mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(honcho): context injection overhaul, 5-tool surface, cost safety, session isolation (#10619)

Browse source 
Salvaged from PR #9884 by erosika. Cherry-picked plugin changes onto
current main with minimal core modifications.

Plugin changes (plugins/memory/honcho/):
- New honcho_reasoning tool (5th tool, splits LLM calls from honcho_context)
- Two-layer context injection: base context (summary + representation + card)
  on contextCadence, dialectic supplement on dialecticCadence
- Multi-pass dialectic depth (1-3 passes) with early bail-out on strong signal
- Cold/warm prompt selection based on session state
- dialecticCadence defaults to 3 (was 1) — ~66% fewer Honcho LLM calls
- Session summary injection for conversational continuity
- Bidirectional peer targeting on all 5 tools
- Correctness fixes: peer param fallback, None guard on set_peer_card,
  schema validation, signal_sufficient anchored regex, mid->medium level fix

Core changes (~20 lines across 3 files):
- agent/memory_manager.py: Enhanced sanitize_context() to strip full
  <memory-context> blocks and system notes (prevents leak from saveMessages)
- run_agent.py: gateway_session_key param for stable per-chat Honcho sessions,
  on_turn_start() call before prefetch_all() for cadence tracking,
  sanitize_context() on user messages to strip leaked memory blocks
- gateway/run.py: skip_memory=True on 2 temp agents (prevents orphan sessions),
  gateway_session_key threading to main agent

Tests: 509 passed (3 skipped — honcho SDK not installed locally)
Docs: Updated honcho.md, memory-providers.md, tools-reference.md, SKILL.md

Co-authored-by: erosika <erosika@users.noreply.github.com>
This commit is contained in:
Teknium 2026-04-15 19:12:19 -07:00 • committed by GitHub
parent 00ff9a26cd
commit cc6e8941db
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 2632 additions and 396 deletions
Download patch file Download diff file Expand all files Collapse all files

