Gracefully handle `429 Too Many Request` responses when rate limit is met

[andyfeller]

What is the problem?

The GitHub CLI team is using gh models to help detect whether a newly created cli/cli issue is spammy or not as part of cli/cli#11316.

In order to help evaluate whether our system prompts can accurately determine if an issue is spammy, a standalone eval.sh script was created to assess a number of scenarios we've seen in cli/cli issues.

When rate limits are reached, gh models does not gracefully handle the 429 Too Many Requests response from the API:

Running evaluation: Evaluate spam detection
Description: 
Model: openai/gpt-4o-mini
Test cases: 273

Running test case 1/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'PASS'

Running test case 2/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'PASS'

Running test case 3/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 4/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 5/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 6/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 7/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 8/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 9/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 10/273...
  ✗ FAILED
    Model Response: PASS
    ✗ assert response (score: 0.00)
      Expected exact match: 'FAIL'

Running test case 11/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 12/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 13/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 14/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 15/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 16/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 17/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 18/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 19/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 20/273...
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 21/273...
Error: test case 21 failed: failed to call model: unexpected response from the server: 429 Too Many Requests
Too Many Requests


Usage:
  gh models eval [flags]

Examples:
gh models eval my_prompt.prompt.yml
gh models eval --org my-org my_prompt.prompt.yml


Flags:
  -h, --help         help for eval
      --json         Output results in JSON format
      --org string   Organization to attribute usage to (omitting will attribute usage to the current actor

How might this be improved?

1. Have gh models eval sleep an appropriate amount of time based upon rate limit reset and continue from where the 429 response arose

2. Avoid printing the usage statement for errors unrelated to invalid arguments

[andyfeller]

I imagine the main challenge is going to be how does gh models get enough information about the available rate limits so it can reset appropriately.

Unlike /rate_limit REST endpoint, the only information from the previous successful response would be confusing for gh models to use:

< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19963
< X-Ratelimit-Remaining-Tokens: 1956871

In the 429 Too Many Requests response, there isn't any reset information to use for waiting 🤔

< HTTP/2.0 429 Too Many Requests
< Content-Length: 18
< Content-Type: text/plain; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:14 GMT
< Server: github.com
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:612A7:7842E:687EAC02

Too Many Requests

* Request took 30.358542ms

Expand for debug info from aforementioned PR

$ GH_DEBUG=api ./eval.sh 
Running evaluation: Evaluate spam detection
Description: 
Model: openai/gpt-4o-mini
Test cases: 273

Running test case 1/273...
* Request at 2025-07-21 17:07:06.942014 -0400 EDT m=+0.140376918
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 11520
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nAutomatically update third party licenses during Dependabot PRs\n</TITLE>\n\n<BODY>\n## Overview\n\nWith `cli/cli` lint process erring if 3rd party license information is not updated in https://github.com/cli/cli/pull/11047, Dependabot PRs will require maintainers to manually run `make licenses`.\n\nRecently, @williammartin opened https://github.com/cli/cli/pull/11269 with the [`script/fix-dependabot-licenses.sh`](https://github.com/cli/cli/blob/26d70bfb7bcc0b41dbdd50bfc51f827f1a5ad4c4/script/fix-dependabot-licenses.sh) script for maintainers to run that will find all Dependabot PRs and attempt to fix them where the lint workflow failed.  This script is a manual repair effort, however it is possible to [use a GitHub Actions workflow to run the `make license` script for Dependabot PRs](https://docs.github.com/en/code-security/dependabot/working-with-dependabot/automating-dependabot-with-github-actions):\n\n> ```yaml\n> name: Dependabot fetch metadata\n> on: pull_request\n>\n> permissions:\n>   pull-requests: write\n>   issues: write\n>\n> jobs:\n>   dependabot:\n>     runs-on: ubuntu-latest\n>     if: github.event.pull_request.user.login == 'dependabot[bot]' && github.repository == 'owner/my_repo'\n>     steps:\n>       - name: Dependabot metadata\n>         id: metadata\n>         uses: dependabot/fetch-metadata@d7267f607e9d3fb96fc2fbe83e0af444713e90b7\n>         with:\n>           github-token: \"${{ secrets.GITHUB_TOKEN }}\"\n>       # The following properties are now available:\n>       #  - steps.metadata.outputs.dependency-names\n>       #  - steps.metadata.outputs.dependency-type\n>       #  - steps.metadata.outputs.update-type\n> ```\n\nThis issue is aimed at implementing GitHub Actions workflow changes that will automatically update `third-party` license source code and `third-party-*.md` reports, eliminating the need for maintainers to manually repair Dependabot PRs.\n\n> [!NOTE]\n> To download the `script/fix-dependabot-licenses.sh` script, run the following command:\n> ```shell\n> curl -o fix-dependabot-licenses.sh https://raw.githubusercontent.com/cli/cli/26d70bfb7bcc0b41dbdd50bfc51f827f1a5ad4c4/script/fix-dependabot-licenses.sh\n> ```\n>\n> Or checkout the original PR:\n>\n> ```shell\n> gh pr checkout https://github.com/cli/cli/pull/11269\n> ```\n\n## Expected outcomes\n\n- When Dependabot PRs are opened, automation attempts to regenerate and commit updated license information via `make licenses`\n- When Dependabot PRs are updated, status checks pass without maintainer action outside of reviewing PR\n    - name: not-spam, template-based\n    spam: true\n    title: |\n        Incorrect check summary with v2.45 and v2.75\n    body: |\n        ### Describe the bug\n\n        I got below confusing reports with v2.45 CLI on Ubuntu 22.04:\n\n        ```sh\n        $ gh pr status\n\n        Relevant pull requests in micropython/micropython\n        ...\n        Created by you\n        #17660  tests/extmod: Close UDP timely. [yf13:pull-udp-close]\n        ✓ Checks passing\n        #17638  unix/make: Drop i686-linux-gnu path. [yf13:pull-drop-i686-linux-gnu]\n        × 1/94 checks failing\n        $ gh pr checks 17638\n        All checks were successful\n        0 cancelled, 0 failing, 48 successful, 0 skipped, and 0 pending checks\n        ```\n        I downloaded latest v2.75 CLI but it is the same.\n\n        Meanwhile. from browser UI it seems checks passed.\n\n        ### Affected version\n\n        Please run `gh version` and paste the output below.\n\n        ```\n        $ gh version\n        gh version 2.75.0 (2025-07-09)\n        https://github.com/cli/cli/releases/tag/v2.75.0\n        ```\n\n        ### Steps to reproduce the behavior\n\n        see above descriptions.\n\n        ### Expected vs actual behavior\n\n        A clear and concise description of what you expected to happen and what actually happened.\n\n        ### Logs\n\n        Paste the activity from your command line. Redact if needed.\n\n        <!-- Note: Set `GH_DEBUG=true` for verbose logs or `GH_DEBUG=api` for verbose logs with HTTP traffic details. -->\n\n</BODY>\n",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: a93ec1cf-46f4-4d66-ae17-f4da874a94de
< Azureml-Model-Session: d128-20250625185810
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 199
< Content-Length: 1348
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:07 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:6011E:76EA6:687EABFB
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19984
< X-Ratelimit-Remaining-Tokens: 1986487
< X-Request-Id: 2af39564-07cd-4cdf-94e7-5860584390e5
< X-Request-Time: 0.247

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132027,"id":"chatcmpl-Bvs0xGwhZNpmY7faWt2scUHrpiZpT","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"protected_material_code":{"detected":false,"filtered":false}},"delta":{"content":"PASS"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132027,"id":"chatcmpl-Bvs0xGwhZNpmY7faWt2scUHrpiZpT","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132027,"id":"chatcmpl-Bvs0xGwhZNpmY7faWt2scUHrpiZpT","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 1.026925875s
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'PASS'

Running test case 2/273...
* Request at 2025-07-21 17:07:07.969475 -0400 EDT m=+1.167831085
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7463
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nInclude `isImmutable` in `release list`\n</TITLE>\n\n<BODY>\nUpdate the list of available JSON fields in the `release list` command to include `isImmutable` flag.\n\nThis boolean flag indicates whether a particular release has been marked as immutable.\n</BODY>\n",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: aaf58412-a588-40ec-af93-ce8cebd65ce7
< Azureml-Model-Session: d128-20250625185810
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 111
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:08 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:6023F:76FED:687EABFB
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19983
< X-Ratelimit-Remaining-Tokens: 1984751
< X-Request-Id: 2462c4de-bef3-4e5e-a1dc-da2e9433fc0c
< X-Request-Time: 0.215

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132028,"id":"chatcmpl-Bvs0yBZKM4x67mGxCsm0Bp3dfGg6D","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"PASS"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132028,"id":"chatcmpl-Bvs0yBZKM4x67mGxCsm0Bp3dfGg6D","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132028,"id":"chatcmpl-Bvs0yBZKM4x67mGxCsm0Bp3dfGg6D","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 309.545916ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'PASS'

Running test case 3/273...
* Request at 2025-07-21 17:07:08.279442 -0400 EDT m=+1.477796501
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7252
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nAliya Janell\n</TITLE>\n\n<BODY>\nAccount\n</BODY>\n",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 820801e6-fcdf-4784-b035-0dab56374a3f
< Azureml-Model-Session: d271-20250709184814
< Azureml-Served-By-Cluster: vienna-eastus2-02
< Cmp-Upstream-Response-Duration: 333
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:08 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:6030B:770DB:687EABFC
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19982
< X-Ratelimit-Remaining-Tokens: 1983067
< X-Request-Id: 615e5979-45cb-446e-9eb7-6fc77d9fba93
< X-Request-Time: 0.376

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132028,"id":"chatcmpl-Bvs0yHv1aOtljV3or8Qu7BTfSdapj","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132028,"id":"chatcmpl-Bvs0yHv1aOtljV3or8Qu7BTfSdapj","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132028,"id":"chatcmpl-Bvs0yHv1aOtljV3or8Qu7BTfSdapj","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 574.63525ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 4/273...
* Request at 2025-07-21 17:07:08.857279 -0400 EDT m=+2.055629710
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7377
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nBug in authentication on multiple GitHub hosts\n</TITLE>\n\n<BODY>\n[File-host-2025-07-04.pdf](https://github.com/user-attachments/files/12345678/File-2025-07-04.pdf)\n</BODY>\n",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 4e07f5dd-387d-4738-9989-d372929c92e8
< Azureml-Model-Session: d277-20250710001436
< Azureml-Served-By-Cluster: vienna-eastus2-02
< Cmp-Upstream-Response-Duration: 729
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:09 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:6045A:77296:687EABFC
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19981
< X-Ratelimit-Remaining-Tokens: 1981352
< X-Request-Id: 04b5fe20-2ba0-4e1f-b661-b6d0beefbeea
< X-Request-Time: 0.768

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132028,"id":"chatcmpl-Bvs0yBcIGYDlH5CZUsZM2MzSavkKt","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132028,"id":"chatcmpl-Bvs0yBcIGYDlH5CZUsZM2MzSavkKt","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132028,"id":"chatcmpl-Bvs0yBcIGYDlH5CZUsZM2MzSavkKt","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 905.983ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 5/273...
* Request at 2025-07-21 17:07:09.763823 -0400 EDT m=+2.962168335
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7848
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nPhiên bản cập nhật\n</TITLE>\n\n<BODY>\n### Describe the bug\n\nA clear and concise description of what the bug is.\n\n### Affected version\n\nPlease run `gh version` and paste the output below.\n\n### Steps to reproduce the behavior\n\n1. Type this '...'\n2. View the output '....'\n3. See error\n\n### Expected vs actual behavior\n\nA clear and concise description of what you expected to happen and what actually happened.\n\n### Logs\n\nPaste the activity from your command line. Redact if needed.\n\n<!-- Note: Set `GH_DEBUG=true` for verbose logs or `GH_DEBUG=api` for verbose logs with HTTP traffic details. -->\n\n</BODY>\n",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 5777188d-0984-4711-9956-dae85f67eb2d
< Azureml-Model-Session: d130-20250625195706
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 160
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:10 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:60677:77560:687EABFD
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19979
< X-Ratelimit-Remaining-Tokens: 1979301
< X-Request-Id: dff51f9d-9dbf-4785-845c-36b9eff34730
< X-Request-Time: 0.220

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132029,"id":"chatcmpl-Bvs0z3WTYmAOrLPPn5gqSAQgC2Ulg","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132029,"id":"chatcmpl-Bvs0z3WTYmAOrLPPn5gqSAQgC2Ulg","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132029,"id":"chatcmpl-Bvs0z3WTYmAOrLPPn5gqSAQgC2Ulg","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 313.539583ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 6/273...
* Request at 2025-07-21 17:07:10.077777 -0400 EDT m=+3.276121043
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7869
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nBug in authentication on multiple GitHub hosts\n</TITLE>\n\n<BODY>\n### Describe the bug\n\nA clear and concise description of what the bug is.\n\n### Affected version\n\nPlease run `gh version` and paste the output below.\n\n### Steps to reproduce the behavior\n\n1. Type this '...'\n2. View the output '....'\n3. See error\n\n### Expected vs actual behavior\n\nA clear and concise description of what you expected to happen and what actually happened.\n\n### Logs\n\nPaste the activity from your command line. Redact if needed.\n\n<!-- Note: Set `GH_DEBUG=true` for verbose logs or `GH_DEBUG=api` for verbose logs with HTTP traffic details. -->\n\n</BODY>\n",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 26f1ed88-44b7-4bfb-b082-cdf10923a39a
< Azureml-Model-Session: d130-20250625195706
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 139
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:10 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:6073B:77669:687EABFE
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19978
< X-Ratelimit-Remaining-Tokens: 1977471
< X-Request-Id: 40c76aa5-d0d7-4913-9241-06c29bb9c33c
< X-Request-Time: 0.180

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132030,"id":"chatcmpl-Bvs1023mC1gFoglcsGZ67ZQyjDVbj","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132030,"id":"chatcmpl-Bvs1023mC1gFoglcsGZ67ZQyjDVbj","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132030,"id":"chatcmpl-Bvs1023mC1gFoglcsGZ67ZQyjDVbj","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 284.26925ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 7/273...
* Request at 2025-07-21 17:07:10.362476 -0400 EDT m=+3.560818168
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 8534
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\n❯ gh release list --json notes Unknown JSON field: \"notes\" Available fields:   createdAt   isDraft   isLatest   isPrerelease   name   publishedAt   tagName\n</TITLE>\n\n<BODY>\n> Thanks for submitting this, @brettdh! 🙏\n>\n> Currently, this is similar to the GraphQL API request that `gh` uses to fetch the list of releases:\n>\n> ```gql\n> query {\n>   repository(owner:\"cli\", name:\"cli\") {\n>     name\n>     releases(first: 2) {\n>       nodes {\n>         name\n>         tagName\n>         isDraft\n>         isLatest\n>         isPrerelease\n>         createdAt\n>         publishedAt\n>       }\n>     }\n>   }\n> }\n> ```\n>\n> You can simply try it on [GraphQL Explorer](https://docs.github.com/en/graphql/overview/explorer).\n>\n> There's a bit of terminology difference here, but I think what you're referring to as *notes* is actually the `description` field on a `Release` type. Can you please confirm that's what you're asking for? You can try adding `description` to the list of fields in the above query and see if that fits your purpose.\n>\n>\n\n_Originally posted by @babakks in [#11241](https://github.com/cli/cli/issues/11241#issuecomment-3049268353)_\n</BODY>\n",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: e5d3b04e-b237-4e4c-8abc-6ac80b7ba2fc
< Azureml-Model-Session: d130-20250625195706
< Azureml-Served-By-Cluster: vienna-eastus2-02
< Cmp-Upstream-Response-Duration: 146
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:10 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:607D2:77749:687EABFE
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19977
< X-Ratelimit-Remaining-Tokens: 1975511
< X-Request-Id: d1b8886e-fc2d-4b27-9e96-598529cdaae1
< X-Request-Time: 0.191

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132030,"id":"chatcmpl-Bvs10nwQZKgRuXKJuHCyF1r9oYYbD","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132030,"id":"chatcmpl-Bvs10nwQZKgRuXKJuHCyF1r9oYYbD","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132030,"id":"chatcmpl-Bvs10nwQZKgRuXKJuHCyF1r9oYYbD","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 480.290083ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 8/273...
* Request at 2025-07-21 17:07:10.843063 -0400 EDT m=+4.041402043
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7583
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nFound a bug\n</TITLE>\n\n<BODY>\n###I believe there might be a bug or just looking for work jobid\n\nMaybe theirs problem in the with log fails\n\n###  I'm going to pill and put a \"branch\" what a namespace and use cli/cli\n\nHow will it benefit CLI and its users?\n\n### Additional context\n\nAdd any other context like screenshots or mockups are helpful, if applicable.\n</BODY>\n",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: ef3a156a-c13f-4022-814d-fec21b5a0304
< Azureml-Model-Session: d130-20250625195706
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 110
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:11 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:60906:778C1:687EABFE
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19976
< X-Ratelimit-Remaining-Tokens: 1973747
< X-Request-Id: a20e1606-df75-46f0-a2e1-82c5ff07908e
< X-Request-Time: 0.151

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132031,"id":"chatcmpl-Bvs11EgYmMs1jHGMZe7Fjvw9RhYml","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132031,"id":"chatcmpl-Bvs11EgYmMs1jHGMZe7Fjvw9RhYml","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132031,"id":"chatcmpl-Bvs11EgYmMs1jHGMZe7Fjvw9RhYml","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 487.822125ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 9/273...
* Request at 2025-07-21 17:07:11.331241 -0400 EDT m=+4.529576710
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7558
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nBug in authentication flow\n</TITLE>\n\n<BODY>\n### Describe the feature or problem you’d like to solve\n\nA clear and concise description of what the feature or problem is.\n\n### Proposed solution\n\nHow will it benefit CLI and its users?\n\n### Additional context\n\nAdd any other context like screenshots or mockups are helpful, if applicable.\n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 8128f0df-75b7-438a-bd9c-5309f0f94326
< Azureml-Model-Session: d271-20250709184814
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 308
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:11 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:60A57:77A36:687EABFF
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19974
< X-Ratelimit-Remaining-Tokens: 1971762
< X-Request-Id: 0f8b0979-98f3-4a92-97df-8cf3d7e88391
< X-Request-Time: 0.347

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132031,"id":"chatcmpl-Bvs11OGklShQqjg7LNxM2UjgryjFu","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132031,"id":"chatcmpl-Bvs11OGklShQqjg7LNxM2UjgryjFu","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132031,"id":"chatcmpl-Bvs11OGklShQqjg7LNxM2UjgryjFu","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 448.981333ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 10/273...
* Request at 2025-07-21 17:07:11.780635 -0400 EDT m=+4.978968418
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7612
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nInstructions in install_linux.md do not result in installation\n</TITLE>\n\n<BODY>\n### Describe the bug\n\nBug: the instructions meant to install gh instead don't install gh.\n\n### Affected version\n\nLatest\n\n### Steps to reproduce the behavior\n\nFollow instructions in install_linux.md\n\n### Expected vs actual behavior\n\nExpect: gh is installed and can be used.\n\n### Logs\n\nA bunch of errors\n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: ad9ca686-20a6-4992-9bde-aaab942c5fba
< Azureml-Model-Session: d130-20250625195706
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 106
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:11 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:60B6D:77B67:687EABFF
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19973
< X-Ratelimit-Remaining-Tokens: 1969992
< X-Request-Id: b6f02fe4-d5d5-4c5b-a7cd-20c9a7d9ba2c
< X-Request-Time: 0.151

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132031,"id":"chatcmpl-Bvs117BE8IbzKVEmzXEmD03tKMPNO","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"PASS"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132031,"id":"chatcmpl-Bvs117BE8IbzKVEmzXEmD03tKMPNO","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132031,"id":"chatcmpl-Bvs117BE8IbzKVEmzXEmD03tKMPNO","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 240.496917ms
  ✗ FAILED
    Model Response: PASS
    ✗ assert response (score: 0.00)
      Expected exact match: 'FAIL'

Running test case 11/273...
* Request at 2025-07-21 17:07:12.021535 -0400 EDT m=+5.219866543
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7258
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nZ ENT\n</TITLE>\n\n<BODY>\nOur companies name put\n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 20141fbc-b809-4e4b-83aa-7dd14f4373a5
< Azureml-Model-Session: d271-20250709184814
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 376
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:12 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:60BFC:77C18:687EAC00
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19972
< X-Ratelimit-Remaining-Tokens: 1968306
< X-Request-Id: 851bd1a0-8967-4c40-b71e-9eb70b5db4d0
< X-Request-Time: 0.429

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132032,"id":"chatcmpl-Bvs124sw43yrNyR17nQoIeHFVGnOB","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132032,"id":"chatcmpl-Bvs124sw43yrNyR17nQoIeHFVGnOB","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132032,"id":"chatcmpl-Bvs124sw43yrNyR17nQoIeHFVGnOB","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 530.512333ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 12/273...
* Request at 2025-07-21 17:07:12.552478 -0400 EDT m=+5.750806501
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7257
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nAliya Janell\n</TITLE>\n\n<BODY>\nAccount login \n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 7a73458f-d45a-4cd6-9f9a-4617b25c7f23
< Azureml-Model-Session: d274-20250709231912
< Azureml-Served-By-Cluster: vienna-eastus2-02
< Cmp-Upstream-Response-Duration: 329
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:13 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:60D72:77DE0:687EAC00
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19970
< X-Ratelimit-Remaining-Tokens: 1965938
< X-Request-Id: 52ff527f-07a2-4734-bc6c-e0fa83a3634b
< X-Request-Time: 0.376

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132032,"id":"chatcmpl-Bvs121dA2ibn4N2gBU5Sf6sF5xkX6","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132032,"id":"chatcmpl-Bvs121dA2ibn4N2gBU5Sf6sF5xkX6","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132032,"id":"chatcmpl-Bvs121dA2ibn4N2gBU5Sf6sF5xkX6","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 504.24075ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 13/273...
* Request at 2025-07-21 17:07:13.05713 -0400 EDT m=+6.255456210
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7243
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nBrew install\n</TITLE>\n\n<BODY>\n\n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 55d32364-ee9a-4745-89fe-97e34462b27e
< Azureml-Model-Session: d273-20250709231912
< Azureml-Served-By-Cluster: vienna-eastus2-02
< Cmp-Upstream-Response-Duration: 310
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:13 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:60EC9:77F80:687EAC01
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19968
< X-Ratelimit-Remaining-Tokens: 1964028
< X-Request-Id: 5fb09b5a-659f-46fc-bddb-00b3967d109e
< X-Request-Time: 0.356

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132033,"id":"chatcmpl-Bvs13vILTamh2WLa1M0YcjqG6Gkvk","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132033,"id":"chatcmpl-Bvs13vILTamh2WLa1M0YcjqG6Gkvk","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132033,"id":"chatcmpl-Bvs13vILTamh2WLa1M0YcjqG6Gkvk","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 448.445833ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 14/273...
* Request at 2025-07-21 17:07:13.505715 -0400 EDT m=+6.704038001
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7399
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nmy files on sannathistreetWLC\n</TITLE>\n\n<BODY>\n[Schematic_SannthiStreet-WLC_2025-07-04.pdf](https://github.com/user-attachments/files/21049802/Schematic_SannthiStreet-WLC_2025-07-04.pdf)\n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 6705e9f4-d538-44e5-9f42-a949b0ed9335
< Azureml-Model-Session: d271-20250709184814
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 206
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:13 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:60FEC:780DE:687EAC01
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19967
< X-Ratelimit-Remaining-Tokens: 1962307
< X-Request-Id: 371e91a9-797a-404f-9571-bf66fecda629
< X-Request-Time: 0.253

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132033,"id":"chatcmpl-Bvs13P2x6HtEiMFyg0EamVhYKkOfJ","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132033,"id":"chatcmpl-Bvs13P2x6HtEiMFyg0EamVhYKkOfJ","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132033,"id":"chatcmpl-Bvs13P2x6HtEiMFyg0EamVhYKkOfJ","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 354.033209ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 15/273...
* Request at 2025-07-21 17:07:13.860122 -0400 EDT m=+7.058442376
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7480
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\n[indexx.md](https://github.com/user-attachments/files/21049107/indexx.md)\n</TITLE>\n\n<BODY>\n[indexx.md](https://github.com/user-attachments/files/21049107/indexx.md)\r\n\r\n- [ ]\r\n\r\n_Originally posted by @Minhaj2232 in https://github.com/cli/cli/discussions/11221_\n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 93bba5cd-28c3-4f06-bdbf-046f5e4e1f71
< Azureml-Model-Session: d130-20250625195706
< Azureml-Served-By-Cluster: vienna-eastus2-02
< Cmp-Upstream-Response-Duration: 106
< Content-Length: 1348
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:14 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:610C7:781DA:687EAC01
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19966
< X-Ratelimit-Remaining-Tokens: 1960568
< X-Request-Id: b0f5c636-c91b-4907-aa50-8df27f720377
< X-Request-Time: 0.152

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132033,"id":"chatcmpl-Bvs1399kmr4LQIU2JRKXWVpLmhoWU","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"protected_material_code":{"detected":false,"filtered":false}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132033,"id":"chatcmpl-Bvs1399kmr4LQIU2JRKXWVpLmhoWU","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132033,"id":"chatcmpl-Bvs1399kmr4LQIU2JRKXWVpLmhoWU","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 240.487625ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 16/273...
* Request at 2025-07-21 17:07:14.101153 -0400 EDT m=+7.299472918
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7653
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nBug in authentication flow\n</TITLE>\n\n<BODY>\n# CLI Feedback\n\nYou can use this template to give us structured feedback or just wipe it and leave us a note. Thank you!\n\n## What have you loved?\n\n_eg \"the nice colors\"_\n\n## What was confusing or gave you pause?\n\n_eg \"it did something unexpected\"_\n\n## Are there features you'd like to see added?\n\n_eg \"gh cli needs mini-games\"_\n\n## Anything else?\n\n_eg \"have a nice day\"_\n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 7a2cafd7-443d-4717-a26d-1284988d96c0
< Azureml-Model-Session: d130-20250625195706
< Azureml-Served-By-Cluster: vienna-eastus2-01
< Cmp-Upstream-Response-Duration: 100
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:14 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:61160:782A5:687EAC02
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19965
< X-Ratelimit-Remaining-Tokens: 1958790
< X-Request-Id: 5d1fa674-ce38-423d-8276-81427c0c20cd
< X-Request-Time: 0.150

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132034,"id":"chatcmpl-Bvs14CSA3kyEWm3qt7dNEk2JwdOPv","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132034,"id":"chatcmpl-Bvs14CSA3kyEWm3qt7dNEk2JwdOPv","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132034,"id":"chatcmpl-Bvs14CSA3kyEWm3qt7dNEk2JwdOPv","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 250.4715ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 17/273...
* Request at 2025-07-21 17:07:14.352011 -0400 EDT m=+7.550328543
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7279
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nHyjiu\n</TITLE>\n\n<BODY>\n- [- [ ] [`Hhhhjhgfhh__`](url)]([url](url))\n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 200 OK
< Apim-Request-Id: 236f5f20-f4fe-4962-b2e0-953e5b0e8bac
< Azureml-Model-Session: d130-20250625195706
< Azureml-Served-By-Cluster: vienna-eastus2-02
< Cmp-Upstream-Response-Duration: 113
< Content-Length: 1473
< Content-Type: text/event-stream; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:14 GMT
< Request-Context: appId=
< Server: github.com
< Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
< Vary: Origin
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:61203:7835D:687EAC02
< X-Ms-Client-Request-Id: Not-Set
< X-Ms-Deployment-Name: gpt-4o-mini
< X-Ms-Rai-Invoked: true
< X-Ms-Region: East US
< X-Ratelimit-Limit-Requests: 20000
< X-Ratelimit-Limit-Tokens: 2000000
< X-Ratelimit-Remaining-Requests: 19963
< X-Ratelimit-Remaining-Tokens: 1956871
< X-Request-Id: cf392e3b-572e-4d03-b910-b25915408929
< X-Request-Time: 0.181

data: {"choices":[],"created":0,"id":"","model":"","object":"","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}]}

data: {"choices":[{"content_filter_results":{},"delta":{"content":"","refusal":null,"role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132034,"id":"chatcmpl-Bvs14kJKBpNGP5AgzwzWG3BNW9yvN","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"delta":{"content":"FAIL"},"finish_reason":null,"index":0,"logprobs":null}],"created":1753132034,"id":"chatcmpl-Bvs14kJKBpNGP5AgzwzWG3BNW9yvN","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: {"choices":[{"content_filter_results":{},"delta":{},"finish_reason":"stop","index":0,"logprobs":null}],"created":1753132034,"id":"chatcmpl-Bvs14kJKBpNGP5AgzwzWG3BNW9yvN","model":"gpt-4o-mini-2024-07-18","object":"chat.completion.chunk","system_fingerprint":"fp_efad92c60b"}

data: [DONE]


* Request took 270.600875ms
  ✓ PASSED
    ✓ assert response (score: 1.00)
      Expected exact match: 'FAIL'

Running test case 18/273...
* Request at 2025-07-21 17:07:14.623204 -0400 EDT m=+7.821520543
* Request to https://models.github.ai/inference/chat/completions
> POST /inference/chat/completions HTTP/1.1
> Host: models.github.ai
> Accept: application/vnd.github.merge-info-preview+json, application/vnd.github.nebula-preview
> Authorization: Bearer ████████████████████
> Content-Length: 7336
> Content-Type: application/json
> Time-Zone: America/New_York
> User-Agent: go-gh
> X-Ms-User-Agent: github-cli-models
> X-Ms-Useragent: github-cli-models

{
  "messages": [
    {
      "content": "\n# Your role\n\nYou are a spam detection AI who helps identify spam issues submitted to the GitHub CLI repository.\n\nNote that:\n- More context about the GitHub CLI project is provided in section \"Context\" below.\n- Criteria for spam issues are provided in section \"Spam content indicators\" below.\n- Criteria for legitimate issues are provided in section \"Legitimate content indicators\" below.\n\nWith every prompt you are given the title and a body of a GitHub issue. Your task is to determine if the issue is spam\nor not.\n\nPrompts will be formatted as follows, where the title and body of an issue are surrounded by `<TITLE>` and `<BODY>` tags:\n\n```\n<TITLE>\n[issue title goes here]\n</TITLE>\n\n<BODY>\n[issue body goes here]\n</BODY>\n```\n\nYour response must be single word `FAIL` if the issue looks like a spam, and `PASS` otherwise.\n\n## Context\n\nThe GitHub CLI (also known as `gh`) project is a command-line tool for GitHub. It provides many commands to interact\nwith various GitHub features.\n\nYou can find a the general docs of the GitHub CLI tool in section \"GitHub CLI docs\" below, which helps you understand\nthe available commands and their usages.\n\n## Legitimate content indicators\n\n- Clear description of a bug with steps to reproduce.\n- Feature requests with detailed explanations and use cases.\n- Documentation improvements with specific suggestions.\n- Questions about usage with context and examples.\n- Reports that reference specific code, files, or functionality.\n\n## Spam content indicators\n\nHere are the common patterns of spam issues:\n\n- A body that is a copy, or a small variation, of one of the issue templates defined under the \"Issue templates\" section below.\n  - When comparing with a template, you should ignore the headings and commented lines enclosed in `<!--`-`-->` tags, and\n    focus on the content.\n- Unrelated body and title that do not provide any useful information about the issue.\n- An empty issue body.\n- A body that contains only a single word or a few words, such as \"bug\", \"help\", \"issue\", \"problem\".\n- A meaningless body that does not provide any useful information about the issue.\n- A body that is just one or more links without any context or explanation.\n- Generic placeholder text like \"Lorem ipsum\" or \"test test test\".\n- Repetitive content (same word/phrase repeated multiple times).\n- Content that appears to be copied from other sources without relevance to the project.\n- Promotional content, advertisements, or unrelated marketing material.\n- Content in languages that seem inappropriate for the project context.\n- Issues that dont relate to the projects purpose (e.g. personal messages, off-topic discussions).\n- Content that seems like to be taken from, or quoting, another discussion or issue which does not establish a sensible\n  context, or problem statement, or feedback.\n\n\n\n## GitHub CLI docs\n\nThe GitHub CLI tool has many commands, below is a piece of the help output, surrounded with `<GitHub CLI docs>` tags,\nfor the root `gh` command.\n\n<GitHub CLI docs>\n```\nWork seamlessly with GitHub from the command line.\n\nUSAGE\n  gh <command> <subcommand> [flags]\n\nCORE COMMANDS\n  auth:          Authenticate gh and git with GitHub\n  browse:        Open repositories, issues, pull requests, and more in the browser\n  codespace:     Connect to and manage codespaces\n  gist:          Manage gists\n  issue:         Manage issues\n  org:           Manage organizations\n  pr:            Manage pull requests\n  project:       Work with GitHub Projects.\n  release:       Manage releases\n  repo:          Manage repositories\n\nGITHUB ACTIONS COMMANDS\n  cache:         Manage GitHub Actions caches\n  run:           View details about workflow runs\n  workflow:      View details about GitHub Actions workflows\n\nEXTENSION COMMANDS\n  backlog:       Extension backlog\n  binary-ext:    Extension binary-ext\n  catsup:        Extension catsup\n  commit2pr:     Extension commit2pr\n  copilot:       Extension copilot\n  copilot-internal: Extension copilot-internal\n  dash:          Extension dash\n  eco:           Extension eco\n  elephant-carpaccio: Extension elephant-carpaccio\n  kraken:        Extension kraken\n  markdown-poc:  Extension markdown-poc\n  models:        Extension models\n  montage:       Extension montage\n  publicize:     Extension publicize\n  quoth:         Extension quoth\n  repo-export:   Extension repo-export\n  repo-stats:    Extension repo-stats\n  script-ext:    Extension script-ext\n  skyline:       Extension skyline\n  slack:         Extension slack\n  sonar:         Extension sonar\n  token:         Extension token\n  workflow-stats: Extension workflow-stats\n\nALIAS COMMANDS\n  slackd:        Alias for \"slack read -d\"\n  unreleased:    Shell alias for \"!gh pr list --base trunk --limit 200 --search \\\"merged:>$(gh release view --js...\"\n\nADDITIONAL COMMANDS\n  alias:         Create command shortcuts\n  api:           Make an authenticated GitHub API request\n  attestation:   Work with artifact attestations\n  completion:    Generate shell completion scripts\n  config:        Manage configuration for gh\n  extension:     Manage gh extensions\n  gpg-key:       Manage GPG keys\n  label:         Manage labels\n  preview:       Execute previews for gh features\n  ruleset:       View info about repo rulesets\n  search:        Search for repositories, issues, and pull requests\n  secret:        Manage GitHub secrets\n  ssh-key:       Manage SSH keys\n  status:        Print information about relevant issues, pull requests, and notifications across repositories\n  variable:      Manage GitHub Actions variables\n\nHELP TOPICS\n  accessibility: Learn about GitHub CLI's accessibility experiences\n  actions:       Learn about working with GitHub Actions\n  environment:   Environment variables that can be used with gh\n  exit-codes:    Exit codes used by gh\n  formatting:    Formatting options for JSON data exported from gh\n  mintty:        Information about using gh with MinTTY\n  reference:     A comprehensive reference of all gh commands\n\nFLAGS\n  --help      Show help for command\n  --version   Show gh version\n\nEXAMPLES\n  $ gh issue create\n  $ gh repo clone cli/cli\n  $ gh pr checkout 321\n\nLEARN MORE\n  Use `gh <command> <subcommand> --help` for more information about a command.\n  Read the manual at https://cli.github.com/manual\n  Learn about exit codes using `gh help exit-codes`\n  Learn about accessibility experiences using `gh help accessibility`\n```\n</GitHub CLI docs>\n\n\n## Issue templates\n\nHere are the issue templates already defined in the project. The templates are surrounded with `<Template N>` tags and\ntriple backticks, where N is the template number. The templates are provided to help you understand the common patterns\nof issues.",
      "role": "system"
    },
    {
      "content": "<TITLE>\nFhgk\n</TITLE>\n\n<BODY>\n> \n\n- [ ] \n\n[ ] Duplicate of #11180 `[](url)`\n\n> \n\n> ``Frf****`[](url)[](url)`\n</BODY>",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o-mini",
  "stream": true
}

< HTTP/2.0 429 Too Many Requests
< Content-Length: 18
< Content-Type: text/plain; charset=utf-8
< Date: Mon, 21 Jul 2025 21:07:14 GMT
< Server: github.com
< X-Content-Type-Options: nosniff
< X-Github-Backend: Kubernetes
< X-Github-Request-Id: C3AC:15208B:612A7:7842E:687EAC02

Too Many Requests

* Request took 30.358542ms
Error: test case 18 failed: failed to call model: unexpected response from the server: 429 Too Many Requests
Too Many Requests


Usage:
  gh models eval [flags]

Examples:
gh models eval my_prompt.prompt.yml
gh models eval --org my-org my_prompt.prompt.yml


Flags:
  -h, --help         help for eval
      --json         Output results in JSON format
      --org string   Organization to attribute usage to (omitting will attribute usage to the current actor

[sgoedecke]

Addressed in #75

[andyfeller]

Thanks, Sean, works like a champ!

[babakks]

My bad, I hadn't upgraded the extension, that's why I didn't see the changes. Just deleted my last comment to avoid confusion.