evals: merge-readiness fixes for the external-harness stack

packages/evals/ARCHITECTURE.mmd

@@ -4,7 +4,6 @@ flowchart TB
         REPL["tui/repl.ts<br/>interactive shell<br/>Esc abort support"]
         BuildCLI["scripts/build-cli.ts<br/>bundled dist/cli bin"]
         BuildESM["scripts/build-esm.ts<br/>dist/esm + assets + datasets"]
-        LegacyCLI["cli-legacy.ts / index.eval.ts<br/>--legacy escape hatch"]
     end
 
     subgraph TUI["TUI Command Layer"]
@@ -33,7 +32,7 @@ flowchart TB
         BenchPlanner["framework/benchPlanner.ts<br/>model matrix<br/>suite expansion<br/>metadata/tags"]
         TaskConfig["taskConfig.ts<br/>default models<br/>agent model entries"]
         Datasets[("datasets/*<br/>WebVoyager<br/>OnlineMind2Web<br/>WebTailBench")]
-        DryRun["dry-run JSON<br/>tasks, skippedTasks,<br/>envOverrides, runOptions"]
+        DryRun["dry-run JSON<br/>target, normalizedTarget, tasks,<br/>envOverrides, runOptions,<br/>matrix, error?"]
     end
 
     subgraph Runner["Unified Runner"]
@@ -94,7 +93,6 @@ flowchart TB
     REPL --> RunCmd
     BuildCLI --> CLI
     BuildESM --> RuntimePaths
-    LegacyCLI --> LegacyRunner["legacy runner path<br/>pre-refactor behavior"]
 
     %% TUI and config
     ConfigCmd <--> ConfigFile

packages/evals/README.md

@@ -1,6 +1,6 @@
 # Stagehand Evals
 
-Agent benchmarks for Stagehand — `act`, `extract`, `observe`, `agent`, plus dataset-backed suites (WebVoyager, OnlineMind2Web, WebTailBench, GAIA).
+Agent benchmarks for Stagehand — `act`, `extract`, `observe`, `agent`, plus dataset-backed suites (WebVoyager, OnlineMind2Web, WebTailBench, Odysseys).
 
 Driven by an interactive TUI (`evals`) or single-shot CLI (`evals run …`). Tasks are auto-discovered from `tasks/bench/<category>/` — no registration step.
 
@@ -68,10 +68,9 @@ Use `Esc` to abort an in-flight run without exiting the REPL.
 | `-e, --env <local\|browserbase>`                                  | Where the browser runs                                      |
 | `-t, --trials <n>`                                                | Trials per task                                             |
 | `-c, --concurrency <n>`                                           | Max parallel sessions                                       |
-| `-m, --model <id>` / `-p, --provider <name>`                      | Override the model/provider matrix                          |
+| `-m, --model <id>`                                                | Override the model matrix                                   |
 | `--api`                                                           | Run via the Stagehand API instead of the SDK                |
 | `--harness <stagehand\|claude_code\|codex>`                       | Which agent harness drives the bench task                   |
-| `--agent-mode <dom\|hybrid\|cua>` / `--agent-modes <csv>`         | Stagehand agent mode (or matrix)                            |
 | `-l, --limit <n>` / `-s, --sample <n>` / `-f, --filter key=value` | Suite shaping for benchmark targets                         |
 | `--preview`                                                       | Print the resolved plan and exit — no browser, no LLM calls |