[Docs] Added github action to auto-update the documentation of mcp-agent #301
Conversation
WalkthroughThis update introduces a new architectural documentation set for the Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Documentation Workflow
participant CodeBoarding Action
participant Repository
User->>Documentation Workflow: Trigger (scheduled or manual)
Documentation Workflow->>Repository: Checkout code
Documentation Workflow->>CodeBoarding Action: Generate/update docs & JSON
CodeBoarding Action->>Repository: Create/Update documentation files
Documentation Workflow->>Repository: Commit & open PR if changes detected
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Poem
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. 📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (1)
✅ Files skipped from review due to trivial changes (1)
✨ Finishing Touches🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![graphite-app[bot]](https://avatars.githubusercontent.com/in/158384?s=60&v=4){kind=small}
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 11
🧹 Nitpick comments (9)
.github/workflows/doc-updates.yml (1)
106-114: Trailing whitespace & missing EOF newlineLines 106 and 114 contain trailing spaces, and the file lacks a newline at EOF.
These break some linters (yamllint) – please trim and add the final newline.docs/codeboarding/on_boarding.mdx (1)
33-35: Strip trailing blank line inside<Info>blockThere is an extra empty line after the closing block that produces an orphan paragraph in some MDX renderers.
docs/docs.json (1)
67-76: Navigation entries rely on implicit extensionMintlify resolves pages without an extension, but the repo contains
.mdxfiles. If later converted to.md, the route will break. Consider adding the extension explicitly to future-proof the nav..codeboarding/Core_Application_Setup.json (1)
65-75: Typo: “Strategy Pattern” registry is mis-labelled
DecoratorRegistryis described as enabling the “Strategy Pattern”.
Decorators alter behaviour at definition time, while Strategy is a runtime interchangeable-object pattern. Consider rephrasing to avoid confusion.docs/codeboarding/Human_Interaction_Layer.mdx (1)
7-17: Inconsistent edge-label capitalisationGraph uses lowercase “uses” for some edges but capitalised “Uses” elsewhere in other docs. Stick to one style to avoid noisy diffs in generated SVGs.
.codeboarding/analysis.json (1)
10-18: Mixed absolute & relative paths – pick one conventionSome
reference_filefields are absolute, others repo-relative. This breaks path-based look-ups in doc websites and VS Code CodeTour.Adopt repository-relative paths everywhere (e.g.
src/mcp_agent/mcp/mcp_connection_manager.py).Also applies to: 28-36, 88-97
docs/codeboarding/Agent_Core_LLM_Integration.mdx (2)
7-18: Add accessible alternative text for the Mermaid diagramScreen-reader users will not benefit from the visual graph.
Consider adding a short textual summary (e.g. under the diagram or via an HTML<figcaption>) describing the relationships.
38-39: Tighten wording (“consistent manner” → “consistently”)The phrase “in a consistent manner” is wordy; “consistently” is clearer.
- ... interact with LLMs in a consistent manner, regardless ... + ... interact with LLMs consistently, regardless ...docs/codeboarding/Core_Application_Setup.mdx (1)
68-72: Missing article before “Signal Registry”Insert “the” for grammatical correctness.
