feat: Add Notion integration tool + skill by dogiladeveloper · Pull Request #26 · NousResearch/hermes-agent

dogiladeveloper · 2026-02-25T21:38:52Z

What this PR adds

Full Notion integration for Hermes Agent — 7 tools covering the complete CRUD lifecycle.

Tools added:

notion_search - Search pages/databases
notion_get_page - Read full page content
notion_create_page - Create new pages
notion_append_blocks - Append content
notion_update_page - Update properties
notion_query_database - Query with filters
notion_delete_block - Archive blocks

Setup:

Add NOTION_API_KEY=secret_xxx to ~/.hermes/.env

Files added:

tools/notion.py
skills/notion/SKILL.md
tests/test_notion.py

DEV ROLE submission — Notion integration built with Claude AI assistance, all tests passing ✅

Discord: dogiladeveloper

Added Notion integration skill documentation including usage, setup, and procedures for various operations.

teknium1 · 2026-02-26T09:05:49Z

Already have a skill for notion!

…space shell Cherry-picked from PR NousResearch#26 (clawjasper56). Replaces hardcoded authenticated=true with useQuery to /api/auth-check endpoint. Resolved conflict with our isMobile state addition.

When the Hermes gateway is running but the HTTP API server is not enabled, the onboarding screen shows generic advice that doesn't address the actual problem. Users can have a fully functional gateway (serving Telegram, Discord, etc.) while the workspace can't connect. Changes: - Onboarding connection error now shows step-by-step instructions: 1. Add API_SERVER_ENABLED=true to ~/.hermes/.env 2. Restart the gateway - Updated .env.example to document the requirement - Added Ollama/LiteLLM/vLLM as explicit alternative backend options Fixes NousResearch#26

…agents (phase 10) The SDK landed PRs NousResearch#24/NousResearch#25/NousResearch#26 in synadia-ai/synadia-agents: - verb-first subjects (`agents.prompt.{a}.{o}.{s}`, `agents.hb.{a}.{o}.{s}`, new `agents.status.{a}.{o}.{s}`) and `metadata.protocol_version="0.3"` - pinned `_INBOX.agents` reply-inbox prefix (caller-side; no-op for us) - `name`+`session` collapsed into a single `session_name` (the 5th subject token) — `Envelope.session` and the `session=` kwarg on `AgentService` / `Agent.prompt` are gone. One service = one session_name. Package + import root rename: `natsagent` → `synadia-ai-agents`, `synadia_ai.agents`. Service-side class `Agent` → `AgentService`. Adapter changes: - Adopt single-service-per-session: rely on Hermes profile isolation for multi-session deployments instead of building an envelope.session demuxer on top of `AgentService`. The `_session_locks` dict collapses to a single `_session_lock`. - The SDK explicitly does not own NATS connections: callers build the client. Adapter calls `nats.connect(servers=...)` or `nats.connect(**sdk.load_context_options(name))` directly. - Config: `extra.name` + `extra.session_default` → required `extra.session_name`; env var `HERMES_NATS_NAME`/`HERMES_NATS_SESSION` → `HERMES_NATS_SESSION_NAME`. No migration shim — branch hadn't merged. - Lock identity rebuilt as `{agent}:{owner}:{session_name}`. Tests + docs: - conftest mock renamed `_ensure_natsagent_mock` → `_ensure_synadia_agents_mock`, installs under `sys.modules["synadia_ai.agents"]`, also stubs `nats` so the adapter's `nats.connect(...)` resolves under test. - New `mock_nats` fixture in test_nats_connect.py; concurrent-distinct- sessions test removed (v0.2-only concept); positive test added that chat_id is sourced from `settings.session_name` regardless of any stray envelope field. - design doc §1-§6/§11/§17 updated for v0.3; progress doc gains a Phase 10 decision-log entry; user-facing nats.md rewritten with verb-first subject examples, status endpoint walkthrough, and `_INBOX.agents.>` permission note. Live-verified end-to-end against `nats-server -p 4223` + `hermes-local` context + `model: anthropic/claude-haiku-4.5` over OpenRouter: real prompt streamed a real haiku reply through `agents.prompt.hermes.rene.local`, multi-turn session continuity intact, `/status` slash command dispatched through the gateway's command registry. Discovery shows `protocol_version: 0.3`. Heartbeats fire on `agents.hb.hermes.rene.local`. Status endpoint replies on `agents.status.hermes.rene.local`. NATS gateway tests: 190/190 green. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

