merge

PLAN.md

@@ -56,7 +56,44 @@ This document outlines the roadmap for standardizing frontend security, cleaning
 
 ---
 
-## Technical Standards
-- **Rust:** No `unwrap()` in production code; use proper error handling (`Result`).
-- **Frontend:** Always use `window.api` wrappers for sensitive operations.
-- **Security:** Secrets must never be logged or hardcoded.
+# Phase 6: Cache Cost & Provider Audit (ACTIVE)
+**Primary Agents:** `frontend-developer`, `backend-developer`, `database-optimizer`, `lab-assistant`
+
+## 6.1 Dashboard UI Updates (@frontend-developer)
+- [ ] **Update Models Page Modal:** Add input fields for `Cache Read Cost` and `Cache Write Cost` in `static/js/pages/models.js`.
+- [ ] **API Integration:** Ensure `window.api.put` includes these new cost fields in the request body.
+- [ ] **Verify Costs Page:** Confirm `static/js/pages/costs.js` displays these rates correctly in the pricing table.
+
+## 6.2 Provider Audit & Stream Fixes (@backend-developer)
+- [ ] **Standard DeepSeek Fix:** Modify `src/providers/deepseek.rs` to stop stripping `stream_options` for `deepseek-chat`.
+- [ ] **Grok Audit:** Verify if Grok correctly returns usage in streaming; it uses `build_openai_body` and doesn't seem to strip it.
+- [ ] **Gemini Audit:** Confirm Gemini returns `usage_metadata` reliably in the final chunk.
+- [ ] **Anthropic Audit:** Check if Anthropic streaming requires `include_usage` or similar flags.
+
+## 6.3 Database & Migration Validation (@database-optimizer)
+- [ ] **Test Migrations:** Run the server to ensure `ALTER TABLE` logic in `src/database/mod.rs` applies the new columns correctly.
+- [ ] **Schema Verification:** Verify `model_configs` has `cache_read_cost_per_m` and `cache_write_cost_per_m` columns.
+
+## 6.4 Token Estimation Refinement (@lab-assistant)
+- [ ] **Analyze Heuristic:** Review `chars / 4` in `src/utils/tokens.rs`.
+- [ ] **Background Precise Recount:** Propose a mechanism for a precise token count (using Tiktoken) after the response is finalized.
+
+## Critical Path
+Migration Validation → UI Fields → Provider Stream Usage Reporting.
+
+```mermaid
+gantt
+  title Phase 6 Timeline
+  dateFormat YYYY-MM-DD
+  section Frontend
+  Models Page UI :2026-03-06, 1d
+  Costs Table Update:after Models Page UI, 1d
+  section Backend
+  DeepSeek Fix :2026-03-06, 1d
+  Provider Audit (Grok/Gemini):after DeepSeek Fix, 2d
+  section Database
+  Migration Test :2026-03-06, 1d
+  section Optimization
+  Token Heuristic Review :2026-03-06, 1d
+```
+