fix: OAuth providers missing from /model picker by linxule · Pull Request #5911 · NousResearch/hermes-agent

linxule · 2026-04-07T18:46:51Z

Summary

Fix _read_auth_store → _load_auth_store import typo in list_authenticated_providers() that causes a silent ImportError
Fix pid in store → check store["providers"] and store["credential_pool"] where OAuth credentials are actually stored
Affects Nous Portal, OpenAI Codex, and Copilot — none appear in /model picker despite valid OAuth credentials

Details

Two compounding bugs in hermes_cli/model_switch.py (section 2 of list_authenticated_providers()):

Import typo (line 794): from hermes_cli.auth import _read_auth_store — this function doesn't exist (_load_auth_store is the correct name). The ImportError is caught by except Exception: pass, so the entire OAuth credential check is silently skipped.
Key lookup (line 796): pid in store checks top-level keys ['version', 'providers', 'active_provider', 'updated_at', 'credential_pool'], but provider entries are nested under store["providers"] and store["credential_pool"]. So even after fixing the import, the check always returns False.

Env-var providers (Kimi, OpenRouter, Anthropic) are unaffected — they're found via section 1's env var check, not this code path.

Diff

-                from hermes_cli.auth import _read_auth_store
-                store = _read_auth_store()
-                if store and pid in store:
+                from hermes_cli.auth import _load_auth_store
+                store = _load_auth_store()
+                if store and (pid in store.get("providers", {}) or pid in store.get("credential_pool", {})):

Test plan

Verified locally: /model now shows Nous Portal, OpenAI Codex alongside Kimi after fix
Confirmed _load_auth_store is the correct export from hermes_cli/auth.py (line 592)
Confirmed auth.json schema: OAuth entries stored under providers and credential_pool keys

Fixes #5910

🤖 Generated with Claude Code

…d key lookup Two bugs in `list_authenticated_providers()` prevent OAuth-authenticated providers (Nous Portal, OpenAI Codex, Copilot) from appearing in the `/model` gateway picker: 1. `_read_auth_store` does not exist — should be `_load_auth_store`. The ImportError is silently caught by `except Exception: pass`. 2. `pid in store` checks top-level keys of the auth dict, but provider entries live under `store["providers"]` and `store["credential_pool"]`. Fixes NousResearch#5910 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Salvaged fixes from community PRs: - fix(model_switch): _read_auth_store → _load_auth_store + fix auth store key lookup (was checking top-level dict instead of store['providers']). OAuth providers now correctly detected in /model picker. Cherry-picked from PR #5911 by Xule Lin (linxule). - fix(ollama): pass num_ctx to override 2048 default context window. Ollama defaults to 2048 context regardless of model capabilities. Now auto-detects from /api/show metadata and injects num_ctx into every request. Config override via model.ollama_num_ctx. Fixes #2708. Cherry-picked from PR #5929 by kshitij (kshitijk4poor). - fix(aux): normalize provider aliases for vision/auxiliary routing. Adds _normalize_aux_provider() with 17 aliases (google→gemini, claude→anthropic, glm→zai, etc). Fixes vision routing failure when provider is set to 'google' instead of 'gemini'. Cherry-picked from PR #5793 by e11i (Elizabeth1979). - fix(aux): rewrite MiniMax /anthropic base URLs to /v1 for OpenAI SDK. MiniMax's inference_base_url ends in /anthropic (Anthropic Messages API), but auxiliary client uses OpenAI SDK which appends /chat/completions → 404 at /anthropic/chat/completions. Generic _to_openai_base_url() helper rewrites terminal /anthropic to /v1 for OpenAI-compatible endpoint. Inspired by PR #5786 by Lempkey. Added debug logging to silent exception blocks across all fixes.

…5983) Salvaged fixes from community PRs: - fix(model_switch): _read_auth_store → _load_auth_store + fix auth store key lookup (was checking top-level dict instead of store['providers']). OAuth providers now correctly detected in /model picker. Cherry-picked from PR #5911 by Xule Lin (linxule). - fix(ollama): pass num_ctx to override 2048 default context window. Ollama defaults to 2048 context regardless of model capabilities. Now auto-detects from /api/show metadata and injects num_ctx into every request. Config override via model.ollama_num_ctx. Fixes #2708. Cherry-picked from PR #5929 by kshitij (kshitijk4poor). - fix(aux): normalize provider aliases for vision/auxiliary routing. Adds _normalize_aux_provider() with 17 aliases (google→gemini, claude→anthropic, glm→zai, etc). Fixes vision routing failure when provider is set to 'google' instead of 'gemini'. Cherry-picked from PR #5793 by e11i (Elizabeth1979). - fix(aux): rewrite MiniMax /anthropic base URLs to /v1 for OpenAI SDK. MiniMax's inference_base_url ends in /anthropic (Anthropic Messages API), but auxiliary client uses OpenAI SDK which appends /chat/completions → 404 at /anthropic/chat/completions. Generic _to_openai_base_url() helper rewrites terminal /anthropic to /v1 for OpenAI-compatible endpoint. Inspired by PR #5786 by Lempkey. Added debug logging to silent exception blocks across all fixes. Co-authored-by: Hermes Agent <hermes@nousresearch.com>

teknium1 · 2026-04-08T05:23:43Z

Merged via PR #5983. Your auth store fix was salvaged onto current main. Thanks @linxule!

`HERMES_OVERLAYS` (providers.py) keys Kimi Code as `kimi-for-coding`, but `PROVIDER_REGISTRY` (auth.py) keys it as `kimi-coding`. `_PROVIDER_ALIASES` bridges most mismatches but lacks an entry for `kimi-for-coding`, so any code path that feeds the overlay slug through `resolve_provider()` fails with: Error: Could not resolve credentials for provider 'Kimi For Coding': Unknown provider 'kimi-for-coding'. The Telegram interactive `/model` picker hits this path: it resolves the list of available providers via `list_authenticated_providers()` (which returns overlay slugs), then passes the chosen slug directly to `resolve_provider()` for credential lookup. Switching to Kimi from the picker therefore fails even though the provider is enumerated and `KIMI_API_KEY` is set. Adds a one-entry alias to mirror the existing `kimi` and `moonshot` mappings, plus a unit test alongside the other `_PROVIDER_ALIASES` tests in `TestResolveProvider`. Related to the alias gap reported in issue NousResearch#5910 (the `model_switch.py` half of that issue was fixed in NousResearch#5983 via PR NousResearch#5911).

…ousResearch#5983) Salvaged fixes from community PRs: - fix(model_switch): _read_auth_store → _load_auth_store + fix auth store key lookup (was checking top-level dict instead of store['providers']). OAuth providers now correctly detected in /model picker. Cherry-picked from PR NousResearch#5911 by Xule Lin (linxule). - fix(ollama): pass num_ctx to override 2048 default context window. Ollama defaults to 2048 context regardless of model capabilities. Now auto-detects from /api/show metadata and injects num_ctx into every request. Config override via model.ollama_num_ctx. Fixes NousResearch#2708. Cherry-picked from PR NousResearch#5929 by kshitij (kshitijk4poor). - fix(aux): normalize provider aliases for vision/auxiliary routing. Adds _normalize_aux_provider() with 17 aliases (google→gemini, claude→anthropic, glm→zai, etc). Fixes vision routing failure when provider is set to 'google' instead of 'gemini'. Cherry-picked from PR NousResearch#5793 by e11i (Elizabeth1979). - fix(aux): rewrite MiniMax /anthropic base URLs to /v1 for OpenAI SDK. MiniMax's inference_base_url ends in /anthropic (Anthropic Messages API), but auxiliary client uses OpenAI SDK which appends /chat/completions → 404 at /anthropic/chat/completions. Generic _to_openai_base_url() helper rewrites terminal /anthropic to /v1 for OpenAI-compatible endpoint. Inspired by PR NousResearch#5786 by Lempkey. Added debug logging to silent exception blocks across all fixes. Co-authored-by: Hermes Agent <hermes@nousresearch.com>