- ### Signal Registry - Provides a mechanism for registering + ### Signal Registry + Provides **the** mechanism for registering
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (23)
.codeboarding/Agent_Core_LLM_Integration.json(1 hunks).codeboarding/Agent_Execution_Workflow_Engine.json(1 hunks).codeboarding/Agent_Workflow_Patterns.json(1 hunks).codeboarding/Core_Application_Setup.json(1 hunks).codeboarding/Human_Interaction_Layer.json(1 hunks).codeboarding/MCP_Service_Integration.json(1 hunks).codeboarding/analysis.json(1 hunks).codeboarding/codeboarding_version.json(1 hunks).github/workflows/doc-updates.yml(1 hunks)docs/codeboarding/Agent_Core_LLM_Integration.mdx(1 hunks)docs/codeboarding/Agent_Execution_Workflow_Engine.mdx(1 hunks)docs/codeboarding/Agent_Workflow_Patterns.mdx(1 hunks)docs/codeboarding/Core_Application_Setup.mdx(1 hunks)docs/codeboarding/Human_Interaction_Layer.mdx(1 hunks)docs/codeboarding/MCP_Service_Integration.mdx(1 hunks)docs/codeboarding/agent-workflow-framework.mdx(0 hunks)docs/codeboarding/core-orchestration-execution.mdx(0 hunks)docs/codeboarding/intent-interaction-management.mdx(0 hunks)docs/codeboarding/llm-external-tooling.mdx(0 hunks)docs/codeboarding/mcp-api-gateway.mdx(0 hunks)docs/codeboarding/on_boarding.mdx(1 hunks)docs/codeboarding/overview.mdx(0 hunks)docs/docs.json(1 hunks)
💤 Files with no reviewable changes (6)
- docs/codeboarding/overview.mdx
- docs/codeboarding/agent-workflow-framework.mdx
- docs/codeboarding/intent-interaction-management.mdx
- docs/codeboarding/core-orchestration-execution.mdx
- docs/codeboarding/mcp-api-gateway.mdx
- docs/codeboarding/llm-external-tooling.mdx
🧰 Additional context used
🧠 Learnings (15)
📓 Common learnings
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/**/mcp_agent.config.yaml : The configuration file mcp_agent.config.yaml must include all required RCM settings (quality_threshold, max_refinement_attempts, consolidation_interval, evaluator_model_provider, verbose_metrics).
docs/codeboarding/Human_Interaction_Layer.mdx (1)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
.codeboarding/analysis.json (2)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/**/mcp_agent.config.yaml : The configuration file mcp_agent.config.yaml must include all required RCM settings (quality_threshold, max_refinement_attempts, consolidation_interval, evaluator_model_provider, verbose_metrics).
.codeboarding/Human_Interaction_Layer.json (1)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
.codeboarding/Agent_Execution_Workflow_Engine.json (1)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
docs/codeboarding/Agent_Core_LLM_Integration.mdx (1)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
.codeboarding/Core_Application_Setup.json (2)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/**/mcp_agent.config.yaml : The configuration file mcp_agent.config.yaml must include all required RCM settings (quality_threshold, max_refinement_attempts, consolidation_interval, evaluator_model_provider, verbose_metrics).
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
docs/codeboarding/on_boarding.mdx (2)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/**/mcp_agent.config.yaml : The configuration file mcp_agent.config.yaml must include all required RCM settings (quality_threshold, max_refinement_attempts, consolidation_interval, evaluator_model_provider, verbose_metrics).
docs/codeboarding/MCP_Service_Integration.mdx (1)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
docs/codeboarding/Core_Application_Setup.mdx (2)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/**/mcp_agent.config.yaml : The configuration file mcp_agent.config.yaml must include all required RCM settings (quality_threshold, max_refinement_attempts, consolidation_interval, evaluator_model_provider, verbose_metrics).
docs/codeboarding/Agent_Execution_Workflow_Engine.mdx (1)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
.codeboarding/MCP_Service_Integration.json (2)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/**/mcp_agent.config.yaml : The configuration file mcp_agent.config.yaml must include all required RCM settings (quality_threshold, max_refinement_attempts, consolidation_interval, evaluator_model_provider, verbose_metrics).
docs/codeboarding/Agent_Workflow_Patterns.mdx (2)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/workflows/conversation_workflow.py : Implement conversation-as-workflow pattern: the entire conversation is a single workflow instance, not individual turns.
.codeboarding/Agent_Workflow_Patterns.json (1)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
.codeboarding/Agent_Core_LLM_Integration.json (2)
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/src/{tasks,workflows}/*.py : Use mcp-agent's Agent abstraction for ALL LLM interactions, including quality evaluation, to ensure consistent tool access, logging, and error handling.
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-06-30T17:58:30.949Z
Learning: Applies to examples/usecases/reliable_conversation/**/mcp_agent.config.yaml : The configuration file mcp_agent.config.yaml must include all required RCM settings (quality_threshold, max_refinement_attempts, consolidation_interval, evaluator_model_provider, verbose_metrics).
🪛 LanguageTool
docs/codeboarding/Agent_Core_LLM_Integration.mdx
[style] ~38-~38: Consider replacing this phrase with the adverb “consistently” to avoid wordiness.
Context: ... of the framework to interact with LLMs in a consistent manner, regardless of the underlying provider....
(IN_A_X_MANNER)
docs/codeboarding/on_boarding.mdx
[misspelling] ~87-~87: This word is normally spelled as one.
