feat(chatbot): add conversational chatbot with Honcho memory#499
Open
MichaelFehdrau0205 wants to merge 4 commits intoplastic-labs:mainfrom
Open
feat(chatbot): add conversational chatbot with Honcho memory#499MichaelFehdrau0205 wants to merge 4 commits intoplastic-labs:mainfrom
MichaelFehdrau0205 wants to merge 4 commits intoplastic-labs:mainfrom
Conversation
Contributor
WalkthroughAdded documentation for a local chatbot example using Honcho memory management and Ollama LLM, along with a new Changes
Sequence DiagramsequenceDiagram
participant User as User/CLI
participant Chatbot as chatbot.py
participant Honcho as Honcho API
participant Ollama as Ollama API
User->>Chatbot: chat(user_id, message)
Chatbot->>Honcho: Get/create session for user
Honcho-->>Chatbot: Session
Chatbot->>Honcho: Load context (messages, peers)
Honcho-->>Chatbot: Context messages
Chatbot->>Chatbot: Truncate context + format system prompt
Chatbot->>Ollama: POST /api/chat with system prompt + recent turns
Ollama-->>Chatbot: Assistant response
Chatbot->>Honcho: Persist user + assistant messages
Honcho-->>Chatbot: Confirmation
Chatbot-->>User: Return assistant reply
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (2)
chatbot.py (2)
37-38: Missing error handling for invalid environment variable values.Direct
int()calls will raiseValueErrorif environment variables contain non-numeric strings. Consider using_env_positive_intfor consistency or add try/except blocks.♻️ Proposed fix using helper function
-CHAT_HISTORY_MAX_MESSAGES = int(os.getenv("CHAT_HISTORY_MAX_MESSAGES", "20")) -HONCHO_CONTEXT_MAX_CHARS = int(os.getenv("HONCHO_CONTEXT_MAX_CHARS", "6000")) +CHAT_HISTORY_MAX_MESSAGES = _env_positive_int("CHAT_HISTORY_MAX_MESSAGES", 20) +HONCHO_CONTEXT_MAX_CHARS = _env_positive_int("HONCHO_CONTEXT_MAX_CHARS", 6000)And move
_env_positive_intdefinition above these lines, or use a simpler inline approach:-CHAT_TURN_MAX_CHARS = int(os.getenv("CHAT_TURN_MAX_CHARS", "3000")) +CHAT_TURN_MAX_CHARS = _env_positive_int("CHAT_TURN_MAX_CHARS", 3000)Also applies to: 51-51
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@chatbot.py` around lines 37 - 38, The environment integer parsing for CHAT_HISTORY_MAX_MESSAGES and HONCHO_CONTEXT_MAX_CHARS currently uses direct int() calls which can raise ValueError for non-numeric env values; update these to use the helper function _env_positive_int (or implement a small wrapper that validates/parses and falls back to the default) and ensure _env_positive_int is defined above where CHAT_HISTORY_MAX_MESSAGES and HONCHO_CONTEXT_MAX_CHARS are set; adjust both occurrences (lines setting CHAT_HISTORY_MAX_MESSAGES and HONCHO_CONTEXT_MAX_CHARS and the similar occurrence noted at 51) to call _env_positive_int("CHAT_HISTORY_MAX_MESSAGES", 20) and _env_positive_int("HONCHO_CONTEXT_MAX_CHARS", 6000) (or equivalent validated parsing) so invalid env values are handled gracefully.
164-170: Consider adding type hint for return value.The function has good logic but lacks a return type hint for consistency with the rest of the codebase.
♻️ Proposed fix
-def _format_peer_context(ctx: PeerContextResponse) -> str: +def _format_peer_context(ctx: PeerContextResponse) -> str: parts: list[str] = [] if ctx.representation: parts.append(ctx.representation) if ctx.peer_card: parts.append("\n".join(ctx.peer_card)) - return "\n\n".join(parts) if parts else "(No memory yet.)" + return "\n\n".join(parts) if parts else "(No memory yet.)"(Already has return type - this is correct as-is)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@chatbot.py` around lines 164 - 170, Add an explicit return type hint to the _format_peer_context function so it matches the codebase style: ensure the signature reads with a return annotation (-> str) for the function that takes PeerContextResponse and returns the formatted string; update the function declaration for _format_peer_context to include this return type if it's missing.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@chatbot.py`:
- Around line 37-38: The environment integer parsing for
CHAT_HISTORY_MAX_MESSAGES and HONCHO_CONTEXT_MAX_CHARS currently uses direct
int() calls which can raise ValueError for non-numeric env values; update these
to use the helper function _env_positive_int (or implement a small wrapper that
validates/parses and falls back to the default) and ensure _env_positive_int is
defined above where CHAT_HISTORY_MAX_MESSAGES and HONCHO_CONTEXT_MAX_CHARS are
set; adjust both occurrences (lines setting CHAT_HISTORY_MAX_MESSAGES and
HONCHO_CONTEXT_MAX_CHARS and the similar occurrence noted at 51) to call
_env_positive_int("CHAT_HISTORY_MAX_MESSAGES", 20) and
_env_positive_int("HONCHO_CONTEXT_MAX_CHARS", 6000) (or equivalent validated
parsing) so invalid env values are handled gracefully.
- Around line 164-170: Add an explicit return type hint to the
_format_peer_context function so it matches the codebase style: ensure the
signature reads with a return annotation (-> str) for the function that takes
PeerContextResponse and returns the formatted string; update the function
declaration for _format_peer_context to include this return type if it's
missing.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 53e0cbaa-ce3e-43fa-8956-e378a7d078e7
📒 Files selected for processing (2)
README.mdchatbot.py
Collaborator
|
This is fun, but not relevant to being merged into honcho itself. Would publish this as a standalone repo. Can you say more about the intention of where this should fit into the repo? |
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
2 participants
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.
What I Built
A conversational chatbot that uses Honcho for persistent memory.
Features
How to Run
Summary by CodeRabbit
New Features
Documentation