ros-rolling-ros2ai (1.0.0-1resolute) resolute; urgency=high

  * Adjust verification.sh to the session mode. (#122 <https://github.com/fujitatomoya/ros2ai/issues/122>)
    ros2 ai without a request now starts the interactive session, so the
    verification blocked on the prompt. The interactive session is driven by
    the requests piped to the standard input instead, and the session file is
    isolated in a temporary directory so that the verification does not touch
    the session of the user. --continue and --trace are verified as well.
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * cosmetic documentation fixes.
  * Hide the trace of the tool calls by default, --trace prints it. (#120 <https://github.com/fujitatomoya/ros2ai/issues/120>) (#121 <https://github.com/fujitatomoya/ros2ai/issues/121>)
    The tool calls, the executed commands and their output are not printed
    unless -T / --trace is given (-v implies it). The commands that change
    the system, the failures and the documentation download are printed
    regardless. The system role tells the model that the user does not see
    the tool results, so that the answer is self-contained.
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * Align documentation with the current implementation. (#116 <https://github.com/fujitatomoya/ros2ai/issues/116>)
    * Align documentation with the current implementation.
    - README: ros2ai is released for every supported distribution, drop the
    unused ollama pip package, fix the PEP 668 link and add the command
    line options table.
    - Dockerfile: drop the unused ollama pip package.
    - Architecture diagram: add Anthropic, OpenAI compatible API and the
    ros2cli tool calling path.
    - overview: add the tool calling policy slide, remove the daemonized
    agent plan (#35 <https://github.com/fujitatomoya/ros2ai/issues/35>) and regenerate the html and pdf exports.
    Co-Authored-By: Claude Fable 5.1 <mailto:noreply@anthropic.com>
    * Drop the unused ollama pip package from the CI script as well.
    Co-Authored-By: Claude Fable 5.1 <mailto:noreply@anthropic.com>
    * Ground the answers on the ROS 2 documentation of the distribution. (#117 <https://github.com/fujitatomoya/ros2ai/issues/117>) (#118 <https://github.com/fujitatomoya/ros2ai/issues/118>)
    Add the documentation tools search_ros2_docs and read_ros2_docs that
    look up the official ROS 2 documentation of the running distribution.
    - The reStructuredText sources of the ROS_DISTRO branch of
    ros2/ros2_documentation are cached under ~/.cache/ros2ai/docs/<distro>
    (ROS2AI_DOCS_CACHE), only the pages are extracted from the branch
    archive, refreshed when older than a week, the lookup works offline.
    - search_ros2_docs scores the pages by the query terms in the title,
    the page name and the text (stem matching, density, phrase bonus) and
    returns the pages with their URL and a snippet.
    - read_ros2_docs returns the page text with the placeholders expanded,
    paged to fit the tool output limit, with the docs.ros.org URL.
    - The page content is only returned to the model (ToolResult.printable),
    the matched pages are printed under the tool call.
    - The system role asks to consult the documentation and to cite the page.
    - README: documentation lookup, ROS2AI_DOCS_CACHE, Ollama context length.
    - overview: documentation grounding slide, exports regenerated.
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
    ---------
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * Support session mode to keep the context of the requests. (#34 <https://github.com/fujitatomoya/ros2ai/issues/34>) (#115 <https://github.com/fujitatomoya/ros2ai/issues/115>)
    ros2 ai without a request starts the interactive session, and
    ros2 ai --continue "<request>" continues the previous session saved
    to the session file, so that the follow-up requests can refer to the
    previous ones. The conversation is kept on the client side and sent
    with every request, grouped by turns so that the tool calls are never
    separated from their results. The oldest turns are dropped beyond
    ROS2AI_CONTEXT_LIMIT, or when the endpoint reports that the context
    length is exceeded.
    closes #34 <https://github.com/fujitatomoya/ros2ai/issues/34>
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * Single entry point without sub-command: ros2 ai "<request>". (#112 <https://github.com/fujitatomoya/ros2ai/issues/112>)
    * Single entry point without sub-command: ros2 ai "<request>".
    ros2 ai no longer has sub-commands, the user passes the question or the
    operation request, and the model decides by itself whether to answer or to
    call the ROS 2 CLI tools via the agent loop.
