mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-06-19 07:08:10 +00:00
Compare commits
4 Commits
fix-skill-
...
ci/python-
| Author | SHA1 | Date | |
|---|---|---|---|
|
4068fa3cfd | ||
|
|
474496f928 | ||
|
|
c2d28b932a | ||
|
|
3fcbc38280 |
28
.github/workflows/pr-size.yml
vendored
28
.github/workflows/pr-size.yml
vendored
@@ -29,4 +29,30 @@ jobs:
|
||||
lib/crewai/src/crewai/cli/templates/**
|
||||
**/*.json
|
||||
**/test_durations/**
|
||||
**/cassettes/**
|
||||
**/cassettes/**
|
||||
|
||||
python-diff-size:
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
|
||||
with:
|
||||
fetch-depth: 0
|
||||
- name: Enforce Python diff size limit
|
||||
env:
|
||||
MAX: "1500"
|
||||
BASE_SHA: ${{ github.event.pull_request.base.sha }}
|
||||
HEAD_SHA: ${{ github.event.pull_request.head.sha }}
|
||||
run: |
|
||||
# Three-dot base...head == merge-base(base, head)..head: matches GitHub's
|
||||
# "Files changed" diff and ignores the synthetic merge commit at HEAD.
|
||||
# Sum added + deleted lines across changed .py files; skip binaries ("-").
|
||||
total=$(git diff --numstat "$BASE_SHA...$HEAD_SHA" -- '*.py' \
|
||||
| awk '$1 != "-" && $2 != "-" { sum += $1 + $2 } END { print sum + 0 }')
|
||||
echo "Python churn: $total lines (limit $MAX)"
|
||||
if [ "$total" -gt "$MAX" ]; then
|
||||
echo "::error::Python changes total $total lines, over the $MAX-line limit. Split into smaller PRs."
|
||||
git diff --numstat "$BASE_SHA...$HEAD_SHA" -- '*.py' | sort -rn
|
||||
exit 1
|
||||
fi
|
||||
@@ -515,7 +515,6 @@
|
||||
"edge/en/enterprise/guides/update-crew",
|
||||
"edge/en/enterprise/guides/enable-crew-studio",
|
||||
"edge/en/enterprise/guides/capture_telemetry_logs",
|
||||
"edge/en/enterprise/guides/datadog",
|
||||
"edge/en/enterprise/guides/azure-openai-setup",
|
||||
"edge/en/enterprise/guides/vertex-ai-workload-identity-setup",
|
||||
"edge/en/enterprise/guides/tool-repository",
|
||||
@@ -8648,7 +8647,6 @@
|
||||
"edge/pt-BR/enterprise/guides/update-crew",
|
||||
"edge/pt-BR/enterprise/guides/enable-crew-studio",
|
||||
"edge/pt-BR/enterprise/guides/capture_telemetry_logs",
|
||||
"edge/pt-BR/enterprise/guides/datadog",
|
||||
"edge/pt-BR/enterprise/guides/azure-openai-setup",
|
||||
"edge/pt-BR/enterprise/guides/tool-repository",
|
||||
"edge/pt-BR/enterprise/guides/custom-mcp-server",
|
||||
@@ -16512,7 +16510,6 @@
|
||||
"edge/ko/enterprise/guides/update-crew",
|
||||
"edge/ko/enterprise/guides/enable-crew-studio",
|
||||
"edge/ko/enterprise/guides/capture_telemetry_logs",
|
||||
"edge/ko/enterprise/guides/datadog",
|
||||
"edge/ko/enterprise/guides/azure-openai-setup",
|
||||
"edge/ko/enterprise/guides/tool-repository",
|
||||
"edge/ko/enterprise/guides/custom-mcp-server",
|
||||
@@ -24568,7 +24565,6 @@
|
||||
"edge/ar/enterprise/guides/update-crew",
|
||||
"edge/ar/enterprise/guides/enable-crew-studio",
|
||||
"edge/ar/enterprise/guides/capture_telemetry_logs",
|
||||
"edge/ar/enterprise/guides/datadog",
|
||||
"edge/ar/enterprise/guides/azure-openai-setup",
|
||||
"edge/ar/enterprise/guides/tool-repository",
|
||||
"edge/ar/enterprise/guides/custom-mcp-server",
|
||||
|
||||
@@ -4,86 +4,6 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
|
||||
icon: "clock"
|
||||
mode: "wide"
|
||||
---
|
||||
<Update label="18 يونيو 2026">
|
||||
## v1.14.8a2
|
||||
|
||||
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a2)
|
||||
|
||||
## ما الذي تغير
|
||||
|
||||
### الميزات
|
||||
- إضافة إجراء عميل واحد إلى تعريفات التدفق
|
||||
- التحقق من تعبيرات CEL للتدفق عند تحميل التعريف
|
||||
|
||||
### الوثائق
|
||||
- إضافة دليل تكامل Datadog مع لوحة عمليات قابلة للاستيراد
|
||||
- تحديث اللقطة وسجل التغييرات للإصدار v1.14.8a1
|
||||
|
||||
## المساهمون
|
||||
|
||||
@joaomdmoura, @lucasgomide, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="18 يونيو 2026">
|
||||
## v1.14.8a1
|
||||
|
||||
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a1)
|
||||
|
||||
## ما الذي تغير
|
||||
|
||||
### الميزات
|
||||
- إضافة تعبير if اختياري إلى خطوات each.do
|
||||
|
||||
### إصلاحات الأخطاء
|
||||
- إصلاح مشكلات JSON crew
|
||||
|
||||
### الوثائق
|
||||
- تحديث snapshot و changelog للإصدار v1.14.8a
|
||||
|
||||
## المساهمون
|
||||
|
||||
@joaomdmoura, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="17 يونيو 2026">
|
||||
## v1.14.8a
|
||||
|
||||
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a)
|
||||
|
||||
## ما الذي تغير
|
||||
|
||||
### الميزات
|
||||
- إضافة إجراء كتلة نصية/كود إلى FlowDefinition
|
||||
- إضافة إجراءات الطاقم إلى FlowDefinition
|
||||
- إضافة إجراء مركب `each` إلى FlowDefinition
|
||||
- تنفيذ دعم وضع DMN في إنشاء الطاقم وتنفيذه
|
||||
- تحسين وظيفة إعادة تعيين الذاكرة ومعالجة الطاقم بتنسيق JSON
|
||||
- إضافة تعبيرات إلى إجراءات FlowDefinition
|
||||
- تنفيذ أدوات تشغيل تعريف التدفق بدون كود Python
|
||||
- دفع التغذية الراجعة البشرية من تعريف التدفق
|
||||
- توصيل التكوين والاستمرارية من FlowDefinition إلى وقت التشغيل
|
||||
- إضافة `crewai run --definition` التجريبية للتدفقات
|
||||
- دعم تراجع نشر ZIP وتشغيل مشاريع الطاقم بتنسيق JSON
|
||||
- تقديم الطواقم بتنسيق JSON أولاً
|
||||
|
||||
### إصلاحات الأخطاء
|
||||
- إصلاح أداة Exa المكررة
|
||||
- إصلاح استخدام الرموز المجمعة عبر جميع استدعاءات LLM
|
||||
- حل المشكلات المتعلقة بتحميل الطاقم ومنطق التحقق
|
||||
|
||||
### الوثائق
|
||||
- توثيق حقول FlowDefinition في مخطط JSON
|
||||
- تحديث وثائق التثبيت والبدء السريع لمشاريع الطاقم بتنسيق JSON أولاً
|
||||
- تحديث سجل التغييرات والإصدار لـ v1.14.7
|
||||
|
||||
## المساهمون
|
||||
|
||||
@gabemilani, @greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay, @lucasgomide, @theCyberTech, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="11 يونيو 2026">
|
||||
## v1.14.7
|
||||
|
||||
|
||||
@@ -9,10 +9,6 @@ mode: "wide"
|
||||
|
||||
تتبع بيانات القياس [اتفاقيات OpenTelemetry GenAI الدلالية](https://opentelemetry.io/docs/specs/semconv/gen-ai/) بالإضافة إلى سمات خاصة بـ CrewAI.
|
||||
|
||||
<Tip>
|
||||
تُعدّ OpenTelemetry **مسار المراقبة الموصى به** — محايدة تجاه الموردين، وتعمل مع أي خلفية متوافقة مع OTLP (Grafana, Honeycomb, NewRelic، أو مجمّعك الخاص). إذا كنت تستخدم Datadog تحديدًا، فراجع دليل [تكامل Datadog](./datadog) المخصص، الذي يغطي كلًا من مسار وكيل Datadog واستيعاب OTLP من Datadog.
|
||||
</Tip>
|
||||
|
||||
## المتطلبات المسبقة
|
||||
|
||||
<CardGroup cols={2}>
|
||||
@@ -45,7 +41,17 @@ mode: "wide"
|
||||
<Frame></Frame>
|
||||
</Tab>
|
||||
<Tab title="Datadog">
|
||||
لإعداد Datadog، راجع دليل [تكامل Datadog](./datadog) المخصص — فهو يغطي كلًا من مسار وكيل Datadog (الموصى به، أرخص لحجم السجلات الكبير) واستيعاب OTLP من Datadog، مع خطوات تهيئة كاملة للمجمّع.
|
||||
- **Datadog Site Domain** — مضيف OTLP لموقع Datadog الخاص بك فقط، دون بروتوكول أو مسار. يقوم CrewAI ببناء نقطة نهاية HTTPS OTLP الكاملة نيابةً عنك. استخدم المضيف المطابق لـ [موقع Datadog](https://docs.datadoghq.com/getting_started/site/) الخاص بك:
|
||||
- `otlp.datadoghq.com` (US1)
|
||||
- `otlp.us3.datadoghq.com` (US3)
|
||||
- `otlp.us5.datadoghq.com` (US5)
|
||||
- `otlp.datadoghq.eu` (EU1)
|
||||
- `otlp.ap1.datadoghq.com` (AP1)
|
||||
- **API Key** — مفتاح واجهة برمجة تطبيقات Datadog الخاص بك. راجع [كيفية إنشاء واحد](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
|
||||
|
||||
يصدّر تكامل Datadog **التتبعات**.
|
||||
|
||||
<Frame></Frame>
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
|
||||
@@ -1,295 +0,0 @@
|
||||
---
|
||||
title: "تكامل Datadog"
|
||||
description: "راقب عمليات نشر CrewAI AMP المُستضافة ذاتيًا في Datadog عبر وكيل Datadog أو استيعاب OTLP من Datadog — يوفر كلا المسارين نفس الواجهات المهيكلة لاستيراد لوحة معلومات العمليات الجاهزة."
|
||||
icon: "dog"
|
||||
mode: "wide"
|
||||
---
|
||||
|
||||
<Note>
|
||||
**الترجمة قيد التقدم** — يتم عرض المحتوى باللغة الإنجليزية.
|
||||
</Note>
|
||||
|
||||
CrewAI ships first-class support for Datadog: two log-ingestion paths, a JSON log schema designed for cheap indexing, and a ready-made operations dashboard you can import in under five minutes.
|
||||
|
||||
<Note>
|
||||
For vendor-neutral observability via any OTLP backend (Grafana, Honeycomb, your own collector), see [OpenTelemetry Export](./capture_telemetry_logs).
|
||||
</Note>
|
||||
|
||||
## Choose a path
|
||||
|
||||
CrewAI supports two log-ingestion paths to Datadog — both are first-class and produce the same structured facets that power the dashboard. Pick the one that fits your infrastructure.
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Datadog Agent">
|
||||
The Datadog Agent runs alongside your CrewAI containers (typically as a DaemonSet on Kubernetes) and tails their stdout. With `CREWAI_LOG_FORMAT=json` set, each log event ships as a single billable line with structured attributes.
|
||||
|
||||
**Setup:**
|
||||
1. Run the Datadog Agent next to your CrewAI containers — see [Datadog's deployment docs](https://docs.datadoghq.com/agent/) for Kubernetes, ECS, or VM setup. Enable log collection (`logs_enabled: true`) and container log collection (`logs_config.container_collect_all: true`).
|
||||
2. Set `CREWAI_LOG_FORMAT=json` as an **automation environment variable** in CrewAI AMP (open your automation → **Settings → Environment Variables**) so each log event is a single line instead of a multi-line traceback. AMP propagates the value to every container in the deployment (API + workers) — don't set it on the container or host directly. See [Enabling JSON output](#enabling-json-output) below for the AMP UI walkthrough and the [log schema reference](#log-schema-reference) for the full field contract.
|
||||
3. Confirm logs arrive in Datadog Logs with the JSON fields parsed — see [Verify ingestion](#verify-ingestion).
|
||||
|
||||
**Pick this path if** you already operate Datadog Agents (e.g. for infrastructure metrics), or your log volume makes per-event ingestion cost a real concern — collapsing tracebacks into single events keeps Agent ingestion cheap at scale.
|
||||
</Tab>
|
||||
<Tab title="Datadog OTLP intake">
|
||||
CrewAI AMP exports OpenTelemetry traffic directly to Datadog's OTLP endpoint with no Agent required. Logs and traces ride a single export pipeline configured in AMP's UI, using the same protocol you'd use for any other OTLP backend.
|
||||
|
||||
**Setup:**
|
||||
1. In CrewAI AMP, go to **Settings → OpenTelemetry Collectors → Add Collector** and pick **Datadog**.
|
||||
2. Configure the connection:
|
||||
- **Datadog Site Domain** — your Datadog site's OTLP host only, no protocol or path. CrewAI builds the full HTTPS OTLP endpoint for you. Use the host that matches your [Datadog site](https://docs.datadoghq.com/getting_started/site/):
|
||||
- `otlp.datadoghq.com` (US1)
|
||||
- `otlp.us3.datadoghq.com` (US3)
|
||||
- `otlp.us5.datadoghq.com` (US5)
|
||||
- `otlp.datadoghq.eu` (EU1)
|
||||
- `otlp.ap1.datadoghq.com` (AP1)
|
||||
- **API Key** — your Datadog API key. See [how to create one](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
|
||||
3. The Datadog template provisions **both signals at once** — when you save, AMP creates a traces collector at `/v1/traces` and a logs collector at `/v1/logs`, both sharing the same Datadog OTLP host and API key. You'll see them as two separate rows in your OTel collectors list.
|
||||
4. *(optional)* Click **Test Connection** to verify CrewAI can reach the endpoint with the credentials you provided. Then click **Save** — both collectors are created in one step.
|
||||
|
||||
<Frame></Frame>
|
||||
|
||||
**Pick this path if** you'd rather not operate a Datadog Agent, you already use OTLP for traces and want one export pipeline, or you may later want to fan out the same telemetry to other backends (Grafana, Honeycomb, etc.) without changing your application setup.
