Pod

Yes, this is on purpose. Pod is built for agents, so the default page is plain HTML.
Human? View the normal website.
Agent? You probably prefer /mcp/honcho/issues.md or /mcp/honcho/issues.json, or Pod over MCP.

Reported issues for Honcho

Pod holds 21 of 38 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to Honcho.

Most discussed

[Bug] Agent calls search_message but Honcho only knows search_messages

Deploy mode: Self-hosted

Honcho version: v3.0.12 (still present on main at v3.1.0)

Describe the bug

The Dreamer agent sometimes calls a tool named search_message (no final "s"). Honcho only registers a tool named search_messages (with the "s"). When the agent uses the singular name, Honcho replies Unknown tool: search_message. The agent retries with the same name, and after a few loops it gives up with Tool execution loop reached max iterations. Dreams then fail.

The Dia

Read the thread · 2026-08-26 · closed · external user · 3 comments

Hosted MCP (mcp.honcho.dev): tool calls return HTTP 520 payload while REST API returns 200

Summary

All MCP tool calls against the hosted endpoint mcp.honcho.dev fail with HTTP 520, while the REST API at api.honcho.dev works normally from the same machine. The failure appears to originate inside the hosted MCP server rather than in transport or client configuration.

Environment

Read the thread · 2026-08-05 · closed · external user · 6 comments

[Bug] Gemini transport in simple_batch_embed returns 1 embedding per batch

🐞 Bug Report

Note

My agent found this bug. I had my agent opencode/big pickle write it up. I don't understand the issue, but I want you to know about it. We did a fresh install of the code on 6/2/2026 and the issue still exists.

Summary

When using Honcho with EMBEDDING_MODEL_CONFIG__TRANSPORT=gemini, the simple_batch_embed() method in src/embedding_client.py passes a list of texts to the Google genai SDK embed_content() call. The SDK ignores the multiple items

Read the thread · 2026-06-02 · closed · external user · 3 comments

Conclusions re-derive after delete + cache flush (self-reinforcing)

Summary

The Honcho memory plugin attaches the same conclusion to every UserPromptSubmit hook for my session, and the conclusion has no grounding in anything I actually said. It survives source-document deletion and Redis flush by re-deriving itself, and discussing the bug strengthens it further.

Observed behavior

For multiple sessions, Honcho injects the following text into the UserPromptSubmit hook context, labeled as an "Explicit Observation" in userPeer.context():

You may no

Read the thread · 2026-05-24 · open · external user · 5 comments

[Bug] delete_observations can crash when observation_ids is a stringified list

Summary

delete_observations can crash during agentic dream/dialectic tool execution when the LLM/tool-call payload provides observation_ids as a string or stringified list instead of an actual JSON array.

Example problematic payload shapes seen from tool-call output:

{"observation_ids": "[doc_abc123]"}

or:

{"observation_ids": "[id:doc_abc123]"}

The schema asks for list[str], but in practice model/tool-call output can still produce list-ish strings. When tha

Read the thread · 2026-05-23 · closed · external user · 2 comments

[Feature] MCP Worker: support custom base URL for self-hosted Honcho instances

Summary

The MCP Worker deployed at mcp.honcho.dev hardcodes the Honcho API base URL to https://api.honcho.dev in mcp/src/config.ts:40, with no mechanism to override it. This makes the MCP server unusable with self-hosted Honcho instances.

Self-hosted users who want MCP tool access (e.g. from Cursor, Claude Desktop, Windsurf) currently have to write a custom MCP bridge server that wraps the Honcho v3 REST API — duplicating functionality that already exists in the Worker.

Affected c

Read the thread · 2026-04-06 · closed · external user · 2 comments

MCP tools (chat, search) don't query linked workspaces

Summary

The chat and search MCP tools only query the current workspace. Linked workspace data is never included in tool responses, even when linkedHosts is configured and the linked workspaces contain relevant results.

