Skip to content

Experience-Driven Black-Box Cost Control for Coding Agents

docs(experiments): point two links at te_bench/runner.py, where AgentRunner now lives

Aaron3b08fc17b210
diff --git a/experiments/docs/COPILOT.md b/experiments/docs/COPILOT.md
index 5997a64..c7bbebc 100644
--- a/experiments/docs/COPILOT.md
+++ b/experiments/docs/COPILOT.md
@@ -1,7 +1,7 @@
# Running the GitHub Copilot CLI as the sealed agent
TokenEconomizer's mechanisms are agent-agnostic, but each sealed agent needs its own runner
-below the [`AgentRunner`](../../tokeneconomizer/runner.py) seam. This page is the Copilot path,
+below the [`AgentRunner`](../te_bench/runner.py) seam. This page is the Copilot path,
end to end, for **both** SWE-bench and Web-Bench. It assumes you have already done
[`SETUP.md`](SETUP.md) steps 1–3 (venv, the two outside-the-repo directories, datasets);
everything Copilot-specific is here.
diff --git a/experiments/docs/SETUP.md b/experiments/docs/SETUP.md
index 73da692..a5b22e5 100644
--- a/experiments/docs/SETUP.md
+++ b/experiments/docs/SETUP.md
@@ -169,7 +169,7 @@ Copilot gate is in [`COPILOT.md`](COPILOT.md) Step 1.
The heavy machinery — launching a sealed agent, applying the economizer's per-task
decisions, grading against gold — sits **below `AgentRunner`**
-([`../tokeneconomizer/runner.py`](../../tokeneconomizer/runner.py), which is the authoritative
+([`te_bench/runner.py`](../te_bench/runner.py), which is the authoritative
contract). The repo ships a reference implementation, [`te_harness/`](../te_harness) — see
[`HARNESS.md`](HARNESS.md) — so this step is a check
rather than something to write. Every launch selects a runner with `RUNNER=module:factory`