Context: ...w_Patterns) Implements various complex, multi-step agent behaviors and patterns. This incl...
(EN_COMPOUNDS_MULTI_STEP)
docs/codeboarding/Core_Application_Setup.mdx
[uncategorized] ~69-~69: You might be missing the article “the” here.
Context: ...r_registry.DecoratorRegistry` ### Signal Registry Provides a mechanism for regis...
(AI_EN_LECTOR_MISSING_DETERMINER_THE)
docs/codeboarding/Agent_Execution_Workflow_Engine.mdx
[misspelling] ~43-~43: This word is normally spelled as one.
Context: ...cture, state, and lifecycle of complex, multi-step processes. It provides the Workflow abs...
(EN_COMPOUNDS_MULTI_STEP)
docs/codeboarding/Agent_Workflow_Patterns.mdx
[misspelling] ~58-~58: This word is normally spelled as one.
Context: ...kflow Responsible for managing complex, multi-step agent behaviors. It defines how agents ...
(EN_COMPOUNDS_MULTI_STEP)
🪛 actionlint (1.7.7)
.github/workflows/doc-updates.yml
55-55: "github.head_ref" is potentially untrusted. avoid using it directly in inline scripts. instead, pass it through an environment variable. see https://docs.github.com/en/actions/security-for-github-actions/security-guides/security-hardening-for-github-actions for more details
(expression)
98-98: the runner of "peter-evans/create-pull-request@v5" action is too old to run on GitHub Actions. update the action's version to fix this issue
(action)
🪛 YAMLlint (1.37.1)
.github/workflows/doc-updates.yml
[error] 106-106: trailing spaces
(trailing-spaces)
[error] 114-114: trailing spaces
(trailing-spaces)
[error] 118-118: no new line character at the end of file
(new-line-at-end-of-file)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: checks / test
🔇 Additional comments (6)
.github/workflows/doc-updates.yml (1)
100-102:PAT_TOKENmay be unnecessary – favourGITHUB_TOKENif possibleBefore adding another secret with wide
reposcope, verify whether the built-inGITHUB_TOKEN(which already hascontents&pull-requests: writein this job) can author the PR. Minimising PAT usage reduces attack surface..codeboarding/MCP_Service_Integration.json (1)
24-25:reference_start_line/reference_end_lineset to0Zero implies “unknown” and breaks some tooling that expects valid ranges. If the exact span is unavailable, omit the keys or supply a sentinel like
null.Also applies to: 36-37, 48-49
.codeboarding/codeboarding_version.json (1)
1-4: Verify thatcommit_hashis updated by the workflowThis file will quickly drift if the workflow doesn’t rewrite it on every doc run. Confirm that
CodeBoarding-GHActionoverwrites the value; otherwise this metadata will become stale..codeboarding/Human_Interaction_Layer.json (1)
10-13: Placeholder line ranges (1-1) hinder source-jump toolingAll
reference_start_line/reference_end_linepairs are1. Either supply real spans or omit the keys; otherwise IDE deep-links open at top of file, defeating the point of the metadata.Also applies to: 21-25, 33-37, 45-49
docs/codeboarding/Agent_Workflow_Patterns.mdx (2)
7-25: Confirm that the Mermaid plugin is enabledThe file uses a ```mermaid fenced block. Ensure
@docusaurus/theme-mermaid(or equivalent) is installed and `markdown.mermaid: true` is set in `docusaurus.config.js`; otherwise the diagram will be rendered as plain text.
58-60: Spurious LanguageTool “multi-step” warning can be ignoredThe hyphenated form multi-step is grammatically correct and preferred in technical writing; no change required.
|
Hey @amr01060! I saw your comments, will take a look at them and get back to you asap. |
|
@amr01060 I fixed the linking. Let me know if there is something else :) |
1 participant
In this PR I have added the integration to auto-update the diagram docs for mcp-agent.
docs/codeboardingdirectoryScopes:
repo (full control of private repositories)
workflow
read:org, etc.
I was unsure if the GITHUB_TOKEN that you have has those so decided to do a new one, lmk if GITHUB_TOKEN has sufficient rights to create a PR - that is for what PAT_TOKEN is used :)
Summary by CodeRabbit
New Features
Documentation