docs: update AGENTS.md robot mode section for --fields, actions, exit codes

Sync the agent instructions with the current robot mode implementation:
- Add RUST_CLI_TOOLS_BEST_PRACTICES.md reference for Rust coding guidance
- Expand robot mode description to cover all new capabilities
- Add --fields examples (minimal preset, custom field lists)
- Document error actions array for automated recovery workflows
- Update response format to show elapsed_ms and actions in error envelope
- Add field selection section with usage examples
- Separate health check to exit code 19 (was overloaded on exit code 1)
- Add robot-docs recommendation for response schema discovery
- Update best practices with --fields minimal for token efficiency

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

AGENTS.md

@@ -35,6 +35,8 @@ We only use **Cargo** in this project, NEVER any other package manager.
 - **Configuration:** Cargo.toml only
 - **Unsafe code:** Forbidden (`#![forbid(unsafe_code)]`)
 
+When writing Rust code, reference RUST_CLI_TOOLS_BEST_PRACTICES.md
+
 ### Release Profile
 
 Use the release profile defined in `Cargo.toml`. If you need to change it, justify the
@@ -591,7 +593,7 @@ If you aren't 100% sure how to use a third-party library, **SEARCH ONLINE** to f
 
 ## Gitlore Robot Mode
 
-The `lore` CLI has a robot mode optimized for AI agent consumption with structured JSON output, meaningful exit codes, and TTY auto-detection.
+The `lore` CLI has a robot mode optimized for AI agent consumption with compact JSON output, structured errors with machine-actionable recovery steps, meaningful exit codes, response timing metadata, field selection for token efficiency, and TTY auto-detection.
 
 ### Activation
 
@@ -616,6 +618,10 @@ LORE_ROBOT=1 lore issues
 lore --robot issues -n 10
 lore --robot mrs -s opened
 
+# List with field selection (reduces token usage ~60%)
+lore --robot issues --fields minimal
+lore --robot mrs --fields iid,title,state,draft
+
 # Show detailed entity info
 lore --robot issues 123
 lore --robot mrs 456 -p group/repo
@@ -645,7 +651,7 @@ lore --robot doctor
 # Document and index statistics
 lore --robot stats
 
-# Quick health pre-flight check (exit 0 = healthy, 1 = unhealthy)
+# Quick health pre-flight check (exit 0 = healthy, 19 = unhealthy)
 lore --robot health
 
 # Generate searchable documents from ingested data
@@ -654,7 +660,7 @@ lore --robot generate-docs
 # Generate vector embeddings via Ollama
 lore --robot embed
 
-# Agent self-discovery manifest (all commands, flags, exit codes)
+# Agent self-discovery manifest (all commands, flags, exit codes, response schemas)
 lore robot-docs
 
 # Version information
@@ -663,16 +669,27 @@ lore --robot version
 
 ### Response Format
 
-All commands return consistent JSON:
+All commands return compact JSON with a uniform envelope and timing metadata:
 
 ```json
-{"ok":true,"data":{...},"meta":{...}}
+{"ok":true,"data":{...},"meta":{"elapsed_ms":42}}
 ```
 
-Errors return structured JSON to stderr:
+Errors return structured JSON to stderr with machine-actionable recovery steps:
 
 ```json
-{"error":{"code":"CONFIG_NOT_FOUND","message":"...","suggestion":"Run 'lore init'"}}
+{"error":{"code":"CONFIG_NOT_FOUND","message":"...","suggestion":"Run 'lore init'","actions":["lore init"]}}
+```
+
+The `actions` array contains executable shell commands for automated recovery. It is omitted when empty.
+
+### Field Selection
+
+The `--fields` flag on `issues` and `mrs` list commands controls which fields appear in the JSON response:
+
+```bash
+lore -J issues --fields minimal                    # Preset: iid, title, state, updated_at_iso
+lore -J mrs --fields iid,title,state,draft,labels  # Custom field list
 ```
 
 ### Exit Codes
@@ -680,7 +697,7 @@ Errors return structured JSON to stderr:
 | Code | Meaning |
 |------|---------|
 | 0 | Success |
-| 1 | Internal error / health check failed / not implemented |
+| 1 | Internal error / not implemented |
 | 2 | Usage error (invalid flags or arguments) |
 | 3 | Config invalid |
 | 4 | Token not set |
@@ -698,6 +715,7 @@ Errors return structured JSON to stderr:
 | 16 | Embedding failed |
 | 17 | Not found (entity does not exist) |
 | 18 | Ambiguous match (use `-p` to specify project) |
+| 19 | Health check failed |
 | 20 | Config not found |
 
 ### Configuration Precedence
@@ -711,7 +729,8 @@ Errors return structured JSON to stderr:
 
 - Use `lore --robot` or `lore -J` for all agent interactions
 - Check exit codes for error handling
-- Parse JSON errors from stderr
+- Parse JSON errors from stderr; use `actions` array for automated recovery
+- Use `--fields minimal` to reduce token usage (~60% fewer tokens)
 - Use `-n` / `--limit` to control response size
 - Use `-q` / `--quiet` to suppress progress bars and non-essential output
 - Use `--color never` in non-TTY automation for ANSI-free output
@@ -719,4 +738,5 @@ Errors return structured JSON to stderr:
 - Use `--log-format json` for machine-readable log output to stderr
 - TTY detection handles piped commands automatically
 - Use `lore --robot health` as a fast pre-flight check before queries
+- Use `lore robot-docs` for response schema discovery
 - The `-p` flag supports fuzzy project matching (suffix and substring)