    - query, exec and status verbs are removed, with the ros2ai.verb
    extension point.
    - --status (-s) and --list-models (-l) replace the status verb.
    - --verbose (-v) replaces both query -v and exec -d.
    - One default system role for both answering and operating the system.
    - When the endpoint or the model does not support tool calling, the model
    answers without tools, the single command fallback is removed.
    - ros2 ai -h prints usage examples, bare ros2 ai prints the help.
    closes #111 <https://github.com/fujitatomoya/ros2ai/issues/111>
    Co-Authored-By: Claude Fable 5.1 <mailto:noreply@anthropic.com>
    * Stream the completions in the agent loop. (#113 <https://github.com/fujitatomoya/ros2ai/issues/113>)
    The content is printed as it arrives, the tool call deltas are assembled
    by their index and executed when the stream ends, so that the answers to
    the questions are streamed as ros2 ai query did.
    - --nostream (-n) disables the streaming, the raw completions are
    printed with -nv only.
    - assemble_stream() tolerates endpoints that omit the tool call ids,
    reuse the index, or append usage chunks without choices.
    - The client prints the reason when the completion did not finish, in
    both streaming and non-streaming modes.
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
    ---------
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * Add composite tools get_node_status and get_topic_status. (#110 <https://github.com/fujitatomoya/ros2ai/issues/110>) (#114 <https://github.com/fujitatomoya/ros2ai/issues/114>)
    Some diagnostic questions ("is /talker healthy?") need the output of
    several ros2 commands at once. The model could chain the single command
    tools, at the cost of one completion per command and of the model deciding
    the sequence. Composite tools run a fixed sequence of read-only ros2
    commands in Python, behind the same ToolProvider interface, and return one
    YAML document of bounded size.
    - ros2ai/api/tools.py: CompositeTool and Executor interfaces,
    CompositeCommand resolved by the provider, the executor classifies every
    sub-command and refuses the ones beyond the policy of the composite tool
    (a read-only tool can not run a mutating command, nobody runs long-running
    commands). Ros2CliProvider.sample() runs commands such as ros2 topic hz
    in parallel for a window, interrupts them with SIGINT and captures the
    output (unbuffered, SIGKILL would lose it). Sub-commands are printed
    indented under the tool call, the argument validation gains integer ranges.
    - ros2ai/api/composite.py: get_node_status(node, window) with node info,
    lifecycle state (lifecycle nodes only), parameter names and the publishing
    rates of the published topics. get_topic_status(topic, window) with topic
    info, endpoints with QoS, publishing rate, a sample message and the QoS
    incompatibilities. Both report the warnings found and the available
    nodes/topics when the name is unknown, the model judges the health.
    - unit tests with a fake executor and outputs captured from Humble and
    Rolling, provider and verb tests for the composite path.
    - README: composite tools section with a transcript.
    Verified with scripts/github_workflows.sh on humble, jazzy, kilted, lyrical
    and rolling, and end-to-end with Ollama (qwen3.8:27b) on rolling and humble.
    Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
  * Operate ROS 2 system via tool calling with ROS 2 CLI tools. (#109 <https://github.com/fujitatomoya/ros2ai/issues/109>)
    ros2 ai exec no longer asks the model for a shell command line that is
    executed with shell=True. The model now calls ROS 2 CLI tools (function
    calling) through an agent loop, observes the output and iterates until the
    request is done. Every command is executed as an argument list without a
    shell, argv[0] is always ros2.
    - ros2ai/api/tools.py: ToolProvider interface and the Ros2CliProvider that
    maps the tools to the ros2 CLI (node, topic, service, action, param,
    interface, pkg, doctor, run, launch, plus a generic ros2_cli tool).
    Tools are classified as read-only (executed automatically), mutating
    (confirmation, -y/--yes skips) and long-running (confirmation, foreground).