Salvaged fixes from community PRs: - fix(model_switch): _read_auth_store → _load_auth_store + fix auth store key lookup (was checking top-level dict instead of store['providers']). OAuth providers now correctly detected in /model picker. Cherry-picked from PR NousResearch#5911 by Xule Lin (linxule). - fix(ollama): pass num_ctx to override 2048 default context window. Ollama defaults to 2048 context regardless of model capabilities. Now auto-detects from /api/show metadata and injects num_ctx into every request. Config override via model.ollama_num_ctx. Fixes NousResearch#2708. Cherry-picked from PR NousResearch#5929 by kshitij (kshitijk4poor). - fix(aux): normalize provider aliases for vision/auxiliary routing. Adds _normalize_aux_provider() with 17 aliases (google→gemini, claude→anthropic, glm→zai, etc). Fixes vision routing failure when provider is set to 'google' instead of 'gemini'. Cherry-picked from PR NousResearch#5793 by e11i (Elizabeth1979). - fix(aux): rewrite MiniMax /anthropic base URLs to /v1 for OpenAI SDK. MiniMax's inference_base_url ends in /anthropic (Anthropic Messages API), but auxiliary client uses OpenAI SDK which appends /chat/completions → 404 at /anthropic/chat/completions. Generic _to_openai_base_url() helper rewrites terminal /anthropic to /v1 for OpenAI-compatible endpoint. Inspired by PR NousResearch#5786 by Lempkey. Added debug logging to silent exception blocks across all fixes.

…ousResearch#5983) Salvaged fixes from community PRs: - fix(model_switch): _read_auth_store → _load_auth_store + fix auth store key lookup (was checking top-level dict instead of store['providers']). OAuth providers now correctly detected in /model picker. Cherry-picked from PR NousResearch#5911 by Xule Lin (linxule). - fix(ollama): pass num_ctx to override 2048 default context window. Ollama defaults to 2048 context regardless of model capabilities. Now auto-detects from /api/show metadata and injects num_ctx into every request. Config override via model.ollama_num_ctx. Fixes NousResearch#2708. Cherry-picked from PR NousResearch#5929 by kshitij (kshitijk4poor). - fix(aux): normalize provider aliases for vision/auxiliary routing. Adds _normalize_aux_provider() with 17 aliases (google→gemini, claude→anthropic, glm→zai, etc). Fixes vision routing failure when provider is set to 'google' instead of 'gemini'. Cherry-picked from PR NousResearch#5793 by e11i (Elizabeth1979). - fix(aux): rewrite MiniMax /anthropic base URLs to /v1 for OpenAI SDK. MiniMax's inference_base_url ends in /anthropic (Anthropic Messages API), but auxiliary client uses OpenAI SDK which appends /chat/completions → 404 at /anthropic/chat/completions. Generic _to_openai_base_url() helper rewrites terminal /anthropic to /v1 for OpenAI-compatible endpoint. Inspired by PR NousResearch#5786 by Lempkey. Added debug logging to silent exception blocks across all fixes. Co-authored-by: Hermes Agent <hermes@nousresearch.com>

teknium1 mentioned this pull request Apr 8, 2026

fix: provider/model resolution — salvage 4 community PRs + MiniMax aux URL fix #5983

Merged

teknium1 closed this Apr 8, 2026

teknium1 mentioned this pull request Apr 8, 2026

feat: add mimo, zai, zai-coding, gemini to provider registry and fallback chains #5914

Closed

linxule mentioned this pull request Apr 8, 2026

fix(auth): add kimi-for-coding alias to _PROVIDER_ALIASES #6287

Closed

4 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

fix: OAuth providers missing from /model picker#5911

fix: OAuth providers missing from /model picker#5911
linxule wants to merge 1 commit into
NousResearch:mainfrom
linxule:fix/model-picker-oauth-providers

linxule commented Apr 7, 2026

Uh oh!

teknium1 commented Apr 8, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

linxule commented Apr 7, 2026

Summary

Details

Diff

Test plan

Uh oh!

teknium1 commented Apr 8, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants