Sho'Nuff
9af0db089b
- V4 Pro is NOT retiring Sep 14: DeepSeek reversed the sunset and continues it unchanged at 1.32/3.96, so the legacy name does not auto-route to Flash - admin-ai built-in map carried the superseded Flash peak rates (0.44 miss / 0.014 cache-hit / 1.32 out) - applied peak override via /model/update (0.30 miss / 0.006 cache-hit / 1.20 out) - verified: persisted in litellm_params, API-reported, live call billed 1.71e-05
7.0 KiB
7.0 KiB
AI Model Architecture — IT Pro Partner
Updated: September 11, 2026
Two separate concepts: fallback chain (survival — direct API keys) and operational chain (daily toolbox — admin-ai only). The two-key strategy means operational keys run through admin-ai/LiteLLM; fallback keys are direct provider API keys with daily limits.
Aug 8 verification: All 18 models confirmed active in LiteLLM DB. New additions since Aug 6: claude-sonnet-4-6, claude-sonnet-4-5, claude-opus-4-8, claude-fable-5, gemini-2.5-flash, gemini-2.5-pro, xai/grok-4.3.
Fallback Chain (auto-failover — direct API keys)
Survives admin-ai outage. All direct provider keys have daily caps. Fires in order — only when the model above is unreachable.
| Tier | Model | Provider | Key type | Daily cap |
|---|---|---|---|---|
| Primary | deepseek-v4-flash |
admin-ai |
operational | $700/30d (~$23.33/day) |
| F1 | deepseek-v4-flash |
deepseek (direct) |
fallback | $3 |
| F2 | gemini-3.8-flash |
google (direct) |
fallback | $2 |
| F3 | grok-4.5 |
xai (direct) |
fallback | $2 |
| F4 | claude-sonnet-5 |
anthropic (direct) |
fallback | $5 |
| F5 | gpt-5-mini |
openai (direct) |
fallback | $2 |
Total emergency budget: $14/day — down from $45 single-leg burn on Aug 5.
Operational Models (daily toolbox — admin-ai only)
All route through admin-ai. Shared budget via hermes-agent-v5 key.
| Role | Model | Provider | Use When |
|---|---|---|---|
| Conductor | deepseek-v4-flash |
admin-ai (DeepSeek) | All standard work — orchestration, delegation, coding |
| Workhorse | deepseek-v4-flash |
admin-ai (DeepSeek) | Delegated tasks, scripts, infra code |
| Batch Workhorse | deepseek-v4-flash |
admin-ai (DeepSeek) | Bulk scripts, log parsing, repetitive tasks |
| Lightweight | claude-haiku-4-5 |
admin-ai (Anthropic) | Email triage, classification, simple tasks |
| Simple Workhorse | gpt-5.6-luna |
admin-ai (OpenAI) | Lightweight tasks under 128K context |
| Auditor | gpt-5.6-luna |
admin-ai (OpenAI) | Code review, QA (primary auditor) |
| Auditor 2 | xai/grok-4.5 |
admin-ai (xAI) | Second-opinion code review (different provider) |
| Critical | claude-sonnet-5 |
admin-ai (Anthropic) | Client comms, legal docs, architecture (explicit) |
| Professional Comms | gemini-3.8-flash |
admin-ai (Google) | Client emails, professional messaging |
| Research | sonar-pro |
admin-ai (Perplexity) | Live-search-grounded: competitive/compliance/market research, current events, cited answers |
| Deep Research | sonar-reasoning-pro |
admin-ai (Perplexity) | Multi-step synthesis, reasoning + citations |
Admin-AI Virtual Keys
hermes-agent-v5 (Main — Sho'Nuff)
- Created: Jul 31, 2026
- Budget: $23.33/day ($700/30d)
- Spend: $184.79 (as of Sep 3)
- Models: deepseek-v4-pro, deepseek-v4-flash, gemini-flash-latest, claude-sonnet-5, claude-haiku-4-5, gpt-5.6-luna, xai/grok-4.5 (+ claude-sonnet-4-6, claude-opus-4-8, claude-fable-5, gemini-2.5-flash/pro, grok-4.3, gpt-5, gpt-5-mini available)
Anita's Hermes Key
- Budget: $3.33/day ($100/30d)
- Spend: $6.86 (as of Sep 3)
- Models: deepseek-v4-pro, deepseek-v4-flash, gemini-flash-latest, claude-sonnet-5, claude-haiku-4-5, gpt-5.6-luna, xai/grok-4.5 (+ same expansions as hermes-agent-v5)
Budget Targets
| Component | Daily est. |
|---|---|
| Conductor + Workhorse (ds-v4-flash) | ~$2.00 |
| Batch Workhorse (ds-v4-flash) | ~$1.50 |
| Lightweight (haiku-4-5) | ~$0.30 |
| Simple Workhorse (luna) | ~$0.50 |
| Auditors (luna + grok-4.5) | ~$0.80 |
| Critical (sonnet-5, sparingly) | ~$2.00 |
| Total | ~$7/day |
Key Decisions
- Jul 29, 2026: DeepSeek V4 Flash demoted from conductor to F1 fallback. Was hallucinating tool calls. V4 Pro promoted to primary conductor.
- Jul 30, 2026: LiteLLM key regenerated — hermes-agent-v3 created but config.yaml NOT updated. Hermes fell back to DeepSeek direct since Jul 30 19:25 UTC.
- Jul 31, 2026: Discovered stale key in config.yaml. Generated hermes-agent-v5 with same model list. Verified chat OK. Cleaned up stale keys (v3, v4, v4b).
- Aug 5, 2026: Admin-ai budget cap hit (~$20). Fallback chain exhausted 4 dead legs, landed on Anthropic direct. Burned $45 in 10 hours on claude-sonnet-5 via direct key. Anthropic key capped until Sep 1.
- Aug 6, 2026: Root cause of Aug 5 outage: 4 fallback legs dead simultaneously (admin-ai budget, DeepSeek balance $0, grok-4.6 404, Anthropic capped). Implemented two-key strategy (operational vs fallback). Rotated all 5 fallback keys. Added F5 (gpt-5-mini via OpenAI). Added haiku-4-5 and grok-4.5 to operational chain. Fixed grok-4.6 → grok-4.5. Synced Anita profile identically. Budget raised to $30.
- Aug 17, 2026: Live verification of fallback chain against the LiteLLM model DB (admin-ai). Confirmed present:
deepseek-v4-flash,gemini-3.6-flash(registered asgemini/gemini-3.6-flash),grok-4.5(xai/grok-4.5),claude-sonnet-5. Replaced F5gpt-4.1-mini→gpt-5-mini— the gpt-4.1 series is no longer present in LiteLLM. Syncedconfig.yamlfallback_providersandmodel.fallbacks. - Sep 3, 2026: DeepSeek promo rates ended and prices rose again. Live LiteLLM map now bills deepseek-v4-pro at $1.32/$3.96 and deepseek-v4-flash at $0.44/$1.32 (peak; off-peak half). Registered gemini-3.8-flash ($0.75/$3.75 intro) on admin-ai. Swapped F2 and Professional Comms gemini-3.6-flash to gemini-3.8-flash (Core + Anita). Restored delegation default to deepseek-v4-pro (was claude-sonnet-5, ~$13/day burn). Corrected F5 name in operational-models.md. Re-baselined cost tracker thresholds ($3/$4 to $15/$20). Verified actual key budgets: hermes-agent-v5 $700/30d ($23.33/day), Anita $100/30d ($3.33/day).
- Sep 3, 2026 (sonar + vision): Seated Perplexity sonar as the Research tier (
sonar-pro+sonar-reasoning-pro, both verified search-grounded via admin-ai with live test calls). Swappedauxiliary.visionclaude-sonnet-5→claude-haiku-4-5(stillanthropicdirect), ~3x cheaper vision; verified with a real image call. Conductor unchanged (staysdeepseek-v4-pro). - Sep 11, 2026: DeepSeek V4.1 Flash released (Sep 10) and surpasses V4 Pro on performance/cost/speed. Flipped primary + delegation from deepseek-v4-pro to deepseek-v4-flash on Core and Anita. V4.1 Flash peak $0.30 input / $1.20 output (off-peak $0.15/$0.60; cache-hit peak $0.006). CORRECTION (verified against the live DeepSeek pricing page, Sep 11): V4 Pro is NOT retiring. DeepSeek reversed the Sep 14 sunset and continues V4 Pro unchanged at $1.32/$3.96, so the legacy name does not auto-route to Flash. Cost map: the admin-ai built-in map carried the superseded Flash peak ($0.44 miss / $0.014 cache-hit / $1.32 out); a peak override ($0.30 miss / $0.006 cache-hit / $1.20 out) was applied to the
deepseek-v4-flashdeployment via/model/updateand verified end-to-end (live call billed 1.71e-05 = 37x3e-07 + 5x1.2e-06). Pro in the map was already correct at $1.32/$0.044/$3.96.