paperclip/packages/adapters/hermes
Harjoth Khara aad97d93fe
fix(hermes): surface real reasoning text from reasoning.available events (#9237)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - When an agent runs through the Hermes gateway adapter, its stdout is
parsed line-by-line into transcript entries that the issue chat renders
(the UI fetches the adapter's `./ui-parser` from
`/api/adapters/:type/ui-parser.js` and runs `parseStdoutLine`
client-side)
> - Reasoning-capable models emit a `reasoning.available` gateway event
carrying the model's reasoning text, and the chat renders `thinking`
parts as expandable chain-of-thought
> - The gateway parser mapped `reasoning.available` to a hardcoded
`"Hermes reasoning available"` string and discarded the event payload,
so the "thinking" part had no real content — the indicator looked static
and expanding it revealed nothing (#9209)
> - This pull request extracts the actual reasoning text from the event
payload and uses it as the `thinking` part's text, keeping the old
string only as a fallback for payloads that carry no text
> - The benefit is that the "Hermes reasoning available" indicator now
surfaces the model's real reasoning, which the existing
expandable-thinking UI can display

## Linked Issues or Issue Description

Fixes: #9209

## What Changed

- `packages/adapters/hermes/src/gateway/ui/parse-stdout.ts`: the
`reasoning.available` handler now extracts the reasoning text from the
event `data` via a small helper (`extractReasoningText`), checking the
plausible field names (`reasoning`, `reasoning_text`, `thinking`,
`text`, `summary`, `content`) and recursing one level into nested `data`
/ `payload` records, with ANSI stripped. The prior `"Hermes reasoning
available"` string is kept only as a fallback when no text field is
present.
- `packages/adapters/hermes/gateway-ui-parser.cjs`: applied the
identical logical change to the committed CommonJS mirror (exported as
`./gateway/ui-parser`), keeping the two files in sync.
- `packages/adapters/hermes/src/gateway/ui/parse-stdout.test.ts` (new):
unit tests for the gateway parser (there were none) covering
direct-field, `summary`, nested `data`/`payload` extraction, the no-text
fallback, and regression guards for `message.delta` and plain stdout.

## Verification

Ran from `packages/adapters/hermes`:

- `node_modules/.bin/vitest run src/gateway/ui/parse-stdout.test.ts` →
**8/8 passed**.
- Negative control: stashed the source changes and re-ran the same test
file against the current (pre-patch) parser → **4/8 failed** (exactly
the reasoning-extraction assertions), then restored — confirming the
tests are discriminating, not vacuous.
- `npx tsc --noEmit -p .` → clean.

Real-behavior proof (driving the actual shipped `gateway-ui-parser.cjs`
`parseStdoutLine`) is in the block below.

## Risks

- **Low risk.** Behavior is unchanged for events that carry no
recognizable text field — the `"Hermes reasoning available"` fallback is
preserved (verified). Only the `reasoning.available` branch changed;
`message.delta`, `run.failed`/`run.error`, and the generic/system/stdout
branches are untouched.
- The exact field name in a real `reasoning.available` payload is
defined by the external Hermes gateway and is not present anywhere in
this repo, so the extraction is intentionally defensive across several
plausible field names rather than pinned to one. If the real event nests
the text differently than `data` / `payload`, it will fall back to the
existing placeholder (i.e. no regression vs. today). Happy to tighten
the field list against real gateway traffic if a maintainer can share a
sample.

## Model Used

Claude Sonnet 5 (`claude-sonnet-5`) via Claude Code, with tool use and
local test execution (ran vitest/tsc against the change). Planning, code
review, and the real-behavior proof were done with Claude (Opus 4.8) in
the same session.

## Real behavior proof

**Behavior addressed:** A `reasoning.available` Hermes gateway event now
produces a `thinking` transcript part containing the model's real
reasoning text, instead of a static `"Hermes reasoning available"`
placeholder with no content behind it (#9209).

