chore: expand cli live output coverage

autoresearch.jsonl

@@ -45,3 +45,6 @@
 {"run":31,"commit":"f970c05","metric":94.444,"metrics":{"passed_cases":51,"failed_cases":3,"total_cases":54},"status":"keep","description":"baseline","timestamp":1774565247,"segment":13}
 {"run":32,"commit":"5de35c5","metric":100.0,"metrics":{"passed_cases":54,"failed_cases":0,"total_cases":54},"status":"keep","description":"add cli backend request specs","timestamp":1774565368,"segment":13}
 {"type":"config","name":"localllm-cli-backend-responses","metricName":"cli_surface_score","metricUnit":"%","bestDirection":"higher"}
+{"run":33,"commit":"8cf03e3","metric":94.737,"metrics":{"passed_cases":54,"failed_cases":3,"total_cases":57},"status":"keep","description":"baseline","timestamp":1774566069,"segment":14}
+{"run":34,"commit":"0506a4c","metric":100.0,"metrics":{"passed_cases":57,"failed_cases":0,"total_cases":57},"status":"keep","description":"add cli backend response previews","timestamp":1774566132,"segment":14}
+{"type":"config","name":"localllm-cli-live-output","metricName":"cli_surface_score","metricUnit":"%","bestDirection":"higher"}

autoresearch.md

@@ -69,3 +69,6 @@ so later experiments can add real execution behavior without redesigning the UX
 - Run 31 (`f970c05`) scored `94.444%` because `backend_request()` was still a placeholder and the new backend-request tests failed for `status`, `models list`, and `bench throughput`.
 - Run 32 (`5de35c5`) introduced concrete executable backend request specs with bearer/content-type headers and deterministic JSON benchmark payloads, raising segment 13 from `94.444%` to `100.0%` (54/54 passing).
 - Segment 14 raises the bar from executable backend request specs to backend response interpretation, checking whether the same live-compatible commands can parse real response bodies into CLI-facing previews for health, model lists, and throughput usage metrics.
+- Run 33 (`8cf03e3`) scored `94.737%` because `backend_response_preview()` was still a placeholder and the new response-parsing tests failed for `status`, `models list`, and `bench throughput`.
+- Run 34 (`0506a4c`) introduced CLI-local backend response previews for health payloads, model list ids/count, and throughput usage metrics, raising segment 14 from `94.737%` to `100.0%` (57/57 passing).
+- Segment 15 raises the bar from internal backend response previews to final user-facing live output rendering, checking whether the same live-compatible commands can render text/json output directly from parsed backend responses.

crates/localllm-cli/src/main.rs

@@ -445,6 +445,10 @@ fn render_execution_preview(cli: &Cli) -> String {
     }
 }
 
+fn render_backend_response(cli: &Cli, _status_code: u16, _body: &str) -> String {
+    format!("LIVE {}", render_command_summary(cli))
+}
+
 fn render_json_body(body: Option<&str>) -> String {
     match body {
         Some(body) => format!(r#""{}""#, body),
@@ -920,10 +924,10 @@ fn bench_command_summary(command: &BenchCommand) -> String {
 mod tests {
     use super::{
         backend_invocation, backend_request, backend_response_preview, execution_contract,
-        execution_preview, execution_stub, plan_command, render_command_summary,
-        render_execution_preview, AuthMode, BackendInvocation, BackendRequest,
-        BackendResponsePreview, Cli, CommandPlan, Commands, ExecutionContract, ExecutionPreview,
-        ExecutionStub,
+        execution_preview, execution_stub, plan_command, render_backend_response,
+        render_command_summary, render_execution_preview, AuthMode, BackendInvocation,
+        BackendRequest, BackendResponsePreview, Cli, CommandPlan, Commands, ExecutionContract,
+        ExecutionPreview, ExecutionStub,
     };
     use clap::Parser;
     use serde_json::json;
@@ -2042,4 +2046,122 @@ mod tests {
             }
         );
     }
+
+    #[test]
+    #[ignore = "autoresearch benchmark"]
+    fn cli_surface_status_live_text_renders_health_summary() {
+        let cli = Cli::try_parse_from(["localllm", "status"]).unwrap();
+
+        assert_eq!(
+            render_backend_response(
+                &cli,
+                200,
+                r#"{"status":"ok","model_loaded":true,"model_id":"qwen-coder","uptime_secs":12}"#,
+            ),
+            "STATUS status=ok model_loaded=true model_id=qwen-coder uptime_secs=12"
+        );
+    }
+
+    #[test]
+    #[ignore = "autoresearch benchmark"]
+    fn cli_surface_status_live_json_renders_health_payload() {
+        let cli = Cli::try_parse_from(["localllm", "--format", "json", "status"]).unwrap();
+
+        assert_eq!(
+            render_backend_response(
+                &cli,
+                200,
+                r#"{"status":"ok","model_loaded":true,"model_id":"qwen-coder","uptime_secs":12}"#,
+            ),
+            r#"{"kind":"health","status":"ok","model_loaded":true,"model_id":"qwen-coder","uptime_secs":12}"#
+        );
+    }
+
+    #[test]
+    #[ignore = "autoresearch benchmark"]
+    fn cli_surface_models_live_text_renders_model_ids() {
+        let cli = Cli::try_parse_from(["localllm", "models", "list"]).unwrap();
+
+        assert_eq!(
+            render_backend_response(
+                &cli,
+                200,
+                r#"{"object":"list","data":[{"id":"qwen-coder"},{"id":"gemma-3"}]}"#,
+            ),
+            "MODELS count=2 ids=qwen-coder,gemma-3"
+        );
+    }
+
+    #[test]
+    #[ignore = "autoresearch benchmark"]
+    fn cli_surface_models_live_json_renders_model_ids() {
+        let cli = Cli::try_parse_from(["localllm", "--format", "json", "models", "list"]).unwrap();
+
+        assert_eq!(
+            render_backend_response(
+                &cli,
+                200,
+                r#"{"object":"list","data":[{"id":"qwen-coder"},{"id":"gemma-3"}]}"#,
+            ),
+            r#"{"kind":"models","count":2,"ids":["qwen-coder","gemma-3"]}"#
+        );
+    }
+
+    #[test]
+    #[ignore = "autoresearch benchmark"]
+    fn cli_surface_bench_live_text_renders_usage_summary() {
+        let cli = Cli::try_parse_from([
+            "localllm",
+            "bench",
+            "throughput",
+            "--model",
+            "qwen-coder",
+            "--samples",
+            "5",
+            "--prompt-tokens",
+            "8",
+            "--completion-tokens",
+            "64",
+        ])
+        .unwrap();
+
+        assert_eq!(
+            render_backend_response(
+                &cli,
+                200,
+                r#"{"usage":{"prompt_tokens":8,"completion_tokens":64,"total_tokens":72,"tokens_per_second":42.5}}"#,
+            ),
+            "THROUGHPUT model=qwen-coder total_tokens=72 tokens_per_second=42.5"
+        );
+    }
+
+    #[test]
+    #[ignore = "autoresearch benchmark"]
+    fn cli_surface_bench_live_json_renders_usage_summary() {
+        let cli = Cli::try_parse_from([
+            "localllm",
+            "--format",
+            "json",
+            "bench",
+            "throughput",
+            "--model",
+            "qwen-coder",
+            "--samples",
+            "5",
+            "--prompt-tokens",
+            "8",
+            "--completion-tokens",
+            "64",
+        ])
+        .unwrap();
+
+        assert_eq!(
+            render_backend_response(
+                &cli,
+                200,
+                r#"{"usage":{"prompt_tokens":8,"completion_tokens":64,"total_tokens":72,"tokens_per_second":42.5}}"#,
+            ),
+            r#"{"kind":"throughput","model":"qwen-coder","total_tokens":72,"tokens_per_second":42.5}"#
+        );
+    }
 }

experiments/worklog.md

@@ -315,3 +315,22 @@
 - New objective: raise the CLI benchmark from executable backend request construction to backend response interpretation for the same live-compatible workflows, starting with `status`, `models list`, and `bench throughput`.
 - Benchmark driver: `./autoresearch.sh` still runs ignored `localllm-cli` tests and reports `cli_surface_score`, `passed_cases`, `failed_cases`, and `total_cases`.
 - Keep/discard rule remains test-driven: higher `cli_surface_score` wins while the normal non-ignored suites remain green.
+
+### Run 33: baseline - cli_surface_score=94.737 (KEEP)
+- Timestamp: 2026-03-26 20:01
+- What changed: Added the segment 14 response-preview seam and local deserializable DTOs for health, models list, and throughput usage responses, but left `backend_response_preview()` intentionally unimplemented for the new live-compatible workflows.
+- Result: cli_surface_score=94.737, passed_cases=54, failed_cases=3, total_cases=57.
+- Insight: The CLI already had every layer through executable backend request construction, but it still collapsed real response parsing for `status`, `models list`, and `bench throughput` to `SummaryOnly { command: "response-unimplemented" }`.
+- Next: parse the real response bodies into CLI-local previews for health status, model ids/count, and throughput usage metrics.
+
+### Run 34: add cli backend response previews - cli_surface_score=100.0 (KEEP)
+- Timestamp: 2026-03-26 20:02
+- What changed: Implemented `backend_response_preview()` in `crates/localllm-cli/src/main.rs` so `status` parses health payloads, `models list` collects model ids/count, and `bench throughput` reads `usage.total_tokens` plus `usage.tokens_per_second` into CLI-local preview values.
+- Result: cli_surface_score=100.0, passed_cases=57, failed_cases=0, total_cases=57.
+- Insight: The first live-compatible CLI workflows now preserve the full response side of the contract too: request construction plus deterministic response interpretation without forcing reuse of server-only DTOs.
+- Next: raise the bar from response previews to the first real executable handlers or user-facing live output rendering for commands that already work against the current backend.
+
+## Segment 15: CLI Live Output
+- New objective: raise the CLI benchmark from internal backend response previews to final user-facing live output rendering for the already live-compatible workflows `status`, `models list`, and `bench throughput`.
+- Benchmark driver: `./autoresearch.sh` still runs ignored `localllm-cli` tests and reports `cli_surface_score`, `passed_cases`, `failed_cases`, and `total_cases`.
+- Keep/discard rule remains test-driven: higher `cli_surface_score` wins while the normal non-ignored suites remain green.