    - ros2ai/api/agent.py: agent loop with maximum steps, tool output limit,
    errors returned to the model, --dry-run printing the command candidates
    that change the system.
    - ros2ai/api/client.py: tools support, tool_choice is left to auto.
    - fallback to the single command prompt when the endpoint or model does not
    support tool calling, still executed without a shell.
    - run_executable() never uses a shell anymore.
    - unit tests for tools, agent and the exec verb with fake client and ros2.
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * Support Anthropic API and generic ROS2AI_* configuration. (#108 <https://github.com/fujitatomoya/ros2ai/issues/108>)
    closes #105 <https://github.com/fujitatomoya/ros2ai/issues/105>
    - ROS2AI_API_KEY, ROS2AI_MODEL_NAME, ROS2AI_ENDPOINT, ROS2AI_TEMPERATURE and
    ROS2AI_ROLE_SYSTEM configure ros2ai agnostic from the LLM managed service.
    legacy OPENAI_* environment variables are still honored as fallback.
    - Anthropic API is supported via OpenAI SDK compatibility endpoint,
    x-api-key header is added for Anthropic so that /v1/models works.
    - user facing wording is agnostic from OpenAI (help, status messages).
    - README, overview slide deck (md/html/pdf), scripts are aligned.
    - verification.sh takes the endpoint and model from the environment.
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * Refactor implementation and add unit tests. (#107 <https://github.com/fujitatomoya/ros2ai/issues/107>)
    No change in capabilities, command line arguments, options or output.
    - split ros2ai/api/__init__.py into arguments.py, drop the curl based
    model listing in favor of the OpenAI python client (curl dependency removed).
    - rename ros2ai/api/openai.py to client.py, the client takes OpenAiConfig
    by composition instead of inheritance, and reports API call failures
    instead of crashing with a traceback afterwards.
    - ChatCompletionParameters becomes a dataclass, chat_messages() helper.
    - config.py: resolve_role_system() shares the role resolution of query/exec,
    dead set_value()/remove_key() removed, is_api_key_valid() folded into status.
    - utils.py: dead run_command() and unused parameters removed,
    extract_ros2_command() composes the command extraction for exec.
    - make the code base pass ament_flake8/pep257/copyright/xmllint.
    - add unit tests (utils, config, argument parsing, mocked verbs) and
    run colcon test in the github workflow for every distribution.
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * Remove Gemini CLI github workflows. (#104 <https://github.com/fujitatomoya/ros2ai/issues/104>)
    closes #103 <https://github.com/fujitatomoya/ros2ai/issues/103>
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * Support Lyrical Luth with docker image. (#102 <https://github.com/fujitatomoya/ros2ai/issues/102>)
    closes #93 <https://github.com/fujitatomoya/ros2ai/issues/93>
    Co-authored-by: Claude Fable 5.1 <mailto:noreply@anthropic.com>
  * 🛠️ Bump actions/create-github-app-token from 3.2.0 to 3.3.0 (#101 <https://github.com/fujitatomoya/ros2ai/issues/101>)
    Bumps [actions/create-github-app-token](https://github.com/actions/create-github-app-token) from 3.2.0 to 3.3.0.
    - [Release notes](https://github.com/actions/create-github-app-token/releases)
    - [Changelog](https://github.com/actions/create-github-app-token/blob/main/CHANGELOG.md)
    - [Commits](https://github.com/actions/create-github-app-token/compare/bcd2ba49218906704ab6c1aa796996da409d3eb1...64ab729a6294000f5aa4a4bc0b73d1f32bc45510)
    ---
    updated-dependencies:
    - dependency-name: actions/create-github-app-token
    dependency-version: 3.3.0
    dependency-type: direct:production
    update-type: version-update:semver-minor
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * 🛠️ Bump actions/stale from 10 to 11 (#100 <https://github.com/fujitatomoya/ros2ai/issues/100>)
    Bumps [actions/stale](https://github.com/actions/stale) from 10 to 11.
