@moda-ai/cli 1.34.1 → 1.36.0

package/dist/{provision-c5sx3s32.js → provision-d242y9qd.js}

@@ -1,15 +1,15 @@
 import {
   selectTenantAndCreateKey
-} from "./cli-4ycvzfdg.js";
+} from "./cli-scjxgaba.js";
 import {
   loadAuthSession
-} from "./cli-eggpzt87.js";
+} from "./cli-yz99t7n8.js";
 import {
   CliAuthError,
   resolveIngestUrl,
   resolveModaBaseUrl,
   stringOption
-} from "./cli-0h32yvwq.js";
+} from "./cli-drabjmaj.js";
 
 // src/provision.ts
 async function runProvision(context, options = {}) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@moda-ai/cli",
-  "version": "1.34.1",
+  "version": "1.36.0",
   "description": "CLI for Moda - AI agent analytics and observability",
   "type": "module",
   "bin": {

package/skills/integration/index.json

@@ -1,7 +1,7 @@
 {
   "schema_version": "moda.skill_index.v1",
-  "bundled_at": "2026-09-22T23:28:01.590Z",
-  "cli_version": "1.34.1",
+  "bundled_at": "2026-09-27T08:58:32.181Z",
+  "cli_version": "1.36.0",
   "skills": [
     {
       "id": "integration-cloudflare-think",

package/skills/moda-cli/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: moda-cli
-version: 2.5.0
-description: Query Moda's AI agent trace analytics and manage code-first prompt versions from the terminal — semantic/keyword/hybrid message search, overview KPIs, topic clusters, message context, user frustration detections, tool failures, and moda prompts status/sync/promote. Use when the user asks about moda, modaflows, trace or conversation analytics, prompt management, user frustrations, agent observability, tool failure debugging, wants to find traces or tool calls about a topic, or wants to investigate how their AI agent is performing.
+version: 2.7.0
+description: Query Moda's AI agent trace analytics and manage code-first prompt versions from the terminal — semantic/keyword/hybrid message search, overview KPIs, topic clusters, message context, user frustration detections, tool failures, custom signals, false-positive review of detections, and moda prompts status/sync/promote. Use when the user asks about moda, modaflows, trace or conversation analytics, prompt management, user frustrations, agent observability, tool failure debugging, custom signals, marking a detection as a false positive, wants to find traces or tool calls about a topic, or wants to investigate how their AI agent is performing.
 ---
 
 # Moda CLI
@@ -58,9 +58,9 @@ Optional:
 
 - `MODA_BASE_URL` defaults to `https://moda.dev`; override only for
   self-hosted or staging.
-- `MODA_SKILL_VERSION` — export to `2.5.0` so search-adoption telemetry can
+- `MODA_SKILL_VERSION` — export to `2.6.0` so search-adoption telemetry can
   attribute usage to this skill version. Set it once per session:
-  `export MODA_SKILL_VERSION=2.5.0`.
+  `export MODA_SKILL_VERSION=2.6.0`.
 
 ## Setup
 
@@ -748,6 +748,82 @@ Rules that keep the proof honest:
   `moda fix <fix_id> --wait`) drives it; a fix left `GATING` will not finish
   on its own.
 
+### 9. Custom signals and false positives
+
+**Mark anything as a false positive with one command.** `--reason` (why the
+detection is wrong) is optional but recommended; marks are logged for Moda's review.
+A marked item disappears from every list and count (`moda problems`,
+`hallucinations`, `laziness`, `tool-failures`, problem evidence, the dashboard);
+`--undo` brings it back.
+
+```bash
+moda false-positive problem <problem_id> --reason="two unrelated tools"   # dismiss: hidden at once
+moda false-positive problem-detection <problem_id> --conversation-id=<id> \
+  --attribution-id=<uuid> --reason="refund was approved"                  # one piece of evidence
+moda false-positive quote <conversation_id> --family=frustration --turn=3 \
+  --quote="this is useless lol" --reason="user was joking"               # one user quote
+moda false-positive tool <conversation_id> --tool=send_invoice \
+  --tool-use-id=<tool_use_id> --reason="retried upstream"               # one failing tool call
+moda false-positive laziness <conversation_id> --reason="reload is expected"
+moda false-positive hallucination <conversation_id> --reason="price came from the tool result"
+moda false-positive custom-signal <signal_id> --conversation-id=<id> --reason="refund was approved"
+moda false-positive laziness <conversation_id> --undo                    # remove a mark (any kind but problem)
+moda false-positives                                                     # every current mark (--kind=tool, --all, --limit)
+moda false-positives <conversation_id>                                   # marks + problem reviews on a trace
+```
+
+What each flag does downstream:
+
+| Kind | Effect |
+|---|---|
+| `problem` | Dismisses the problem: it leaves `moda problems` and the dashboard at once, and the reason is folded into the next reconcile. Cannot be undone from the CLI |
+| `problem-detection` | Drops that evidence from the problem and teaches the problem reader (same as `detection-review --verdict=false_positive`) |
+| `custom-signal` | Saved as a `does_not_fit` label with the reason, so the signal learns from it and the live match is retracted (same as `signal-label`). `--undo` removes the label |
+| `quote`, `tool`, `laziness`, `hallucination` | Audit only: recorded for review, never fed back to the detectors |
+
+Find targets with the read commands: `--family`, `--turn` and `--quote` verbatim
+from a `user_quotes` entry in `moda emotions`; a failing call's `tool_use_id` (or `msg_index` when it has none) from
+`moda tool-failure-detail <tool_name>`;
+laziness traces from `moda laziness`; hallucination traces from
+`moda hallucinations`; custom-signal hits from `moda trace-signals` or
+`moda signal <id> --detections`; problem evidence ids from
+`moda problem <id> --evidence`.
+
+**Custom signals** are tenant-defined behaviors (pass/fail criteria) judged on
+every trace. Read them, then label hits so the signal learns:
+
+```bash
+moda signals                                          # every signal: criteria, status, 7-day judged/matched
+moda signal <signal_id>                               # one signal's summary
+moda signal <signal_id> --detections --days-back=30   # recent hits (limit 1–20, --offset to page)
+moda trace-signals <conversation_id>                  # signal hits on one trace
+moda signal-label <signal_id> --conversation-id=<id> --label=does_not_fit \
+  --note="refund was approved" --msg-index=<anchor_msg_index>
+```
+
+`--label=does_not_fit` marks a hit a **false positive** and retracts the live
+match; `--label=fits` confirms it. Pass the hit's `anchor_msg_index` (or
+`--msg-dedup-token=<anchor_dedup_token>`) so the example points at the right
+message, and always give a `--note` when rejecting. Labels are throttled to 10
+per minute per API key and are never retried automatically.
+
+**Problem detections** (the dashboard's flag on problem evidence) are reviewed with
+`detection-review`. A `false_positive` drops the detection out of
+`moda problem <id> --evidence` and is fed back to the problem reader; `clear`
+undoes an earlier review.
+
+```bash
+moda detection-reviews <conversation_id>              # problem detections on a trace + review state
+moda detection-review <problem_id> --conversation-id=<id> \
+  --attribution-id=<uuid> --verdict=false_positive --note="retry was expected"
+moda detection-review <problem_id> --conversation-id=<id> \
+  --attribution-id=<uuid> --verdict=clear             # undo
+```
+
+`attribution_id` comes from `moda detection-reviews <conversation_id>` or
+`moda problem <problem_id> --evidence`. Prefer `detection-review` over
+`problem-feedback --action=flag_attribution` for a single wrong detection.
+
 ## Common workflow recipes
 
 ### Find where something happened (search → context)
@@ -917,7 +993,16 @@ npx: `npx -p @moda-ai/cli moda <command>`.
 | `moda tool-failure-detail <tool_name>` | Per-tool failure breakdown + examples |
 | `moda problems` | Rank cross-signal Problems by root cause (what to fix first) |
 | `moda problem <problem_id>` | One Problem: dossier, or `--evidence`/`--reports`/`--traces`/`--feedback` pages (`--conversations` is a legacy alias of `--traces`) (`--limit` 1–50, `--cursor` verbatim keyset token) |
-| `moda problem-feedback <problem_id>` | Write: `--action=mark_fixed\|dismiss\|flag_attribution\|rename`. `--reason` required for dismiss/flag_attribution; `--new-name` for rename; `--attribution-id` (UUID) required for flag_attribution |
+| `moda problem-feedback <problem_id>` | Write: `--action=mark_fixed\|dismiss\|flag_attribution\|rename`. `--reason` required for flag_attribution, optional for dismiss; `--new-name` for rename; `--attribution-id` (UUID) required for flag_attribution |
+| `moda false-positive <kind> <target>` | Write: kinds `problem\|problem-detection\|quote\|tool\|laziness\|hallucination\|custom-signal`; `--reason` optional; problem-detection needs `--conversation-id` + `--attribution-id`; quote needs `--family`, `--turn`, `--quote`; tool needs `--tool` plus `--tool-use-id` or `--msg-index`; custom-signal needs `--conversation-id`; `--undo` removes a mark (not for problem) |
+| `moda false-positives [conversation_id]` | Current false-positive marks: all (`--kind`, `--all` to include removed, `--limit`) or one trace with its problem detection reviews |
+| `moda laziness` | Laziness detections per trace (`--days-back`, `--limit` 1-50, `--conversation-id`, `--family`) |
+| `moda detection-reviews <conversation_id>` | Problem detections on a trace with review state (`--attribution-id=UUID` narrows to one) |
+| `moda detection-review <problem_id>` | Write: `--conversation-id`, `--attribution-id` (UUID), `--verdict=correct\|false_positive\|clear`, optional `--note` |
+| `moda signals` | Custom signals: criteria, status, 7-day judged/matched stats |
+| `moda signal <signal_id>` | One custom signal; `--detections` pages recent hits (`--days-back` 1–90, `--limit` 1–20, `--offset`) |
+| `moda trace-signals <conversation_id>` | Custom signal hits on one trace |
+| `moda signal-label <signal_id>` | Write: `--conversation-id`, `--label=fits\|does_not_fit` (false positive), optional `--note`, `--msg-index`/`--msg-dedup-token` |
 | `moda step-scores <conversation_id>` | Graph-PRM step scores: per-segment curves, first bad step, rollup |
 | `moda world-state <conversation_id>` | Agent memory: slots/threads/events; `--summary-only`; `--snapshot --msg-index=N` (state at a turn); `--replay --message-count=N` (state over time) |
 | `moda failures` | Production failures worth fixing first |