load-context

Load Context

Load session state from CONTEXT-{stream}-llm.md in the session directory and optionally expand full resources.

.context/session/
  INDEX.md                        index of streams
  CONTEXT-llm.md                  default stream
  CONTEXT-{name}-llm.md           named stream
  done/CONTEXT-{name}-llm.md      archived stream (status done or parked)

Speed: < 3 seconds (default), 5-8 seconds (--full)

⚠️ AskUserQuestion Guard

CRITICAL: After EVERY AskUserQuestion call, check if answers are empty/blank. Known harness bug: outside Plan Mode, AskUserQuestion can silently return empty answers without showing UI.

If answers are empty: DO NOT proceed with assumptions. Instead:

1. Output: "Questions didn't display (known AskUserQuestion bug outside Plan Mode)."
2. Present the options as a numbered text list and ask user to reply with their choice number.
3. WAIT for user reply before continuing.

Performance Rules

1. Use rtk for shell commands when it is installed (a harness hook may already rewrite them; bare commands are also fine)
2. Parallel tool calls — ALL independent calls in one message
3. Minimize round-trips
4. No unnecessary synthesis — present parsed data directly

Workflow

Phase 1: Detect & Read (parallel)

Bash: ls -t .context/session/CONTEXT-*llm.md .context/session/done/CONTEXT-*llm.md 2>/dev/null || true
Read: .context/session/CONTEXT-{stream}-llm.md (if stream known from $ARGUMENTS)

If not found in the session directory, check its done/ subfolder. If found there, note 📦 (from done/) in report.

If multiple streams and no selection → AskUserQuestion with options (mark done/ files with 📦).

Filename: default → CONTEXT-llm.md, {name} → CONTEXT-{name}-llm.md

Phase 2: Expand Resources (if --full)

Parallel Read: OpenSpec project/proposal/tasks.md, top 3 hot files, manifest.yaml. DO NOT restore tasks — informational only.

Thinking Artifacts (if ## Thinking Artifacts section exists in CONTEXT file):

• Default mode: display artifact paths in resume report (no content read)
• --full mode: Read referenced thinking artifacts and include brief summaries in report