From b0fd06259b3ee73796e415cd44b6db7323f172ba Mon Sep 17 00:00:00 2001 From: Kral Date: Sat, 3 Oct 2026 20:11:45 +0200 Subject: [PATCH] Budget: real ratio ledger/2.7 (Ollama page 24.63 USD) --- CLAUDE.md | 2 +- docs/devir-notlari.md | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/CLAUDE.md b/CLAUDE.md index 10402ea..f97c7ab 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -45,7 +45,7 @@ - A4H is small: MCP limit is 8 sessions (by design). The server shares ONE RFC connection between sessions; a parallel call gets "[LOCK] Concurrent call detected". `mcp_client.py` retries this. Keep parallel runs low (max 3). DDIC activation during setup is sensitive to parallel runs. -- Budget: `runs/ledger.jsonl` (list prices, upper bound; real cost ≈ ledger / 1.47, measured 2026-10-03). `.env`: `BUDGET_LIMIT_USD`, `BUDGET_CYCLE_START`. +- Budget: `runs/ledger.jsonl` (list prices, upper bound; real cost ≈ ledger / 2.7, measured 2026-10-03 20:15: ledger 66.97 vs Ollama monthly usage 24.63 USD (earlier ratio 1.47 was wrong)). `.env`: `BUDGET_LIMIT_USD`, `BUDGET_CYCLE_START`. Ollama usage resets on 12 October 2026, then +60 USD per month. At the limit, stop cloud work. - Objects: package `$TMP` only. Prefix `Z` + run (4 chars base36) + task (3 chars base36) + `_` (`harness/task.py`). Teardown after each run with the ADT deletion API (`adt_client.py`, credentials in `.env`). diff --git a/docs/devir-notlari.md b/docs/devir-notlari.md index 4a834cd..f6b7b13 100644 --- a/docs/devir-notlari.md +++ b/docs/devir-notlari.md @@ -91,10 +91,10 @@ base model (step 2) needs step 1. Details and next steps: `train/STATE.md`. ## 5. Budget -- Cycle budget 60 USD until 12 October 2026. Ledger 63.3 USD (list prices) ≈ 43 USD real (ratio 1.47, - measured 2026-10-03). About 17 USD real left. -- Guard: `BUDGET_LIMIT_USD=75` (ledger) ≈ 51 USD real. -- Tonight: about 25 DeepSeek reruns (≈ 1.5 USD real) and judge calls for H tasks in the baseline (small). +- Real usage (Ollama page, Kral, 2026-10-03 20:15): 24.63 of 60 USD. Ledger (list prices): 66.97 USD. + New ratio: real ≈ ledger / 2.7 (the old ratio 1.47 was wrong). About 35 USD real left until 12 October. +- Guard: `BUDGET_LIMIT_USD=75` (ledger) is now about 28 USD real: too strict. Proposal: raise it so that the + real cap is about 50 of 60 USD: ledger ≈ 135. Not changed yet; Kral decides. +- Planned cloud work is small: reruns (G0119, G0162, ≈ 0.15 USD real) and judge calls for H tasks in the baseline. The baseline itself is local and free. -- The agent now limits a cloud turn to 32k output tokens. Before, runaway reasoning (393k tokens) took 46 % of - the run cost. +- The agent limits a cloud turn to 32k output tokens. Before, runaway reasoning (393k tokens) took 46 % of the run cost.