125
website/docs/user-guide/features/honcho.md
View file

@ -18,12 +18,15 @@ Honcho is integrated into the [Memory Providers](./memory-providers.md) system.
|-----------|----------------|--------|
| Cross-session persistence | ✔ File-based MEMORY.md/USER.md | ✔ Server-side with API |
| User profile | ✔ Manual agent curation | ✔ Automatic dialectic reasoning |
| Session summary | — | ✔ Session-scoped context injection |
| Multi-agent isolation | — | ✔ Per-peer profile separation |
| Observation modes | — | ✔ Unified or directional observation |
| Conclusions (derived insights) | — | ✔ Server-side reasoning about patterns |
| Search across history | ✔ FTS5 session search | ✔ Semantic search over conclusions |
**Dialectic reasoning**: After each conversation, Honcho analyzes the exchange and derives "conclusions" — insights about the user's preferences, habits, and goals. These conclusions accumulate over time, giving the agent a deepening understanding that goes beyond what the user explicitly stated.
**Dialectic reasoning**: After each conversation turn (gated by `dialecticCadence`), Honcho analyzes the exchange and derives insights about the user's preferences, habits, and goals. These accumulate over time, giving the agent a deepening understanding that goes beyond what the user explicitly stated. The dialectic supports multi-pass depth (1–3 passes) with automatic cold/warm prompt selection — cold start queries focus on general user facts while warm queries prioritize session-scoped context.
**Session-scoped context**: Base context now includes the session summary alongside the user representation and peer card. This gives the agent awareness of what has already been discussed in the current session, reducing repetition and enabling continuity.
**Multi-agent profiles**: When multiple Hermes instances talk to the same user (e.g., a coding assistant and a personal assistant), Honcho maintains separate "peer" profiles. Each peer sees only its own observations and conclusions, preventing cross-contamination of context.
@ -42,40 +45,128 @@ memory:
```
```bash
echo "HONCHO_API_KEY=your-key" >> ~/.hermes/.env
echo "HONCHO_API_KEY=*** >> ~/.hermes/.env
```
Get an API key at [honcho.dev](https://honcho.dev).
## Architecture
### Two-Layer Context Injection
Every turn (in `hybrid` or `context` mode), Honcho assembles two layers of context injected into the system prompt:
1. **Base context** — session summary, user representation, user peer card, AI self-representation, and AI identity card. Refreshed on `contextCadence`. This is the "who is this user" layer.
2. **Dialectic supplement** — LLM-synthesized reasoning about the user's current state and needs. Refreshed on `dialecticCadence`. This is the "what matters right now" layer.
Both layers are concatenated and truncated to the `contextTokens` budget (if set).
### Cold/Warm Prompt Selection
The dialectic automatically selects between two prompt strategies:
- **Cold start** (no base context yet): General query — "Who is this person? What are their preferences, goals, and working style?"
- **Warm session** (base context exists): Session-scoped query — "Given what's been discussed in this session so far, what context about this user is most relevant?"
This happens automatically based on whether base context has been populated.
### Three Orthogonal Config Knobs
Cost and depth are controlled by three independent knobs:
| Knob | Controls | Default |
|------|----------|---------|
| `contextCadence` | Turns between `context()` API calls (base layer refresh) | `1` |
| `dialecticCadence` | Turns between `peer.chat()` LLM calls (dialectic layer refresh) | `3` |
| `dialecticDepth` | Number of `.chat()` passes per dialectic invocation (1–3) | `1` |
These are orthogonal — you can have frequent context refreshes with infrequent dialectic, or deep multi-pass dialectic at low frequency. Example: `contextCadence: 1, dialecticCadence: 5, dialecticDepth: 2` refreshes base context every turn, runs dialectic every 5 turns, and each dialectic run makes 2 passes.
### Dialectic Depth (Multi-Pass)
When `dialecticDepth` > 1, each dialectic invocation runs multiple `.chat()` passes:
- **Pass 0**: Cold or warm prompt (see above)
- **Pass 1**: Self-audit — identifies gaps in the initial assessment and synthesizes evidence from recent sessions
- **Pass 2**: Reconciliation — checks for contradictions between prior passes and produces a final synthesis
Each pass uses a proportional reasoning level (lighter early passes, base level for the main pass). Override per-pass levels with `dialecticDepthLevels` — e.g., `["minimal", "medium", "high"]` for a depth-3 run.
Passes bail out early if the prior pass returned strong signal (long, structured output), so depth 3 doesn't always mean 3 LLM calls.
## Configuration Options
```yaml
# ~/.hermes/config.yaml
honcho:
observation: directional # "unified" (default for new installs) or "directional"
peer_name: "" # auto-detected from platform, or set manually
```
Honcho is configured in `~/.honcho/config.json` (global) or `$HERMES_HOME/honcho.json` (profile-local). The setup wizard handles this for you.
**Observation modes:**
- `unified` — All observations go into a single pool. Simpler, good for single-agent setups.
