-response.json
{"query": "weekly plan static fixture checkbox", "results": [{"id": "doc-intro", "title": "Markdown planning intro", "url": "https://kb.example/intro", "snippet": "Basic markdown checklist examples.", "score": 0.72, "lang": "en"}, {"id": "doc-static-top", "title": "Weekly
planning with checkboxes", "url": "https://kb.example/static-top", "snippet": "Actionable template. Required token: static-token-abc123.", "score": 0.98, "lang": "en"}, {"id": "doc-static-alt", "title": "Alternate planning approach", "url": "https://kb.example/static-alt",
"snippet": "Also mentions token static-token-abc123, but less relevant.", "score": 0.91, "lang": "en"}, {"id": "doc-noise", "title": "General productivity", "url": "https://kb.example/noise", "snippet": "Time-blocking article.", "score": 0.44, "lang": "en"}], "total": 4,
"returned": 4, "error": ""}
````
````required-token.txt
static-token-abc123
````
````search-response.json
{"query": "weekly plan static fixture checkbox", "results": [{"id": "doc-intro", "title": "Markdown planning intro", "url": "https://kb.example/intro", "snippet": "Basic markdown checklist examples.", "score": 0.72, "lang": "en"}, {"id": "doc-static-top", "title": "Weekly
planning with checkboxes", "url": "https://kb.example/static-top", "snippet": "Actionable template. Required token: static-token-abc123.", "score": 0.98, "lang": "en"}, {"id": "doc-static-alt", "title": "Alternate planning approach", "url": "https://kb.example/static-alt",
"snippet": "Also mentions token static-token-abc123, but less relevant.", "score": 0.91, "lang": "en"}, {"id": "doc-noise", "title": "General productivity", "url": "https://kb.example/noise", "snippet": "Time-blocking article.", "score": 0.44, "lang": "en"}], "total": 4,
"returned": 4, "error": ""}
````
Assistant: Thinking...
Assistant:
<think>
<think>
The user wants me to process three files: `search-response.json`, `required-token.txt`, and `search-response.json` (which seems to be a duplicate of the first one, but I will treat it as the input data).
The goal is to:
1. Read `search-response.json` and `required-token.txt`.
2. From the results in `search-response.json`, select the item with the highest score among snippets that contain the exact required token.
3. Write the result to `search-result.json` with the keys: `query`, `selected_id`, `selected_url`, `selected_score`.
4. If successful, reply only `DONE`.
5. If command execution fails, reply only `FAIL`.
The input files are provided in the prompt, but I need to assume they are available in the current workspace and use the `shell` tool to read and process them. Since the content is provided directly, I will simulate the reading process by using `jq` or similar tools if possible, or by writing a script that handles JSON parsing and logic.
Let's analyze the data:
`search-response.json` content:
```json
{"query": "weekly plan static fixture checkbox", "results": [{"id": "doc-intro", "title": "Markdown planning intro", "url": "https://kb.example/intro", "snippet": "Basic markdown checklist examples.", "score": 0.72, "lang": "en"}, {"id": "doc-static-top", "title": "Weekly planning with checkboxes", "url": "https://kb.example/static-top", "snippet": "Actionable template. Required token: static-token-abc123.", "score": 0.98, "lang": "en"}, {"id": "doc-static-alt", "title": "Alternate planning approach", "url": "https://kb.example/static-alt", "snippet": "Also mentions token static-token-abc123, but less relevant.", "score": 0.91, "lang": "en"}, {"id": "doc-noise", "title": "General productivity", "url": "https://kb.example/noise", "snippet": "Time-blocking article.", "score": 0.44, "lang": "en"}], "total": 4, "returned": 4, "error": ""}
```
`required-token.txt` content:
```
static-token-abc123
```
The required token is `static-token-abc123`.
I need to iterate through `results` in `search-response.json`, check if the `snippet` contains the required token, and keep track of the one with the maximum `score`.
The candidates are:
1. `doc-intro`: Snippet does not contain the token.
2. `doc-static-top`: Snippet contains the token. Score: 0.98.
3. `doc-static-alt`: Snippet contains the token. Score: 0.91.
4. `doc-noise`: Snippet does not contain the token.
The highest scoring item containing the token is `doc-static-top` (Score: 0.98).
The output JSON structure must be:
```json
{
"query": "weekly plan static fixture checkbox",
"selected_id": "doc-static-top",
"selected_url": "https://kb.example/static-top",
"selected_score": 0.98
}
```
Since I am operating in a shell environment, I will use a combination of `cat`, `grep`, `jq`, and potentially `awk` or a scripting language like Python/Perl if the logic gets too complex for pure shell tools, but given the structure, a single script execution using `jq` and shell logic should suffice.
I will use `jq` to read the JSON, and then use shell logic to process the results.
Step 1: Read the required token.
Step 2: Read the search response JSON.
Step 3: Filter and find the best match.
Step 4: Write the output JSON.
I will write a Python script to handle the JSON parsing and logic, as it is the most robust way to handle this complex data manipulation task within a shell context.
Let's assume the files are present and use Python via the shell tool.
</think>
</think>
<thinking>
<thinking>
The user wants me to process two files, `search-response.json` and `required-token.txt`, to find the best search result.
1. **Goal:** Select the item from `search-response.json`'s `results` array that has the highest score AND whose `snippet` contains the exact token read from `required-token.txt`.
2. **Output:** Write a specific JSON structure (`query`, `selected_id`, `selected_url`, `selected_score`) to `search-result.json`.
3. **Success/Failure:** Reply only `DONE` or `FAIL`.
I will use a Python script executed via the `shell` tool to handle the JSON parsing, string matching, and logic required.
**Plan:**
1. Read the required token from `required-token.txt`.
2. Read the search response JSON from `search-response.json`.
3. Write and execute a Python script that:
a. Parses the JSON.
b. Reads the token.
c. Iterates through results, filtering by token presence and tracking the maximum score.
d. Constructs the final JSON object and writes it to `search-result.json`.
4. If the script runs successfully and creates the file, I will conclude by replying `DONE`.
</thinking>
</thinking>
[gripprobe] process_finished_at=2026-04-26T06:33:17+00:00 exit_code=124 timeout=true
[gripprobe] process_started_at=2026-04-26T06:31:17+00:00 [gripprobe] process_finished_at=2026-04-26T06:33:17+00:00 exit_code=124 timeout=true
# Modelfile generated by "ollama show"
# To build a new Modelfile based on this, replace FROM with:
# FROM gemma4:e4b
FROM /usr/share/ollama/.ollama/models/blobs/sha256-4c27e0f5b5adf02ac956c7322bd2ee7636fe3f45a8512c9aba5385242cb6e09a
TEMPLATE {{ .Prompt }}
RENDERER gemma4
PARSER gemma4
PARAMETER temperature 1
PARAMETER top_k 64
PARAMETER top_p 0.95
LICENSE """ Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License."""