fix: wait for async eval completion with polling

[trieloff]

Problem

tessl eval run is async — it starts the eval server-side and returns immediately with a run ID. The workflow was calling tessl eval view --last 1 second later, before the run had even registered, getting 'No eval runs found' and treating it as success.

Additionally, the workflow used echo -e with \\n string concatenation for summary rows, which produces literal backslash-n in the GitHub step summary (same bug fixed in tessl-review.yml via #59).

Fix

1. Poll for completion: After tessl eval run, extract the run ID (UUID) from stdout, then poll tessl eval view <run-id> --json every 30 seconds, checking the status field until it's completed or failed (timeout after 15 minutes).

2. Use specific run ID: Replace tessl eval view --last with tessl eval view $RUN_ID for reliable result retrieval.

3. Fix summary formatting: Use temp files (mktemp) instead of echo -e / backslash-n string concatenation, matching the pattern from Fix step summary table formatting in tessl-review workflow #59.

Changes

• .github/workflows/tessl-eval.yml: Replaced eval + view logic with polling pattern

[Copilot]

Pull request overview

Updates the tessl-eval GitHub Actions workflow to reliably wait for asynchronous tessl eval run executions to finish before fetching results, and fixes step summary table formatting.

Changes:

• Extracts the eval run ID from tessl eval run output and polls tessl eval view <run-id> --json until completion/failure (with timeout).
• Switches result retrieval from tessl eval view --last to tessl eval view $RUN_ID.
• Replaces echo -e/\n concatenation with temp files for GitHub Step Summary rows and error details.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

STATUS_OUTPUT=$(tessl eval view "$RUN_ID" --json 2>&1) mixes stderr into stdout, which can easily break JSON parsing (and currently causes EVAL_STATUS to stay unknown until timeout). Capture JSON from stdout only, and handle non-zero exit codes / non-JSON responses explicitly (e.g., check exit status; treat auth/invalid run-id as immediate failure, and only retry on transient “not found yet” cases).

Suggested change

	STATUS_OUTPUT=$(tessl eval view "$RUN_ID" --json 2>&1) || true
	EVAL_STATUS=$(echo "$STATUS_OUTPUT" | python3 -c "import sys,json; print(json.load(sys.stdin)['data']['attributes']['status'])" 2>/dev/null) || EVAL_STATUS="unknown"
	STATUS_STDOUT_FILE=$(mktemp)
	STATUS_STDERR_FILE=$(mktemp)
	VIEW_EXIT_CODE=0
	tessl eval view "$RUN_ID" --json >"$STATUS_STDOUT_FILE" 2>"$STATUS_STDERR_FILE" || VIEW_EXIT_CODE=$?
	if [ "$VIEW_EXIT_CODE" -eq 0 ]; then
	EVAL_STATUS=$(python3 -c "import json,sys; print(json.load(open(sys.argv[1]))['data']['attributes']['status'])" "$STATUS_STDOUT_FILE" 2>/dev/null) || EVAL_STATUS="unknown"
	if [ "$EVAL_STATUS" = "unknown" ]; then
	echo " [$TILE_NAME] Poll at ${ELAPSED}s: received non-JSON or unexpected JSON from tessl eval view"
	fi
	else
	STATUS_ERROR=$(cat "$STATUS_STDERR_FILE")
	echo " [$TILE_NAME] Poll at ${ELAPSED}s: tessl eval view failed (exit code $VIEW_EXIT_CODE): $STATUS_ERROR"
	if echo "$STATUS_ERROR" | grep -Eqi 'not[[:space:]-]*found|no such run|run.*not.*found'; then
	EVAL_STATUS="unknown"
	else
	EVAL_STATUS="failed"
	fi
	fi
	rm -f "$STATUS_STDOUT_FILE" "$STATUS_STDERR_FILE"