**Real environment tested:** Drove the actual shipped production
artifact — `packages/adapters/hermes/gateway-ui-parser.cjs`, the exact
module the UI loads via `/api/adapters/hermes-gateway/ui-parser.js` and
runs to parse gateway stdout — on Node v24.16.0, macOS. The input is a
raw stdout line in the exact format emitted by
`packages/adapters/hermes/src/gateway/server/execute.ts`
(`[hermes-gateway:event] run=… event=reasoning.available data=…`). Only
the external gateway boundary (the raw line) is synthesized; the parser
code path is the real one.

**Exact steps or command run after this patch:**
```
# BEFORE = git show HEAD:…/gateway-ui-parser.cjs ; AFTER = patched artifact
node proof.cjs   # requires each parser build and calls parseStdoutLine(line, ts)
# line = [hermes-gateway:event] run=run-abc123 event=reasoning.available \
#        data={"text":"Checking whether the cache key includes the tenant id before I refactor the lookup."}
```

**Evidence after fix:**
```
===== BEFORE (master / old code) =====
[ { "kind": "thinking", "ts": "…", "text": "Hermes reasoning available" } ]
thinking part carries real reasoning text? -> NO (static placeholder, nothing for the UI to expand)

===== AFTER (this patch) =====
[ { "kind": "thinking", "ts": "…",
    "text": "Checking whether the cache key includes the tenant id before I refactor the lookup." } ]
thinking part carries real reasoning text? -> YES
```
Additional cases through the same shipped artifact after the patch:
```
-- nested payload (data.payload.reasoning) --
{"kind":"thinking","ts":"…","text":"Weighing two migration orders."}
-- bare signal, no text field (regression guard) --
{"kind":"thinking","ts":"…","text":"Hermes reasoning available"}     # fallback preserved
-- message.delta still works (regression guard) --
{"kind":"assistant","ts":"…","text":"Hello","delta":true}
```

**Observed result after fix:** The `reasoning.available` event yields a
`thinking` part carrying the model's real reasoning text (top-level or
nested), which the existing expandable-thinking rendering in the chat
can display. Events with no text field still yield the original
placeholder, and unrelated events are unaffected.

**What was not tested:** I did not run against a live Hermes gateway —
Paperclip's Hermes gateway binary and its credentials aren't available
on this machine, and no captured real `reasoning.available` payload
exists in the repo, so the exact wire field name is inferred (hence the
defensive multi-field extraction + safe fallback). I also did not render
the full React chat component in jsdom; the change is confined to the
parser, and the chat's expandable `thinking` rendering already exists
(`ui/src/components/IssueChatThread.tsx`). CI / unit tests here are
supplemental to the runtime proof above.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above (searched `9209 in:body` and keyword variants — none found)
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change
(`fix/hermes-reasoning-available-payload`) and contains no internal
Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] I have updated relevant documentation to reflect my changes (no
user-facing docs describe this behavior; none needed)
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green (will confirm once CI runs on the
PR)
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
(will address on review)
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-18 14:19:04 -05:00
..
scripts [codex] Add built-in Hermes adapters (#8543) 2026-06-26 16:04:58 -05:00
skills/paperclip-task-bridge [codex] Add built-in Hermes adapters (#8543) 2026-06-26 16:04:58 -05:00
src fix(hermes): surface real reasoning text from reasoning.available events (#9237) 2026-08-18 14:19:04 -05:00
LICENSE [codex] Add built-in Hermes adapters (#8543) 2026-06-26 16:04:58 -05:00
README.md docs: point Paperclip docs links at docs.paperclip.ing (#9300) 2026-07-09 19:24:46 -05:00
gateway-ui-parser.cjs fix(hermes): surface real reasoning text from reasoning.available events (#9237) 2026-08-18 14:19:04 -05:00
package.json build(deps-dev): bump @types/node from 22.19.21 to 22.20.1 (#10304) 2026-07-28 10:48:45 -07:00
tsconfig.json [codex] Add built-in Hermes adapters (#8543) 2026-06-26 16:04:58 -05:00
ui-parser.cjs fix(hermes): strip ANSI escape codes from terminal output in UI parsers (#8731) 2026-07-06 12:07:55 -07:00
vitest.config.ts [codex] Add built-in Hermes adapters (#8543) 2026-06-26 16:04:58 -05:00

README.md

Paperclip Adapters for Hermes Agent

A Paperclip adapter package that lets you run Hermes Agent as a managed employee in a Paperclip company.

Hermes Agent is a full-featured AI agent by Nous Research with 30+ native tools, persistent memory, session persistence, 80+ skills, MCP support, and multi-provider model access.

This package owns both built-in Hermes adapter types:

  • hermes_local runs the local Hermes CLI as a child process. The package root exports remain compatible with the original local adapter.
  • hermes_gateway calls an already-running Hermes API server over HTTP/SSE. Gateway entrypoints live under the ./gateway export namespace.

Choose hermes_local when Paperclip and Hermes run on the same trusted host and Paperclip should start hermes chat for each heartbeat. Choose hermes_gateway when Hermes is already running as an API server, often on another host, in Docker, or behind a private-network/TLS endpoint. The adapter type keys did not change during package consolidation.

Key Features

This adapter provides:

  • 8 inference providers — Anthropic, OpenRouter, OpenAI, Nous, OpenAI Codex, ZAI, Kimi Coding, MiniMax
  • Skills integration — Scans both Paperclip-managed and Hermes-native skills (~/.hermes/skills/), with sync/list/resolve APIs
  • Structured transcript parsing — Raw Hermes stdout is parsed into typed TranscriptEntry objects so Paperclip renders proper tool cards with status icons and expand/collapse
  • Rich post-processing — Converts Hermes ASCII banners, setext headings, and +--+ table borders into clean GFM markdown
  • Comment-driven wakes — Agents wake to respond to issue comments, not just task assignments
  • Auto model detection — Reads ~/.hermes/config.yaml to pre-populate the UI with the user's configured model
  • Session codec — Structured validation and migration of session state across heartbeats
  • Benign stderr reclassification — MCP init messages and structured logs are reclassified so they don't appear as errors in the UI
  • Session source tagging — Sessions are tagged as tool source so they don't clutter the user's interactive history
  • Filesystem checkpoints — Optional --checkpoints for rollback safety
  • Thinking effort control — Passes --reasoning-effort for thinking/reasoning models

Hermes Agent Capabilities

Feature Claude Code Codex Hermes Agent
Persistent memory ❌ ❌ ✅ Remembers across sessions
Native tools ~5 ~5 30+ (terminal, file, web, browser, vision, git, etc.)
Skills system ❌ ❌ ✅ 80+ loadable skills
Session search ❌ ❌ ✅ FTS5 search over past conversations
Sub-agent delegation ❌ ❌ ✅ Parallel sub-tasks
Context compression ❌ ❌ ✅ Auto-compresses long conversations
MCP client ❌ ❌ ✅ Connect to any MCP server
Multi-provider Anthropic only OpenAI only ✅ 8 providers out of the box

Installation

This package ships with Paperclip core as the built-in hermes_local and hermes_gateway adapters. No Adapter manager installation is required for normal Paperclip use.

Prerequisites

  • Hermes Agent installed (pip install hermes-agent)
  • Python 3.10+
  • At least one LLM API key (Anthropic, OpenRouter, or OpenAI)

Quick Start

1. Optional: override the built-in for adapter development

For local adapter development, install the package from a local path in Adapter manager, or add an entry to ~/.paperclip/adapter-plugins.json and restart Paperclip. The external package can override either built-in Hermes adapter while it is enabled:

[
  {
    "packageName": "@paperclipai/hermes-paperclip-adapter",
    "localPath": "/absolute/path/to/paperclip/packages/adapters/hermes",
    "type": "hermes_local",
    "installedAt": "2026-06-23T00:00:00.000Z"
  }
]

Use "type": "hermes_gateway" with the same package when testing a gateway override.

The package root exports createServerAdapter() for the local server adapter, a declarative config schema for the generic agent form, and ./ui-parser for local run transcript parsing. Gateway entrypoints are exported from ./gateway, ./gateway/server, ./gateway/ui, ./gateway/cli, and ./gateway/ui-parser. Paperclip core imports these same package entrypoints for built-in adapter registration.

