#Kimi not working still

1 messages · Page 1 of 1 (latest)

heady fiber
#

🔌 Provider: kimi-coding Model: kimi-k2.6
🌐 Endpoint: https://api.kimi.com/coding
📝 Error: HTTP 404: The requested resource was not found
📋 Details: {'message': 'The requested resource was not found', 'type': 'resource_not_found_error'}
⚠️ Max retries (3) exhausted — trying fallback...
❌ API failed after 3 retries — HTTP 404: The requested resource was not found
💀 Final error: HTTP 404: The requested resource was not found
─ ◈ Lain ─────────────────────────────────────────────────────────

 API call failed after 3 retries: HTTP 404: The requested         
 resource was not found

────────────────────────────────────────────────────────────────────

⚙️ /debug
⚠️ This will upload the following to a public paste service:
• System info (OS, Python version, Hermes version, provider, which API keys
are configured — NOT the actual keys)
• Recent log lines (agent.log, errors.log, gateway.log — may contain
conversation fragments and file paths)
• Full agent.log and gateway.log (up to 512 KB each — likely contains
conversation content, tool outputs, and file paths)

Pastes auto-delete after 6 hours.

Collecting debug report...
Uploading...

Debug report uploaded:
Report https://dpaste.com/EH6NM2XH8
agent.log https://dpaste.com/7Q2BUH6J9
gateway.log https://dpaste.com/CAYG8RCJN

⏱ Pastes will auto-delete in 6 hours.
To delete now: hermes debug delete <url>

Share these links with the Hermes team for support.

wet shard
#

This one is getting past Hermes config far enough to call Kimi. The current failure is Kimi returning 404 resource_not_found for:

provider=kimi-coding
model=kimi-k2.6
endpoint=https://api.kimi.com/coding

So this does not look like a Hermes tool execution error yet. The model call itself is failing before tools matter.

Two things to try first.

Start a fresh session, not the existing one. The failing session in the log is already around 203 messages and 115k tokens, and it was switched in-place from opencode-go to Kimi.

Then use the Kimi Coding model alias first:

hermes model

Choose Kimi / Moonshot, then choose kimi-for-coding if it is listed.

If you want to set it directly:

hermes config set model.provider kimi-coding
hermes config set model.default kimi-for-coding
hermes config set model.base_url https://api.kimi.com/coding

Then restart the gateway/session you are actually using and try one tiny prompt, like:

Say hello and do not use tools.

If that works, then test one tiny tool task.

If kimi-for-coding also returns 404, check what your Kimi key is actually allowed to use:

curl -sS https://api.kimi.com/coding/v1/models \
  -H "Authorization: Bearer $KIMI_API_KEY" \
  -H "User-Agent: claude-code/0.1.0"

Do not paste the key. Paste only the returned model names or the error body.

The other errors in the log are separate: OpenCode Go is hitting subscription quota, Telegram has a polling conflict from more than one bot instance, and one MCP server is intermittently failing. Those are real cleanup items, but they are not the reason this Kimi request is returning 404.

heady fiber
#

will try

wet shard
#

cool. lmk either way

heady fiber