    - [Release notes](https://github.com/actions/stale/releases)
    - [Changelog](https://github.com/actions/stale/blob/main/CHANGELOG.md)
    - [Commits](https://github.com/actions/stale/compare/v10...v11)
    ---
    updated-dependencies:
    - dependency-name: actions/stale
    dependency-version: '11'
    dependency-type: direct:production
    update-type: version-update:semver-major
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * 🛠️ Bump actions/checkout from 7.0.0 to 7.0.1 (#99 <https://github.com/fujitatomoya/ros2ai/issues/99>)
    Bumps [actions/checkout](https://github.com/actions/checkout) from 7.0.0 to 7.0.1.
    - [Release notes](https://github.com/actions/checkout/releases)
    - [Commits](https://github.com/actions/checkout/compare/v7...v7.0.1)
    ---
    updated-dependencies:
    - dependency-name: actions/checkout
    dependency-version: 7.0.1
    dependency-type: direct:production
    update-type: version-update:semver-patch
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * 🛠️ Bump actions/setup-python from 6 to 7 (#98 <https://github.com/fujitatomoya/ros2ai/issues/98>)
    Bumps [actions/setup-python](https://github.com/actions/setup-python) from 6 to 7.
    - [Release notes](https://github.com/actions/setup-python/releases)
    - [Commits](https://github.com/actions/setup-python/compare/v6...v7)
    ---
    updated-dependencies:
    - dependency-name: actions/setup-python
    dependency-version: '7'
    dependency-type: direct:production
    update-type: version-update:semver-major
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * remove deprecated warnings from newer setuptools. (#97 <https://github.com/fujitatomoya/ros2ai/issues/97>)
  * fix rolling nightly build, that depends on statically ubuntu24.04. (#96 <https://github.com/fujitatomoya/ros2ai/issues/96>)
  * 🛠️ Bump actions/checkout from 6.0.3 to 7.0.0 (#94 <https://github.com/fujitatomoya/ros2ai/issues/94>)
    Bumps [actions/checkout](https://github.com/actions/checkout) from 6.0.3 to 7.0.0.
    - [Release notes](https://github.com/actions/checkout/releases)
    - [Commits](https://github.com/actions/checkout/compare/v6.0.3...v7)
    ---
    updated-dependencies:
    - dependency-name: actions/checkout
    dependency-version: 7.0.0
    dependency-type: direct:production
    update-type: version-update:semver-major
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * 🛠️ Bump actions/checkout from 6.0.2 to 6.0.3 (#92 <https://github.com/fujitatomoya/ros2ai/issues/92>)
    Bumps [actions/checkout](https://github.com/actions/checkout) from 6.0.2 to 6.0.3.
    - [Release notes](https://github.com/actions/checkout/releases)
    - [Commits](https://github.com/actions/checkout/compare/v6.0.2...v6.0.3)
    ---
    updated-dependencies:
    - dependency-name: actions/checkout
    dependency-version: 6.0.3
    dependency-type: direct:production
    update-type: version-update:semver-patch
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * 🛠️ Bump actions/create-github-app-token from 3.1.1 to 3.2.0 (#91 <https://github.com/fujitatomoya/ros2ai/issues/91>)
    Bumps [actions/create-github-app-token](https://github.com/actions/create-github-app-token) from 3.1.1 to 3.2.0.
    - [Release notes](https://github.com/actions/create-github-app-token/releases)
    - [Changelog](https://github.com/actions/create-github-app-token/blob/main/CHANGELOG.md)
    - [Commits](https://github.com/actions/create-github-app-token/compare/1b10c78c7865c340bc4f6099eb2f838309f1e8c3...bcd2ba49218906704ab6c1aa796996da409d3eb1)
    ---
    updated-dependencies:
    - dependency-name: actions/create-github-app-token
    dependency-version: 3.2.0
    dependency-type: direct:production
    update-type: version-update:semver-minor
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * 🛠️ Bump actions/create-github-app-token from 3.0.0 to 3.1.1 (#90 <https://github.com/fujitatomoya/ros2ai/issues/90>)
    Bumps [actions/create-github-app-token](https://github.com/actions/create-github-app-token) from 3.0.0 to 3.1.1.
