@tsuga/cli 1.0.10 → 1.0.12

package/README.md

@@ -43,36 +43,9 @@ Show current configuration:
 tsuga config
 ```
 
-## Clusters
-
-If your tenant has multiple clusters, you can target a specific one:
-
-```bash
-# List clusters
-tsuga cluster list
-
-# Save the cluster you want to use by default
-tsuga cluster use <cluster-id>
-
-# Clear the saved cluster
-tsuga cluster reset
-```
-
-You can also override the cluster per-command:
-
-```bash
-# Environment variable
-export TSUGA_CLUSTER_ID=<cluster-id>
-
-# CLI flag (highest priority)
-tsuga --cluster <cluster-id> logs search
-```
-
-Priority order: `--cluster` flag → `TSUGA_CLUSTER_ID` env var → saved config. If unset, the backend falls back to the first cluster.
-
 ## Defaults
 
-Telemetry commands have built-in defaults so you can omit common flags:
+Commands have built-in defaults so you can omit common flags:
 
 | Flag            | Default |
 | --------------- | ------- |
@@ -81,7 +54,7 @@ Telemetry commands have built-in defaults so you can omit common flags:
 | `--query`       | `*`     |
 | `--max-results` | `100`   |
 
-Override defaults for your session:
+Override defaults persistently:
 
 ```bash
 tsuga defaults set from -1h
@@ -94,12 +67,44 @@ View all current defaults (custom overrides marked with `*`):
 tsuga defaults
 ```
 
-Reset custom defaults:
+Reset all custom defaults:
 
 ```bash
 tsuga defaults reset
 ```
 
+Clear a single default by setting it to an empty value:
+
+```bash
+tsuga defaults set cluster ''
+```
+
+## Clusters
+
+If your tenant has multiple clusters, list them:
+
+```bash
+tsuga cluster list
+```
+
+Pick the cluster you want to use by default via the defaults mechanism:
+
+```bash
+tsuga defaults set cluster <cluster-id>
+```
+
+Override per-command without persisting:
+
+```bash
+# Environment variable
+export TSUGA_CLUSTER_ID=<cluster-id>
+
+# CLI flag (highest priority)
+tsuga --cluster <cluster-id> logs search
+```
+
+Priority order: `--cluster` flag → `TSUGA_CLUSTER_ID` env var → `defaults.cluster`. If unset, the backend falls back to the first cluster.
+
 ## Usage
 
 Most resources follow the same CRUD pattern:
@@ -274,6 +279,39 @@ Inspect service dependency graphs:
 tsuga service-graph get <service-id> --from -1h --query 'env:prod'
 ```
 
+## Experimental
+
+Commands under `tsuga experimental` are unstable and may change or be removed without notice. Use them only if you accept that risk.
+
+### PromQL
+
+Run a PromQL query against the metrics backend. Returns a timeseries shape matching `tsuga aggregation timeseries`.
+
+```bash
+tsuga experimental promql --generate-skeleton > query.json
+# edit query.json
+tsuga experimental promql -f query.json
+```
+
+Or inline:
+
+```bash
+tsuga experimental promql -d '{"query":"sum(rate(http_requests_total[5m]))","timeRange":{"from":1704067200,"to":1704070800},"step":"30s"}'
+```
+
+`timeRange.from` / `timeRange.to` are Unix timestamps in seconds.
+
+## LLM telemetry
+
+Configure local Claude Code (`~/.claude/settings.json`) or Codex (`~/.codex/config.toml`) to ship OpenTelemetry data to your Tsuga cluster. Needs an OTLP base URL and an [ingestion API key](https://app.tsuga.com/settings/api-keys?ingestion=true) (not the same as your operation API key).
+
+```bash
+tsuga setup claude-code --endpoint <otlp-base-url> --ingestion-api-key <key>
+tsuga setup codex --endpoint <otlp-base-url> --ingestion-api-key <key>
+```
+
+Both options also read from env (`TSUGA_OTLP_ENDPOINT`, `TSUGA_INGESTION_API_KEY`). Pass `--no-include-prompts` to strip user prompts + tool content from telemetry (default: include). The previous config is saved alongside the file as `.bak.<ISO>`; restart any running `claude` / `codex` sessions afterward.
+
 ## Documentation
 
 Browse and search the Tsuga documentation: