bytelyst/bytelyst-devops-tools
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Tighten Telegram fallback wording

Browse Source
This commit is contained in:
Saravana Kumar 2026-05-27 20:18:46 +00:00
parent 8145484136
commit c89018ae47
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/hermes-operations.md
View File

@ -20,7 +20,7 @@ Observed on 2026-05-27:
- `llama3.2-vision` - `llama3.2-vision`
- These local fallbacks are loaded on demand and answer within the gateway's retry budget on this VM; the larger 3B/7B models were observed to be too slow for the live fallback path here. - These local fallbacks are loaded on demand and answer within the gateway's retry budget on this VM; the larger 3B/7B models were observed to be too slow for the live fallback path here.
- Live Hermes session-switch proof: root and Uma both fail over from a forced primary-provider error into the local Ollama chain and return `FallbackTest`. - Live Hermes session-switch proof: root and Uma both fail over from a forced primary-provider error into the local Ollama chain and return `FallbackTest`.
- Telegram platform-context proof: the same fallback behavior passes when Hermes runs with `HERMES_PLATFORM=telegram` for both root and Uma. - Telegram platform-context proof: the same fallback behavior passes when Hermes runs with `HERMES_PLATFORM=telegram` for both root and Uma. This is platform-context proof, not a separately replayed inbound Telegram network message.
- Web backend target: Firecrawl, configured locally on root and Uma with a private API key - Web backend target: Firecrawl, configured locally on root and Uma with a private API key
- Browser automation: enabled on both Hermes gateways; root was smoke-tested privately against `https://example.com` - Browser automation: enabled on both Hermes gateways; root was smoke-tested privately against `https://example.com`
- Backup cron: `Sync Hermes persistent-data backup to GitHub`, every 30 minutes, local delivery - Backup cron: `Sync Hermes persistent-data backup to GitHub`, every 30 minutes, local delivery

2
docs/hermes-setup-upgrade-roadmap.md
View File

@ -224,7 +224,7 @@ A healthy ByteLyst Hermes setup should be:
- vijay: current default is OpenAI Codex OAuth; fallback provider order is now the shared local Ollama chain. - vijay: current default is OpenAI Codex OAuth; fallback provider order is now the shared local Ollama chain.
- vijay: preferred default is explicitly `gpt-5.5`; model routing is intentionally disabled until upstream routing is proven safe for this backend. - vijay: preferred default is explicitly `gpt-5.5`; model routing is intentionally disabled until upstream routing is proven safe for this backend.
- [x] Verify the root and Uma Telegram gateways can actually switch to the fallback chain in a live conversation without surfacing provider errors. - [x] Verify the root and Uma Telegram session path can switch to the fallback chain without surfacing provider errors.
- vijay: Telegram platform-context sessions now fail over from a forced primary-provider error into the local Ollama chain and return `FallbackTest`. - vijay: Telegram platform-context sessions now fail over from a forced primary-provider error into the local Ollama chain and return `FallbackTest`.
- bheem: same Telegram platform-context fallback proof passed for Uma. - bheem: same Telegram platform-context fallback proof passed for Uma.