@mrkaran/hodor 0.6.2 → 0.6.3-rc.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 CHANGED
@@ -1,5 +1,3 @@
1
- <a href="https://zerodha.tech"><img src="https://zerodha.tech/static/images/github-badge.svg" align="right" /></a>
2
-
3
1
  # Hodor
4
2
 
5
3
  > Agentic code reviewer for GitHub PRs, GitLab MRs, Gitea/Forgejo PRs, and local diffs. Powered by the [pi-coding-agent](https://github.com/badlogic/pi-mono) SDK.
@@ -113,6 +111,8 @@ Local mode:
113
111
  | `--review-style` | `hybrid` | GitLab posting style: `summary`, `inline`, or `hybrid` |
114
112
  | `--code-quality` | – | Write a CodeClimate JSON artifact for GitLab code quality reports |
115
113
  | `--commit-status` | Off | Post a pass/fail commit status to the GitLab MR head SHA |
114
+ | `--require-delivery` | Off | Exit non-zero if requested comments, statuses, or artifacts are not delivered |
115
+ | `--fail-on-priority` | – | Exit non-zero for findings at or above `P0`, `P1`, `P2`, or `P3` |
116
116
  | `--prompt` | – | Append custom instructions to the review prompt |
117
117
  | `--prompt-file` | – | Use a custom prompt file |
118
118
  | `--workspace` | Temp dir | Workspace directory (reuse for faster multi-PR reviews) |
@@ -165,7 +165,7 @@ hodor "$MR_OR_PR_URL" --prometheus-push "$METRICS_PUSH_URL"
165
165
 
166
166
  In CI, set `METRICS_PUSH_URL` as a secret/variable and add `--prometheus-push "$METRICS_PUSH_URL"` to the Hodor command. Metrics are best-effort: push failures are logged as warnings and do not fail the review job.
167
167
 
168
- Each metric is labeled with `platform`, `model`, `verdict`, and for PR/MR URLs also `project` (`owner/repo`) and `mr_iid`/PR number. Exported metrics include token usage, cache read/write tokens, cache hit ratio, cost, turns, tool calls, duration, and findings by priority (`P0`–`P3`). A generic Grafana dashboard is available in [`docs/grafana/`](./docs/grafana/).
168
+ Each metric is labeled with `platform`, `model`, `verdict`, `outcome`, and for PR/MR URLs also `project` (`owner/repo`). MR/PR numbers are deliberately excluded to avoid unbounded time-series cardinality. Exported metrics include token usage, cache read/write tokens, cache hit ratio, cost, turns, tool calls, duration, and findings by priority (`P0`–`P3`). A generic Grafana dashboard is available in [`docs/grafana/`](./docs/grafana/).
169
169
 
170
170
  ### GitHub Actions
171
171
 
@@ -262,6 +262,8 @@ Skills are loaded automatically during reviews. See [SKILLS.md](./docs/SKILLS.md
262
262
  bun install # Install dependencies
263
263
  bun run build # Build
264
264
  bun run test # Run tests
265
+ bun run eval:list # Validate and list review-quality eval cases
266
+ bun run eval -- --model <provider/model> # Execute model evals (uses API credentials)
265
267
  bun run dev -- <url> # Run from source
266
268
  ```
267
269