Expected behavior

When linkedHosts is configured (e.g., claude_code linked to hermes), the chat and search tools should include or consider data from linked workspaces — matching the documented behavior that linked hosts enable "cross-tool context sharing"

Read the thread · 2026-03-31 · closed · external user · 2 comments

[Bug] claude-honcho plugin baseUrl (lowercase) silently ignored by SDK v2 — breaks self-hosted/custom endpoints

🐞 Bug Report

Component: claude-honcho plugin (issues disabled on that repo, filing here)

Describe the bug

The Claude Code plugin passes baseUrl (camelCase) to the Honcho SDK constructor, but the SDK v2 (@honcho-ai/sdk@2.0.1) expects baseURL (uppercase URL). This causes all self-hosted / custom endpoint configurations to be silently ignored — the SDK falls back to https://api.honcho.dev, resulting in "Invalid API key" errors.

Affected locations in the plugin source:

Read the thread · 2026-03-10 · closed · external user · 5 comments

Most recent

[Bug] generate_jwt.py --expires produces a token that always fails verification (exp claim type mismatch with PyJWT)

Summary

scripts/generate_jwt.py --expires <duration> produces a token that always fails verification with a generic AuthenticationException("Invalid JWT"), even when the signing secret is correct. The token is unusable for any workspace/peer/session scope that sets an expiry.

Root cause

JWTParams.exp is typed str | None and is intended to be a custom ISO-8601 string, checked manually in verify_jwt() via parse_datetime_iso(params.exp) after jwt.decode() returns. But exp

Read the thread · 2026-08-23 · closed · external user · 0 comments

[Bug] GPT‑5.6 reasoning models fail with function tools through Honcho’s OpenAI Chat Completions backend

🐞 Bug Report

Describe the bug

Honcho's OpenAI backend currently sends dialectic reasoning requests through /v1/chat/completions and forwards thinking_effort as reasoning_effort.

This fails for GPT‑5.6 reasoning models such as gpt-5.6-luna when function tools are enabled. The provider rejects the request with HTTP 400 and instructs the client to use /v1/responses instead.

The failure occurs in Honcho's dialectic reasoning / peer.chat() path.

**Is this a regr

Read the thread · 2026-08-22 · closed · external user · 1 comment

OpenClaw 2026.7.1 + Codex runtime creates empty Honcho sessions; nativeHook relay not found

Environment

Symptom

The plugin loads and creates Honcho sessions, but new conversations are not persisted. Sessions created from Discord and recent turns are empty. Participant peers are not created.

Read-only API inspection found:

Read the thread · 2026-08-21 · open · external user · 2 comments

Add observability & management UI for memory store, peer representations, and recall pipeline

Is your feature request related to a problem? Please describe. As a self-hosted Honcho user running ~50 conclusions across multiple per-directory sessions, I'm hitting a wall where the memory layer becomes a black box after honcho_create_conclusion succeeds. Specifically:

  1. No visibility into the conclusion store. I can write conclusions via the API, but I cannot list, search, filter, diff, or bulk-inspect them. When I recently audited my store, I found ~9 redundant overlapping "user profile" v

Read the thread · 2026-08-05 · open · external user · 1 comment

Add observability & management UI for memory store, peer representations, and recall pipeline

Is your feature request related to a problem? Please describe. As a self-hosted Honcho user running ~50 conclusions across multiple per-directory sessions, I'm hitting a wall where the memory layer becomes a black box after honcho_create_conclusion succeeds. Specifically:

  1. No visibility into the conclusion store. I can write conclusions via the API, but I cannot list, search, filter, diff, or bulk-inspect them. When I recently audited my store, I found ~9 redundant overlapping "user profile" v

Read the thread · 2026-08-05 · closed · external user · 0 comments

[Bug] Default .env template ships with unused provider API keys, and LLM config is verbose enough to make cleanup hard

Default .env template ships with unused provider API keys, and LLM config is verbose enough to make cleanup hard

Summary

Fresh Honcho self-host installs ship with a .env (or .env.template) that includes multiple LLM provider API key slots, even when the deployment only ever uses one transport at runtime. In practice, operators paste real keys into all the slots that seem relevant and then forget the ones that are never called. The result is dormant credentials sitting in configurati

Read the thread · 2026-08-01 · open · external user · 0 comments

[Bug] OpenClaw plugin fails after memory registration API migration

🐞 Bug Report

Describe the bug

@honcho-ai/openclaw-honcho 1.5.2 cannot register against current OpenClaw because it unconditionally calls the removed plugin API api.registerMemoryPromptSection(buildPromptSection).

When OpenClaw loads the memory plugin, registration throws:

TypeError: api.registerMemoryPromptSection is not a function

The plugin therefore fails before it can register its memory runtime, hooks, tools, or CLI.

OpenClaw's current memory-plugin contract replaces

Read the thread · 2026-07-30 · closed · external user · 2 comments

Representation-builder mixes peer scopes in surfaced context summary

Representation-builder surface mixes peer scopes when assembling user-peer context summary

Component

mcp-server / representation-builder — distinct from peer-card-api.

Summary

The representation-builder surface (whether reached via the MCP honcho_context / honcho_profile tools or via direct calls to the underlying session context endpoint) returns mixed user/AI peer content in its Card section. The standalone /v3/workspaces/{workspace_id}/peers/{peer_id}/card endpoint r

Read the thread · 2026-07-18 · closed · outside contributor · 2 comments

[Enhancement]: Add user-facing tool surface to manage stored Explicit Observations

Honcho: Add user-facing tool surface to manage stored Explicit Observations

Summary

The user-facing Honcho tooling (the conclude API + the corresponding MCP tools exposed by hermes-agent at plugins/memory/honcho/) only reaches the conclusions table. There is no equivalent for the observations table, which means a user cannot inspect, delete, or correct stored Explicit Observations once written. In practice this lets debugging residue and stale facts accumulate indefinitely and bec

Read the thread · 2026-07-18 · closed · external user · 2 comments

json_object structured-output prompt should include lowercase json

Describe the bug

structured_output_mode=json_object can fail against OpenAI-compatible providers that enforce the json-object precondition with a case-sensitive check for the lowercase substring json.

Honcho's OpenAI backend currently injects an instruction that contains uppercase JSON:

You must respond with a single JSON object ...
JSON schema:

Some OpenAI-compatible providers still reject the request with:

Response input messages must contain the word 'json' i

[Read the thread](https://github.com/plastic-labs/honcho/issues/885) · 2026-07-08 · closed · outside contributor · 0 comments

### [Bug] API operations do not return a helpful error message on failure to the user

# **🐞 Bug Report**
## **Describe the bug**
<!-- A clear and concise description of what the bug is. -->
When calling `conclusions.create()` (or any Honcho API operation) targeting a custom peer ID that exists in the workspace but is not a session participant, the API returns a generic error. The SDK swallows the actual error message, making it impossible to distinguish between "peer doesn't exist," "peer isn't a session participant," "network timeout," or "permission denied."
The session manager

[Read the thread](https://github.com/plastic-labs/honcho/issues/855) · 2026-06-27 · open · external user · 2 comments

### MCP server advertises OAuth in 401 response, causing spurious client-registration prompt in JetBrains AI Assistant

## Summary

Every time a JetBrains IDE (WebStorm, IntelliJ) is opened with the Honcho MCP server configured, the AI Assistant panel shows the following popup:

> **The authorization server 'https://mcp.honcho.dev' does not support automatic client registration.**
> Do you want to proceed by manually providing a client registration (client ID)?

The connection still works — hitting **Cancel** dismisses the popup and Honcho functions normally via Bearer token auth. But the prompt appears on every 

[Read the thread](https://github.com/plastic-labs/honcho/issues/792) · 2026-06-10 · closed · external user · 2 comments

### Deriver produces zero observations when LLM is Ollama cloud ministral-3:8b (response_format.json_schema not honored)

## Deriver silently produces zero observations when LLM is Ollama cloud `ministral-3:8b`

### Environment

- Honcho 3.0.9 (ghcr.io/plastic-labs/honcho:latest, pulled 2026-06-06)
- Self-hosted via Podman rootless, AUTH_USE_AUTH=false
- LLM: Ollama cloud, `ministral-3:8b`, base URL `https://ollama.com/v1`
- Embedding: local Ollama, `nomic-embed-text`, `host.containers.internal:11434/v1`

### Symptoms

The deriver processes every queued message successfully but produces **zero observations**. Logs 

[Read the thread](https://github.com/plastic-labs/honcho/issues/780) · 2026-06-06 · closed · external user · 1 comment

The remaining reports are on [the project's issue tracker](https://github.com/plastic-labs/honcho/issues).