Add Context7 MCP documentation tool#23
Open
h4ksclaw wants to merge 2 commits into
Open
Conversation
Integrates context7.com API as a new agent tool (`context7`) that fetches real-time library/framework documentation. The agent can now look up current API docs for any programming library by name or topic. - New file: cloudbot/agent/tools/context7.py - Tool registered via @tool decorator in the agent registry - Returns structured markdown with code examples - Capped at 5 entries / 4000 chars to respect token budgets - Error-wrapped for resilience against API failures Resolves: add Context7 MCP integration for better library doc access
📝 WalkthroughWalkthroughThe PR updates the tool package initialization to enable side-effect imports for tool registration, then adds a new ChangesTool Registration and Context7 Documentation
🎯 2 (Simple) | ⏱️ ~8 minutes
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
⚔️ Resolve merge conflicts
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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@cloudbot/agent/tools/context7.py`:
- Line 15: Remove the unused import safe_tool from the import statement in
context7.py to fix the flake8 F401 violation; keep the required run_in_executor
import from cloudbot.agent.common and update the line that currently reads "from
cloudbot.agent.common import run_in_executor, safe_tool" to only import
run_in_executor so the module no longer references the unused symbol safe_tool.
- Around line 48-60: The joined output from parts is not being capped to 4000
characters; update the return logic so after creating final =
"\n\n---\n\n".join(parts) you enforce a 4000-character limit (e.g., if
len(final) > 4000 then truncate final to final[:4000] and append a clear "...
(truncated)" suffix) before returning; reference the parts list and the existing
join expression and perform the truncation right before the return to guarantee
the aggregated response cannot exceed 4000 chars.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 21b6a4cc-445a-4e96-9433-a995c34cb581
📒 Files selected for processing (2)
cloudbot/agent/tools/__init__.pycloudbot/agent/tools/context7.py
|
|
||
| import requests | ||
|
|
||
| from cloudbot.agent.common import run_in_executor, safe_tool |
There was a problem hiding this comment.
Remove the unused safe_tool import (Line 15).
This is currently a flake8 F401 violation and can block CI.
Suggested fix
-from cloudbot.agent.common import run_in_executor, safe_tool
+from cloudbot.agent.common import run_in_executor📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| from cloudbot.agent.common import run_in_executor, safe_tool | |
| from cloudbot.agent.common import run_in_executor |
🧰 Tools
🪛 Flake8 (7.3.0)
[error] 15-15: 'cloudbot.agent.common.safe_tool' imported but unused
(F401)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@cloudbot/agent/tools/context7.py` at line 15, Remove the unused import
safe_tool from the import statement in context7.py to fix the flake8 F401
violation; keep the required run_in_executor import from cloudbot.agent.common
and update the line that currently reads "from cloudbot.agent.common import
run_in_executor, safe_tool" to only import run_in_executor so the module no
longer references the unused symbol safe_tool.
Comment on lines
+48
to
+60
| for entry in data[:5]: # cap at 5 entries to stay within limits | ||
| title = entry.get("title", "Untitled") | ||
| content = entry.get("content", "") or entry.get("text", "") or "" | ||
| source = entry.get("source", "") or entry.get("url", "") | ||
| block = f"## {title}\n" | ||
| if source: | ||
| block += f"*Source: {source}*\n\n" | ||
| # Truncate long entries | ||
| if len(content) > 3000: | ||
| content = content[:3000] + "\n... (truncated)" | ||
| block += content | ||
| parts.append(block) | ||
| return "\n\n---\n\n".join(parts) |
There was a problem hiding this comment.
Enforce the 4000-character cap on aggregated list output.
Line 60 returns joined sections without a final cap, so multi-result responses can exceed the stated limit.
Suggested fix
logger = logging.getLogger("cloudbot")
_CONTEXT7_BASE = "https://api.context7.com"
+_MAX_RESPONSE_CHARS = 4000
+_TRUNCATION_SUFFIX = "\n... (truncated)"
@@
- return "\n\n---\n\n".join(parts)
+ result = "\n\n---\n\n".join(parts)
+ if len(result) > _MAX_RESPONSE_CHARS:
+ cutoff = _MAX_RESPONSE_CHARS - len(_TRUNCATION_SUFFIX)
+ result = result[:cutoff] + _TRUNCATION_SUFFIX
+ return result
@@
- if len(content) > 4000:
- content = content[:4000] + "\n... (truncated)"
+ if len(content) > _MAX_RESPONSE_CHARS:
+ cutoff = _MAX_RESPONSE_CHARS - len(_TRUNCATION_SUFFIX)
+ content = content[:cutoff] + _TRUNCATION_SUFFIX
return content
else:
- return str(data)[:4000]
+ return str(data)[:_MAX_RESPONSE_CHARS]🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@cloudbot/agent/tools/context7.py` around lines 48 - 60, The joined output
from parts is not being capped to 4000 characters; update the return logic so
after creating final = "\n\n---\n\n".join(parts) you enforce a 4000-character
limit (e.g., if len(final) > 4000 then truncate final to final[:4000] and append
a clear "... (truncated)" suffix) before returning; reference the parts list and
the existing join expression and perform the truncation right before the return
to guarantee the aggregated response cannot exceed 4000 chars.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a Context7 integration as a new agent tool (
context7) that fetches real-time library/framework documentation from context7.com.What this adds
cloudbot/agent/tools/context7.pycontext7— accepts a library name or topic query, returns structured markdown docs with code examplescloudbot/agent/tools/__init__.pyHow it works
.context7 "react hooks"(or any lib/topic)https://api.context7.com/docs?query=...Example usage
Why Context7?
Context7 provides always-up-to-date documentation for hundreds of libraries and frameworks — better than the agent guessing from training data or fetching random URLs. Gives the agent a dedicated "look up current docs" capability.
Files changed
cloudbot/agent/tools/context7.py(new)cloudbot/agent/tools/__init__.py(1 line added)