@tsuga/cli 1.0.11 → 1.0.13

package/README.md

@@ -37,7 +37,7 @@ Priority order: `--operation-api-key` flag → `TSUGA_OPERATION_API_KEY` env var
 
 ## Configuration
 
-Show current configuration:
+Show current configuration (includes defaults):
 
 ```bash
 tsuga config
@@ -57,26 +57,22 @@ Commands have built-in defaults so you can omit common flags:
 Override defaults persistently:
 
 ```bash
-tsuga defaults set from -1h
-tsuga defaults set query 'level:ERROR'
+tsuga config set default from -1h
+tsuga config set default query 'level:ERROR'
 ```
 
-View all current defaults (custom overrides marked with `*`):
-
-```bash
-tsuga defaults
-```
+Current defaults are listed by `tsuga config` (custom overrides marked with `*`).
 
 Reset all custom defaults:
 
 ```bash
-tsuga defaults reset
+tsuga config reset defaults
 ```
 
 Clear a single default by setting it to an empty value:
 
 ```bash
-tsuga defaults set cluster ''
+tsuga config set default cluster ''
 ```
 
 ## Clusters
@@ -90,7 +86,7 @@ tsuga cluster list
 Pick the cluster you want to use by default via the defaults mechanism:
 
 ```bash
-tsuga defaults set cluster <cluster-id>
+tsuga config set default cluster <cluster-id>
 ```
 
 Override per-command without persisting:
@@ -130,6 +126,16 @@ You can also pass JSON inline with `-d`:
 tsuga teams create -d '{"name": "Platform", "visibility": "public"}'
 ```
 
+### Explaining a call with `--rationale`
+
+API-calling commands accept an optional `--rationale` flag to record why they are being run.
+It does not change the result; the text is sent as a request header and recorded in the
+backend request log, which is useful for understanding agent behavior.
+
+```bash
+tsuga logs patterns --rationale "exploring telemetry to investigate prod outage"
+```
+
 ### Available resources
 
 `cloud-resources`, `dashboards`, `ingestion-api-keys`, `monitors`, `notification-rules`, `notification-silences`, `quality-reports`, `retention-policies`, `routes`, `services`, `tag-policies`, `teams`
@@ -301,6 +307,17 @@ tsuga experimental promql -d '{"query":"sum(rate(http_requests_total[5m]))","tim
 
 `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:
@@ -310,6 +327,14 @@ tsuga docs search 'log routes'
 tsuga docs get getting-started/send-your-first-logs
 ```
 
+## Feedback
+
+Report friction with Tsuga tools or APIs (a failing command, unusable output, confusing behavior):
+
+```bash
+tsuga feedback the traces command keeps timing out on large services
+```
+
 ## Tips
 
 Default output is JSON, so you can pipe to `jq`: