Issue Station
Sign In
Tools hereToolbox

hermes - ✅(Solved) Fix [Feature]: The missing "." in the model name was automatically switched to "-" [1 pull requests, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
NousResearch/hermes-agent#15072•Fetched 2026-04-25 06:24:42
View on GitHub
Comments
0
Participants
1
Timeline
5
Reactions
0
Author
GerrylinuxGerrylinux
Participants
GerrylinuxGerrylinux
Timeline (top)
labeled ×4cross-referenced ×1

Error Message

📝 Error: HTTP 404: Model 'qwen3-6-35B' configuration not found. 📋 Details: {'error': {'code': 'model_not_found', 'message': "Model 'qwen3-6-35B' configuration not found.", 'type': 'invalid_request_error'}} ⚠️ Non-retryable error (HTTP 404) — trying fallback... ❌ Non-retryable error (HTTP 404): HTTP 404: Model 'qwen3-6-35B' configuration not found. ❌ Non-retryable client error (HTTP 404). Aborting. 💡 This type of error won't be fixed by retrying. Error: Error code: 404 - {'error': {'code': 'model_not_found', 'message': "Model 'qwen3-6-35B'

Fix Action

Fix / Workaround

⚠️ API call failed (attempt 1/3): NotFoundError [HTTP 404] 🔌 Provider: custom Model: qwen3.6-35B 🌐 Endpoint: https://aigateway.qqww.com/api/anthropic 📝 Error: HTTP 404: Model 'qwen3-6-35B' configuration not found. 📋 Details: {'error': {'code': 'model_not_found', 'message': "Model 'qwen3-6-35B' configuration not found.", 'type': 'invalid_request_error'}} ⚠️ Non-retryable error (HTTP 404) — trying fallback... ❌ Non-retryable error (HTTP 404): HTTP 404: Model 'qwen3-6-35B' configuration not found. ❌ Non-retryable client error (HTTP 404). Aborting. 🔌 Provider: custom Model: qwen3.6-35B 🌐 Endpoint: https://aigateway.qqww.com/api/anthropic 💡 This type of error won't be fixed by retrying. ─ ⚕ Hermes ────────────────────────────────────────────────────────────────────────────────────────────────────

PR fix notes

PR #15087: fix: preserve dotted non-Claude model ids on Anthropic wire

Description (problem / solution / changelog)

Closes #15072

Summary

Fix Anthropic model normalization so Hermes only converts dots to hyphens for Claude model IDs.

Before this change, Anthropic wire normalization rewrote any dotted model ID, which broke Anthropic-compatible custom endpoints serving non-Claude models such as:

  • qwen3.6-35B
  • qwen3.5-plus
  • MiniMax-M2.7

That produced requests like qwen3-6-35B, which the upstream endpoint rejected as model_not_found.

Root cause

agent.anthropic_adapter.normalize_model_name() applied this rule globally:

  • strip anthropic/
  • replace . with -

That is correct for Claude IDs like claude-sonnet-4.6 -> claude-sonnet-4-6, but incorrect for non-Claude IDs on Anthropic-compatible APIs.

Fix

Change Anthropic normalization to:

  • keep stripping anthropic/
  • only replace . with - when the bare model ID starts with claude-
  • keep dotted non-Claude IDs unchanged by default

Examples after this patch:

  • anthropic/claude-sonnet-4.6 -> claude-sonnet-4-6
  • qwen3.6-35B -> qwen3.6-35B
  • anthropic/qwen3.6-35B -> qwen3.6-35B
  • MiniMax-M2.7 -> MiniMax-M2.7

Tests

Added/updated regression coverage for:

  • Qwen-style dotted model IDs staying intact on the Anthropic path
  • existing Claude dot-to-hyphen behavior remaining unchanged
  • MiniMax normalization expectation aligned with the new non-Claude behavior

Validation

Passed locally:

  • pytest -o addopts='' tests/agent/test_anthropic_adapter.py
  • pytest -o addopts='' tests/agent/test_minimax_provider.py -k 'normalize_'

I did not run the full test_minimax_provider.py file in this environment because it imports run_agent and the local env is missing the fire dependency, which is unrelated to this fix.

Changed files

  • agent/anthropic_adapter.py (modified, +6/-4)
  • tests/agent/test_anthropic_adapter.py (modified, +5/-0)
  • tests/agent/test_minimax_provider.py (modified, +2/-2)
RAW_BUFFERClick to expand / collapse

Problem or Use Case

hello

Initializing agent... ────────────────────────────────────────

⚠️ API call failed (attempt 1/3): NotFoundError [HTTP 404] 🔌 Provider: custom Model: qwen3.6-35B 🌐 Endpoint: https://aigateway.qqww.com/api/anthropic 📝 Error: HTTP 404: Model 'qwen3-6-35B' configuration not found. 📋 Details: {'error': {'code': 'model_not_found', 'message': "Model 'qwen3-6-35B' configuration not found.", 'type': 'invalid_request_error'}} ⚠️ Non-retryable error (HTTP 404) — trying fallback... ❌ Non-retryable error (HTTP 404): HTTP 404: Model 'qwen3-6-35B' configuration not found. ❌ Non-retryable client error (HTTP 404). Aborting. 🔌 Provider: custom Model: qwen3.6-35B 🌐 Endpoint: https://aigateway.qqww.com/api/anthropic 💡 This type of error won't be fixed by retrying. ─ ⚕ Hermes ────────────────────────────────────────────────────────────────────────────────────────────────────

 Error: Error code: 404 - {'error': {'code': 'model_not_found', 'message': "Model 'qwen3-6-35B'
 configuration not found.", 'type': 'invalid_request_error'}}

───────────────────────────────────────────────────────────────────────────────────────────────────────────────── ⚕ qwen3.6-35B │ 0/256K │ [░░░░░░░░░░] 0% │ 4m │ ⏲ 0s

My model name is qwen3.6-35B, and the missing one has been modified to "-"

Proposed Solution

As above

Alternatives Considered

No response

Feature Type

New tool

Scope

None

Contribution

  • I'd like to implement this myself and submit a PR

Debug Report (optional)

extent analysis

TL;DR

The issue can likely be fixed by updating the model name to match the expected format, replacing the "." with a "-" to match the error message's suggestion.

Guidance

  • Verify that the model name "qwen3.6-35B" is correctly formatted and matches the expected naming convention for the API endpoint.
  • Check the API documentation for the correct model name format and update the code accordingly.
  • Test the API call with the updated model name to see if the error persists.
  • If the issue still occurs, review the error message and details for any additional clues about the cause of the problem.

Example

No code snippet is provided as the issue does not contain sufficient information about the code.

Notes

The error message suggests that the model name "qwen3-6-35B" is not found, implying that the correct model name might be "qwen3-6-35B" instead of "qwen3.6-35B".

Recommendation

Apply workaround: Update the model name to "qwen3-6-35B" to match the expected format, as suggested by the error message.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#parallel task#integration issue#index setup#retrieval issue

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING