fix: provider/model resolution — salvage 4 community PRs + MiniMax aux URL fix#5983
Merged
Conversation
|
Friendly bump on this PR in case it fell through the cracks \u2014 would love a review when someone has a minute. Thanks! |
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.
04bd6f6 to
46733bf
Compare
This was referenced Apr 8, 2026
8 tasks
linxule
added a commit
to linxule/hermes-agent
that referenced
this pull request
Apr 8, 2026
`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).
4 tasks
1 task
Tommyeds
pushed a commit
to Tommyeds/hermes-agent
that referenced
this pull request
Apr 12, 2026
…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>
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 27, 2026
…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>
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…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>
olympus-terminal
pushed a commit
to olympus-terminal/hermes-agent
that referenced
this pull request
May 16, 2026
…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>
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…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>
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…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>
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
3 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
Salvages 4 confirmed bugfixes from community PRs into a single combined fix, plus an additional MiniMax auxiliary client URL fix.
Changes
1. Auth store import typo fix (from PR #5911 by @linxule)
_read_auth_store→_load_auth_store(function didn't exist, ImportError silently swallowed)store['providers']/modelpicker2. Ollama num_ctx override (from PR #5929 by @kshitijk4poor)
/api/showmetadata (GGUF context_length, Modelfile num_ctx)num_ctxinto every Ollama chat request viaextra_body.optionsmodel.ollama_num_ctxin config.yaml3. Provider alias normalization (from PR #5793 by @Elizabeth1979)
_normalize_aux_provider()with 17 aliases (google→gemini, claude→anthropic, glm→zai, etc.)auxiliary.vision.provideris set to "google" instead of "gemini"4. MiniMax /anthropic → /v1 URL fix (inspired by PR #5786 by @Lempkey)
inference_base_urlends in/anthropic(Anthropic Messages API endpoint)/chat/completions→ 404 at/anthropic/chat/completions_to_openai_base_url()helper rewrites terminal/anthropicto/v1Files changed (7)
hermes_cli/model_switch.py— auth store fix + debug loggingagent/auxiliary_client.py— alias normalization + MiniMax URL fixagent/model_metadata.py—query_ollama_num_ctx()functionrun_agent.py— Ollama num_ctx init + injection in_build_api_kwargstests/agent/test_auxiliary_client.py— google alias teststests/agent/test_minimax_auxiliary_url.py— MiniMax URL rewrite tests (new)tests/test_ollama_num_ctx.py— Ollama num_ctx detection tests (new)Test results
PRs to close after merge