RomanNum3ral
/
honcho
mirror of https://github.com/plastic-labs/honcho.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: move perspective taking to representation

This commit is contained in:
vintro 2025-12-04 10:21:43 -05:00
parent 189b043e9a
commit 77a240cfd6
No known key found for this signature in database
2 changed files with 4 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
docs/v2/documentation/core-concepts/architecture.mdx
View File

@ -89,15 +89,6 @@ When you need context from Honcho, you query through the chat endpoint or get_co
The diagram above shows how agents write messages to Honcho, which triggers reasoning that updates peer representations. Agents can then query representations to get additional context for their next response. Black arrows represent read/write of regular data (messages, storage), while red arrows represent read/write of reasoned-over data (logic, peer representations).
## Perspective Taking
One of Honcho's unique capabilities is modeling how different peers perceive each other based on their interactions. When multiple peers interact in a session, Honcho can build a representation of a peer itself (based on all the messages they've sent across all sessions) and representations of the peers a certain peer has interacted with (built only from messages they've observed from specific peers). It makes architecting the following figure effortless:
![](/images/perspectives.jpeg)
This perspective-taking ability enables sophisticated multi-agent scenarios where each peer maintains distinct representations of the other participants they've interacted with.
## Configuration & Extensibility
Honcho is designed to be flexible. Settings cascade hierarchically from workspace to peer to session, so you can set defaults at the workspace level and override them for specific peers or sessions. Feature flags let you enable or disable reasoning modes, perspective tracking, and other capabilities. You can bring your own LLM provider--OpenAI, Anthropic, or custom endpoints--and metadata fields let you extend any primitive with custom JSONB data. TODO: devs fact check pls-->Batch operations let you create up to 100 messages in a single API call for efficient bulk ingestion.

4
docs/v2/documentation/core-concepts/representation.mdx
View File

@ -44,6 +44,10 @@ There are two types of representations:
**Other-representations** are a peer's understanding of another peer, built only from messages they've observed from that peer. If Alice and Bob are in a session together, Bob's other-representation of Alice is based solely on what Alice said in sessions Bob was part of. Bob's representation of Alice might be completely different from Carol's representation of Alice if they've observed different interactions.
![](/images/perspectives.jpeg)
The diagram above shows how perspective-taking works in practice. Each peer can maintain their own representation (self) and representations of other peers they've interacted with, all based on what they've observed.
This perspective-taking ability is configured through the `observe_me` and `observe_others` settings. A peer's `observe_me` configuration controls whether Honcho forms a representation of them at all. The `observe_others` configuration (set at the session level) controls whether a peer should form representations of other peers in that session.
Why would you want this? In multi-agent systems, different agents might need different understandings of the same peer based on their role. A support agent might see a user as frustrated and time-sensitive, while a sales agent in a different context sees the same user as curious and exploratory. Perspective-taking lets you model these different viewpoints accurately.