2. Create a local Hermes agent in Paperclip

In the Paperclip UI or via API, create an agent with adapter type hermes_local:

{
  "name": "Hermes Engineer",
  "adapterType": "hermes_local",
  "adapterConfig": {
    "model": "anthropic/claude-sonnet-4",
    "maxIterations": 50,
    "timeoutSec": 300,
    "persistSession": true,
    "enabledToolsets": ["terminal", "file", "web"]
  }
}

This mode shells out to the local hermes CLI. Paperclip injects runtime environment variables and captures stdout/stderr from the child process.

3. Create a Hermes gateway agent in Paperclip

Start Hermes with its API server enabled first:

API_SERVER_ENABLED=true \
API_SERVER_KEY=<generated-secret> \
hermes gateway run --replace --accept-hooks

Then create an agent with adapter type hermes_gateway:

{
  "name": "Hermes Gateway Engineer",
  "adapterType": "hermes_gateway",
  "adapterConfig": {
    "apiBaseUrl": "http://127.0.0.1:8642",
    "apiKey": "<same-value-as-API_SERVER_KEY>",
    "paperclipApiUrl": "http://127.0.0.1:3100",
    "sessionKeyStrategy": "issue",
    "timeoutSec": 600
  }
}

If the URL you have is the default Hermes dashboard at http://127.0.0.1:9119 or the default chat URL at http://127.0.0.1:9119/chat, Paperclip maps it to http://127.0.0.1:9119/api before calling Hermes API routes. /chat and the dashboard root are browser UI routes; Paperclip tests /api/health and starts runs with /api/v1/runs after mapping them to the API base.

This mode does not start Hermes. It creates runs with POST /v1/runs, streams Hermes events with SSE, polls run status as a fallback, and stops timed-out runs with POST /v1/runs/{run_id}/stop.

Compatibility with the old gateway package

@paperclipai/adapter-hermes-gateway remains as a deprecated compatibility shim for one release. It re-exports the gateway entrypoints from @paperclipai/hermes-paperclip-adapter/gateway and preserves the legacy exports for existing plugin installs. New installs and built-in Paperclip registrations should use @paperclipai/hermes-paperclip-adapter; the adapter type remains hermes_gateway.

Runtime API guidance

Hermes receives Paperclip runtime identity through environment variables:

  • PAPERCLIP_API_URL
  • PAPERCLIP_API_KEY
  • PAPERCLIP_RUN_ID

Prompts should reference those variables directly. Command output may redact secret values, so do not copy printed tokens into comments or config. Use Authorization: Bearer $PAPERCLIP_API_KEY on Paperclip API requests and X-Paperclip-Run-Id: $PAPERCLIP_RUN_ID on mutating issue requests. For multiline comments or status updates, preserve newlines with a heredoc plus jq --arg.

Hermes-originated Paperclip tasks

The package includes a Hermes skill/helper for the reverse direction: a user starts in Hermes and asks Hermes to create or update Paperclip work. This is not the same as Paperclip waking Hermes through hermes_local or hermes_gateway.

Configure Paperclip access in Hermes env/profile secrets, not prompt text:

PAPERCLIP_API_URL=http://127.0.0.1:3100/api
PAPERCLIP_BRIDGE_API_KEY=<task-bridge-scoped-agent-api-key>

Optional env values:

  • PAPERCLIP_COMPANY_ID
  • PAPERCLIP_AGENT_ID
  • PAPERCLIP_RUN_ID

The bundled paperclip-task-bridge skill provides deterministic helper commands:

node ./paperclip-task.mjs list-assigned
node ./paperclip-task.mjs create-task --parent-id "<approved-parent-issue-id>" --title "Investigate checkout failures" --description "Capture failing request and root cause."
node ./paperclip-task.mjs comment --issue PAP-123 --body "Found the failing request path."
node ./paperclip-task.mjs update-status --issue PAP-123 --status in_review --comment "Ready for review."

The helper reads credentials from environment variables and prints only JSON summaries. It supports create-task, comment, update-status, and list-assigned.

Create the bridge key with scope.kind = "task_bridge" plus a parentIssueId or projectId boundary. Do not use a normal claimed agent API key for internet-facing Hermes chat/webhook task-bridge operations.

4. Assign work

Create issues in Paperclip and assign them to your Hermes agent. On each heartbeat, Hermes will:

  1. Receive the task instructions
  2. Use its full tool suite to complete the work
  3. Report results back to Paperclip
  4. Persist session state for continuity

Configuration Reference

Core

Field Type Default Description
model string anthropic/claude-sonnet-4 Model in provider/model format
provider string (auto-detected) API provider: auto, openrouter, nous, openai-codex, zai, kimi-coding, minimax, minimax-cn
timeoutSec number 300 Execution timeout in seconds
graceSec number 10 Grace period before SIGKILL

Tools

Field Type Default Description
toolsets string (all) Comma-separated toolsets to enable (e.g. "terminal,file,web")

Available toolsets: terminal, file, web, browser, code_execution, vision, mcp, creative, productivity

Session & Workspace

Field Type Default Description
persistSession boolean true Resume sessions across heartbeats
worktreeMode boolean false Git worktree isolation
checkpoints boolean false Enable filesystem checkpoints for rollback

Advanced

Field Type Default Description
hermesCommand string hermes Custom CLI binary path
verbose boolean false Enable verbose output
quiet boolean true Quiet mode (clean output, no banner/spinner)
extraArgs string[] [] Additional CLI arguments
env object {} Extra environment variables
promptTemplate string (built-in) Custom prompt template
paperclipApiUrl string http://127.0.0.1:3100/api Paperclip API base URL

Prompt Template Variables

Use {{variable}} syntax in promptTemplate:

Variable Description
{{agentId}} Paperclip agent ID
{{agentName}} Agent display name
{{companyId}} Company ID
{{companyName}} Company name
{{runId}} Current heartbeat run ID
{{taskId}} Assigned task/issue ID
{{taskTitle}} Task title
{{taskBody}} Task instructions
{{projectName}} Project name
{{paperclipApiUrl}} Paperclip API base URL
{{commentId}} Comment ID (when woken by a comment)
{{wakeReason}} Reason this run was triggered

Conditional sections:

  • {{#taskId}}...{{/taskId}} — included only when a task is assigned
  • {{#noTask}}...{{/noTask}} — included only when no task (heartbeat check)
  • {{#commentId}}...{{/commentId}} — included only when woken by a comment

Architecture

Paperclip                          Hermes Agent
┌──────────────────┐               ┌──────────────────┐
│  Heartbeat       │               │                  │
│  Scheduler       │───execute()──▶│  hermes chat -q  │
│                  │               │                  │
│  Issue System    │               │  30+ Tools       │
│  Comment Wakes   │◀──results─────│  Memory System   │
│                  │               │  Session DB      │
│  Cost Tracking   │               │  Skills          │
│                  │               │  MCP Client      │
│  Skill Sync      │◀──snapshot────│  ~/.hermes/skills│
│  Org Chart       │               │                  │
└──────────────────┘               └──────────────────┘

The adapter spawns Hermes Agent's CLI in single-query mode (-q). Hermes processes the task using its full tool suite, then exits. The adapter:

  1. Captures stdout/stderr and parses token usage, session IDs, and cost
  2. Parses raw output into structured TranscriptEntry objects (tool cards with status icons)
  3. Post-processes Hermes ASCII formatting (banners, setext headings, table borders) into clean GFM markdown
  4. Reclassifies benign stderr (MCP init, structured logs) so they don't show as errors
  5. Tags sessions as tool source to keep them separate from interactive usage
  6. Reports results back to Paperclip with cost, usage, and session state

Session persistence works via Hermes's --resume flag — each run picks up where the last one left off, maintaining conversation context, memories, and tool state across heartbeats. The sessionCodec validates and migrates session state between runs.

Skills Integration

The adapter scans two skill sources and merges them:

  • Paperclip-managed skills — bundled with the adapter, togglable from the UI
  • Hermes-native skills — from ~/.hermes/skills/, read-only, always loaded

The listSkills / syncSkills APIs expose a unified snapshot so the Paperclip UI can display both managed and native skills in one view.

Development

git clone https://github.com/paperclipai/paperclip
cd paperclip/packages/adapters/hermes
pnpm install
pnpm build

License

MIT — see LICENSE