- `directional` — Observations are tagged with direction (user→agent, agent→user). Enables richer analysis of conversation dynamics.
### Full Config Reference
| Key | Default | Description |
|-----|---------|-------------|
| `contextTokens` | `null` (uncapped) | Token budget for auto-injected context per turn. Set to an integer (e.g. 1200) to cap. Truncates at word boundaries |
| `contextCadence` | `1` | Minimum turns between `context()` API calls (base layer refresh) |
| `dialecticCadence` | `3` | Minimum turns between `peer.chat()` LLM calls (dialectic layer). In `tools` mode, irrelevant — model calls explicitly |
| `dialecticDepth` | `1` | Number of `.chat()` passes per dialectic invocation. Clamped to 1–3 |
| `dialecticDepthLevels` | `null` | Optional array of reasoning levels per pass, e.g. `["minimal", "low", "medium"]`. Overrides proportional defaults |
| `dialecticReasoningLevel` | `'low'` | Base reasoning level: `minimal`, `low`, `medium`, `high`, `max` |
| `dialecticDynamic` | `true` | When `true`, model can override reasoning level per-call via tool param |
| `dialecticMaxChars` | `600` | Max chars of dialectic result injected into system prompt |
| `recallMode` | `'hybrid'` | `hybrid` (auto-inject + tools), `context` (inject only), `tools` (tools only) |
| `writeFrequency` | `'async'` | When to flush messages: `async` (background thread), `turn` (sync), `session` (batch on end), or integer N |
| `saveMessages` | `true` | Whether to persist messages to Honcho API |
| `observationMode` | `'directional'` | `directional` (all on) or `unified` (shared pool). Override with `observation` object for granular control |
| `messageMaxChars` | `25000` | Max chars per message sent via `add_messages()`. Chunked if exceeded |
| `dialecticMaxInputChars` | `10000` | Max chars for dialectic query input to `peer.chat()` |
| `sessionStrategy` | `'per-directory'` | `per-directory`, `per-repo`, `per-session`, or `global` |
**Session strategy** controls how Honcho sessions map to your work:
- `per-session` — each `hermes` run gets a fresh session. Clean starts, memory via tools. Recommended for new users.
- `per-directory` — one Honcho session per working directory. Context accumulates across runs.
- `per-repo` — one session per git repository.
- `global` — single session across all directories.
**Recall mode** controls how memory flows into conversations:
- `hybrid` — context auto-injected into system prompt AND tools available (model decides when to query).
- `context` — auto-injection only, tools hidden.
- `tools` — tools only, no auto-injection. Agent must explicitly call `honcho_reasoning`, `honcho_search`, etc.
**Settings per recall mode:**
| Setting | `hybrid` | `context` | `tools` |
|---------|----------|-----------|---------|
| `writeFrequency` | flushes messages | flushes messages | flushes messages |
| `contextCadence` | gates base context refresh | gates base context refresh | irrelevant — no injection |
| `dialecticCadence` | gates auto LLM calls | gates auto LLM calls | irrelevant — model calls explicitly |
| `dialecticDepth` | multi-pass per invocation | multi-pass per invocation | irrelevant — model calls explicitly |
| `contextTokens` | caps injection | caps injection | irrelevant — no injection |
| `dialecticDynamic` | gates model override | N/A (no tools) | gates model override |
In `tools` mode, the model is fully in control — it calls `honcho_reasoning` when it wants, at whatever `reasoning_level` it picks. Cadence and budget settings only apply to modes with auto-injection (`hybrid` and `context`).
## Tools
When Honcho is active as the memory provider, four additional tools become available:
When Honcho is active as the memory provider, five tools become available:
| Tool | Purpose |
|------|---------|
| `honcho_conclude` | Trigger server-side dialectic reasoning on recent conversations |
| `honcho_context` | Retrieve relevant context from Honcho's memory for the current conversation |
| `honcho_profile` | View or update the user's Honcho profile |
| `honcho_search` | Semantic search across all stored conclusions and observations |
| `honcho_profile` | Read or update peer card — pass `card` (list of facts) to update, omit to read |
| `honcho_search` | Semantic search over context — raw excerpts, no LLM synthesis |
| `honcho_context` | Full session context — summary, representation, card, recent messages |
| `honcho_reasoning` | Synthesized answer from Honcho's LLM — pass `reasoning_level` (minimal/low/medium/high/max) to control depth |
| `honcho_conclude` | Create or delete conclusions — pass `conclusion` to create, `delete_id` to remove (PII only) |
## CLI Commands
```bash
hermes honcho status # Show connection status and config
hermes honcho status # Connection status, config, and key settings
hermes honcho setup # Interactive setup wizard
hermes honcho strategy # Show or set session strategy
hermes honcho peer # Update peer names for multi-agent setups
hermes honcho mode # Show or set recall mode
hermes honcho tokens # Show or set context token budget
hermes honcho identity # Show Honcho peer identity
hermes honcho sync # Sync host blocks for all profiles
hermes honcho enable # Enable Honcho
hermes honcho disable # Disable Honcho
```
## Migrating from `hermes honcho`