    - [Release notes](https://github.com/actions/create-github-app-token/releases)
    - [Commits](https://github.com/actions/create-github-app-token/compare/f8d387b68d61c58ab83c6c016672934102569859...1b10c78c7865c340bc4f6099eb2f838309f1e8c3)
    ---
    updated-dependencies:
    - dependency-name: actions/create-github-app-token
    dependency-version: 3.1.1
    dependency-type: direct:production
    update-type: version-update:semver-minor
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
    Co-authored-by: Tomoya Fujita <tomoya.fujita825@gmail.com>
  * 🛠️ Bump actions/github-script from 8.0.0 to 9.0.0 (#89 <https://github.com/fujitatomoya/ros2ai/issues/89>)
    Bumps [actions/github-script](https://github.com/actions/github-script) from 8.0.0 to 9.0.0.
    - [Release notes](https://github.com/actions/github-script/releases)
    - [Commits](https://github.com/actions/github-script/compare/ed597411d8f924073f98dfc5c65a23a2325f34cd...3a2844b7e9c422d3c10d287c895573f7108da1b3)
    ---
    updated-dependencies:
    - dependency-name: actions/github-script
    dependency-version: 9.0.0
    dependency-type: direct:production
    update-type: version-update:semver-major
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * 🛠️ Bump actions/create-github-app-token from 2.2.1 to 3.0.0 (#88 <https://github.com/fujitatomoya/ros2ai/issues/88>)
    Bumps [actions/create-github-app-token](https://github.com/actions/create-github-app-token) from 2.2.1 to 3.0.0.
    - [Release notes](https://github.com/actions/create-github-app-token/releases)
    - [Commits](https://github.com/actions/create-github-app-token/compare/29824e69f54612133e76f7eaac726eef6c875baf...f8d387b68d61c58ab83c6c016672934102569859)
    ---
    updated-dependencies:
    - dependency-name: actions/create-github-app-token
    dependency-version: 3.0.0
    dependency-type: direct:production
    update-type: version-update:semver-major
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * 🛠️ Bump actions/checkout from 4.3.1 to 6.0.2 (#87 <https://github.com/fujitatomoya/ros2ai/issues/87>)
    Bumps [actions/checkout](https://github.com/actions/checkout) from 4.3.1 to 6.0.2.
    - [Release notes](https://github.com/actions/checkout/releases)
    - [Commits](https://github.com/actions/checkout/compare/v4.3.1...v6.0.2)
    ---
    updated-dependencies:
    - dependency-name: actions/checkout
    dependency-version: 6.0.2
    dependency-type: direct:production
    update-type: version-update:semver-major
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * 🛠️ Bump actions/github-script from 7.0.1 to 8.0.0 (#85 <https://github.com/fujitatomoya/ros2ai/issues/85>)
    Bumps [actions/github-script](https://github.com/actions/github-script) from 7.0.1 to 8.0.0.
    - [Release notes](https://github.com/actions/github-script/releases)
    - [Commits](https://github.com/actions/github-script/compare/60a0d83039c74a4aee543508d2ffcb1c3799cdea...ed597411d8f924073f98dfc5c65a23a2325f34cd)
    ---
    updated-dependencies:
    - dependency-name: actions/github-script
    dependency-version: 8.0.0
    dependency-type: direct:production
    update-type: version-update:semver-major
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
    Co-authored-by: Tomoya Fujita <tomoya.fujita825@gmail.com>
  * 🛠️ Bump actions/checkout from 3 to 6 (#84 <https://github.com/fujitatomoya/ros2ai/issues/84>)
    Bumps [actions/checkout](https://github.com/actions/checkout) from 3 to 6.
    - [Release notes](https://github.com/actions/checkout/releases)
    - [Commits](https://github.com/actions/checkout/compare/v3...v6)
    ---
    updated-dependencies:
    - dependency-name: actions/checkout
    dependency-version: '6'
    dependency-type: direct:production
    update-type: version-update:semver-major
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
    Co-authored-by: Tomoya Fujita <tomoya.fujita825@gmail.com>
  * 🛠️ Bump actions/setup-python from 5 to 6 (#83 <https://github.com/fujitatomoya/ros2ai/issues/83>)
    Bumps [actions/setup-python](https://github.com/actions/setup-python) from 5 to 6.
    - [Release notes](https://github.com/actions/setup-python/releases)
    - [Commits](https://github.com/actions/setup-python/compare/v5...v6)
    ---
    updated-dependencies:
    - dependency-name: actions/setup-python
    dependency-version: '6'
    dependency-type: direct:production
    update-type: version-update:semver-major
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
    Co-authored-by: Tomoya Fujita <tomoya.fujita825@gmail.com>
  * 🛠️ Bump actions/create-github-app-token from 2.1.1 to 2.2.1 (#86 <https://github.com/fujitatomoya/ros2ai/issues/86>)
    Bumps [actions/create-github-app-token](https://github.com/actions/create-github-app-token) from 2.1.1 to 2.2.1.
    - [Release notes](https://github.com/actions/create-github-app-token/releases)
    - [Commits](https://github.com/actions/create-github-app-token/compare/a8d616148505b5069dccd32f177bb87d7f39123b...29824e69f54612133e76f7eaac726eef6c875baf)
    ---
    updated-dependencies:
    - dependency-name: actions/create-github-app-token
    dependency-version: 2.2.1
    dependency-type: direct:production
    update-type: version-update:semver-minor
    ...
    Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
  * enable dependabot.yml. (#82 <https://github.com/fujitatomoya/ros2ai/issues/82>)
  * add binary package installation.
  * Upgrade github action/run-gemini-cli workflows. (#81 <https://github.com/fujitatomoya/ros2ai/issues/81>)
  * enable actions/stale to close issues and PRs. (#80 <https://github.com/fujitatomoya/ros2ai/issues/80>)
  * Contributors: Tomoya Fujita, Tomoya.Fujita, dependabot[bot]

 -- "Tomoya Fujita" <tomoya.fujita825@gmail.com>  Thu, 12 Nov 2026 15:00:00 -0000

ros-rolling-ros2ai (0.1.3-1resolute) resolute; urgency=high

  * remove Ollama dependency. (#78 <https://github.com/fujitatomoya/ros2ai/issues/78>)
  * Correct the name of a dependent package (#77 <https://github.com/fujitatomoya/ros2ai/issues/77>)

 -- "Tomoya Fujita" <tomoya.fujita825@gmail.com>  Thu, 11 Dec 2025 15:00:00 -0000

ros-rolling-ros2ai (0.1.2-1resolute) resolute; urgency=high

  * Use non-root user and group in default for Docker images. (#75 <https://github.com/fujitatomoya/ros2ai/issues/75>)
  * update overview slidedeck. (#73 <https://github.com/fujitatomoya/ros2ai/issues/73>)
  * make sure only single command starts with "ros2". (#68 <https://github.com/fujitatomoya/ros2ai/issues/68>)

 -- "Tomoya Fujita" <tomoya.fujita825@gmail.com>  Sun, 07 Dec 2025 15:00:00 -0000

ros-rolling-ros2ai (0.1.1-1resolute) resolute; urgency=high

  * Support Kilted Kaiju with docker image. (#67 <https://github.com/fujitatomoya/ros2ai/issues/67>)
  * change OPENAI_TEMPERATURE default into 1.0.
  * enable gemini-cli github action. (#64 <https://github.com/fujitatomoya/ros2ai/issues/64>)
  * support codespell check via github action. (#61 <https://github.com/fujitatomoya/ros2ai/issues/61>)
  * add nightly workflow files for each distro. (#57 <https://github.com/fujitatomoya/ros2ai/issues/57>)
  * remove Iron Irwini support, which is E.O.L. (#56 <https://github.com/fujitatomoya/ros2ai/issues/56>)
  * use 127.0.0.1 instead of localhost that is invalid URL by validator. (#53 <https://github.com/fujitatomoya/ros2ai/issues/53>)
  * Fix a typo in package.xml (#50 <https://github.com/fujitatomoya/ros2ai/issues/50>)
  * enable blank_issues_enabled.
  * update issue templates.
  * add issue templates. (#48 <https://github.com/fujitatomoya/ros2ai/issues/48>)
  * ROSCon 2024 talk slide (draft) (#44 <https://github.com/fujitatomoya/ros2ai/issues/44>)
  * github workflow status shows rolling branch.
  * add --net=host option to docker command for Ollama use case. (#46 <https://github.com/fujitatomoya/ros2ai/issues/46>)
  * 20240916 overview update (#43 <https://github.com/fujitatomoya/ros2ai/issues/43>)
  * pull llama3.1 before example tutorial.
  * add mirror-rolling-to-main.yaml.
  * add architecture overview.
  * Validate the URL before calling OpenAI APIs. (#42 <https://github.com/fujitatomoya/ros2ai/issues/42>)
  * Doc update for Ollama Support. (#40 <https://github.com/fujitatomoya/ros2ai/issues/40>)
  * remove backticks from the executable command line string.
  * adjust some parameters and variables for Ollama OpenAI support (#38 <https://github.com/fujitatomoya/ros2ai/issues/38>)
  * add --dry-run to the test script.
  * Enable the use of self-hosted LLMs (#36 <https://github.com/fujitatomoya/ros2ai/issues/36>)
    Co-authored-by: Tomoya Fujita <mailto:Tomoya.Fujita@sony.com>
  * joke sub-command is not gonna be developed.
  * Jazzy Jalisco support (#33 <https://github.com/fujitatomoya/ros2ai/issues/33>)
  * docker command should be checked before docker login.
  * some comment fixes with gpt-4o.
  * configure AI model with gpt-4o by default. (#32 <https://github.com/fujitatomoya/ros2ai/issues/32>)
  * add signal handler for SIGINT and SIGTERM. (#29 <https://github.com/fujitatomoya/ros2ai/issues/29>)
  * add --break-system-packages option to pip install.
  * fix openai rosdep (#27 <https://github.com/fujitatomoya/ros2ai/issues/27>)
  * minor script bug fix.
  * ROS distribution is always set with completion API.
  * add ROS Developers POdcast interview.
  * fetch ROS_DISTRO env value to set completion request. (#24 <https://github.com/fujitatomoya/ros2ai/issues/24>)
  * script bug fix.
  * add demo video with docker containers in marp.
  * add doc section for docker container support. (#20 <https://github.com/fujitatomoya/ros2ai/issues/20>)
  * fujitatomoya/support dockerfiles and test (#18 <https://github.com/fujitatomoya/ros2ai/issues/18>)
  * add workflows badges in the top page.
  * support github workflows with rolling distro. (#15 <https://github.com/fujitatomoya/ros2ai/issues/15>)
  * add overview slide deck on the top README.md
  * update package.xml
  * support temperature param for chat.completion.
  * add html version presentation slide deck.
  * update oveview markdown presentation.
  * add overview markdown presentation with proposals.
  * update README.md
  * support execute subcommand. (#9 <https://github.com/fujitatomoya/ros2ai/issues/9>)
  * add system attribution for query command.
  * change copyright into the correct one.
  * remove redundant class just for stream option.
  * support max token via command line option.
  * change default model into gpt-4 since it has better response time.
  * default streaming response.
  * support streaming responses. (#4 <https://github.com/fujitatomoya/ros2ai/issues/4>)
  * support list option for status subcommand to show models.
  * support query subcommand. (#1 <https://github.com/fujitatomoya/ros2ai/issues/1>)
  * add add_global_arguments method.
  * ros2ai status subcommand support.
  * add class OpenAiConfig.
  * command stub completed for ai and status command.
  * add config methods and constants.
  * add mock command line for ros2ci.
  * add basic ros2 package structure.
  * Initial commit
  * Contributors: Tomoya Fujita, Barry Xu, Jeremie Deray

 -- "Tomoya Fujita" <tomoya.fujita825@gmail.com>  Wed, 05 Nov 2025 15:00:00 -0000