) When the WebUI's model picker sets the active provider to "venice" (or "crof", "bankr", "cometapi"), the agent's resolve_provider_client() looked up the slug in PROVIDER_REGISTRY, failed to find it, and raised: "Provider 'venice' is set in config.yaml but no API key was found. Set the VENICE_API_KEY environment variable..." VENICE_API_KEY WAS set in env — the failure was because the agent had no idea which env var or base URL to use for "venice" as a slug. PROVIDER_REGISTRY entries for the other OpenAI-compatible aggregators (Z.AI, MiniMax, Mistral, etc.) already existed; Venice/CrofAI/Bankr/CometAPI just hadn't been added in the upstream code. Adds four api_key-auth entries mirroring the existing OpenAI-compat ones: - venice → https://api.venice.ai/api/v1 + VENICE_API_KEY - crof → https://crof.ai/v1 + CROF_API_KEY - bankr → https://gateway.bankr.bot/v1 + BANKR_API_KEY - cometapi → https://api.cometapi.com/v1 + COMETAPI_API_KEY Companion to the WebUI side (PRs #26/#27/#29/#30/#32/#33) which made these providers discoverable in the model picker with their live /v1/models catalogs. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…agents (phase 10) The SDK landed PRs NousResearch#24/NousResearch#25/NousResearch#26 in synadia-ai/synadia-agents: - verb-first subjects (`agents.prompt.{a}.{o}.{s}`, `agents.hb.{a}.{o}.{s}`, new `agents.status.{a}.{o}.{s}`) and `metadata.protocol_version="0.3"` - pinned `_INBOX.agents` reply-inbox prefix (caller-side; no-op for us) - `name`+`session` collapsed into a single `session_name` (the 5th subject token) — `Envelope.session` and the `session=` kwarg on `AgentService` / `Agent.prompt` are gone. One service = one session_name. Package + import root rename: `natsagent` → `synadia-ai-agents`, `synadia_ai.agents`. Service-side class `Agent` → `AgentService`. Adapter changes: - Adopt single-service-per-session: rely on Hermes profile isolation for multi-session deployments instead of building an envelope.session demuxer on top of `AgentService`. The `_session_locks` dict collapses to a single `_session_lock`. - The SDK explicitly does not own NATS connections: callers build the client. Adapter calls `nats.connect(servers=...)` or `nats.connect(**sdk.load_context_options(name))` directly. - Config: `extra.name` + `extra.session_default` → required `extra.session_name`; env var `HERMES_NATS_NAME`/`HERMES_NATS_SESSION` → `HERMES_NATS_SESSION_NAME`. No migration shim — branch hadn't merged. - Lock identity rebuilt as `{agent}:{owner}:{session_name}`. Tests + docs: - conftest mock renamed `_ensure_natsagent_mock` → `_ensure_synadia_agents_mock`, installs under `sys.modules["synadia_ai.agents"]`, also stubs `nats` so the adapter's `nats.connect(...)` resolves under test. - New `mock_nats` fixture in test_nats_connect.py; concurrent-distinct- sessions test removed (v0.2-only concept); positive test added that chat_id is sourced from `settings.session_name` regardless of any stray envelope field. - design doc §1-§6/§11/§17 updated for v0.3; progress doc gains a Phase 10 decision-log entry; user-facing nats.md rewritten with verb-first subject examples, status endpoint walkthrough, and `_INBOX.agents.>` permission note. Live-verified end-to-end against `nats-server -p 4223` + `hermes-local` context + `model: anthropic/claude-haiku-4.5` over OpenRouter: real prompt streamed a real haiku reply through `agents.prompt.hermes.rene.local`, multi-turn session continuity intact, `/status` slash command dispatched through the gateway's command registry. Discovery shows `protocol_version: 0.3`. Heartbeats fire on `agents.hb.hermes.rene.local`. Status endpoint replies on `agents.status.hermes.rene.local`. NATS gateway tests: 190/190 green. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Fixes 12 remaining MEDIUM issues from the deep audit (19 total, 7 fixed in Round 12): design_agent: - NousResearch#15: add asyncio.wait_for(300s) around LLM API call to prevent infinite hangs - NousResearch#17: replace 2x hardcoded 'claude-opus-4-8' with shared DEFAULT_MODEL constant qa_agent / validate_agent: - NousResearch#20,NousResearch#22,NousResearch#23: already fixed in Round 12 (verified — dynamic timeout/threshold values used) memory.py: - NousResearch#24: frontmatter parser uses regex r'^---$' instead of str.split('---',2), preventing false splits on content containing '---' (SQL, markdown tables) - NousResearch#25: parse and preserve 'description' field from frontmatter in metadata, fixing write→load roundtrip data loss profiles.py: - NousResearch#26: ProfileConfig now frozen=True (immutable dataclass per coding standards) deploy_agent: - NousResearch#31: replace 2x sync subprocess.run with asyncio.create_subprocess_exec - fix 5x .decode() → .decode('utf-8', errors='replace') for Windows CJK safety - remove unused import subprocess db.py: - NousResearch#27: add class docstring explaining RLock + _unlocked pattern - NousResearch#28: FK constraints already in DDL (verified PRAGMA foreign_keys=ON active) - NousResearch#29: add _ensure_connection() with PRAGMA integrity_check(1) + auto-reconnect on 4 critical methods (create_task, get_task, claim_task, submit_result) - extract _create_connection() static method for reuse by reconnect Tests: 79 passed, 0 failed

- react-router: 7.14.2 → 7.17.0 (CVE-2026-42342, GHSA-8x6r-g9mw-2r78) - Fixes Dependabot alert #26

…Research#27) The desktop picker listed no Anthropic models at all while the Claude subscription token was perfectly valid. list_authenticated_providers() decided whether to emit the provider row from os.environ + auth.json only, so a backend spawned from a stripped launcher environment saw none of ANTHROPIC_API_KEY / ANTHROPIC_TOKEN / CLAUDE_CODE_OAUTH_TOKEN and dropped the row before any model list was built. Claude Code persists that token as a Windows USER env var (HKCU\Environment), which a process inherits only if every ancestor of its launch chain did -- hence the intermittent, recurring failure. Two layers had to change: - model_switch: new _has_resolvable_provider_token() delegates to resolve_anthropic_token(), which already implements the documented resolution order (env -> HKCU registry -> credential file -> pool). Wired into both credential gates, after the cheap env test so the common path stays allocation-free, and defensively imported so a broken adapter cannot take down the whole picker. - auth: is_provider_explicitly_configured() excluded CLAUDE_CODE_OAUTH_TOKEN as ambient, which filtered the row back out of every explicit_only surface (the chat picker passes explicit_only=1) even once the listing gate accepted it. A token inherited in the process env is still treated as ambient; one persisted under HKCU\Environment is durable user configuration. Verified live against the running backend on port 54306: before the fix GET /api/model/options omitted anthropic entirely and ?explicit_only=1 showed a single-model re-auth placeholder row (claude-sonnet-4-6 only), which is why no other Claude model could be selected. After the fix the same code path emits all ten models (claude-sonnet-5, claude-fable-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-sonnet-4-6 and the dated 4.5/4.1 snapshots) in both modes, and still does when the live catalog fetch fails, so a cold gateway restart keeps a populated list. Also documents the CRITICAL NousResearch#26 context clamp at its application site. The 1M window on these models is real; the 200K default is deliberate billing protection, because >200K input on a subscription bills the non-refilling extra-usage lane. The clamp and its anthropic.long_context escape hatch are unchanged and now pinned by a test in both directions. Corrects a stale comment referencing a _seed_from_singletons() helper that does not exist.

