Files
PaperClipAI/packages/adapters/hermes
DottaandPaperclip 9f7057e122 feat(connections): configure custom model providers across agent harnesses (#14970)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agents use a harness, a model, and a credential to run tasks.
> - Connections already store credentials and control who can use them.
> - Custom providers also need an endpoint and a supported API format.
> - A per-agent endpoint would duplicate credentials and access rules.
> - This pull request stores routing on the connection and projects it
into the harness.
> - Isolated credentials and protocol checks keep the selected
connection authoritative.

## Linked Issues or Issue Description

Refs #37, #13083, #14104, #14565, #12692.

#14016 is a reference only. This PR has its own schema, vault
persistence, routing validation, runtime projection, and tests. None of
the five commits in #14016 is an ancestor of this branch. We do not
depend on or plan to merge it. #14967 addresses task-pinned account
pools. #14422 addresses another provider integration.

This is the first of two linked PRs. Merge this connection change before
#15341, which refines agent setup and adds the qualification harness.
The split keeps each review below 100 changed files. Provider catalog
entries have usable setup forms in this PR. Local browser subscription
sign-in is included.

## What Changed

- Store non-secret routing metadata on AI connections. Vault provider
API keys, including Bedrock bearer API keys. Reject general AWS access
keys.
- Enforce company, owner, human audience, agent access, connection
status, and protocol checks before resolving credentials. Keep reconnect
destinations immutable and retain connection identity during key
rotation.
- Project OpenRouter and compatible custom endpoints into Codex, Claude,
OpenCode, and local Hermes. Carry these settings through both legacy and
native runner transports. Clear conflicting host credentials and redact
keys from diagnostics.
- Preserve older OpenRouter accounts and native personal defaults. Add
Google API-key accounts and migration `0306` for the two
provider-default constraints.
- Run local Claude and Codex subscription sign-in behind the existing
browser sign-in card. Use private attempt homes and owner-bound
completion instead of a copied terminal command.
- Seed isolated Gemini authentication and preserve OpenCode workspace
permissions. Keep the selected connection authoritative. The independent
Gemini and Grok workflow fixes are in #15341.
- Keep native OpenCode custom gateway keys in a runner-owned
selected-model proxy; the harness config contains only a session-scoped
capability. Honor runtime outgoing proxy and certificate settings.
Preserve streamed responses and revoke the proxy on close or startup
failure.
- Allow ordinary members to connect native personal accounts before an
agent exists.
- Repair routed accounts from task cards using the saved provider
destination, protocol, model aliases, and connection identity.
- Add provider catalog definitions, model discovery, pinned logos, and
complete native and routed setup forms. Allow a personal routed
connection before a new agent exists. Keep endpoint authentication keys
out of Hermes terminal children.
- Recover cancelled or restarted browser sign-in with a clear restart
action. Support no-auth endpoints without a vault credential. Add
isolation and recovery regressions and runtime documentation.

## Verification

- Updated with `origin/master` at `22a3ea341`. Migration `0306` follows
the new master migration and passes migration and snapshot checks.
- The integrated connection regressions passed 152 tests and 50 native
OpenCode driver tests, including key-free child-shell configuration
reads, authenticated/no-auth forwarding, streaming, model/path
restrictions, cancellation, outgoing proxy routing, and NO_PROXY bypass.
Provider setup has 14 passing tests. The pinned real OpenCode 1.18.34
executable also completed a turn through the proxy against a local
synthetic provider; the reusable key was absent from its config. A
second real-executable smoke passed with an HTTPS CONNECT proxy and
runtime-specific synthetic certificate trust. Certificate-file and
certificate-directory regressions pass.
- Task-card repair passed 48 tests, including OpenRouter, Bedrock, and
custom gateway reconnect cases. UI typecheck and token gates passed.
- The prior core regression set passed 133 tests across new-agent setup,
provider forms, browser sign-in, routing projection, and connection
authorization. Token gates and UI typecheck passed.
- Full workspace typecheck and production build passed again after the
latest integration and credential-proxy fix. The merged deterministic
runner E2E suite passed 1,400 Vitest tests and 128 Node tests.
- Full workspace typecheck passed on the prior linked combined
implementation. Production build, Storybook build, 1,316 browser-harness
Vitest tests, and 128 Node tests passed. Head `9d964c8d9` includes the
latest master integration and regenerated migration. This exact head
passed 54 remote checks with four expected skips and Greptile 5/5; no
review threads remain open. An unchanged server fixture had a random
six-character issue-prefix collision on its first attempt. All 245 tests
passed locally and the single CI retry passed.
- A provider-free terminal check used the cited supported Hermes source
and dummy keys. Gateway and OpenRouter terminal children could not read
the selected key.
- The broad local Vitest attempt passed 15,442 tests but was not green.
It had an embedded-Postgres startup failure, an HTTP logger timeout, an
origin socket error, and a browser cancellation wait timeout. The
cancellation wait was corrected. The relevant connection tests and the
full origin test file passed separately. Latest-head CI must pass before
merge.
- Prior credential-backed acceptance exercised task creation, tool use,
artifact delivery, completion, and context-dependent follow-up. Claude
legacy and native runners passed Bedrock with `us-east-1` and
`us.anthropic.claude-sonnet-4-6`.
- Historical local qualification retained 43 passing API/gateway cells
out of 46. Those attempts span earlier builds. They do not qualify this
exact commit or staging. All subscription combinations and staging
remain unqualified.
- Verify native subscription and API-key setup. Connect a regular
provider catalog row. Verify an incompatible harness and a changed
reconnect URL are rejected. Use #15341 for the complete browser
campaign.

## Risks

- Migration `0306` changes two check constraints. It preserves rows and
is safe to reapply. It takes normal constraint-change locks.
- Credential projection touches several harnesses. CLI upgrades can
change provider configuration and session behavior.
- The native OpenCode proxy adds a loopback hop, pins requests to the
selected model, limits request bodies to 16 MiB, rejects redirects, and
expires at session close. It prevents reusable keys in the child
configuration; it is not an OS isolation boundary against a process
debugger running as the same user.
- Custom endpoints must be reachable from the agent environment. Saving
a connection does not prove connectivity. Bedrock keys require rotation
before expiry.
- Gemini CLI 0.58.0 has an upstream ACP new-file error conversion
defect. Provider overloads and an unresolved follow-up timeout also
affect live Gemini qualification. We have not patched the installed CLI
or marked those cases as passing.
- OpenClaw Gateway, Hermes Gateway, Claude Managed, AWS AgentCore,
Process, HTTP, and legacy ACPX local are excluded. Vertex, ambient AWS
identity, arbitrary auth headers, and custom routing for other harnesses
are excluded.
- These PRs do not establish production or staging qualification for
every provider and login method.

## Model Used

OpenAI GPT-6 through Codex, with reasoning, repository tools, code
execution, and browser testing. The exact deployment model ID and
context window size were not exposed in this session.

## 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
- [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 (e.g. `docs/...`, `fix/...`)
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
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-10-06 13:29:03 -05:00
..

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