@tangle-network/traces 0.9.0 → 0.9.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +4 -4
- package/dist/{chunk-5SBXL62V.js → chunk-RUG26PIS.js} +716 -574
- package/dist/cli.js +20 -64
- package/dist/index.d.ts +15 -15
- package/dist/index.js +1 -1
- package/package.json +3 -3
package/README.md
CHANGED
|
@@ -49,7 +49,7 @@ traces watch --all
|
|
|
49
49
|
traces stream --all --mode findings
|
|
50
50
|
```
|
|
51
51
|
|
|
52
|
-
That's the command in the demo above. The **deterministic pass** checks stuck loops, token growth, output decay, missing self-verification, and
|
|
52
|
+
That's the command in the demo above. The **deterministic pass** checks stuck loops, token growth, output decay, missing self-verification, tool failures, and human corrections. Each supported issue is returned as a finding with evidence, an action, confidence, and a validation plan. It needs no API key and costs nothing.
|
|
53
53
|
|
|
54
54
|
Add `--llm` for the **agentic analysts** (failure-mode / knowledge-gap / knowledge-poisoning / improvement); they call OpenAI and respect `--budget <usd>`.
|
|
55
55
|
|
|
@@ -96,8 +96,8 @@ Every adapter captures the full conversation: the **user's prompt** and the **as
|
|
|
96
96
|
|
|
97
97
|
```bash
|
|
98
98
|
traces list --harness claude-code --last 20 # discover sessions
|
|
99
|
-
traces analyze --harness codex --last 1 # $0
|
|
100
|
-
traces investigate --all --last 10 --out report.md #
|
|
99
|
+
traces analyze --harness codex --last 1 # $0 findings with actions + checks
|
|
100
|
+
traces investigate --all --last 10 --out report.md # explicit investigation alias
|
|
101
101
|
traces improve --all --last 10 --dir .traces/improvement
|
|
102
102
|
traces analyze --all --since 2026-06-18 --out report.md
|
|
103
103
|
traces convert --harness claude-code --last 1 --otlp spans.jsonl # OTLP only
|
|
@@ -126,7 +126,7 @@ traces upload --since 24h # upload last day to the Inte
|
|
|
126
126
|
| `--otlp <path>` | OTLP artifact path (also evidence provenance / dry-run upload preview) |
|
|
127
127
|
| `--format <kind>` | `export` / file `stream`: `auto`, `policy-evidence`, `sandbox-events`, or `openinference` |
|
|
128
128
|
| `--llm` / `--budget <usd>` | Enable agentic analysts (needs `OPENAI_API_KEY`) / cap their spend |
|
|
129
|
-
| `--config <path>` | `investigate` / `improve` / `stream`: load BYO analysts, live analysts, and external analyzers |
|
|
129
|
+
| `--config <path>` | `analyze` / `investigate` / `improve` / `stream`: load BYO analysts, live analysts, and external analyzers |
|
|
130
130
|
| `--interval <s>` / `--window <m>` | `watch` / live `stream`: poll seconds (default 5) / active-session window minutes (default 30) |
|
|
131
131
|
| `--min-loop <n>` | Identical repeated calls before flagging a loop (default 3) |
|
|
132
132
|
| `--mode <kind>` | `stream`: `visualizer` (spans + findings), `findings` (low-volume), or `agent` (findings + reports) |
|