draftcat 0.8.0 → 0.10.0

package/README.md

@@ -5,7 +5,7 @@
 <p align="center"><b>Governed AI pipelines where the LLM can't fire actions — one Go binary, self-hosted, human-in-the-loop.</b></p>
 
 <p align="center">
-  <a href="https://github.com/renezander030/draftcat/stargazers"><img src="https://img.shields.io/github/stars/renezander030/draftcat?style=flat-square" alt="Stars"></a>
+  <a href="https://github.com/renezander030/draftcat"><img src="https://img.shields.io/github/stars/renezander030/draftcat?style=flat-square" alt="Stars"></a>
   <a href="LICENSE"><img src="https://img.shields.io/github/license/renezander030/draftcat?style=flat-square" alt="License"></a>
   <img src="https://img.shields.io/badge/Go-1.25-00ADD8?style=flat-square&logo=go" alt="Go 1.25">
   <a href="docs/voice.md"><img src="https://img.shields.io/badge/voice%20AI-EU%20residency%20%C2%B7%20Dograh-00D4AA?style=flat-square" alt="Voice AI plugin"></a>
@@ -65,6 +65,8 @@ Sometimes a customer, auditor, or partner needs evidence that a human approved a
 
 This is an **experimental cryptographic preview**, not a production compliance claim. It uses an embedded BN254/Groth16 circuit and a development single-party setup; the circuit has not received an independent audit. Use it to evaluate the disclosure model, then replace the setup through a ceremony before relying on it in production. See [zero-knowledge approval proofs](docs/zk-approval-proofs.md) for the trust model, exact statement, and limitations.
 
+> **New in v0.9.0:** daily model usage persists in SQLite, parallel pipelines keep separate budget totals, and every engine model call passes one admission gate. Approval records commit before work is released. Unconsumed tool actions can be revoked, consumed actions accept durable caller-reported outcomes, and live or recovered permits share expiration and policy checks. Exact scalar output validation and bounded provider reads complete the release. See the [budget and lifecycle guide](docs/governance-lifecycle.md).
+>
 > **New in v0.8.0:** webhook retries can carry a durable `Idempotency-Key`, signed replay identities are claimed atomically, and tool permits recheck their policy before execution. Requests reject oversized or ambiguous data and retain exact numbers. Older state stores upgrade safely; completed and failed runs carry exact approval identities. Audit commands read without modifying the database, and `draftcat receipts verify` checks exported JSONL offline. See the [upgrade and reliability guide](docs/reliability.md).
 >
 > **New in v0.7.0:** execution decisions now carry their proof. Every tool-gate route is authenticated, each request has a stable action identity and exact policy binding, and an allowed decision becomes an atomic consume-once permit before the side effect runs. Webhook acceptance is durable before HTTP 202 and can be polled after handoff. Versioned receipts bind action, payload, policy, and expiry, with `draftcat receipts list|show|export` for verification-ready JSONL. Ordered `model_policy` rules can deny or send matching model input/output to a human, while `/healthz` and `/readyz` give orchestrators a safe listener contract.
@@ -162,7 +164,7 @@ cp secrets.yaml.example secrets.yaml
 docker compose up
 ```
 
-Pipelines live in `config.yaml`, prompts in `skills/`. A SQLite store opens at `./state.db` on first boot. To add the EU-resident **voice AI** plugin: `go build -tags voice -o draftcat .` — the lean binary is unchanged when the tag is off.
+Pipelines live in `config.yaml`, prompts in `skills/`. Run `draftcat doctor` to check credentials, operators, the state store and schedules before the first start. A SQLite store opens at `./state.db` on first boot. To add the EU-resident **voice AI** plugin: `go build -tags voice -o draftcat .` — the lean binary is unchanged when the tag is off.
 
 ## Deploy — where it runs
 
@@ -280,6 +282,7 @@ budgets:
   per_day_tokens:      100000
   per_day_cost:        5.00     # money cap, same unit as your model rates (0 = off)
   per_pipeline_cost:   0.50
+  alert_at:            [0.5, 0.8]   # tell the operator at 50% and 80% of a daily cap
 
 observability: {spans: false}   # or DRAFTCAT_TRACE=1
 state:         {path: ./state.db}
@@ -295,7 +298,7 @@ An approval step can narrow who may decide it:
   approvers: [111111, 222222]   # which ones (subset of allowed_users)
 ```
 
-Cost caps are checked between calls: a call is refused once spend has reached the cap. Pair them with `per_step_tokens` to bound the size of any single call. A transient provider failure (429, 408, 5xx) is retried with backoff — honouring `Retry-After` — before it fails a step; `provider.max_retries` sets the budget.
+Cost caps are checked between calls: a call is refused once spend has reached the cap. Pair them with `per_step_tokens` to bound the size of any single call. Explicit rate-limit rejections (HTTP 429 without declared usage) retry with backoff and honour `Retry-After`; `provider.max_retries` sets the attempt limit. Transport errors, timeouts, server errors, and responses with uncertain billing halt the call and require usage reconciliation before another dispatch. See the [budget recovery guide](docs/governance-lifecycle.md).
 
 The tool-call gate is configured the same way, per tool:
 
@@ -355,6 +358,7 @@ Skills are YAML prompt templates in `skills/` with an `output_schema` the engine
 ```bash
 draftcat                       # run the engine (validates config first; refuses to start on errors)
 draftcat validate [--strict]   # lint config + skills
+draftcat doctor [--json]       # read-only preflight: credentials, operators, state, ports, schedules
 draftcat test <pipeline>       # dry-run against fixtures/<pipeline>/ (never touches real APIs)
 draftcat runs [pipeline]       # recent runs + the approval decisions in each (--json to archive)
 draftcat pending               # approval gates waiting on a human right now (--json)
@@ -385,7 +389,9 @@ Approval rows can be made tamper-evident with signed receipts, so a later audit
 can verify which operator approved which payload hash. See
 [`docs/action-receipts.md`](docs/action-receipts.md).
 
-A pipeline's `schedule` decides when it runs — an interval (`1h`), `manual` (operator `/run` only), or `webhook`. The `webhook` server is opt-in and opens no port unless enabled:
+A pipeline's `schedule` decides when it runs — an interval (`1h`), a cron expression in the pipeline's time zone (`"0 8 * * 1-5"` with `timezone: Europe/Berlin`), `@daily`-style shortcuts, `manual` (operator `/run` only), or `webhook`. Schedules continue from the recorded run history across restarts, `pause_after_failures` stops a pipeline that keeps failing, and `SIGTERM` lets running pipelines finish within `timeouts.shutdown_grace`. See [running Draftcat unattended](docs/operations.md).
+
+The `webhook` server is opt-in and opens no port unless enabled:
 
 ```yaml
 webhook: {enabled: true, addr: 127.0.0.1:8088, secret_env: DRAFTCAT_WEBHOOK_SECRET}
@@ -435,7 +441,7 @@ The deterministic-boundary architecture is documented in the **Production AI Aut
 - [#12 LLM Skills as YAML](https://gist.github.com/renezander030/a28f118dec07d275ccc825aa833aba92) — prompt + output_schema + role in versioned YAML, validated by a linter
 - [#13 Inbound Agent Webhook Auth](https://gist.github.com/renezander030/26d46d4c7fb9ab1b43fe19bc5bad6d07) — constant-time bearer token, fail-closed on empty secret, async 202 dispatch
 - [#14 Self-Improving Voice Agent](https://gist.github.com/renezander030/262d8b8c44b4cddf51b3b84c40f3f669) — harvest Learning-Items, group, propose a minimal workflow diff, two approval gates, git commit + auto-versioned Dograh publish
-- [#15 AI Action Audit Trail](https://gist.github.com/renezander030/ad81c7a805a09a844983f881e2c487e5) — append-only `action_approvals` table + queries: who approved which payload, when; find gated actions that ran with no approval (GDPR Art. 22)
+- [#15 AI Action Audit Trail](https://gist.github.com/renezander030/ad81c7a805a09a844983f881e2c487e5) — versioned action-bound `action_approvals` receipts: who approved which payload, when; action-level receipt binding, expiry and fail-closed audit persistence
 
 ## Related projects
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "draftcat",
-  "version": "0.8.0",
+  "version": "0.10.0",
   "description": "Governed AI pipelines with human approval gates",
   "license": "MIT",
   "author": "Rene Zander",