feat: OpenAI-compatible API server + streaming support#956
Closed
teknium1 wants to merge 10 commits into
Closed
Conversation
Cherry-picked from PR #828, rebased onto current main with conflict resolution.
… CORS Cherry-picked from PR #828.
Cherry-picked from PR #828.
Cherry-picked from PR #828.
Cherry-picked from PR #828.
Cherry-picked from PR #828, resolved conflicts with main.
… WebUI Cherry-picked from PR #828, resolved conflicts with main.
…tion, cache streaming config, add setup integration and security docs - Remove unused _write_sse_chat_completion pseudo-streaming method (dead code) - Extract _resolve_model() helper in gateway/run.py, use from api_server - Cache streaming config at GatewayRunner init instead of YAML parsing per-message - Add API_SERVER_* env vars to OPTIONAL_ENV_VARS for hermes setup integration - Add security warning about network exposure without API_SERVER_KEY
Add configurable reply_to_mode for Telegram multi-chunk replies: - off: never thread replies to original message - first: only first chunk threads (default, preserves current behavior) - all: all chunks thread to original message Configurable via reply_to_mode in platform config or TELEGRAM_REPLY_TO_MODE env var. Cherry-picked from PR #855 by raulvidis, rebased onto current main. Dropped asyncio_mode=auto pyproject.toml change, added @pytest.mark.asyncio decorators, fixed test IDs to use numeric strings. Co-authored-by: Raul <77628552+raulvidis@users.noreply.github.com>
3 tasks
This was referenced Mar 16, 2026
teknium1
added a commit
that referenced
this pull request
Mar 17, 2026
Salvaged from PR #956 (teknium1) onto current main. Adds an OpenAI-compatible HTTP server as a new gateway platform adapter. Any frontend that speaks the OpenAI format — Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc. — can connect to hermes-agent by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless chat (full conversation per request) - POST /v1/responses — stateful via previous_response_id or named conversations - GET/DELETE /v1/responses/{id} — retrieve/delete stored responses - GET /v1/models — model discovery - GET /health — health check Key features: - Real SSE streaming via stream_delta_callback - Responses API with server-side conversation state (in-memory LRU, max 100) - Named conversations via 'conversation' parameter - System prompt layering (frontend prompts add to core agent prompt) - Bearer token auth (optional, via HTTP_SERVER_KEY) - CORS support for browser-based frontends - Binds to 127.0.0.1 by default (secure) - Uses aiohttp (existing dependency, no new deps) Files: - gateway/platforms/http_server.py — adapter implementation - gateway/config.py — Platform.HTTP_SERVER enum + env var overrides - gateway/run.py — adapter factory branch - toolsets.py — hermes-http_server toolset - hermes_cli/config.py — setup env vars - .env.example — HTTP server env vars - tests/gateway/test_http_server.py — 72 tests - website/docs/ — HTTP server guide, Open WebUI integration guide Closes #956
teknium1
added a commit
that referenced
this pull request
Mar 17, 2026
Salvaged from PR #956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR #956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference
teknium1
added a commit
that referenced
this pull request
Mar 17, 2026
…ix (#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR #956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR #956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR #1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR #1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 27, 2026
…ix (NousResearch#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR NousResearch#956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR NousResearch#956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR NousResearch#1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR NousResearch#1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 28, 2026
Salvaged from PR NousResearch#956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR NousResearch#956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 28, 2026
Salvaged from PR NousResearch#956 (teknium1) onto current main. Adds an OpenAI-compatible HTTP server as a new gateway platform adapter. Any frontend that speaks the OpenAI format — Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc. — can connect to hermes-agent by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless chat (full conversation per request) - POST /v1/responses — stateful via previous_response_id or named conversations - GET/DELETE /v1/responses/{id} — retrieve/delete stored responses - GET /v1/models — model discovery - GET /health — health check Key features: - Real SSE streaming via stream_delta_callback - Responses API with server-side conversation state (in-memory LRU, max 100) - Named conversations via 'conversation' parameter - System prompt layering (frontend prompts add to core agent prompt) - Bearer token auth (optional, via HTTP_SERVER_KEY) - CORS support for browser-based frontends - Binds to 127.0.0.1 by default (secure) - Uses aiohttp (existing dependency, no new deps) Files: - gateway/platforms/http_server.py — adapter implementation - gateway/config.py — Platform.HTTP_SERVER enum + env var overrides - gateway/run.py — adapter factory branch - toolsets.py — hermes-http_server toolset - hermes_cli/config.py — setup env vars - .env.example — HTTP server env vars - tests/gateway/test_http_server.py — 72 tests - website/docs/ — HTTP server guide, Open WebUI integration guide Closes NousResearch#956
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…ix (NousResearch#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR NousResearch#956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR NousResearch#956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR NousResearch#1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR NousResearch#1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
olympus-terminal
pushed a commit
to olympus-terminal/hermes-agent
that referenced
this pull request
May 16, 2026
…ix (NousResearch#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR NousResearch#956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR NousResearch#956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR NousResearch#1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR NousResearch#1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
CumulusService
pushed a commit
to Cumulus-Service-GmbH/hermes-agent
that referenced
this pull request
May 30, 2026
Salvaged from PR NousResearch#956 (teknium1) onto current main. Adds an OpenAI-compatible HTTP server as a new gateway platform adapter. Any frontend that speaks the OpenAI format — Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc. — can connect to hermes-agent by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless chat (full conversation per request) - POST /v1/responses — stateful via previous_response_id or named conversations - GET/DELETE /v1/responses/{id} — retrieve/delete stored responses - GET /v1/models — model discovery - GET /health — health check Key features: - Real SSE streaming via stream_delta_callback - Responses API with server-side conversation state (in-memory LRU, max 100) - Named conversations via 'conversation' parameter - System prompt layering (frontend prompts add to core agent prompt) - Bearer token auth (optional, via HTTP_SERVER_KEY) - CORS support for browser-based frontends - Binds to 127.0.0.1 by default (secure) - Uses aiohttp (existing dependency, no new deps) Files: - gateway/platforms/http_server.py — adapter implementation - gateway/config.py — Platform.HTTP_SERVER enum + env var overrides - gateway/run.py — adapter factory branch - toolsets.py — hermes-http_server toolset - hermes_cli/config.py — setup env vars - .env.example — HTTP server env vars - tests/gateway/test_http_server.py — 72 tests - website/docs/ — HTTP server guide, Open WebUI integration guide Closes NousResearch#956
CumulusService
pushed a commit
to Cumulus-Service-GmbH/hermes-agent
that referenced
this pull request
May 30, 2026
Salvaged from PR NousResearch#956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR NousResearch#956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…ix (NousResearch#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR NousResearch#956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR NousResearch#956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR NousResearch#1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR NousResearch#1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…ix (NousResearch#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR NousResearch#956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR NousResearch#956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR NousResearch#1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR NousResearch#1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Rebased and improved version of PR #828. Adds an OpenAI-compatible HTTP API server as a gateway platform adapter, plus streaming support across all platforms.
What this enables
Any OpenAI-compatible frontend — Open WebUI (126k★), LobeChat (73k★), LibreChat (34k★), AnythingLLM (56k★), NextChat (87k★), ChatBox (39k★), etc. — can connect to hermes-agent by pointing at
http://localhost:8642/v1.Endpoints
/v1/chat/completions/v1/responsesprevious_response_idorconversation)/v1/responses/{id}/v1/responses/{id}/v1/models/healthKey features
conversationparameterAPI_SERVER_KEYenv varImprovements over PR #828
_write_sse_chat_completionpseudo-streaming method deleted_resolve_model()helper in gateway/run.py — API server now imports it instead of duplicating the YAML parsingGatewayRunner.__init__instead of parsing config.yaml on every messageAPI_SERVER_ENABLED,API_SERVER_KEY,API_SERVER_PORT,API_SERVER_HOSTregistered inOPTIONAL_ENV_VARSsohermes setupprompts for themDocumentation
Test results