HermesNative renders ```sankey (researchoors/hermes-native#198) and ```timeline (researchoors/hermes-native#199) blocks natively and captures id-bearing ones as living artifacts. Both kinds replace wholesale on merge (no per-kind merge needed), so only the agent tool's allowlist and schema enum need to know about them — the store already handles unknown kinds by replacement. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

…AN-1385) (NousResearch#26) baileys 7.0.0-rc.9->rc13 (clears NousResearch#43 critical) + protobufjs 7.6.4 (NousResearch#59,NousResearch#58) in whatsapp-bridge; esbuild+tsx (NousResearch#46,NousResearch#61) in ui-tui; @babel/core (NousResearch#84) in web; joi+http-proxy-middleware (NousResearch#51,NousResearch#89) in website. js-yaml NousResearch#86 accepted (no in-range fix via gray-matter). Bridge startup verified. NousResearch#93/NousResearch#94 (code fixes) separate. Co-Authored-By: Claude <noreply@anthropic.com>

Dep-inventory items #26/#27/#32: three copies of the same uv - pip - ensurepip strategy grew independently, and lazy_deps' docstring admitted being a mirror of tools_config's. Copies drift: the lazy copy had learned that a uv resolver failure must be final (falling to pip discards exclude-newer and can install a quarantined release) while the setup-hook copy still fell through, and only one of them hid console windows on Windows. installation/pip_ladder.py now owns the mechanics, stdlib-only under the same run-dont-parse audit as the rest of the package (the ladder exists precisely for venvs that are missing pip). The policy choices that used to be baked into each copy are arguments: * uv_bin - the caller decides what acquiring uv is worth. Setup hooks pass ensure_uv() (downloading uv is in scope during setup); lazy installs pass resolve_uv() (a download as a side effect of an optional import is not). * uv_resolver_failure_is_final - the lazy policy above. Availability failures (binary vanished, could not exec) always fall through: uv never evaluated the requirements, so pip is not a second opinion. * target/constraints - the durable overlay mode sealed installs use. tools_config._pip_install and lazy_deps._venv_pip_install are now thin policy wrappers; agent/lsp/install.py already delegated to the former, so the third copy collapses transitively. A structural test walks both wrappers' AST (code, not docstrings) and fails if either regrows a private ladder. The 5 failing tests in test_lazy_deps.py fail identically without this change (verified by stash round-trip): pre-existing on the branch, not introduced here.

…usResearch#24 NousResearch#26 NousResearch#25 NousResearch#27 NousResearch#28)

Dep-inventory items #26/#27/#32: three copies of the same uv - pip - ensurepip strategy grew independently, and lazy_deps' docstring admitted being a mirror of tools_config's. Copies drift: the lazy copy had learned that a uv resolver failure must be final (falling to pip discards exclude-newer and can install a quarantined release) while the setup-hook copy still fell through, and only one of them hid console windows on Windows. installation/pip_ladder.py now owns the mechanics, stdlib-only under the same run-dont-parse audit as the rest of the package (the ladder exists precisely for venvs that are missing pip). The policy choices that used to be baked into each copy are arguments: * uv_bin - the caller decides what acquiring uv is worth. Setup hooks pass ensure_uv() (downloading uv is in scope during setup); lazy installs pass resolve_uv() (a download as a side effect of an optional import is not). * uv_resolver_failure_is_final - the lazy policy above. Availability failures (binary vanished, could not exec) always fall through: uv never evaluated the requirements, so pip is not a second opinion. * target/constraints - the durable overlay mode sealed installs use. tools_config._pip_install and lazy_deps._venv_pip_install are now thin policy wrappers; agent/lsp/install.py already delegated to the former, so the third copy collapses transitively. A structural test walks both wrappers' AST (code, not docstrings) and fails if either regrows a private ladder. The 5 failing tests in test_lazy_deps.py fail identically without this change (verified by stash round-trip): pre-existing on the branch, not introduced here.

…eway-wsl-conflict-issue168 fix(desktop): 处理已存在其它 Hermes Agent 时桌面端无法启动飞书网关 (NousResearch#168)

dogiladeveloper added 5 commits February 26, 2026 00:29

Add files via upload

da606b8

Add Notion integration skill documentation

ec8ff58

Added Notion integration skill documentation including usage, setup, and procedures for various operations.

Add files via upload

677e23c

Add files via upload

d83977f

Update GitHub handle in PR description

231c637

teknium1 closed this Feb 26, 2026

kshitijk4poor mentioned this pull request Apr 15, 2026

feat: add TouchDesigner integration skill (twozero MCP) #10081

Closed

jerilynzheng mentioned this pull request Apr 20, 2026

feat: add pricing, attribution, and dynamic discovery for ai-gateway jerilynzheng/hermes-agent#2

Open

4 tasks

unimatrix27 mentioned this pull request May 12, 2026

Finance reconciliation: reconcile-receipts skill + cron (closes unimatrix27/ideas#25) unimatrix27/hermes-agent#6

Open

10 tasks

ashneil12 mentioned this pull request May 18, 2026

fix(auth): register Venice/Crof/Bankr/CometAPI in PROVIDER_REGISTRY ashneil12/vanilla-hermes-agent#16

Merged

3 tasks

Axighi mentioned this pull request May 29, 2026

Rebrand #10: Update Nix flake and Homebrew packaging Axighi/atlaz#13

Closed

3 tasks

acoastalfog mentioned this pull request Jun 3, 2026

Guided KB Review Sessions: Telegram queue cards #38025

Closed

dizhaky mentioned this pull request Jun 4, 2026

fix(deps): bump react-router-dom to ^7.15.0 (HIGH CVE-2026-42342) dizhaky/hermes-agent#4

Merged

dizhaky referenced this pull request in dizhaky/hermes-agent Jun 4, 2026

fix(deps): bump react-router-dom to ^7.15.0 to fix ReDoS (#4)

b514c8b

- react-router: 7.14.2 → 7.17.0 (CVE-2026-42342, GHSA-8x6r-g9mw-2r78) - Fixes Dependabot alert #26

SollanSystems mentioned this pull request Jun 9, 2026

fix(profile): fast alias scan + setup roadmap artifacts (M1–M7) #43040

Closed

zero-two-rafaeltab mentioned this pull request Jun 11, 2026

Add a Hermes-native child session terminal continuation seam #44448

Closed

webtecnica mentioned this pull request Jul 27, 2026

feat(agent): add live upgrade — checkpoint subagents before restart and adopt orphans on startup (#71023) #71027

Open

GottZ mentioned this pull request Jul 30, 2026

Deepen Notion API skill and docs #27915

Open

DavidMetcalfe mentioned this pull request Aug 10, 2026

[Bug] Gateway clarify reply bypass misses on profile-namespaced session keys — follow-up messages queued instead of resolving pending clarify (Telegram) #82975

Closed

choi138 added a commit to choi138/hermes-agent that referenced this pull request Aug 18, 2026

merge: integrate M8 gateway chain (NousResearch#22 NousResearch#23 No…

b9ad5f4

…usResearch#24 NousResearch#26 NousResearch#25 NousResearch#27 NousResearch#28)

daragao3 mentioned this pull request Aug 24, 2026

fix(session-bridge): align auth-recovery daily-limit ceiling with launch daragao3/hermes-agent#6

Merged

rikets Bot mentioned this pull request Aug 26, 2026

Kanban stop-nudge is formatted as a prompt injection, so safety-trained models refuse it and crash-loop #95488

Open

Navigation Menu

Uh oh!

feat: Add Notion integration tool + skill - #26

feat: Add Notion integration tool + skill#26
dogiladeveloper wants to merge 5 commits into
NousResearch:mainfrom
dogiladeveloper:main

dogiladeveloper commented Feb 25, 2026

Uh oh!

teknium1 commented Feb 26, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

dogiladeveloper commented Feb 25, 2026

What this PR adds

Tools added:

Setup:

Files added:

Uh oh!

teknium1 commented Feb 26, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants