hermes-agent/hermes_cli
Teknium 70768665a4
fix(mcp): consolidate OAuth handling, pick up external token refreshes (#11383)
* feat(mcp-oauth): scaffold MCPOAuthManager

Central manager for per-server MCP OAuth state. Provides
get_or_build_provider (cached), remove (evicts cache + deletes
disk), invalidate_if_disk_changed (mtime watch, core fix for
external-refresh workflow), and handle_401 (dedup'd recovery).

No behavior change yet — existing call sites still use
build_oauth_auth directly. Task 1 of 8 in the MCP OAuth
consolidation (fixes Cthulhu's BetterStack reliability issues).

* feat(mcp-oauth): add HermesMCPOAuthProvider with pre-flow disk watch

Subclasses the MCP SDK's OAuthClientProvider to inject a disk
mtime check before every async_auth_flow, via the central
manager. When a subclass instance is used, external token
refreshes (cron, another CLI instance) are picked up before
the next API call.

Still dead code: the manager's _build_provider still delegates
to build_oauth_auth and returns the plain OAuthClientProvider.
Task 4 wires this subclass in. Task 2 of 8.

* refactor(mcp-oauth): extract build_oauth_auth helpers

Decomposes build_oauth_auth into _configure_callback_port,
_build_client_metadata, _maybe_preregister_client, and
_parse_base_url. Public API preserved. These helpers let
MCPOAuthManager._build_provider reuse the same logic in Task 4
instead of duplicating the construction dance.

Also updates the SDK version hint in the warning from 1.10.0 to
1.26.0 (which is what we actually require for the OAuth types
used here). Task 3 of 8.

* feat(mcp-oauth): manager now builds HermesMCPOAuthProvider directly

_build_provider constructs the disk-watching subclass using the
helpers from Task 3, instead of delegating to the plain
build_oauth_auth factory. Any consumer using the manager now gets
pre-flow disk-freshness checks automatically.

build_oauth_auth is preserved as the public API for backwards
compatibility. The code path is now:

    MCPOAuthManager.get_or_build_provider  ->
      _build_provider  ->
        _configure_callback_port
        _build_client_metadata
        _maybe_preregister_client
        _parse_base_url
        HermesMCPOAuthProvider(...)

Task 4 of 8.

* feat(mcp): wire OAuth manager + add _reconnect_event

MCPServerTask gains _reconnect_event alongside _shutdown_event.
When set, _run_http / _run_stdio exit their async-with blocks
cleanly (no exception), and the outer run() loop re-enters the
transport to rebuild the MCP session with fresh credentials.
This is the recovery path for OAuth failures that the SDK's
in-place httpx.Auth cannot handle (e.g. cron externally consumed
the refresh_token, or server-side session invalidation).

_run_http now asks MCPOAuthManager for the OAuth provider
instead of calling build_oauth_auth directly. Config-time,
runtime, and reconnect paths all share one provider instance
with pre-flow disk-watch active.

shutdown() defensively sets both events so there is no race
between reconnect and shutdown signalling.

Task 5 of 8.

* feat(mcp): detect auth failures in tool handlers, trigger reconnect

All 5 MCP tool handlers (tool call, list_resources, read_resource,
list_prompts, get_prompt) now detect auth failures and route
through MCPOAuthManager.handle_401:

  1. If the manager says recovery is viable (disk has fresh tokens,
     or SDK can refresh in-place), signal MCPServerTask._reconnect_event
     to tear down and rebuild the MCP session with fresh credentials,
     then retry the tool call once.

  2. If no recovery path exists, return a structured needs_reauth
     JSON error so the model stops hallucinating manual refresh
     attempts (the 'let me curl the token endpoint' loop Cthulhu
     pasted from Discord).

_is_auth_error catches OAuthFlowError, OAuthTokenError,
OAuthNonInteractiveError, and httpx.HTTPStatusError(401). Non-auth
exceptions still surface via the generic error path unchanged.

Task 6 of 8.

* feat(mcp-cli): route add/remove through manager, add 'hermes mcp login'

cmd_mcp_add and cmd_mcp_remove now go through MCPOAuthManager
instead of calling build_oauth_auth / remove_oauth_tokens
directly. This means CLI config-time state and runtime MCP
session state are backed by the same provider cache — removing
a server evicts the live provider, adding a server populates
the same cache the MCP session will read from.

New 'hermes mcp login <name>' command:
  - Wipes both the on-disk tokens file and the in-memory
    MCPOAuthManager cache
  - Triggers a fresh OAuth browser flow via the existing probe
    path
  - Intended target for the needs_reauth error Task 6 returns
    to the model

Task 7 of 8.

* test(mcp-oauth): end-to-end integration tests

Five new tests exercising the full consolidation with real file
I/O and real imports (no transport mocks):

  1. external_refresh_picked_up_without_restart — Cthulhu's cron
     workflow. External process writes fresh tokens to disk;
     on the next auth flow the manager's mtime-watch flips
     _initialized and the SDK re-reads from storage.

  2. handle_401_deduplicates_concurrent_callers — 10 concurrent
     handlers for the same failed token fire exactly ONE recovery
     attempt (thundering-herd protection).

  3. handle_401_returns_false_when_no_provider — defensive path
     for unknown servers.

  4. invalidate_if_disk_changed_handles_missing_file — pre-auth
     state returns False cleanly.

  5. provider_is_reused_across_reconnects — cache stickiness so
     reconnects preserve the disk-watch baseline mtime.

Task 8 of 8 — consolidation complete.
2026-04-16 21:57:10 -07:00
..
__init__.py chore: release v0.10.0 (2026.4.16) (#11209) 2026-04-16 12:53:06 -07:00
auth.py feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270) 2026-04-16 16:49:00 -07:00
auth_commands.py feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270) 2026-04-16 16:49:00 -07:00
backup.py feat: fix SQLite safety in hermes backup + add --quick snapshots + /snapshot command (#8971) 2026-04-13 04:46:13 -07:00
banner.py refactor: remove dead code — 1,784 lines across 77 files (#9180) 2026-04-13 16:32:04 -07:00
callbacks.py fix: ESC cancels secret/sudo prompts, clearer skip messaging (#9902) 2026-04-14 16:11:37 -07:00
claw.py fix: unify OpenClaw detection, add isatty guard, fix print_warning import 2026-04-12 16:40:37 -07:00
cli_output.py refactor: remove dead code — 1,784 lines across 77 files (#9180) 2026-04-13 16:32:04 -07:00
clipboard.py feat(gateway): WSL-aware gateway with smart systemd detection (#7510) 2026-04-10 21:15:47 -07:00
codex_models.py fix: add gpt-5.4-mini to Codex fallback catalog (#3855) 2026-03-29 20:10:00 -07:00
colors.py feat: respect NO_COLOR env var and TERM=dumb (#4079) 2026-03-30 17:07:21 -07:00
commands.py feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270) 2026-04-16 16:49:00 -07:00
completion.py fix: preserve profile name completion in dynamic shell completion 2026-04-14 10:45:42 -07:00
config.py feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270) 2026-04-16 16:49:00 -07:00
copilot_auth.py fix(copilot): resolve GHE token poisoning when GITHUB_TOKEN is set 2026-04-13 05:12:36 -07:00
cron.py feat(cron): track delivery failures in job status (#6042) 2026-04-07 22:49:01 -07:00
curses_ui.py feat: ungate Tool Gateway — subscription-based access with per-tool opt-in 2026-04-16 12:36:49 -07:00
debug.py fix: bump debug share paste TTL from 1 hour to 6 hours (#11240) 2026-04-16 14:34:46 -07:00
default_soul.py fix: reset default SOUL.md to baseline identity text (#3159) 2026-03-26 01:34:27 -07:00
doctor.py feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270) 2026-04-16 16:49:00 -07:00
dump.py fix: QQBot missing integration points, timestamp parsing, test fix 2026-04-14 00:11:49 -07:00
env_loader.py fix: detect and strip non-ASCII characters from API keys (#6843) 2026-04-14 20:20:31 -07:00
gateway.py fix: use POSIX ps -A instead of BSD -ax for Docker compat (#9723) (#10569) 2026-04-15 17:07:22 -07:00
logs.py feat: component-separated logging with session context and filtering (#7991) 2026-04-11 17:23:36 -07:00
main.py fix(mcp): consolidate OAuth handling, pick up external token refreshes (#11383) 2026-04-16 21:57:10 -07:00
mcp_config.py fix(mcp): consolidate OAuth handling, pick up external token refreshes (#11383) 2026-04-16 21:57:10 -07:00
memory_setup.py fix(memory): discover user-installed memory providers from $HERMES_HOME/plugins/ (#10529) 2026-04-15 14:25:40 -07:00
model_normalize.py feat: add Ollama Cloud as built-in provider 2026-04-16 02:22:09 -07:00
model_switch.py fix(opencode): strip /v1 from base_url on mid-session /model switch to Anthropic-routed models (#11286) 2026-04-16 19:41:41 -07:00
models.py feat: add claude-opus-4.7 to Nous Portal curated model list (#11398) 2026-04-16 21:37:06 -07:00
nous_subscription.py feat: ungate Tool Gateway — subscription-based access with per-tool opt-in 2026-04-16 12:36:49 -07:00
pairing.py chore: fix 154 f-strings, simplify getattr/URL patterns, remove dead code (#3119) 2026-03-25 19:47:58 -07:00
platforms.py feat(gateway): unify QQBot branding, add PLATFORM_HINTS, fix streaming, restore missing setup functions 2026-04-14 00:11:49 -07:00
plugins.py feat(plugins): add dispatch_tool() to PluginContext (#10763) 2026-04-15 22:23:01 -07:00
plugins_cmd.py fix: no auto-activation + unified hermes plugins UI with provider categories 2026-04-10 19:15:50 -07:00
profiles.py fix: improve profile creation UX — seed SOUL.md + credential warning (#8553) 2026-04-12 12:22:34 -07:00
providers.py feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270) 2026-04-16 16:49:00 -07:00
runtime_provider.py feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270) 2026-04-16 16:49:00 -07:00
setup.py fix(models): add glm-5.1 to opencode-go catalogs 2026-04-16 16:49:22 -07:00
skills_config.py refactor: remove dead code — 1,784 lines across 77 files (#9180) 2026-04-13 16:32:04 -07:00
skills_hub.py fix(skills): cache GitHub repo trees to avoid rate-limit exhaustion on install 2026-04-12 16:39:04 -07:00
skin_engine.py fix(cli): handle null/non-dict display config in skin initialization 2026-04-16 06:35:31 -07:00
status.py feat: ungate Tool Gateway — subscription-based access with per-tool opt-in 2026-04-16 12:36:49 -07:00
tips.py refactor: remove dead code — 1,784 lines across 77 files (#9180) 2026-04-13 16:32:04 -07:00
tools_config.py feat(image_gen): multi-model FAL support with picker in hermes tools (#11265) 2026-04-16 20:19:53 -07:00
uninstall.py refactor: remove dead code — 1,784 lines across 77 files (#9180) 2026-04-13 16:32:04 -07:00
web_server.py dashboard: show GATEWAY_HEALTH_URL instead of PID for remote gateways 2026-04-16 16:48:14 -07:00
webhook.py refactor: replace inline HERMES_HOME re-implementations with get_hermes_home() 2026-04-07 10:40:34 -07:00