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
Either path lands the same structured facets in Datadog (`@automation_id`, `@kickoff_id`, `@execution_id`, `@automation_name`, `@crewai_version`, `@exception.type`, `@gen_ai.*`), so the dashboard works identically with either choice.
|
||||
|
||||
## Log schema reference
|
||||
|
||||
<Info>
|
||||
This schema applies to the **Datadog Agent path** — stdout JSON logs produced when `CREWAI_LOG_FORMAT=json` is set. Logs delivered via the **Datadog OTLP intake** use OpenTelemetry attribute names and may differ; see [OpenTelemetry Export](./capture_telemetry_logs).
|
||||
</Info>
|
||||
|
||||
When `CREWAI_LOG_FORMAT=json` is set, every log event is emitted as a **single JSON object per line** to stdout, with internal newlines escaped. The format is plain JSON — Datadog parses it natively, and the same payload is also consumable by Splunk, Loki, Elasticsearch, and CloudWatch without custom log pipelines.
|
||||
|
||||
### Why JSON output
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="Lower ingestion cost" icon="dollar-sign">
|
||||
Most managed log backends bill per event. A Python traceback in text format is counted as one event per line — 30+ events for a single error. JSON output collapses each traceback into a single event with the stack trace as an escaped string field.
|
||||
</Card>
|
||||
<Card title="Structured search" icon="magnifying-glass">
|
||||
Search by `@automation_id`, `@exception.type`, `@kickoff_id` instead of grepping free-text. Build dashboards on typed facets without parser configuration.
|
||||
</Card>
|
||||
<Card title="APM ↔ logs correlation" icon="link">
|
||||
Every event carries `trace_id` and `span_id` when fired inside a recording span, so backends auto-link logs to traces.
|
||||
</Card>
|
||||
<Card title="Stable contract" icon="file-shield">
|
||||
The `schema` field gates compatibility — within `v1`, fields are added but never renamed or removed.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
### Enabling JSON output
|
||||
|
||||
`CREWAI_LOG_FORMAT=json` must be set as an **automation environment variable** in CrewAI AMP — it is **not** a container, host, or Docker setting. Open your automation in AMP, click the **Settings** icon, and add the variable under the **Environment Variables** section. AMP applies the value to every container in the deployment (API + workers) on the next restart. See [Update Your Crew](./update-crew) for the full UI walkthrough with screenshots.
|
||||
|
||||
```shell
|
||||
CREWAI_LOG_FORMAT=json
|
||||
```
|
||||
|
||||
Restart the deployment to pick up the change. Every log line on stdout from that point on is a single JSON object.
|
||||
|
||||
<Note>
|
||||
The default value is `text`, which preserves the legacy human-readable line format byte-for-byte. Setting any value other than `json` falls back to text mode. There is no migration step — the variable is read at process start and the format switches immediately.
|
||||
</Note>
|
||||
|
||||
### Example events
|
||||
|
||||
A single info-level log inside an active automation kickoff:
|
||||
|
||||
```json
|
||||
{
|
||||
"schema": "v1",
|
||||
"ts": "2026-06-17T16:14:23.482914Z",
|
||||
"level": "INFO",
|
||||
"logger": "crewai_enterprise.utilities.pii_redaction",
|
||||
"crewai_version": "1.14.7",
|
||||
"msg": "PII tracking state reset (engines preserved)",
|
||||
"automation_id": "12",
|
||||
"task_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"kickoff_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"execution_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"automation_name": "research_flow"
|
||||
}
|
||||
```
|
||||
|
||||
An error with a Python exception is collapsed into a single event with the traceback as a string:
|
||||
|
||||
```json
|
||||
{
|
||||
"schema": "v1",
|
||||
"ts": "2026-06-17T16:14:31.218450Z",
|
||||
"level": "ERROR",
|
||||
"logger": "api.tasks.flow_run_task",
|
||||
"crewai_version": "1.14.7",
|
||||
"msg": "Flow execution failed",
|
||||
"automation_id": "12",
|
||||
"kickoff_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"execution_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"automation_name": "research_flow",
|
||||
"exception": {
|
||||
"type": "ValueError",
|
||||
"message": "Topic cannot be empty",
|
||||
"stacktrace": "Traceback (most recent call last):\n File \"/app/flow.py\", line 42, in summarize\n ...\nValueError: Topic cannot be empty\n"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The same error in legacy text mode would have produced ~25 separate log events (one per traceback line) — all of which the backend would bill and index individually.
|
||||
|
||||
### Schema v1 fields
|
||||
|
||||
Within the `v1` schema, fields are only added, never renamed or removed. New fields will appear as soon as a deployment is upgraded.
|
||||
|
||||
| Field | Type | Always present | Source |
|
||||
|-------|------|----------------|--------|
|
||||
| `schema` | string | Yes | Constant `"v1"`. Increment indicates a breaking schema change. |
|
||||
| `ts` | string (ISO-8601 UTC, microseconds) | Yes | Record creation time, e.g. `2026-06-17T16:14:23.482914Z`. |
|
||||
| `level` | string | Yes | Python log level name: `DEBUG` / `INFO` / `WARNING` / `ERROR` / `CRITICAL`. |
|
||||
| `logger` | string | Yes | Dotted logger name, e.g. `api.tasks.flow_run_task`. |
|
||||
| `crewai_version` | string | Yes (when `crewai` package metadata is resolvable) | Installed `crewai` package version, e.g. `"1.14.7"`. |
|
||||
| `msg` | string | Yes | Rendered log message (after `%`-formatting / `{}`-formatting). |
|
||||
| `automation_id` | string | When `CREWAI_PLUS_ID` env var is set | Numeric deployment ID (AMP provisions this on every container). |
|
||||
| `task_id` | string | On Celery worker logs | Celery task UUID, or `"no-task"` for non-task contexts. |
|
||||
| `kickoff_id` | string | Inside an automation kickoff | UUID of the current kickoff. |
|
||||
| `execution_id` | string | Inside an automation kickoff | UUID of the current sub-execution. Equal to `kickoff_id` at the top level; differs for nested flow methods that spawn sub-executions. |
|
||||
| `automation_name` | string | Inside an automation kickoff | Human-readable automation/flow name, e.g. `"research_flow"`. |
|
||||
| `trace_id` | string (32-hex) | Inside a recording OpenTelemetry span | Hex trace ID. Omitted when no span is active. |
|
||||
| `span_id` | string (16-hex) | Inside a recording OpenTelemetry span | Hex span ID. Omitted when no span is active. |
|
||||
| `exception` | object | When the log record has `exc_info` | `{type, message, stacktrace}` — full traceback as a single escaped string. |
|
||||
|
||||
<Tip>
|
||||
Any additional `extra={...}` kwargs passed to a logger call appear as top-level JSON fields verbatim. Reserved field names above always win to keep the schema stable.
|
||||
</Tip>
|
||||
|
||||
### Stability promise
|
||||
|
||||
The `schema` field declares the contract. Within `v1`, CrewAI commits to:
|
||||
|
||||
- **Never removing a field** that customers may have built queries or dashboards against.
|
||||
- **Never renaming a field** in place — renames happen via a schema bump (e.g. `v2`), with the old name kept as a deprecated alias for at least one release cycle.
|
||||
- **Adding new fields** at any time. Consumers should ignore unknown top-level keys.
|
||||
|
||||
When a `v2` is introduced, both the `schema` field and the migration guide will be published in advance, and `v1` will continue to be emitted for one release cycle so dashboards and queries have time to migrate.
|
||||
|
||||
## Prerequisite: promote facets
|
||||
|
||||
Datadog auto-discovers fields the first time it sees them but doesn't make them queryable in widgets until they're promoted to **facets**. This is a one-time setup in your Datadog account.
|
||||
|
||||
<Steps>
|
||||
<Step title="Search for a CrewAI log">
|
||||
Open [Logs Explorer](https://app.datadoghq.com/logs) and search `service:crewai*`. You should see at least one log event.
|
||||
</Step>
|
||||
<Step title="Promote each field">
|
||||
Click any log entry to open the right-hand details panel. For each field below, hover the field name → click the gear icon → **Create facet**.
|
||||
|
||||
- `automation_id`, `automation_name`, `execution_id`, `kickoff_id`, `task_id`
|
||||
- `crewai_version`, `model_id`
|
||||
- `exception.type`, `exception.message`
|
||||
|
||||
Skip any field that already shows a star icon next to its name — that means it's already a facet. The `gen_ai.usage.input_tokens`, `gen_ai.usage.output_tokens`, and `gen_ai.request.model` facets are typically promoted automatically by Datadog's LLM Observability auto-discovery, but verify they exist before importing the dashboard.
|
||||
</Step>
|
||||
</Steps>
|
||||
|
||||
## Import the dashboard
|
||||
|
||||
<Steps>
|
||||
<Step title="Download the dashboard JSON">
|
||||
Save [`datadog_dashboard.json`](https://raw.githubusercontent.com/crewAIInc/crewAI/main/docs/edge/en/enterprise/guides/datadog_dashboard.json) to your machine.
|
||||
</Step>
|
||||
<Step title="Open the import dialog in Datadog">
|
||||
Navigate to **Dashboards → New Dashboard**. Click the **gear icon** in the top right of the empty dashboard and select **Import Dashboard JSON**.
|
||||
</Step>
|
||||
<Step title="Paste or upload the JSON">
|
||||
Paste the contents of `datadog_dashboard.json` into the import dialog (or drag the file in). Click **Import**.
|
||||
|
||||
Datadog creates the dashboard immediately and lands you on it. The first load may show empty widgets for a few seconds while queries execute against the time range.
|
||||
</Step>
|
||||
</Steps>
|
||||
|
||||
<Tip>
|
||||
Datadog's [Dashboard API](https://docs.datadoghq.com/api/latest/dashboards/#create-a-new-dashboard) accepts the same JSON via `POST /api/v1/dashboard`. Use it if you manage dashboards through Terraform, Pulumi, or CI.
|
||||
</Tip>
|
||||
|
||||
## What you get
|
||||
|
||||
The dashboard is organized into four sections plus a placeholder for a custom drill-down widget:
|
||||
|
||||
| Section | Widgets | Useful for |
|
||||
|---------|---------|------------|
|
||||
| **Header** | Total Executions · Error Rate (%) · Active Automations · CrewAI Versions in Use | At-a-glance health for the last hour. Error Rate is conditionally formatted (green ≤ 5%, yellow ≤ 10%, red > 10%). |
|
||||
| **Throughput** | Executions per Hour by Automation (top 10, stacked bars) | Spotting traffic shifts, surfacing busy automations, validating that a rollout didn't change baseline volume. |
|
||||
| **Errors** | Errors by Exception Type (top 5, stacked bars) · Top Exception Types by Count (toplist) | Triaging failures — which exception types are spiking, which automations they're hitting. |
|
||||
| **Cost** | Total Tokens per Hour by Model (input + output, stacked area) | Tracking LLM token spend by model. Useful for catching cost regressions when an automation switches model or starts looping. |
|
||||
| **Drill-Down** | _(empty placeholder)_ | See [Customization](#customize) for adding a recent-errors log stream here. |
|
||||
|
||||
Three template variables at the top of the dashboard re-scope every widget at once:
|
||||
|
||||
- **`$automation`** — filter to a single automation by name.
|
||||
- **`$version`** — filter to a single `crewai` SDK version (useful for comparing pre- and post-upgrade behavior).
|
||||
- **`$service`** — filter to a specific Datadog `service` tag (useful when multiple CrewAI deployments share one Datadog account).
|
||||
|
||||
## Verify ingestion
|
||||
|
||||
Open [Logs Explorer](https://app.datadoghq.com/logs) and run a query that matches your ingestion path:
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Datadog Agent">
|
||||
Search `service:crewai* @schema:v1`. You should see structured logs with the JSON fields parsed into Datadog facets. Pick a recent event and verify it has `@automation_id`, `@kickoff_id`, `@execution_id`, `@crewai_version`, and (when running inside a span) `@trace_id` / `@span_id` populated.
|
||||
|
||||
If nothing appears, confirm `CREWAI_LOG_FORMAT=json` is set under your automation's **Environment Variables** in AMP, the deployment was restarted after the change, and the Datadog Agent is tailing container stdout.
|
||||
</Tab>
|
||||
<Tab title="Datadog OTLP intake">
|
||||
Search `source:otlp service:crewai*`. OTLP attributes land with their OpenTelemetry names (`automation_id`, `crewai.kickoff.id`, etc.) rather than the stdout JSON keys, but they map to the same dashboard facets after [facet promotion](#prerequisite-promote-facets).
|
||||
|
||||
If nothing appears, verify the collector endpoint is correct (`/v1/logs` for logs, `/v1/traces` for traces) and **Test Connection** succeeded when the collector was saved.
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
## Customize
|
||||
|
||||
The dashboard ships with deliberate gaps so you can extend it without uninstalling and re-importing.
|
||||
|
||||
### Add a Recent Errors log stream
|
||||
|
||||
The **Drill-Down** section is intentionally empty. Add a Log Stream widget to it for an inline view of recent failures:
|
||||
|
||||
1. Edit the dashboard and click **+ Add Widgets** inside the Drill-Down group.
|
||||
2. Drag in a **Log Stream** widget.
|
||||
3. Set the filter query to `status:error $automation $version $service`.
|
||||
4. Choose columns: `@timestamp`, `@automation_name`, `@exception.type`, `@exception.message`, `@execution_id`.
|
||||
5. Sort by most recent, limit to 25 entries.
|
||||
|
||||
Clicking any row jumps to Logs Explorer with the same filter pre-applied.
|
||||
|
||||
### Add p95 latency
|
||||
|
||||
Logs don't include execution duration by default. Two ways to add a latency widget:
|
||||
|
||||
- **From APM traces** — if you also export OTLP traces to Datadog, add a Timeseries widget with data source **Traces**, query `service:crewai*`, aggregation `p95 of @duration`. Datadog APM auto-tracks span duration.
|
||||
- **From metric extraction** — extract a `flow.duration_ms` metric from logs via [Datadog's log-to-metric pipeline](https://docs.datadoghq.com/logs/log_configuration/logs_to_metrics/), then chart it like any other metric. Useful if you don't run APM.
|
||||
|
||||
### Re-scope to multiple deployments
|
||||
|
||||
The `$service` template variable defaults to `*` and will catch every CrewAI deployment in your Datadog account. Change the default to a specific service name in **Configure → Template Variables** if you want the dashboard to focus on one deployment by default.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
| Symptom | Likely cause | Fix |
|
||||
|---------|--------------|-----|
|
||||
| All widgets show "No data" | Facets aren't promoted | Re-do the [Promote facets](#prerequisite-promote-facets) step. Datadog won't query against an un-promoted field. |
|
||||
| Error Rate widget shows `NaN` | No executions in the time window | Either no traffic, or `@execution_id` isn't faceted. Expand the time range and re-check facets. |
|
||||
| Throughput chart is flat at the same value | Logs aren't reaching Datadog | Search `service:crewai*` in Logs Explorer. If nothing shows, verify the Datadog Agent is running (Agent path) or the OTel collector endpoint is correct (OTLP path). |
|
||||
| `crewai_version` shows fewer values than expected | Some containers predate the structured-logs work | The `crewai_version` field was added alongside JSON output. Older deployments running text mode (or older AMP builds) won't emit it. Upgrade those deployments to pick up the field. See the [log schema reference](#log-schema-reference) for the full field contract. |
|
||||
| Template variables don't filter widgets | The widget's filter line doesn't reference the template variable | Edit the widget and confirm the search includes `$automation $version $service`. |
|
||||
|
||||
## Next steps
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="OpenTelemetry Export" icon="magnifying-glass-chart" href="./capture_telemetry_logs">
|
||||
Vendor-neutral observability for non-Datadog stacks (Grafana, Honeycomb, your own collector) — or as a Datadog complement when you want to fan out telemetry to multiple backends.
|
||||
</Card>
|
||||
<Card title="Datadog Log Search Syntax" icon="magnifying-glass" href="https://docs.datadoghq.com/logs/explorer/search_syntax/">
|
||||
Reference for customizing widget queries against the structured facets above.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
@@ -4,86 +4,6 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
|
||||
icon: "clock"
|
||||
mode: "wide"
|
||||
---
|
||||
<Update label="Jun 18, 2026">
|
||||
## v1.14.8a2
|
||||
|
||||
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a2)
|
||||
|
||||
## What's Changed
|
||||
|
||||
### Features
|
||||
- Add single agent action to Flow definitions
|
||||
- Validate flow CEL expressions at definition load time
|
||||
|
||||
### Documentation
|
||||
- Add Datadog integration guide with importable operations dashboard
|
||||
- Update snapshot and changelog for v1.14.8a1
|
||||
|
||||
## Contributors
|
||||
|
||||
@joaomdmoura, @lucasgomide, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="Jun 18, 2026">
|
||||
## v1.14.8a1
|
||||
|
||||
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a1)
|
||||
|
||||
## What's Changed
|
||||
|
||||
### Features
|
||||
- Add optional if expression to each.do steps
|
||||
|
||||
### Bug Fixes
|
||||
- Fix JSON crew issues
|
||||
|
||||
### Documentation
|
||||
- Update snapshot and changelog for v1.14.8a
|
||||
|
||||
## Contributors
|
||||
|
||||
@joaomdmoura, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="Jun 17, 2026">
|
||||
## v1.14.8a
|
||||
|
||||
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a)
|
||||
|
||||
## What's Changed
|
||||
|
||||
### Features
|
||||
- Add script/code block action to FlowDefinition
|
||||
- Add crew actions to FlowDefinition
|
||||
- Add `each` composite action to FlowDefinition
|
||||
- Implement DMN mode support in crew creation and execution
|
||||
- Enhance memory reset functionality and JSON crew handling
|
||||
- Add expressions to FlowDefinition actions
|
||||
- Implement Flow definition run tools without Python code
|
||||
- Drive human feedback from the flow definition
|
||||
- Wire config and persistence from FlowDefinition into the runtime
|
||||
- Add experimental `crewai run --definition` for flows
|
||||
- Support ZIP deployment fallback and JSON crew project env runs
|
||||
- Introduce JSON first crews
|
||||
|
||||
### Bug Fixes
|
||||
- Fix duplicated Exa tool
|
||||
- Fix aggregate token usage across all LLM calls
|
||||
- Resolve issues with crew loading and validation logic
|
||||
|
||||
### Documentation
|
||||
- Document FlowDefinition fields in the JSON schema
|
||||
- Update installation and quickstart documentation for JSON-first crew projects
|
||||
- Update changelog and version for v1.14.7
|
||||
|
||||
## Contributors
|
||||
|
||||
@gabemilani, @greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay, @lucasgomide, @theCyberTech, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="Jun 11, 2026">
|
||||
## v1.14.7
|
||||
|
||||
|
||||
@@ -9,10 +9,6 @@ CrewAI AMP can export OpenTelemetry **traces** and **logs** from your deployment
|
||||
|
||||
Telemetry data follows the [OpenTelemetry GenAI semantic conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/) plus additional CrewAI-specific attributes.
|
||||
|
||||
<Tip>
|
||||
OpenTelemetry is the **recommended observability path** — vendor-neutral, works with any OTLP-compatible backend (Grafana, Honeycomb, NewRelic, your own collector). If you specifically use Datadog, see the dedicated [Datadog Integration](./datadog) guide which covers both the Datadog Agent path and Datadog's OTLP intake.
|
||||
</Tip>
|
||||
|
||||
## Prerequisites
|
||||
|
||||
<CardGroup cols={2}>
|
||||
@@ -45,7 +41,17 @@ OpenTelemetry is the **recommended observability path** — vendor-neutral, work
|
||||
<Frame></Frame>
|
||||
</Tab>
|
||||
<Tab title="Datadog">
|
||||
For Datadog setup, see the dedicated [Datadog Integration](./datadog) guide — it covers both the Datadog Agent path (recommended, cheaper for log volume) and Datadog's OTLP intake with full collector configuration steps.
|
||||
- **Datadog Site Domain** — Your Datadog site's OTLP host only, with no protocol or path. CrewAI builds the full HTTPS OTLP endpoint for you. Use the host that matches your [Datadog site](https://docs.datadoghq.com/getting_started/site/):
|
||||
- `otlp.datadoghq.com` (US1)
|
||||
- `otlp.us3.datadoghq.com` (US3)
|
||||
- `otlp.us5.datadoghq.com` (US5)
|
||||
- `otlp.datadoghq.eu` (EU1)
|
||||
- `otlp.ap1.datadoghq.com` (AP1)
|
||||
- **API Key** — Your Datadog API key. See [how to create one](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
|
||||
|
||||
The Datadog integration exports **traces**.
|
||||
|
||||
<Frame></Frame>
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
|
||||
@@ -1,291 +0,0 @@
|
||||
---
|
||||
title: "Datadog Integration"
|
||||
description: "Monitor self-hosted CrewAI AMP deployments in Datadog via the Datadog Agent or Datadog's OTLP intake — either path lands the same structured facets so you can import the ready-made operations dashboard."
|
||||
icon: "dog"
|
||||
mode: "wide"
|
||||
---
|
||||
|
||||
CrewAI ships first-class support for Datadog: two log-ingestion paths, a JSON log schema designed for cheap indexing, and a ready-made operations dashboard you can import in under five minutes.
|
||||
|
||||
<Note>
|
||||
For vendor-neutral observability via any OTLP backend (Grafana, Honeycomb, your own collector), see [OpenTelemetry Export](./capture_telemetry_logs).
|
||||
</Note>
|
||||
|
||||
## Choose a path
|
||||
|
||||
CrewAI supports two log-ingestion paths to Datadog — both are first-class and produce the same structured facets that power the dashboard. Pick the one that fits your infrastructure.
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Datadog Agent">
|
||||
The Datadog Agent runs alongside your CrewAI containers (typically as a DaemonSet on Kubernetes) and tails their stdout. With `CREWAI_LOG_FORMAT=json` set, each log event ships as a single billable line with structured attributes.
|
||||
|
||||
**Setup:**
|
||||
1. Run the Datadog Agent next to your CrewAI containers — see [Datadog's deployment docs](https://docs.datadoghq.com/agent/) for Kubernetes, ECS, or VM setup. Enable log collection (`logs_enabled: true`) and container log collection (`logs_config.container_collect_all: true`).
|
||||
2. Set `CREWAI_LOG_FORMAT=json` as an **automation environment variable** in CrewAI AMP (open your automation → **Settings → Environment Variables**) so each log event is a single line instead of a multi-line traceback. AMP propagates the value to every container in the deployment (API + workers) — don't set it on the container or host directly. See [Enabling JSON output](#enabling-json-output) below for the AMP UI walkthrough and the [log schema reference](#log-schema-reference) for the full field contract.
|
||||
3. Confirm logs arrive in Datadog Logs with the JSON fields parsed — see [Verify ingestion](#verify-ingestion).
|
||||
|
||||
**Pick this path if** you already operate Datadog Agents (e.g. for infrastructure metrics), or your log volume makes per-event ingestion cost a real concern — collapsing tracebacks into single events keeps Agent ingestion cheap at scale.
|
||||
</Tab>
|
||||
<Tab title="Datadog OTLP intake">
|
||||
CrewAI AMP exports OpenTelemetry traffic directly to Datadog's OTLP endpoint with no Agent required. Logs and traces ride a single export pipeline configured in AMP's UI, using the same protocol you'd use for any other OTLP backend.
|
||||
|
||||
**Setup:**
|
||||
1. In CrewAI AMP, go to **Settings → OpenTelemetry Collectors → Add Collector** and pick **Datadog**.
|
||||
2. Configure the connection:
|
||||
- **Datadog Site Domain** — your Datadog site's OTLP host only, no protocol or path. CrewAI builds the full HTTPS OTLP endpoint for you. Use the host that matches your [Datadog site](https://docs.datadoghq.com/getting_started/site/):
|
||||
- `otlp.datadoghq.com` (US1)
|
||||
- `otlp.us3.datadoghq.com` (US3)
|
||||
- `otlp.us5.datadoghq.com` (US5)
|
||||
- `otlp.datadoghq.eu` (EU1)
|
||||
- `otlp.ap1.datadoghq.com` (AP1)
|
||||
- **API Key** — your Datadog API key. See [how to create one](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
|
||||
3. The Datadog template provisions **both signals at once** — when you save, AMP creates a traces collector at `/v1/traces` and a logs collector at `/v1/logs`, both sharing the same Datadog OTLP host and API key. You'll see them as two separate rows in your OTel collectors list.
|
||||
4. *(optional)* Click **Test Connection** to verify CrewAI can reach the endpoint with the credentials you provided. Then click **Save** — both collectors are created in one step.
|
||||
|
||||
<Frame></Frame>
|
||||
|
||||
**Pick this path if** you'd rather not operate a Datadog Agent, you already use OTLP for traces and want one export pipeline, or you may later want to fan out the same telemetry to other backends (Grafana, Honeycomb, etc.) without changing your application setup.
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
Either path lands the same structured facets in Datadog (`@automation_id`, `@kickoff_id`, `@execution_id`, `@automation_name`, `@crewai_version`, `@exception.type`, `@gen_ai.*`), so the dashboard works identically with either choice.
|
||||
|
||||
## Log schema reference
|
||||
|
||||
<Info>
|
||||
This schema applies to the **Datadog Agent path** — stdout JSON logs produced when `CREWAI_LOG_FORMAT=json` is set. Logs delivered via the **Datadog OTLP intake** use OpenTelemetry attribute names and may differ; see [OpenTelemetry Export](./capture_telemetry_logs).
|
||||
</Info>
|
||||
|
||||
When `CREWAI_LOG_FORMAT=json` is set, every log event is emitted as a **single JSON object per line** to stdout, with internal newlines escaped. The format is plain JSON — Datadog parses it natively, and the same payload is also consumable by Splunk, Loki, Elasticsearch, and CloudWatch without custom log pipelines.
|
||||
|
||||
### Why JSON output
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="Lower ingestion cost" icon="dollar-sign">
|
||||
Most managed log backends bill per event. A Python traceback in text format is counted as one event per line — 30+ events for a single error. JSON output collapses each traceback into a single event with the stack trace as an escaped string field.
|
||||
</Card>
|
||||
<Card title="Structured search" icon="magnifying-glass">
|
||||
Search by `@automation_id`, `@exception.type`, `@kickoff_id` instead of grepping free-text. Build dashboards on typed facets without parser configuration.
|
||||
</Card>
|
||||
<Card title="APM ↔ logs correlation" icon="link">
|
||||
Every event carries `trace_id` and `span_id` when fired inside a recording span, so backends auto-link logs to traces.
|
||||
</Card>
|
||||
<Card title="Stable contract" icon="file-shield">
|
||||
The `schema` field gates compatibility — within `v1`, fields are added but never renamed or removed.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
### Enabling JSON output
|
||||
|
||||
`CREWAI_LOG_FORMAT=json` must be set as an **automation environment variable** in CrewAI AMP — it is **not** a container, host, or Docker setting. Open your automation in AMP, click the **Settings** icon, and add the variable under the **Environment Variables** section. AMP applies the value to every container in the deployment (API + workers) on the next restart. See [Update Your Crew](./update-crew) for the full UI walkthrough with screenshots.
|
||||
|
||||
```shell
|
||||
CREWAI_LOG_FORMAT=json
|
||||
```
|
||||
|
||||
Restart the deployment to pick up the change. Every log line on stdout from that point on is a single JSON object.
|
||||
|
||||
<Note>
|
||||
The default value is `text`, which preserves the legacy human-readable line format byte-for-byte. Setting any value other than `json` falls back to text mode. There is no migration step — the variable is read at process start and the format switches immediately.
|
||||
</Note>
|
||||
|
||||
### Example events
|
||||
|
||||
A single info-level log inside an active automation kickoff:
|
||||
|
||||
```json
|
||||
{
|
||||
"schema": "v1",
|
||||
"ts": "2026-06-17T16:14:23.482914Z",
|
||||
"level": "INFO",
|
||||
"logger": "crewai_enterprise.utilities.pii_redaction",
|
||||
"crewai_version": "1.14.7",
|
||||
"msg": "PII tracking state reset (engines preserved)",
|
||||
"automation_id": "12",
|
||||
"task_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"kickoff_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"execution_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"automation_name": "research_flow"
|
||||
}
|
||||
```
|
||||
|
||||
An error with a Python exception is collapsed into a single event with the traceback as a string:
|
||||
|
||||
```json
|
||||
{
|
||||
"schema": "v1",
|
||||
"ts": "2026-06-17T16:14:31.218450Z",
|
||||
"level": "ERROR",
|
||||
"logger": "api.tasks.flow_run_task",
|
||||
"crewai_version": "1.14.7",
|
||||
"msg": "Flow execution failed",
|
||||
"automation_id": "12",
|
||||
"kickoff_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"execution_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"automation_name": "research_flow",
|
||||
"exception": {
|
||||
"type": "ValueError",
|
||||
"message": "Topic cannot be empty",
|
||||
"stacktrace": "Traceback (most recent call last):\n File \"/app/flow.py\", line 42, in summarize\n ...\nValueError: Topic cannot be empty\n"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The same error in legacy text mode would have produced ~25 separate log events (one per traceback line) — all of which the backend would bill and index individually.
|
||||
|
||||
### Schema v1 fields
|
||||
|
||||
Within the `v1` schema, fields are only added, never renamed or removed. New fields will appear as soon as a deployment is upgraded.
|
||||
|
||||
| Field | Type | Always present | Source |
|
||||
|-------|------|----------------|--------|
|
||||
| `schema` | string | Yes | Constant `"v1"`. Increment indicates a breaking schema change. |
|
||||
| `ts` | string (ISO-8601 UTC, microseconds) | Yes | Record creation time, e.g. `2026-06-17T16:14:23.482914Z`. |
|
||||
| `level` | string | Yes | Python log level name: `DEBUG` / `INFO` / `WARNING` / `ERROR` / `CRITICAL`. |
|
||||
| `logger` | string | Yes | Dotted logger name, e.g. `api.tasks.flow_run_task`. |
|
||||
| `crewai_version` | string | Yes (when `crewai` package metadata is resolvable) | Installed `crewai` package version, e.g. `"1.14.7"`. |
|
||||
| `msg` | string | Yes | Rendered log message (after `%`-formatting / `{}`-formatting). |
|
||||
| `automation_id` | string | When `CREWAI_PLUS_ID` env var is set | Numeric deployment ID (AMP provisions this on every container). |
|
||||
| `task_id` | string | On Celery worker logs | Celery task UUID, or `"no-task"` for non-task contexts. |
|
||||
| `kickoff_id` | string | Inside an automation kickoff | UUID of the current kickoff. |
|
||||
| `execution_id` | string | Inside an automation kickoff | UUID of the current sub-execution. Equal to `kickoff_id` at the top level; differs for nested flow methods that spawn sub-executions. |
|
||||
| `automation_name` | string | Inside an automation kickoff | Human-readable automation/flow name, e.g. `"research_flow"`. |
|
||||
| `trace_id` | string (32-hex) | Inside a recording OpenTelemetry span | Hex trace ID. Omitted when no span is active. |
|
||||
| `span_id` | string (16-hex) | Inside a recording OpenTelemetry span | Hex span ID. Omitted when no span is active. |
|
||||
| `exception` | object | When the log record has `exc_info` | `{type, message, stacktrace}` — full traceback as a single escaped string. |
|
||||
|
||||
<Tip>
|
||||
Any additional `extra={...}` kwargs passed to a logger call appear as top-level JSON fields verbatim. Reserved field names above always win to keep the schema stable.
|
||||
</Tip>
|
||||
|
||||
### Stability promise
|
||||
|
||||
The `schema` field declares the contract. Within `v1`, CrewAI commits to:
|
||||
|
||||
- **Never removing a field** that customers may have built queries or dashboards against.
|
||||
- **Never renaming a field** in place — renames happen via a schema bump (e.g. `v2`), with the old name kept as a deprecated alias for at least one release cycle.
|
||||
- **Adding new fields** at any time. Consumers should ignore unknown top-level keys.
|
||||
|
||||
When a `v2` is introduced, both the `schema` field and the migration guide will be published in advance, and `v1` will continue to be emitted for one release cycle so dashboards and queries have time to migrate.
|
||||
|
||||
## Prerequisite: promote facets
|
||||
|
||||
Datadog auto-discovers fields the first time it sees them but doesn't make them queryable in widgets until they're promoted to **facets**. This is a one-time setup in your Datadog account.
|
||||
|
||||
<Steps>
|
||||
<Step title="Search for a CrewAI log">
|
||||
Open [Logs Explorer](https://app.datadoghq.com/logs) and search `service:crewai*`. You should see at least one log event.
|
||||
</Step>
|
||||
<Step title="Promote each field">
|
||||
Click any log entry to open the right-hand details panel. For each field below, hover the field name → click the gear icon → **Create facet**.
|
||||
|
||||
- `automation_id`, `automation_name`, `execution_id`, `kickoff_id`, `task_id`
|
||||
- `crewai_version`, `model_id`
|
||||
- `exception.type`, `exception.message`
|
||||
|
||||
Skip any field that already shows a star icon next to its name — that means it's already a facet. The `gen_ai.usage.input_tokens`, `gen_ai.usage.output_tokens`, and `gen_ai.request.model` facets are typically promoted automatically by Datadog's LLM Observability auto-discovery, but verify they exist before importing the dashboard.
|
||||
</Step>
|
||||
</Steps>
|
||||
|
||||
## Import the dashboard
|
||||
|
||||
<Steps>
|
||||
<Step title="Download the dashboard JSON">
|
||||
Save [`datadog_dashboard.json`](https://raw.githubusercontent.com/crewAIInc/crewAI/main/docs/edge/en/enterprise/guides/datadog_dashboard.json) to your machine.
|
||||
</Step>
|
||||
<Step title="Open the import dialog in Datadog">
|
||||
Navigate to **Dashboards → New Dashboard**. Click the **gear icon** in the top right of the empty dashboard and select **Import Dashboard JSON**.
|
||||
</Step>
|
||||
<Step title="Paste or upload the JSON">
|
||||
Paste the contents of `datadog_dashboard.json` into the import dialog (or drag the file in). Click **Import**.
|
||||
|
||||
Datadog creates the dashboard immediately and lands you on it. The first load may show empty widgets for a few seconds while queries execute against the time range.
|
||||
</Step>
|
||||
</Steps>
|
||||
|
||||
<Tip>
|
||||
Datadog's [Dashboard API](https://docs.datadoghq.com/api/latest/dashboards/#create-a-new-dashboard) accepts the same JSON via `POST /api/v1/dashboard`. Use it if you manage dashboards through Terraform, Pulumi, or CI.
|
||||
</Tip>
|
||||
|
||||
## What you get
|
||||
|
||||
The dashboard is organized into four sections plus a placeholder for a custom drill-down widget:
|
||||
|
||||
| Section | Widgets | Useful for |
|
||||
|---------|---------|------------|
|
||||
| **Header** | Total Executions · Error Rate (%) · Active Automations · CrewAI Versions in Use | At-a-glance health for the last hour. Error Rate is conditionally formatted (green ≤ 5%, yellow ≤ 10%, red > 10%). |
|
||||
| **Throughput** | Executions per Hour by Automation (top 10, stacked bars) | Spotting traffic shifts, surfacing busy automations, validating that a rollout didn't change baseline volume. |
|
||||
| **Errors** | Errors by Exception Type (top 5, stacked bars) · Top Exception Types by Count (toplist) | Triaging failures — which exception types are spiking, which automations they're hitting. |
|
||||
| **Cost** | Total Tokens per Hour by Model (input + output, stacked area) | Tracking LLM token spend by model. Useful for catching cost regressions when an automation switches model or starts looping. |
|
||||
| **Drill-Down** | _(empty placeholder)_ | See [Customization](#customize) for adding a recent-errors log stream here. |
|
||||
|
||||
Three template variables at the top of the dashboard re-scope every widget at once:
|
||||
|
||||
- **`$automation`** — filter to a single automation by name.
|
||||
- **`$version`** — filter to a single `crewai` SDK version (useful for comparing pre- and post-upgrade behavior).
|
||||
- **`$service`** — filter to a specific Datadog `service` tag (useful when multiple CrewAI deployments share one Datadog account).
|
||||
|
||||
## Verify ingestion
|
||||
|
||||
Open [Logs Explorer](https://app.datadoghq.com/logs) and run a query that matches your ingestion path:
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Datadog Agent">
|
||||
Search `service:crewai* @schema:v1`. You should see structured logs with the JSON fields parsed into Datadog facets. Pick a recent event and verify it has `@automation_id`, `@kickoff_id`, `@execution_id`, `@crewai_version`, and (when running inside a span) `@trace_id` / `@span_id` populated.
|
||||
|
||||
If nothing appears, confirm `CREWAI_LOG_FORMAT=json` is set under your automation's **Environment Variables** in AMP, the deployment was restarted after the change, and the Datadog Agent is tailing container stdout.
|
||||
</Tab>
|
||||
<Tab title="Datadog OTLP intake">
|
||||
Search `source:otlp service:crewai*`. OTLP attributes land with their OpenTelemetry names (`automation_id`, `crewai.kickoff.id`, etc.) rather than the stdout JSON keys, but they map to the same dashboard facets after [facet promotion](#prerequisite-promote-facets).
|
||||
|
||||
If nothing appears, verify the collector endpoint is correct (`/v1/logs` for logs, `/v1/traces` for traces) and **Test Connection** succeeded when the collector was saved.
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
## Customize
|
||||
|
||||
The dashboard ships with deliberate gaps so you can extend it without uninstalling and re-importing.
|
||||
|
||||
### Add a Recent Errors log stream
|
||||
|
||||
The **Drill-Down** section is intentionally empty. Add a Log Stream widget to it for an inline view of recent failures:
|
||||
|
||||
1. Edit the dashboard and click **+ Add Widgets** inside the Drill-Down group.
|
||||
2. Drag in a **Log Stream** widget.
|
||||
3. Set the filter query to `status:error $automation $version $service`.
|
||||
4. Choose columns: `@timestamp`, `@automation_name`, `@exception.type`, `@exception.message`, `@execution_id`.
|
||||
5. Sort by most recent, limit to 25 entries.
|
||||
|
||||
Clicking any row jumps to Logs Explorer with the same filter pre-applied.
|
||||
|
||||
### Add p95 latency
|
||||
|
||||
Logs don't include execution duration by default. Two ways to add a latency widget:
|
||||
|
||||
- **From APM traces** — if you also export OTLP traces to Datadog, add a Timeseries widget with data source **Traces**, query `service:crewai*`, aggregation `p95 of @duration`. Datadog APM auto-tracks span duration.
|
||||
- **From metric extraction** — extract a `flow.duration_ms` metric from logs via [Datadog's log-to-metric pipeline](https://docs.datadoghq.com/logs/log_configuration/logs_to_metrics/), then chart it like any other metric. Useful if you don't run APM.
|
||||
|
||||
### Re-scope to multiple deployments
|
||||
|
||||
The `$service` template variable defaults to `*` and will catch every CrewAI deployment in your Datadog account. Change the default to a specific service name in **Configure → Template Variables** if you want the dashboard to focus on one deployment by default.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
| Symptom | Likely cause | Fix |
|
||||
|---------|--------------|-----|
|
||||
| All widgets show "No data" | Facets aren't promoted | Re-do the [Promote facets](#prerequisite-promote-facets) step. Datadog won't query against an un-promoted field. |
|
||||
| Error Rate widget shows `NaN` | No executions in the time window | Either no traffic, or `@execution_id` isn't faceted. Expand the time range and re-check facets. |
|
||||
| Throughput chart is flat at the same value | Logs aren't reaching Datadog | Search `service:crewai*` in Logs Explorer. If nothing shows, verify the Datadog Agent is running (Agent path) or the OTel collector endpoint is correct (OTLP path). |
|
||||
| `crewai_version` shows fewer values than expected | Some containers predate the structured-logs work | The `crewai_version` field was added alongside JSON output. Older deployments running text mode (or older AMP builds) won't emit it. Upgrade those deployments to pick up the field. See the [log schema reference](#log-schema-reference) for the full field contract. |
|
||||
| Template variables don't filter widgets | The widget's filter line doesn't reference the template variable | Edit the widget and confirm the search includes `$automation $version $service`. |
|
||||
|
||||
## Next steps
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="OpenTelemetry Export" icon="magnifying-glass-chart" href="./capture_telemetry_logs">
|
||||
Vendor-neutral observability for non-Datadog stacks (Grafana, Honeycomb, your own collector) — or as a Datadog complement when you want to fan out telemetry to multiple backends.
|
||||
</Card>
|
||||
<Card title="Datadog Log Search Syntax" icon="magnifying-glass" href="https://docs.datadoghq.com/logs/explorer/search_syntax/">
|
||||
Reference for customizing widget queries against the structured facets above.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
@@ -1,582 +0,0 @@
|
||||
{
|
||||
"title": "crewAI -- Operations",
|
||||
"description": "Monitoring dashboard for self-hosted crewAI deployments running structured JSON logs. Tracks executions, errors, token usage, and automation health.",
|
||||
"widgets": [
|
||||
{
|
||||
"id": 8810001,
|
||||
"definition": {
|
||||
"title": "Header",
|
||||
"background_color": "vivid_blue",
|
||||
"show_title": true,
|
||||
"type": "group",
|
||||
"layout_type": "ordered",
|
||||
"widgets": [
|
||||
{
|
||||
"id": 9910001,
|
||||
"definition": {
|
||||
"title": "Total Executions",
|
||||
"time": {
|
||||
"live_span": "1h"
|
||||
},
|
||||
"type": "query_value",
|
||||
"requests": [
|
||||
{
|
||||
"response_format": "scalar",
|
||||
"queries": [
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query1",
|
||||
"search": {
|
||||
"query": "$automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "cardinality",
|
||||
"metric": "@execution_id"
|
||||
},
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
}
|
||||
],
|
||||
"formulas": [
|
||||
{
|
||||
"formula": "query1"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"autoscale": true,
|
||||
"precision": 0
|
||||
},
|
||||
"layout": {
|
||||
"x": 0,
|
||||
"y": 0,
|
||||
"width": 3,
|
||||
"height": 2
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 9910002,
|
||||
"definition": {
|
||||
"title": "Error Rate (%)",
|
||||
"time": {
|
||||
"live_span": "1h"
|
||||
},
|
||||
"type": "query_value",
|
||||
"requests": [
|
||||
{
|
||||
"response_format": "scalar",
|
||||
"queries": [
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query1",
|
||||
"search": {
|
||||
"query": "status:error $automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "count"
|
||||
},
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query2",
|
||||
"search": {
|
||||
"query": "$automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "cardinality",
|
||||
"metric": "@execution_id"
|
||||
},
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
}
|
||||
],
|
||||
"formulas": [
|
||||
{
|
||||
"formula": "query1 / query2 * 100"
|
||||
}
|
||||
],
|
||||
"conditional_formats": [
|
||||
{
|
||||
"comparator": ">",
|
||||
"value": 10,
|
||||
"palette": "white_on_red"
|
||||
},
|
||||
{
|
||||
"comparator": ">",
|
||||
"value": 5,
|
||||
"palette": "white_on_yellow"
|
||||
},
|
||||
{
|
||||
"comparator": ">=",
|
||||
"value": 0,
|
||||
"palette": "white_on_green"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"autoscale": false,
|
||||
"custom_unit": "%",
|
||||
"precision": 2
|
||||
},
|
||||
"layout": {
|
||||
"x": 3,
|
||||
"y": 0,
|
||||
"width": 3,
|
||||
"height": 2
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 9910003,
|
||||
"definition": {
|
||||
"title": "Active Automations",
|
||||
"time": {
|
||||
"live_span": "1h"
|
||||
},
|
||||
"type": "query_value",
|
||||
"requests": [
|
||||
{
|
||||
"response_format": "scalar",
|
||||
"queries": [
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query1",
|
||||
"search": {
|
||||
"query": "$automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "cardinality",
|
||||
"metric": "@automation_id"
|
||||
},
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
}
|
||||
],
|
||||
"formulas": [
|
||||
{
|
||||
"formula": "query1"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"autoscale": true,
|
||||
"precision": 0
|
||||
},
|
||||
"layout": {
|
||||
"x": 6,
|
||||
"y": 0,
|
||||
"width": 3,
|
||||
"height": 2
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 9910004,
|
||||
"definition": {
|
||||
"title": "CrewAI Versions in Use",
|
||||
"time": {
|
||||
"live_span": "1h"
|
||||
},
|
||||
"type": "query_value",
|
||||
"requests": [
|
||||
{
|
||||
"response_format": "scalar",
|
||||
"queries": [
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query1",
|
||||
"search": {
|
||||
"query": "$automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "cardinality",
|
||||
"metric": "@crewai_version"
|
||||
},
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
}
|
||||
],
|
||||
"formulas": [
|
||||
{
|
||||
"formula": "query1"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"autoscale": true,
|
||||
"precision": 0
|
||||
},
|
||||
"layout": {
|
||||
"x": 9,
|
||||
"y": 0,
|
||||
"width": 3,
|
||||
"height": 2
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"layout": {
|
||||
"x": 0,
|
||||
"y": 0,
|
||||
"width": 12,
|
||||
"height": 3
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 8820001,
|
||||
"definition": {
|
||||
"title": "Throughput",
|
||||
"background_color": "vivid_green",
|
||||
"show_title": true,
|
||||
"type": "group",
|
||||
"layout_type": "ordered",
|
||||
"widgets": [
|
||||
{
|
||||
"id": 9920001,
|
||||
"definition": {
|
||||
"title": "Executions per Hour by Automation (top 10)",
|
||||
"show_legend": false,
|
||||
"type": "timeseries",
|
||||
"requests": [
|
||||
{
|
||||
"response_format": "timeseries",
|
||||
"queries": [
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query1",
|
||||
"search": {
|
||||
"query": "$automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "cardinality",
|
||||
"metric": "@execution_id",
|
||||
"interval": 3600000
|
||||
},
|
||||
"group_by": [
|
||||
{
|
||||
"facet": "@automation_name",
|
||||
"limit": 10,
|
||||
"sort": {
|
||||
"aggregation": "cardinality",
|
||||
"metric": "@execution_id",
|
||||
"order": "desc"
|
||||
}
|
||||
}
|
||||
],
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
}
|
||||
],
|
||||
"formulas": [
|
||||
{
|
||||
"formula": "query1"
|
||||
}
|
||||
],
|
||||
"style": {
|
||||
"palette": "semantic"
|
||||
},
|
||||
"display_type": "bars"
|
||||
}
|
||||
]
|
||||
},
|
||||
"layout": {
|
||||
"x": 0,
|
||||
"y": 0,
|
||||
"width": 12,
|
||||
"height": 3
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"layout": {
|
||||
"x": 0,
|
||||
"y": 3,
|
||||
"width": 12,
|
||||
"height": 4
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 8830001,
|
||||
"definition": {
|
||||
"title": "Errors",
|
||||
"background_color": "vivid_orange",
|
||||
"show_title": true,
|
||||
"type": "group",
|
||||
"layout_type": "ordered",
|
||||
"widgets": [
|
||||
{
|
||||
"id": 9930001,
|
||||
"definition": {
|
||||
"title": "Errors by Exception Type (top 5)",
|
||||
"show_legend": false,
|
||||
"type": "timeseries",
|
||||
"requests": [
|
||||
{
|
||||
"response_format": "timeseries",
|
||||
"queries": [
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query1",
|
||||
"search": {
|
||||
"query": "status:error $automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "count"
|
||||
},
|
||||
"group_by": [
|
||||
{
|
||||
"facet": "@exception.type",
|
||||
"limit": 5,
|
||||
"sort": {
|
||||
"aggregation": "count",
|
||||
"order": "desc"
|
||||
}
|
||||
}
|
||||
],
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
}
|
||||
],
|
||||
"formulas": [
|
||||
{
|
||||
"formula": "query1"
|
||||
}
|
||||
],
|
||||
"style": {
|
||||
"palette": "warm"
|
||||
},
|
||||
"display_type": "bars"
|
||||
}
|
||||
]
|
||||
},
|
||||
"layout": {
|
||||
"x": 0,
|
||||
"y": 0,
|
||||
"width": 6,
|
||||
"height": 3
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 9930002,
|
||||
"definition": {
|
||||
"title": "Top Exception Types by Count",
|
||||
"type": "toplist",
|
||||
"requests": [
|
||||
{
|
||||
"response_format": "scalar",
|
||||
"queries": [
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query1",
|
||||
"search": {
|
||||
"query": "status:error $automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "count"
|
||||
},
|
||||
"group_by": [
|
||||
{
|
||||
"facet": "@exception.type",
|
||||
"limit": 10,
|
||||
"sort": {
|
||||
"aggregation": "count",
|
||||
"order": "desc"
|
||||
}
|
||||
}
|
||||
],
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
}
|
||||
],
|
||||
"formulas": [
|
||||
{
|
||||
"formula": "query1"
|
||||
}
|
||||
],
|
||||
"sort": {
|
||||
"count": 10,
|
||||
"order_by": [
|
||||
{
|
||||
"type": "formula",
|
||||
"index": 0,
|
||||
"order": "desc"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"style": {
|
||||
"palette": "datadog16"
|
||||
}
|
||||
},
|
||||
"layout": {
|
||||
"x": 6,
|
||||
"y": 0,
|
||||
"width": 6,
|
||||
"height": 3
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"layout": {
|
||||
"x": 0,
|
||||
"y": 7,
|
||||
"width": 12,
|
||||
"height": 4
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 8840001,
|
||||
"definition": {
|
||||
"title": "Cost",
|
||||
"background_color": "vivid_purple",
|
||||
"show_title": true,
|
||||
"type": "group",
|
||||
"layout_type": "ordered",
|
||||
"widgets": [
|
||||
{
|
||||
"id": 9940001,
|
||||
"definition": {
|
||||
"title": "Total Tokens per Hour by Model (input + output)",
|
||||
"show_legend": false,
|
||||
"type": "timeseries",
|
||||
"requests": [
|
||||
{
|
||||
"response_format": "timeseries",
|
||||
"queries": [
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query1",
|
||||
"search": {
|
||||
"query": "$automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "sum",
|
||||
"metric": "@gen_ai.usage.input_tokens",
|
||||
"interval": 3600000
|
||||
},
|
||||
"group_by": [
|
||||
{
|
||||
"facet": "@gen_ai.request.model",
|
||||
"limit": 10,
|
||||
"sort": {
|
||||
"aggregation": "sum",
|
||||
"metric": "@gen_ai.usage.input_tokens",
|
||||
"order": "desc"
|
||||
}
|
||||
}
|
||||
],
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data_source": "logs",
|
||||
"name": "query2",
|
||||
"search": {
|
||||
"query": "$automation $version $service"
|
||||
},
|
||||
"compute": {
|
||||
"aggregation": "sum",
|
||||
"metric": "@gen_ai.usage.output_tokens",
|
||||
"interval": 3600000
|
||||
},
|
||||
"group_by": [
|
||||
{
|
||||
"facet": "@gen_ai.request.model",
|
||||
"limit": 10,
|
||||
"sort": {
|
||||
"aggregation": "sum",
|
||||
"metric": "@gen_ai.usage.output_tokens",
|
||||
"order": "desc"
|
||||
}
|
||||
}
|
||||
],
|
||||
"indexes": [
|
||||
"*"
|
||||
]
|
||||
}
|
||||
],
|
||||
"formulas": [
|
||||
{
|
||||
"formula": "query1 + query2",
|
||||
"alias": "Total Tokens"
|
||||
}
|
||||
],
|
||||
"style": {
|
||||
"palette": "cool"
|
||||
},
|
||||
"display_type": "area"
|
||||
}
|
||||
]
|
||||
},
|
||||
"layout": {
|
||||
"x": 0,
|
||||
"y": 0,
|
||||
"width": 12,
|
||||
"height": 3
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"layout": {
|
||||
"x": 0,
|
||||
"y": 11,
|
||||
"width": 12,
|
||||
"height": 4
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 8850002,
|
||||
"definition": {
|
||||
"title": "Drill-Down",
|
||||
"background_color": "gray",
|
||||
"show_title": true,
|
||||
"type": "group",
|
||||
"layout_type": "ordered",
|
||||
"widgets": []
|
||||
},
|
||||
"layout": {
|
||||
"x": 0,
|
||||
"y": 15,
|
||||
"width": 12,
|
||||
"height": 1
|
||||
}
|
||||
}
|
||||
],
|
||||
"template_variables": [
|
||||
{
|
||||
"name": "automation",
|
||||
"prefix": "@automation_name",
|
||||
"available_values": [],
|
||||
"default": "*"
|
||||
},
|
||||
{
|
||||
"name": "version",
|
||||
"prefix": "@crewai_version",
|
||||
"available_values": [],
|
||||
"default": "*"
|
||||
},
|
||||
{
|
||||
"name": "service",
|
||||
"prefix": "service",
|
||||
"available_values": [],
|
||||
"default": "*"
|
||||
}
|
||||
],
|
||||
"layout_type": "ordered",
|
||||
"notify_list": [],
|
||||
"pause_auto_refresh": false,
|
||||
"reflow_type": "fixed",
|
||||
"tags": [
|
||||
"ai:created_with_ai"
|
||||
]
|
||||
}
|
||||
@@ -28,60 +28,6 @@ mode: "wide"
|
||||
|
||||
<div style={{ display: 'flex', flexWrap: 'wrap', gap: 12, justifyContent: 'center' }}>
|
||||
<a className="button button-primary" href="/en/quickstart">Get started</a>
|
||||
<button
|
||||
type="button"
|
||||
className="button"
|
||||
onClick={async (event) => {
|
||||
const prompt = `Set up this environment so I can build with CrewAI.
|
||||
|
||||
First install the official CrewAI coding-agent skills if this environment supports npx:
|
||||
|
||||
npx skills add crewaiinc/skills
|
||||
|
||||
If npx is missing or the current agent cannot load skills, do not fail the whole setup. Report the exact issue and continue using the CrewAI docs directly.
|
||||
|
||||
Use these CrewAI docs as source of truth before making assumptions:
|
||||
- https://skills.crewai.com
|
||||
- https://docs.crewai.com/llms.txt
|
||||
- https://docs.crewai.com/en/installation
|
||||
- https://docs.crewai.com/en/guides/coding-tools/build-with-ai
|
||||
|
||||
Setup steps:
|
||||
1. Check python3 --version. CrewAI requires Python >=3.10 and <3.14.
|
||||
2. Install uv if missing:
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
3. Source the uv environment if needed:
|
||||
source "$HOME/.local/bin/env"
|
||||
4. Install the CrewAI CLI:
|
||||
uv tool install crewai
|
||||
5. Verify the CLI:
|
||||
crewai version
|
||||
crewai create --help
|
||||
6. Create a project:
|
||||
CREWAI_DMN=true crewai create
|
||||
7. After project creation, inspect the generated files before editing.
|
||||
8. Run:
|
||||
crewai install
|
||||
crewai run
|
||||
|
||||
Do not hardcode API keys. Use .env.
|
||||
Do not invent CLI flags. Validate with crewai --help or crewai create --help.
|
||||
If a command fails, show the exact command and error, explain the likely cause, fix what you can safely fix, and retry once.`;
|
||||
const button = event.currentTarget;
|
||||
try {
|
||||
await navigator.clipboard.writeText(prompt);
|
||||
button.textContent = "Copied";
|
||||
} catch {
|
||||
button.textContent = "Copy failed";
|
||||
} finally {
|
||||
window.setTimeout(() => {
|
||||
button.textContent = "Copy instructions for coding agents";
|
||||
}, 1600);
|
||||
}
|
||||
}}
|
||||
>
|
||||
Copy instructions for coding agents
|
||||
</button>
|
||||
<a className="button" href="/en/changelog">View changelog</a>
|
||||
<a className="button" href="/en/api-reference/introduction">API Reference</a>
|
||||
</div>
|
||||
|
||||
@@ -9,60 +9,7 @@ mode: "wide"
|
||||
|
||||
Install our coding agent skills (Claude Code, Codex, ...) to quickly get your coding agents up and running with CrewAI.
|
||||
|
||||
<button
|
||||
type="button"
|
||||
className="button button-primary"
|
||||
onClick={async (event) => {
|
||||
const prompt = `Set up this environment so I can build with CrewAI.
|
||||
|
||||
First install the official CrewAI coding-agent skills if this environment supports npx:
|
||||
|
||||
npx skills add crewaiinc/skills
|
||||
|
||||
If npx is missing or the current agent cannot load skills, do not fail the whole setup. Report the exact issue and continue using the CrewAI docs directly.
|
||||
|
||||
Use these CrewAI docs as source of truth before making assumptions:
|
||||
- https://skills.crewai.com
|
||||
- https://docs.crewai.com/llms.txt
|
||||
- https://docs.crewai.com/en/installation
|
||||
- https://docs.crewai.com/en/guides/coding-tools/build-with-ai
|
||||
|
||||
Setup steps:
|
||||
1. Check python3 --version. CrewAI requires Python >=3.10 and <3.14.
|
||||
2. Install uv if missing:
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
3. Source the uv environment if needed:
|
||||
source "$HOME/.local/bin/env"
|
||||
4. Install the CrewAI CLI:
|
||||
uv tool install crewai
|
||||
5. Verify the CLI:
|
||||
crewai version
|
||||
crewai create --help
|
||||
6. Create a project:
|
||||
CREWAI_DMN=true crewai create
|
||||
7. After project creation, inspect the generated files before editing.
|
||||
8. Run:
|
||||
crewai install
|
||||
crewai run
|
||||
|
||||
Do not hardcode API keys. Use .env.
|
||||
Do not invent CLI flags. Validate with crewai --help or crewai create --help.
|
||||
If a command fails, show the exact command and error, explain the likely cause, fix what you can safely fix, and retry once.`;
|
||||
const button = event.currentTarget;
|
||||
try {
|
||||
await navigator.clipboard.writeText(prompt);
|
||||
button.textContent = "Copied";
|
||||
} catch {
|
||||
button.textContent = "Copy failed";
|
||||
} finally {
|
||||
window.setTimeout(() => {
|
||||
button.textContent = "Copy instructions for coding agents";
|
||||
}, 1600);
|
||||
}
|
||||
}}
|
||||
>
|
||||
Copy instructions for coding agents
|
||||
</button>
|
||||
You can install it with `npx skills add crewaiinc/skills`
|
||||
|
||||
<iframe src="https://www.loom.com/embed/befb9f68b81f42ad8112bfdd95a780af" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style={{width: "100%", height: "400px"}}></iframe>
|
||||
|
||||
|
||||
@@ -4,86 +4,6 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
|
||||
icon: "clock"
|
||||
mode: "wide"
|
||||
---
|
||||
<Update label="2026년 6월 18일">
|
||||
## v1.14.8a2
|
||||
|
||||
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a2)
|
||||
|
||||
## 변경 사항
|
||||
|
||||
### 기능
|
||||
- Flow 정의에 단일 에이전트 작업 추가
|
||||
- 정의 로드 시 흐름 CEL 표현식 검증
|
||||
|
||||
### 문서
|
||||
- 가져올 수 있는 운영 대시보드와 함께 Datadog 통합 가이드 추가
|
||||
- v1.14.8a1의 스냅샷 및 변경 로그 업데이트
|
||||
|
||||
## 기여자
|
||||
|
||||
@joaomdmoura, @lucasgomide, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="2026년 6월 18일">
|
||||
## v1.14.8a1
|
||||
|
||||
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a1)
|
||||
|
||||
## 변경 사항
|
||||
|
||||
### 기능
|
||||
- 각 do 단계에 선택적 if 표현식을 추가
|
||||
|
||||
### 버그 수정
|
||||
- JSON 크루 문제 수정
|
||||
|
||||
### 문서
|
||||
- v1.14.8a의 스냅샷 및 변경 로그 업데이트
|
||||
|
||||
## 기여자
|
||||
|
||||
@joaomdmoura, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="2026년 6월 17일">
|
||||
## v1.14.8a
|
||||
|
||||
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a)
|
||||
|
||||
## 변경 사항
|
||||
|
||||
### 기능
|
||||
- FlowDefinition에 스크립트/코드 블록 액션 추가
|
||||
- FlowDefinition에 크루 액션 추가
|
||||
- FlowDefinition에 `each` 복합 액션 추가
|
||||
- 크루 생성 및 실행에서 DMN 모드 지원 구현
|
||||
- 메모리 재설정 기능 및 JSON 크루 처리 기능 향상
|
||||
- FlowDefinition 액션에 표현식 추가
|
||||
- Python 코드 없이 Flow 정의 실행 도구 구현
|
||||
- Flow 정의에서 인간 피드백 유도
|
||||
- FlowDefinition의 구성 및 지속성을 런타임에 연결
|
||||
- 흐름을 위한 실험적 `crewai run --definition` 추가
|
||||
- ZIP 배포 대체 및 JSON 크루 프로젝트 환경 실행 지원
|
||||
- JSON 우선 크루 도입
|
||||
|
||||
### 버그 수정
|
||||
- 중복된 Exa 도구 수정
|
||||
- 모든 LLM 호출에서 집계 토큰 사용 수정
|
||||
- 크루 로딩 및 검증 로직 관련 문제 해결
|
||||
|
||||
### 문서
|
||||
- JSON 스키마에서 FlowDefinition 필드 문서화
|
||||
- JSON 우선 크루 프로젝트에 대한 설치 및 빠른 시작 문서 업데이트
|
||||
- v1.14.7에 대한 변경 로그 및 버전 업데이트
|
||||
|
||||
## 기여자
|
||||
|
||||
@gabemilani, @greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay, @lucasgomide, @theCyberTech, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="2026년 6월 11일">
|
||||
## v1.14.7
|
||||
|
||||
|
||||
@@ -9,10 +9,6 @@ CrewAI AMP는 배포에서 OpenTelemetry **트레이스**와 **로그**를 자
|
||||
|
||||
텔레메트리 데이터는 [OpenTelemetry GenAI 시맨틱 규칙](https://opentelemetry.io/docs/specs/semconv/gen-ai/)과 추가적인 CrewAI 전용 속성을 따릅니다.
|
||||
|
||||
<Tip>
|
||||
OpenTelemetry는 **권장되는 관측 가능성 경로**입니다 — 벤더 중립적이며, OTLP 호환 백엔드(Grafana, Honeycomb, NewRelic, 자체 수집기)에서 작동합니다. Datadog을 사용하는 경우, Datadog Agent 경로와 Datadog의 OTLP 수집을 모두 다루는 전용 [Datadog 통합](./datadog) 가이드를 참조하세요.
|
||||
</Tip>
|
||||
|
||||
## 사전 요구 사항
|
||||
|
||||
<CardGroup cols={2}>
|
||||
@@ -45,7 +41,17 @@ OpenTelemetry는 **권장되는 관측 가능성 경로**입니다 — 벤더
|
||||
<Frame></Frame>
|
||||
</Tab>
|
||||
<Tab title="Datadog">
|
||||
Datadog 설정은 전용 [Datadog 통합](./datadog) 가이드를 참조하세요 — Datadog Agent 경로(권장, 로그 볼륨에 더 저렴)와 Datadog의 OTLP 수집을 모두 다루며, 수집기 구성 단계를 완전히 설명합니다.
|
||||
- **Datadog Site Domain** — Datadog 사이트의 OTLP 호스트만 입력합니다 (프로토콜이나 경로 제외). CrewAI가 전체 HTTPS OTLP 엔드포인트를 자동으로 구성합니다. [Datadog 사이트](https://docs.datadoghq.com/getting_started/site/)에 맞는 호스트를 사용하세요:
|
||||
- `otlp.datadoghq.com` (US1)
|
||||
- `otlp.us3.datadoghq.com` (US3)
|
||||
- `otlp.us5.datadoghq.com` (US5)
|
||||
- `otlp.datadoghq.eu` (EU1)
|
||||
- `otlp.ap1.datadoghq.com` (AP1)
|
||||
- **API Key** — Datadog API 키입니다. [키 생성 방법](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys)을 참고하세요.
|
||||
|
||||
Datadog 통합은 **트레이스**를 내보냅니다.
|
||||
|
||||
<Frame></Frame>
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
|
||||
@@ -1,295 +0,0 @@
|
||||
---
|
||||
title: "Datadog 통합"
|
||||
description: "Datadog Agent 또는 Datadog의 OTLP 수집을 통해 자체 호스팅 CrewAI AMP 배포를 Datadog에서 모니터링하세요 — 두 경로 모두 동일한 구조화된 패싯을 생성하므로 기성 운영 대시보드를 가져올 수 있습니다."
|
||||
icon: "dog"
|
||||
mode: "wide"
|
||||
---
|
||||
|
||||
<Note>
|
||||
**번역 진행 중** — 콘텐츠가 영어로 표시됩니다.
|
||||
</Note>
|
||||
|
||||
CrewAI ships first-class support for Datadog: two log-ingestion paths, a JSON log schema designed for cheap indexing, and a ready-made operations dashboard you can import in under five minutes.
|
||||
|
||||
<Note>
|
||||
For vendor-neutral observability via any OTLP backend (Grafana, Honeycomb, your own collector), see [OpenTelemetry Export](./capture_telemetry_logs).
|
||||
</Note>
|
||||
|
||||
## Choose a path
|
||||
|
||||
CrewAI supports two log-ingestion paths to Datadog — both are first-class and produce the same structured facets that power the dashboard. Pick the one that fits your infrastructure.
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Datadog Agent">
|
||||
The Datadog Agent runs alongside your CrewAI containers (typically as a DaemonSet on Kubernetes) and tails their stdout. With `CREWAI_LOG_FORMAT=json` set, each log event ships as a single billable line with structured attributes.
|
||||
|
||||
**Setup:**
|
||||
1. Run the Datadog Agent next to your CrewAI containers — see [Datadog's deployment docs](https://docs.datadoghq.com/agent/) for Kubernetes, ECS, or VM setup. Enable log collection (`logs_enabled: true`) and container log collection (`logs_config.container_collect_all: true`).
|
||||
2. Set `CREWAI_LOG_FORMAT=json` as an **automation environment variable** in CrewAI AMP (open your automation → **Settings → Environment Variables**) so each log event is a single line instead of a multi-line traceback. AMP propagates the value to every container in the deployment (API + workers) — don't set it on the container or host directly. See [Enabling JSON output](#enabling-json-output) below for the AMP UI walkthrough and the [log schema reference](#log-schema-reference) for the full field contract.
|
||||
3. Confirm logs arrive in Datadog Logs with the JSON fields parsed — see [Verify ingestion](#verify-ingestion).
|
||||
|
||||
**Pick this path if** you already operate Datadog Agents (e.g. for infrastructure metrics), or your log volume makes per-event ingestion cost a real concern — collapsing tracebacks into single events keeps Agent ingestion cheap at scale.
|
||||
</Tab>
|
||||
<Tab title="Datadog OTLP intake">
|
||||
CrewAI AMP exports OpenTelemetry traffic directly to Datadog's OTLP endpoint with no Agent required. Logs and traces ride a single export pipeline configured in AMP's UI, using the same protocol you'd use for any other OTLP backend.
|
||||
|
||||
**Setup:**
|
||||
1. In CrewAI AMP, go to **Settings → OpenTelemetry Collectors → Add Collector** and pick **Datadog**.
|
||||
2. Configure the connection:
|
||||
- **Datadog Site Domain** — your Datadog site's OTLP host only, no protocol or path. CrewAI builds the full HTTPS OTLP endpoint for you. Use the host that matches your [Datadog site](https://docs.datadoghq.com/getting_started/site/):
|
||||
- `otlp.datadoghq.com` (US1)
|
||||
- `otlp.us3.datadoghq.com` (US3)
|
||||
- `otlp.us5.datadoghq.com` (US5)
|
||||
- `otlp.datadoghq.eu` (EU1)
|
||||
- `otlp.ap1.datadoghq.com` (AP1)
|
||||
- **API Key** — your Datadog API key. See [how to create one](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
|
||||
3. The Datadog template provisions **both signals at once** — when you save, AMP creates a traces collector at `/v1/traces` and a logs collector at `/v1/logs`, both sharing the same Datadog OTLP host and API key. You'll see them as two separate rows in your OTel collectors list.
|
||||
4. *(optional)* Click **Test Connection** to verify CrewAI can reach the endpoint with the credentials you provided. Then click **Save** — both collectors are created in one step.
|
||||
|
||||
<Frame></Frame>
|
||||
|
||||
**Pick this path if** you'd rather not operate a Datadog Agent, you already use OTLP for traces and want one export pipeline, or you may later want to fan out the same telemetry to other backends (Grafana, Honeycomb, etc.) without changing your application setup.
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
Either path lands the same structured facets in Datadog (`@automation_id`, `@kickoff_id`, `@execution_id`, `@automation_name`, `@crewai_version`, `@exception.type`, `@gen_ai.*`), so the dashboard works identically with either choice.
|
||||
|
||||
## Log schema reference
|
||||
|
||||
<Info>
|
||||
This schema applies to the **Datadog Agent path** — stdout JSON logs produced when `CREWAI_LOG_FORMAT=json` is set. Logs delivered via the **Datadog OTLP intake** use OpenTelemetry attribute names and may differ; see [OpenTelemetry Export](./capture_telemetry_logs).
|
||||
</Info>
|
||||
|
||||
When `CREWAI_LOG_FORMAT=json` is set, every log event is emitted as a **single JSON object per line** to stdout, with internal newlines escaped. The format is plain JSON — Datadog parses it natively, and the same payload is also consumable by Splunk, Loki, Elasticsearch, and CloudWatch without custom log pipelines.
|
||||
|
||||
### Why JSON output
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="Lower ingestion cost" icon="dollar-sign">
|
||||
Most managed log backends bill per event. A Python traceback in text format is counted as one event per line — 30+ events for a single error. JSON output collapses each traceback into a single event with the stack trace as an escaped string field.
|
||||
</Card>
|
||||
<Card title="Structured search" icon="magnifying-glass">
|
||||
Search by `@automation_id`, `@exception.type`, `@kickoff_id` instead of grepping free-text. Build dashboards on typed facets without parser configuration.
|
||||
</Card>
|
||||
<Card title="APM ↔ logs correlation" icon="link">
|
||||
Every event carries `trace_id` and `span_id` when fired inside a recording span, so backends auto-link logs to traces.
|
||||
</Card>
|
||||
<Card title="Stable contract" icon="file-shield">
|
||||
The `schema` field gates compatibility — within `v1`, fields are added but never renamed or removed.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
### Enabling JSON output
|
||||
|
||||
`CREWAI_LOG_FORMAT=json` must be set as an **automation environment variable** in CrewAI AMP — it is **not** a container, host, or Docker setting. Open your automation in AMP, click the **Settings** icon, and add the variable under the **Environment Variables** section. AMP applies the value to every container in the deployment (API + workers) on the next restart. See [Update Your Crew](./update-crew) for the full UI walkthrough with screenshots.
|
||||
|
||||
```shell
|
||||
CREWAI_LOG_FORMAT=json
|
||||
```
|
||||
|
||||
Restart the deployment to pick up the change. Every log line on stdout from that point on is a single JSON object.
|
||||
|
||||
<Note>
|
||||
The default value is `text`, which preserves the legacy human-readable line format byte-for-byte. Setting any value other than `json` falls back to text mode. There is no migration step — the variable is read at process start and the format switches immediately.
|
||||
</Note>
|
||||
|
||||
### Example events
|
||||
|
||||
A single info-level log inside an active automation kickoff:
|
||||
|
||||
```json
|
||||
{
|
||||
"schema": "v1",
|
||||
"ts": "2026-06-17T16:14:23.482914Z",
|
||||
"level": "INFO",
|
||||
"logger": "crewai_enterprise.utilities.pii_redaction",
|
||||
"crewai_version": "1.14.7",
|
||||
"msg": "PII tracking state reset (engines preserved)",
|
||||
"automation_id": "12",
|
||||
"task_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"kickoff_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"execution_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"automation_name": "research_flow"
|
||||
}
|
||||
```
|
||||
|
||||
An error with a Python exception is collapsed into a single event with the traceback as a string:
|
||||
|
||||
```json
|
||||
{
|
||||
"schema": "v1",
|
||||
"ts": "2026-06-17T16:14:31.218450Z",
|
||||
"level": "ERROR",
|
||||
"logger": "api.tasks.flow_run_task",
|
||||
"crewai_version": "1.14.7",
|
||||
"msg": "Flow execution failed",
|
||||
"automation_id": "12",
|
||||
"kickoff_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"execution_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"automation_name": "research_flow",
|
||||
"exception": {
|
||||
"type": "ValueError",
|
||||
"message": "Topic cannot be empty",
|
||||
"stacktrace": "Traceback (most recent call last):\n File \"/app/flow.py\", line 42, in summarize\n ...\nValueError: Topic cannot be empty\n"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The same error in legacy text mode would have produced ~25 separate log events (one per traceback line) — all of which the backend would bill and index individually.
|
||||
|
||||
### Schema v1 fields
|
||||
|
||||
Within the `v1` schema, fields are only added, never renamed or removed. New fields will appear as soon as a deployment is upgraded.
|
||||
|
||||
| Field | Type | Always present | Source |
|
||||
|-------|------|----------------|--------|
|
||||
| `schema` | string | Yes | Constant `"v1"`. Increment indicates a breaking schema change. |
|
||||
| `ts` | string (ISO-8601 UTC, microseconds) | Yes | Record creation time, e.g. `2026-06-17T16:14:23.482914Z`. |
|
||||
| `level` | string | Yes | Python log level name: `DEBUG` / `INFO` / `WARNING` / `ERROR` / `CRITICAL`. |
|
||||
| `logger` | string | Yes | Dotted logger name, e.g. `api.tasks.flow_run_task`. |
|
||||
| `crewai_version` | string | Yes (when `crewai` package metadata is resolvable) | Installed `crewai` package version, e.g. `"1.14.7"`. |
|
||||
| `msg` | string | Yes | Rendered log message (after `%`-formatting / `{}`-formatting). |
|
||||
| `automation_id` | string | When `CREWAI_PLUS_ID` env var is set | Numeric deployment ID (AMP provisions this on every container). |
|
||||
| `task_id` | string | On Celery worker logs | Celery task UUID, or `"no-task"` for non-task contexts. |
|
||||
| `kickoff_id` | string | Inside an automation kickoff | UUID of the current kickoff. |
|
||||
| `execution_id` | string | Inside an automation kickoff | UUID of the current sub-execution. Equal to `kickoff_id` at the top level; differs for nested flow methods that spawn sub-executions. |
|
||||
| `automation_name` | string | Inside an automation kickoff | Human-readable automation/flow name, e.g. `"research_flow"`. |
|
||||
| `trace_id` | string (32-hex) | Inside a recording OpenTelemetry span | Hex trace ID. Omitted when no span is active. |
|
||||
| `span_id` | string (16-hex) | Inside a recording OpenTelemetry span | Hex span ID. Omitted when no span is active. |
|
||||
| `exception` | object | When the log record has `exc_info` | `{type, message, stacktrace}` — full traceback as a single escaped string. |
|
||||
|
||||
<Tip>
|
||||
Any additional `extra={...}` kwargs passed to a logger call appear as top-level JSON fields verbatim. Reserved field names above always win to keep the schema stable.
|
||||
</Tip>
|
||||
|
||||
### Stability promise
|
||||
|
||||
The `schema` field declares the contract. Within `v1`, CrewAI commits to:
|
||||
|
||||
- **Never removing a field** that customers may have built queries or dashboards against.
|
||||
- **Never renaming a field** in place — renames happen via a schema bump (e.g. `v2`), with the old name kept as a deprecated alias for at least one release cycle.
|
||||
- **Adding new fields** at any time. Consumers should ignore unknown top-level keys.
|
||||
|
||||
When a `v2` is introduced, both the `schema` field and the migration guide will be published in advance, and `v1` will continue to be emitted for one release cycle so dashboards and queries have time to migrate.
|
||||
|
||||
## Prerequisite: promote facets
|
||||
|
||||
Datadog auto-discovers fields the first time it sees them but doesn't make them queryable in widgets until they're promoted to **facets**. This is a one-time setup in your Datadog account.
|
||||
|
||||
<Steps>
|
||||
<Step title="Search for a CrewAI log">
|
||||
Open [Logs Explorer](https://app.datadoghq.com/logs) and search `service:crewai*`. You should see at least one log event.
|
||||
</Step>
|
||||
<Step title="Promote each field">
|
||||
Click any log entry to open the right-hand details panel. For each field below, hover the field name → click the gear icon → **Create facet**.
|
||||
|
||||
- `automation_id`, `automation_name`, `execution_id`, `kickoff_id`, `task_id`
|
||||
- `crewai_version`, `model_id`
|
||||
- `exception.type`, `exception.message`
|
||||
|
||||
Skip any field that already shows a star icon next to its name — that means it's already a facet. The `gen_ai.usage.input_tokens`, `gen_ai.usage.output_tokens`, and `gen_ai.request.model` facets are typically promoted automatically by Datadog's LLM Observability auto-discovery, but verify they exist before importing the dashboard.
|
||||
</Step>
|
||||
</Steps>
|
||||
|
||||
## Import the dashboard
|
||||
|
||||
<Steps>
|
||||
<Step title="Download the dashboard JSON">
|
||||
Save [`datadog_dashboard.json`](https://raw.githubusercontent.com/crewAIInc/crewAI/main/docs/edge/en/enterprise/guides/datadog_dashboard.json) to your machine.
|
||||
</Step>
|
||||
<Step title="Open the import dialog in Datadog">
|
||||
Navigate to **Dashboards → New Dashboard**. Click the **gear icon** in the top right of the empty dashboard and select **Import Dashboard JSON**.
|
||||
</Step>
|
||||
<Step title="Paste or upload the JSON">
|
||||
Paste the contents of `datadog_dashboard.json` into the import dialog (or drag the file in). Click **Import**.
|
||||
|
||||
Datadog creates the dashboard immediately and lands you on it. The first load may show empty widgets for a few seconds while queries execute against the time range.
|
||||
</Step>
|
||||
</Steps>
|
||||
|
||||
<Tip>
|
||||
Datadog's [Dashboard API](https://docs.datadoghq.com/api/latest/dashboards/#create-a-new-dashboard) accepts the same JSON via `POST /api/v1/dashboard`. Use it if you manage dashboards through Terraform, Pulumi, or CI.
|
||||
</Tip>
|
||||
|
||||
## What you get
|
||||
|
||||
The dashboard is organized into four sections plus a placeholder for a custom drill-down widget:
|
||||
|
||||
| Section | Widgets | Useful for |
|
||||
|---------|---------|------------|
|
||||
| **Header** | Total Executions · Error Rate (%) · Active Automations · CrewAI Versions in Use | At-a-glance health for the last hour. Error Rate is conditionally formatted (green ≤ 5%, yellow ≤ 10%, red > 10%). |
|
||||
| **Throughput** | Executions per Hour by Automation (top 10, stacked bars) | Spotting traffic shifts, surfacing busy automations, validating that a rollout didn't change baseline volume. |
|
||||
| **Errors** | Errors by Exception Type (top 5, stacked bars) · Top Exception Types by Count (toplist) | Triaging failures — which exception types are spiking, which automations they're hitting. |
|
||||
| **Cost** | Total Tokens per Hour by Model (input + output, stacked area) | Tracking LLM token spend by model. Useful for catching cost regressions when an automation switches model or starts looping. |
|
||||
| **Drill-Down** | _(empty placeholder)_ | See [Customization](#customize) for adding a recent-errors log stream here. |
|
||||
|
||||
Three template variables at the top of the dashboard re-scope every widget at once:
|
||||
|
||||
- **`$automation`** — filter to a single automation by name.
|
||||
- **`$version`** — filter to a single `crewai` SDK version (useful for comparing pre- and post-upgrade behavior).
|
||||
- **`$service`** — filter to a specific Datadog `service` tag (useful when multiple CrewAI deployments share one Datadog account).
|
||||
|
||||
## Verify ingestion
|
||||
|
||||
Open [Logs Explorer](https://app.datadoghq.com/logs) and run a query that matches your ingestion path:
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Datadog Agent">
|
||||
Search `service:crewai* @schema:v1`. You should see structured logs with the JSON fields parsed into Datadog facets. Pick a recent event and verify it has `@automation_id`, `@kickoff_id`, `@execution_id`, `@crewai_version`, and (when running inside a span) `@trace_id` / `@span_id` populated.
|
||||
|
||||
If nothing appears, confirm `CREWAI_LOG_FORMAT=json` is set under your automation's **Environment Variables** in AMP, the deployment was restarted after the change, and the Datadog Agent is tailing container stdout.
|
||||
</Tab>
|
||||
<Tab title="Datadog OTLP intake">
|
||||
Search `source:otlp service:crewai*`. OTLP attributes land with their OpenTelemetry names (`automation_id`, `crewai.kickoff.id`, etc.) rather than the stdout JSON keys, but they map to the same dashboard facets after [facet promotion](#prerequisite-promote-facets).
|
||||
|
||||
If nothing appears, verify the collector endpoint is correct (`/v1/logs` for logs, `/v1/traces` for traces) and **Test Connection** succeeded when the collector was saved.
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
## Customize
|
||||
|
||||
The dashboard ships with deliberate gaps so you can extend it without uninstalling and re-importing.
|
||||
|
||||
### Add a Recent Errors log stream
|
||||
|
||||
The **Drill-Down** section is intentionally empty. Add a Log Stream widget to it for an inline view of recent failures:
|
||||
|
||||
1. Edit the dashboard and click **+ Add Widgets** inside the Drill-Down group.
|
||||
2. Drag in a **Log Stream** widget.
|
||||
3. Set the filter query to `status:error $automation $version $service`.
|
||||
4. Choose columns: `@timestamp`, `@automation_name`, `@exception.type`, `@exception.message`, `@execution_id`.
|
||||
5. Sort by most recent, limit to 25 entries.
|
||||
|
||||
Clicking any row jumps to Logs Explorer with the same filter pre-applied.
|
||||
|
||||
### Add p95 latency
|
||||
|
||||
Logs don't include execution duration by default. Two ways to add a latency widget:
|
||||
|
||||
- **From APM traces** — if you also export OTLP traces to Datadog, add a Timeseries widget with data source **Traces**, query `service:crewai*`, aggregation `p95 of @duration`. Datadog APM auto-tracks span duration.
|
||||
- **From metric extraction** — extract a `flow.duration_ms` metric from logs via [Datadog's log-to-metric pipeline](https://docs.datadoghq.com/logs/log_configuration/logs_to_metrics/), then chart it like any other metric. Useful if you don't run APM.
|
||||
|
||||
### Re-scope to multiple deployments
|
||||
|
||||
The `$service` template variable defaults to `*` and will catch every CrewAI deployment in your Datadog account. Change the default to a specific service name in **Configure → Template Variables** if you want the dashboard to focus on one deployment by default.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
| Symptom | Likely cause | Fix |
|
||||
|---------|--------------|-----|
|
||||
| All widgets show "No data" | Facets aren't promoted | Re-do the [Promote facets](#prerequisite-promote-facets) step. Datadog won't query against an un-promoted field. |
|
||||
| Error Rate widget shows `NaN` | No executions in the time window | Either no traffic, or `@execution_id` isn't faceted. Expand the time range and re-check facets. |
|
||||
| Throughput chart is flat at the same value | Logs aren't reaching Datadog | Search `service:crewai*` in Logs Explorer. If nothing shows, verify the Datadog Agent is running (Agent path) or the OTel collector endpoint is correct (OTLP path). |
|
||||
| `crewai_version` shows fewer values than expected | Some containers predate the structured-logs work | The `crewai_version` field was added alongside JSON output. Older deployments running text mode (or older AMP builds) won't emit it. Upgrade those deployments to pick up the field. See the [log schema reference](#log-schema-reference) for the full field contract. |
|
||||
| Template variables don't filter widgets | The widget's filter line doesn't reference the template variable | Edit the widget and confirm the search includes `$automation $version $service`. |
|
||||
|
||||
## Next steps
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="OpenTelemetry Export" icon="magnifying-glass-chart" href="./capture_telemetry_logs">
|
||||
Vendor-neutral observability for non-Datadog stacks (Grafana, Honeycomb, your own collector) — or as a Datadog complement when you want to fan out telemetry to multiple backends.
|
||||
</Card>
|
||||
<Card title="Datadog Log Search Syntax" icon="magnifying-glass" href="https://docs.datadoghq.com/logs/explorer/search_syntax/">
|
||||
Reference for customizing widget queries against the structured facets above.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
@@ -4,86 +4,6 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
|
||||
icon: "clock"
|
||||
mode: "wide"
|
||||
---
|
||||
<Update label="18 jun 2026">
|
||||
## v1.14.8a2
|
||||
|
||||
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a2)
|
||||
|
||||
## O que Mudou
|
||||
|
||||
### Funcionalidades
|
||||
- Adicionar ação de agente único às definições de Fluxo
|
||||
- Validar expressões CEL de fluxo no momento do carregamento da definição
|
||||
|
||||
### Documentação
|
||||
- Adicionar guia de integração do Datadog com painel de operações importável
|
||||
- Atualizar snapshot e changelog para v1.14.8a1
|
||||
|
||||
## Contributors
|
||||
|
||||
@joaomdmoura, @lucasgomide, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="18 jun 2026">
|
||||
## v1.14.8a1
|
||||
|
||||
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a1)
|
||||
|
||||
## O que Mudou
|
||||
|
||||
### Recursos
|
||||
- Adicionar expressão if opcional aos passos each.do
|
||||
|
||||
### Correções de Bugs
|
||||
- Corrigir problemas de JSON da equipe
|
||||
|
||||
### Documentação
|
||||
- Atualizar snapshot e changelog para v1.14.8a
|
||||
|
||||
## Contribuidores
|
||||
|
||||
@joaomdmoura, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="17 jun 2026">
|
||||
## v1.14.8a
|
||||
|
||||
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.8a)
|
||||
|
||||
## O que Mudou
|
||||
|
||||
### Recursos
|
||||
- Adicionar ação de bloco de script/código ao FlowDefinition
|
||||
- Adicionar ações de equipe ao FlowDefinition
|
||||
- Adicionar ação composta `each` ao FlowDefinition
|
||||
- Implementar suporte ao modo DMN na criação e execução de equipes
|
||||
- Melhorar a funcionalidade de redefinição de memória e o manuseio de equipes em JSON
|
||||
- Adicionar expressões às ações do FlowDefinition
|
||||
- Implementar ferramentas de execução de definição de fluxo sem código Python
|
||||
- Conduzir feedback humano a partir da definição de fluxo
|
||||
- Conectar configuração e persistência do FlowDefinition ao tempo de execução
|
||||
- Adicionar `crewai run --definition` experimental para fluxos
|
||||
- Suportar fallback de implantação ZIP e execuções de projeto de equipe em JSON
|
||||
- Introduzir equipes em JSON primeiro
|
||||
|
||||
### Correções de Bugs
|
||||
- Corrigir ferramenta Exa duplicada
|
||||
- Corrigir uso de token agregado em todas as chamadas LLM
|
||||
- Resolver problemas com o carregamento de equipes e lógica de validação
|
||||
|
||||
### Documentação
|
||||
- Documentar campos do FlowDefinition no esquema JSON
|
||||
- Atualizar documentação de instalação e início rápido para projetos de equipe em JSON-primeiro
|
||||
- Atualizar changelog e versão para v1.14.7
|
||||
|
||||
## Contribuidores
|
||||
|
||||
@gabemilani, @greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay, @lucasgomide, @theCyberTech, @vinibrsl
|
||||
|
||||
</Update>
|
||||
|
||||
<Update label="11 jun 2026">
|
||||
## v1.14.7
|
||||
|
||||
|
||||
@@ -9,10 +9,6 @@ O CrewAI AMP pode exportar **traces** e **logs** do OpenTelemetry das suas impla
|
||||
|
||||
Os dados de telemetria seguem as [convenções semânticas GenAI do OpenTelemetry](https://opentelemetry.io/docs/specs/semconv/gen-ai/) além de atributos adicionais específicos do CrewAI.
|
||||
|
||||
<Tip>
|
||||
OpenTelemetry é o **caminho de observabilidade recomendado** — neutro em relação a fornecedores, funciona com qualquer backend compatível com OTLP (Grafana, Honeycomb, NewRelic, seu próprio coletor). Se você usa especificamente o Datadog, veja o guia dedicado [Integração com Datadog](./datadog), que cobre tanto o caminho do Datadog Agent quanto o ingest OTLP do Datadog.
|
||||
</Tip>
|
||||
|
||||
## Pré-requisitos
|
||||
|
||||
<CardGroup cols={2}>
|
||||
@@ -45,7 +41,17 @@ OpenTelemetry é o **caminho de observabilidade recomendado** — neutro em rela
|
||||
<Frame></Frame>
|
||||
</Tab>
|
||||
<Tab title="Datadog">
|
||||
Para configurar o Datadog, veja o guia dedicado [Integração com Datadog](./datadog) — ele cobre tanto o caminho do Datadog Agent (recomendado, mais barato para volumes altos de log) quanto o ingest OTLP do Datadog, com os passos completos de configuração do coletor.
|
||||
- **Datadog Site Domain** — Apenas o host OTLP do seu site Datadog, sem protocolo ou caminho. O CrewAI monta o endpoint HTTPS OTLP completo para você. Use o host correspondente ao seu [site Datadog](https://docs.datadoghq.com/getting_started/site/):
|
||||
- `otlp.datadoghq.com` (US1)
|
||||
- `otlp.us3.datadoghq.com` (US3)
|
||||
- `otlp.us5.datadoghq.com` (US5)
|
||||
- `otlp.datadoghq.eu` (EU1)
|
||||
- `otlp.ap1.datadoghq.com` (AP1)
|
||||
- **API Key** — Sua chave de API do Datadog. Veja [como criar uma](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
|
||||
|
||||
A integração com o Datadog exporta **traces**.
|
||||
|
||||
<Frame></Frame>
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
|
||||
@@ -1,295 +0,0 @@
|
||||
---
|
||||
title: "Integração com Datadog"
|
||||
description: "Monitore implantações CrewAI AMP auto-hospedadas no Datadog via Datadog Agent ou ingest OTLP do Datadog — ambos os caminhos entregam as mesmas facetas estruturadas para importar o dashboard de operações pronto."
|
||||
icon: "dog"
|
||||
mode: "wide"
|
||||
---
|
||||
|
||||
<Note>
|
||||
**Tradução em andamento** — conteúdo exibido em inglês.
|
||||
</Note>
|
||||
|
||||
CrewAI ships first-class support for Datadog: two log-ingestion paths, a JSON log schema designed for cheap indexing, and a ready-made operations dashboard you can import in under five minutes.
|
||||
|
||||
<Note>
|
||||
For vendor-neutral observability via any OTLP backend (Grafana, Honeycomb, your own collector), see [OpenTelemetry Export](./capture_telemetry_logs).
|
||||
</Note>
|
||||
|
||||
## Choose a path
|
||||
|
||||
CrewAI supports two log-ingestion paths to Datadog — both are first-class and produce the same structured facets that power the dashboard. Pick the one that fits your infrastructure.
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Datadog Agent">
|
||||
The Datadog Agent runs alongside your CrewAI containers (typically as a DaemonSet on Kubernetes) and tails their stdout. With `CREWAI_LOG_FORMAT=json` set, each log event ships as a single billable line with structured attributes.
|
||||
|
||||
**Setup:**
|
||||
1. Run the Datadog Agent next to your CrewAI containers — see [Datadog's deployment docs](https://docs.datadoghq.com/agent/) for Kubernetes, ECS, or VM setup. Enable log collection (`logs_enabled: true`) and container log collection (`logs_config.container_collect_all: true`).
|
||||
2. Set `CREWAI_LOG_FORMAT=json` as an **automation environment variable** in CrewAI AMP (open your automation → **Settings → Environment Variables**) so each log event is a single line instead of a multi-line traceback. AMP propagates the value to every container in the deployment (API + workers) — don't set it on the container or host directly. See [Enabling JSON output](#enabling-json-output) below for the AMP UI walkthrough and the [log schema reference](#log-schema-reference) for the full field contract.
|
||||
3. Confirm logs arrive in Datadog Logs with the JSON fields parsed — see [Verify ingestion](#verify-ingestion).
|
||||
|
||||
**Pick this path if** you already operate Datadog Agents (e.g. for infrastructure metrics), or your log volume makes per-event ingestion cost a real concern — collapsing tracebacks into single events keeps Agent ingestion cheap at scale.
|
||||
</Tab>
|
||||
<Tab title="Datadog OTLP intake">
|
||||
CrewAI AMP exports OpenTelemetry traffic directly to Datadog's OTLP endpoint with no Agent required. Logs and traces ride a single export pipeline configured in AMP's UI, using the same protocol you'd use for any other OTLP backend.
|
||||
|
||||
**Setup:**
|
||||
1. In CrewAI AMP, go to **Settings → OpenTelemetry Collectors → Add Collector** and pick **Datadog**.
|
||||
2. Configure the connection:
|
||||
- **Datadog Site Domain** — your Datadog site's OTLP host only, no protocol or path. CrewAI builds the full HTTPS OTLP endpoint for you. Use the host that matches your [Datadog site](https://docs.datadoghq.com/getting_started/site/):
|
||||
- `otlp.datadoghq.com` (US1)
|
||||
- `otlp.us3.datadoghq.com` (US3)
|
||||
- `otlp.us5.datadoghq.com` (US5)
|
||||
- `otlp.datadoghq.eu` (EU1)
|
||||
- `otlp.ap1.datadoghq.com` (AP1)
|
||||
- **API Key** — your Datadog API key. See [how to create one](https://docs.datadoghq.com/account_management/api-app-keys/#api-keys).
|
||||
3. The Datadog template provisions **both signals at once** — when you save, AMP creates a traces collector at `/v1/traces` and a logs collector at `/v1/logs`, both sharing the same Datadog OTLP host and API key. You'll see them as two separate rows in your OTel collectors list.
|
||||
4. *(optional)* Click **Test Connection** to verify CrewAI can reach the endpoint with the credentials you provided. Then click **Save** — both collectors are created in one step.
|
||||
|
||||
<Frame></Frame>
|
||||
|
||||
**Pick this path if** you'd rather not operate a Datadog Agent, you already use OTLP for traces and want one export pipeline, or you may later want to fan out the same telemetry to other backends (Grafana, Honeycomb, etc.) without changing your application setup.
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
Either path lands the same structured facets in Datadog (`@automation_id`, `@kickoff_id`, `@execution_id`, `@automation_name`, `@crewai_version`, `@exception.type`, `@gen_ai.*`), so the dashboard works identically with either choice.
|
||||
|
||||
## Log schema reference
|
||||
|
||||
<Info>
|
||||
This schema applies to the **Datadog Agent path** — stdout JSON logs produced when `CREWAI_LOG_FORMAT=json` is set. Logs delivered via the **Datadog OTLP intake** use OpenTelemetry attribute names and may differ; see [OpenTelemetry Export](./capture_telemetry_logs).
|
||||
</Info>
|
||||
|
||||
When `CREWAI_LOG_FORMAT=json` is set, every log event is emitted as a **single JSON object per line** to stdout, with internal newlines escaped. The format is plain JSON — Datadog parses it natively, and the same payload is also consumable by Splunk, Loki, Elasticsearch, and CloudWatch without custom log pipelines.
|
||||
|
||||
### Why JSON output
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="Lower ingestion cost" icon="dollar-sign">
|
||||
Most managed log backends bill per event. A Python traceback in text format is counted as one event per line — 30+ events for a single error. JSON output collapses each traceback into a single event with the stack trace as an escaped string field.
|
||||
</Card>
|
||||
<Card title="Structured search" icon="magnifying-glass">
|
||||
Search by `@automation_id`, `@exception.type`, `@kickoff_id` instead of grepping free-text. Build dashboards on typed facets without parser configuration.
|
||||
</Card>
|
||||
<Card title="APM ↔ logs correlation" icon="link">
|
||||
Every event carries `trace_id` and `span_id` when fired inside a recording span, so backends auto-link logs to traces.
|
||||
</Card>
|
||||
<Card title="Stable contract" icon="file-shield">
|
||||
The `schema` field gates compatibility — within `v1`, fields are added but never renamed or removed.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
### Enabling JSON output
|
||||
|
||||
`CREWAI_LOG_FORMAT=json` must be set as an **automation environment variable** in CrewAI AMP — it is **not** a container, host, or Docker setting. Open your automation in AMP, click the **Settings** icon, and add the variable under the **Environment Variables** section. AMP applies the value to every container in the deployment (API + workers) on the next restart. See [Update Your Crew](./update-crew) for the full UI walkthrough with screenshots.
|
||||
|
||||
```shell
|
||||
CREWAI_LOG_FORMAT=json
|
||||
```
|
||||
|
||||
Restart the deployment to pick up the change. Every log line on stdout from that point on is a single JSON object.
|
||||
|
||||
<Note>
|
||||
The default value is `text`, which preserves the legacy human-readable line format byte-for-byte. Setting any value other than `json` falls back to text mode. There is no migration step — the variable is read at process start and the format switches immediately.
|
||||
</Note>
|
||||
|
||||
### Example events
|
||||
|
||||
A single info-level log inside an active automation kickoff:
|
||||
|
||||
```json
|
||||
{
|
||||
"schema": "v1",
|
||||
"ts": "2026-06-17T16:14:23.482914Z",
|
||||
"level": "INFO",
|
||||
"logger": "crewai_enterprise.utilities.pii_redaction",
|
||||
"crewai_version": "1.14.7",
|
||||
"msg": "PII tracking state reset (engines preserved)",
|
||||
"automation_id": "12",
|
||||
"task_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"kickoff_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"execution_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"automation_name": "research_flow"
|
||||
}
|
||||
```
|
||||
|
||||
An error with a Python exception is collapsed into a single event with the traceback as a string:
|
||||
|
||||
```json
|
||||
{
|
||||
"schema": "v1",
|
||||
"ts": "2026-06-17T16:14:31.218450Z",
|
||||
"level": "ERROR",
|
||||
"logger": "api.tasks.flow_run_task",
|
||||
"crewai_version": "1.14.7",
|
||||
"msg": "Flow execution failed",
|
||||
"automation_id": "12",
|
||||
"kickoff_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"execution_id": "0843a930-b306-464b-89c8-bfafa78cc711",
|
||||
"automation_name": "research_flow",
|
||||
"exception": {
|
||||
"type": "ValueError",
|
||||
"message": "Topic cannot be empty",
|
||||
"stacktrace": "Traceback (most recent call last):\n File \"/app/flow.py\", line 42, in summarize\n ...\nValueError: Topic cannot be empty\n"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The same error in legacy text mode would have produced ~25 separate log events (one per traceback line) — all of which the backend would bill and index individually.
|
||||
|
||||
### Schema v1 fields
|
||||
|
||||
Within the `v1` schema, fields are only added, never renamed or removed. New fields will appear as soon as a deployment is upgraded.
|
||||
|
||||
| Field | Type | Always present | Source |
|
||||
|-------|------|----------------|--------|
|
||||
| `schema` | string | Yes | Constant `"v1"`. Increment indicates a breaking schema change. |
|
||||
| `ts` | string (ISO-8601 UTC, microseconds) | Yes | Record creation time, e.g. `2026-06-17T16:14:23.482914Z`. |
|
||||
| `level` | string | Yes | Python log level name: `DEBUG` / `INFO` / `WARNING` / `ERROR` / `CRITICAL`. |
|
||||
| `logger` | string | Yes | Dotted logger name, e.g. `api.tasks.flow_run_task`. |
|
||||
| `crewai_version` | string | Yes (when `crewai` package metadata is resolvable) | Installed `crewai` package version, e.g. `"1.14.7"`. |
|
||||
| `msg` | string | Yes | Rendered log message (after `%`-formatting / `{}`-formatting). |
|
||||
| `automation_id` | string | When `CREWAI_PLUS_ID` env var is set | Numeric deployment ID (AMP provisions this on every container). |
|
||||
| `task_id` | string | On Celery worker logs | Celery task UUID, or `"no-task"` for non-task contexts. |
|
||||
| `kickoff_id` | string | Inside an automation kickoff | UUID of the current kickoff. |
|
||||
| `execution_id` | string | Inside an automation kickoff | UUID of the current sub-execution. Equal to `kickoff_id` at the top level; differs for nested flow methods that spawn sub-executions. |
|
||||
| `automation_name` | string | Inside an automation kickoff | Human-readable automation/flow name, e.g. `"research_flow"`. |
|
||||
| `trace_id` | string (32-hex) | Inside a recording OpenTelemetry span | Hex trace ID. Omitted when no span is active. |
|
||||
| `span_id` | string (16-hex) | Inside a recording OpenTelemetry span | Hex span ID. Omitted when no span is active. |
|
||||
| `exception` | object | When the log record has `exc_info` | `{type, message, stacktrace}` — full traceback as a single escaped string. |
|
||||
|
||||
<Tip>
|
||||
Any additional `extra={...}` kwargs passed to a logger call appear as top-level JSON fields verbatim. Reserved field names above always win to keep the schema stable.
|
||||
</Tip>
|
||||
|
||||
### Stability promise
|
||||
|
||||
The `schema` field declares the contract. Within `v1`, CrewAI commits to:
|
||||
|
||||
- **Never removing a field** that customers may have built queries or dashboards against.
|
||||
- **Never renaming a field** in place — renames happen via a schema bump (e.g. `v2`), with the old name kept as a deprecated alias for at least one release cycle.
|
||||
- **Adding new fields** at any time. Consumers should ignore unknown top-level keys.
|
||||
|
||||
When a `v2` is introduced, both the `schema` field and the migration guide will be published in advance, and `v1` will continue to be emitted for one release cycle so dashboards and queries have time to migrate.
|
||||
|
||||
## Prerequisite: promote facets
|
||||
|
||||
Datadog auto-discovers fields the first time it sees them but doesn't make them queryable in widgets until they're promoted to **facets**. This is a one-time setup in your Datadog account.
|
||||
|
||||
<Steps>
|
||||
<Step title="Search for a CrewAI log">
|
||||
Open [Logs Explorer](https://app.datadoghq.com/logs) and search `service:crewai*`. You should see at least one log event.
|
||||
</Step>
|
||||
<Step title="Promote each field">
|
||||
Click any log entry to open the right-hand details panel. For each field below, hover the field name → click the gear icon → **Create facet**.
|
||||
|
||||
- `automation_id`, `automation_name`, `execution_id`, `kickoff_id`, `task_id`
|
||||
- `crewai_version`, `model_id`
|
||||
- `exception.type`, `exception.message`
|
||||
|
||||
Skip any field that already shows a star icon next to its name — that means it's already a facet. The `gen_ai.usage.input_tokens`, `gen_ai.usage.output_tokens`, and `gen_ai.request.model` facets are typically promoted automatically by Datadog's LLM Observability auto-discovery, but verify they exist before importing the dashboard.
|
||||
</Step>
|
||||
</Steps>
|
||||
|
||||
## Import the dashboard
|
||||
|
||||
<Steps>
|
||||
<Step title="Download the dashboard JSON">
|
||||
Save [`datadog_dashboard.json`](https://raw.githubusercontent.com/crewAIInc/crewAI/main/docs/edge/en/enterprise/guides/datadog_dashboard.json) to your machine.
|
||||
</Step>
|
||||
<Step title="Open the import dialog in Datadog">
|
||||
Navigate to **Dashboards → New Dashboard**. Click the **gear icon** in the top right of the empty dashboard and select **Import Dashboard JSON**.
|
||||
</Step>
|
||||
<Step title="Paste or upload the JSON">
|
||||
Paste the contents of `datadog_dashboard.json` into the import dialog (or drag the file in). Click **Import**.
|
||||
|
||||
Datadog creates the dashboard immediately and lands you on it. The first load may show empty widgets for a few seconds while queries execute against the time range.
|
||||
</Step>
|
||||
</Steps>
|
||||
|
||||
<Tip>
|
||||
Datadog's [Dashboard API](https://docs.datadoghq.com/api/latest/dashboards/#create-a-new-dashboard) accepts the same JSON via `POST /api/v1/dashboard`. Use it if you manage dashboards through Terraform, Pulumi, or CI.
|
||||
</Tip>
|
||||
|
||||
## What you get
|
||||
|
||||
The dashboard is organized into four sections plus a placeholder for a custom drill-down widget:
|
||||
|
||||
| Section | Widgets | Useful for |
|
||||
|---------|---------|------------|
|
||||
| **Header** | Total Executions · Error Rate (%) · Active Automations · CrewAI Versions in Use | At-a-glance health for the last hour. Error Rate is conditionally formatted (green ≤ 5%, yellow ≤ 10%, red > 10%). |
|
||||
| **Throughput** | Executions per Hour by Automation (top 10, stacked bars) | Spotting traffic shifts, surfacing busy automations, validating that a rollout didn't change baseline volume. |
|
||||
| **Errors** | Errors by Exception Type (top 5, stacked bars) · Top Exception Types by Count (toplist) | Triaging failures — which exception types are spiking, which automations they're hitting. |
|
||||
| **Cost** | Total Tokens per Hour by Model (input + output, stacked area) | Tracking LLM token spend by model. Useful for catching cost regressions when an automation switches model or starts looping. |
|
||||
| **Drill-Down** | _(empty placeholder)_ | See [Customization](#customize) for adding a recent-errors log stream here. |
|
||||
|
||||
Three template variables at the top of the dashboard re-scope every widget at once:
|
||||
|
||||
- **`$automation`** — filter to a single automation by name.
|
||||
- **`$version`** — filter to a single `crewai` SDK version (useful for comparing pre- and post-upgrade behavior).
|
||||
- **`$service`** — filter to a specific Datadog `service` tag (useful when multiple CrewAI deployments share one Datadog account).
|
||||
|
||||
## Verify ingestion
|
||||
|
||||
Open [Logs Explorer](https://app.datadoghq.com/logs) and run a query that matches your ingestion path:
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Datadog Agent">
|
||||
Search `service:crewai* @schema:v1`. You should see structured logs with the JSON fields parsed into Datadog facets. Pick a recent event and verify it has `@automation_id`, `@kickoff_id`, `@execution_id`, `@crewai_version`, and (when running inside a span) `@trace_id` / `@span_id` populated.
|
||||
|
||||
If nothing appears, confirm `CREWAI_LOG_FORMAT=json` is set under your automation's **Environment Variables** in AMP, the deployment was restarted after the change, and the Datadog Agent is tailing container stdout.
|
||||
</Tab>
|
||||
<Tab title="Datadog OTLP intake">
|
||||
Search `source:otlp service:crewai*`. OTLP attributes land with their OpenTelemetry names (`automation_id`, `crewai.kickoff.id`, etc.) rather than the stdout JSON keys, but they map to the same dashboard facets after [facet promotion](#prerequisite-promote-facets).
|
||||
|
||||
If nothing appears, verify the collector endpoint is correct (`/v1/logs` for logs, `/v1/traces` for traces) and **Test Connection** succeeded when the collector was saved.
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
## Customize
|
||||
|
||||
The dashboard ships with deliberate gaps so you can extend it without uninstalling and re-importing.
|
||||
|
||||
### Add a Recent Errors log stream
|
||||
|
||||
The **Drill-Down** section is intentionally empty. Add a Log Stream widget to it for an inline view of recent failures:
|
||||
|
||||
1. Edit the dashboard and click **+ Add Widgets** inside the Drill-Down group.
|
||||
2. Drag in a **Log Stream** widget.
|
||||
3. Set the filter query to `status:error $automation $version $service`.
|
||||
4. Choose columns: `@timestamp`, `@automation_name`, `@exception.type`, `@exception.message`, `@execution_id`.
|
||||
5. Sort by most recent, limit to 25 entries.
|
||||
|
||||
Clicking any row jumps to Logs Explorer with the same filter pre-applied.
|
||||
|
||||
### Add p95 latency
|
||||
|
||||
Logs don't include execution duration by default. Two ways to add a latency widget:
|
||||
|
||||
- **From APM traces** — if you also export OTLP traces to Datadog, add a Timeseries widget with data source **Traces**, query `service:crewai*`, aggregation `p95 of @duration`. Datadog APM auto-tracks span duration.
|
||||
- **From metric extraction** — extract a `flow.duration_ms` metric from logs via [Datadog's log-to-metric pipeline](https://docs.datadoghq.com/logs/log_configuration/logs_to_metrics/), then chart it like any other metric. Useful if you don't run APM.
|
||||
|
||||
### Re-scope to multiple deployments
|
||||
|
||||
The `$service` template variable defaults to `*` and will catch every CrewAI deployment in your Datadog account. Change the default to a specific service name in **Configure → Template Variables** if you want the dashboard to focus on one deployment by default.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
| Symptom | Likely cause | Fix |
|
||||
|---------|--------------|-----|
|
||||
| All widgets show "No data" | Facets aren't promoted | Re-do the [Promote facets](#prerequisite-promote-facets) step. Datadog won't query against an un-promoted field. |
|
||||
| Error Rate widget shows `NaN` | No executions in the time window | Either no traffic, or `@execution_id` isn't faceted. Expand the time range and re-check facets. |
|
||||
| Throughput chart is flat at the same value | Logs aren't reaching Datadog | Search `service:crewai*` in Logs Explorer. If nothing shows, verify the Datadog Agent is running (Agent path) or the OTel collector endpoint is correct (OTLP path). |
|
||||
| `crewai_version` shows fewer values than expected | Some containers predate the structured-logs work | The `crewai_version` field was added alongside JSON output. Older deployments running text mode (or older AMP builds) won't emit it. Upgrade those deployments to pick up the field. See the [log schema reference](#log-schema-reference) for the full field contract. |
|
||||
| Template variables don't filter widgets | The widget's filter line doesn't reference the template variable | Edit the widget and confirm the search includes `$automation $version $service`. |
|
||||
|
||||
## Next steps
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="OpenTelemetry Export" icon="magnifying-glass-chart" href="./capture_telemetry_logs">
|
||||
Vendor-neutral observability for non-Datadog stacks (Grafana, Honeycomb, your own collector) — or as a Datadog complement when you want to fan out telemetry to multiple backends.
|
||||
</Card>
|
||||
<Card title="Datadog Log Search Syntax" icon="magnifying-glass" href="https://docs.datadoghq.com/logs/explorer/search_syntax/">
|
||||
Reference for customizing widget queries against the structured facets above.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
@@ -8,7 +8,7 @@ authors = [
|
||||
]
|
||||
requires-python = ">=3.10, <3.14"
|
||||
dependencies = [
|
||||
"crewai-core==1.14.8a2",
|
||||
"crewai-core==1.14.7",
|
||||
"click>=8.1.7,<9",
|
||||
"pydantic>=2.11.9,<2.13",
|
||||
"pydantic-settings~=2.10.1",
|
||||
|
||||
@@ -1 +1 @@
|
||||
__version__ = "1.14.8a2"
|
||||
__version__ = "1.14.7"
|
||||
|
||||
@@ -89,16 +89,13 @@ description = "{name} using crewAI"
|
||||
authors = [{{ name = "Your Name", email = "you@example.com" }}]
|
||||
requires-python = ">=3.10,<3.14"
|
||||
dependencies = [
|
||||
"crewai[tools]==1.14.8a1"
|
||||
"crewai[tools]>=1.14.7"
|
||||
]
|
||||
|
||||
[build-system]
|
||||
requires = ["hatchling"]
|
||||
build-backend = "hatchling.build"
|
||||
|
||||
[tool.hatch.build.targets.wheel]
|
||||
only-include = ["agents", "crew.jsonc", "tools", "knowledge", "skills"]
|
||||
|
||||
[tool.crewai]
|
||||
type = "crew"
|
||||
"""
|
||||
|
||||
@@ -34,25 +34,6 @@ _C_MUTED = "#666666" # dimmer than _C_DIM for past timeline
|
||||
_STEP_NUMBER_RE = re.compile(r"\bstep\s+(\d+)\b", re.IGNORECASE)
|
||||
_REFINEMENT_RE = re.compile(r"^\s*step\s+(\d+)\s*:\s*(.+)\s*$", re.IGNORECASE)
|
||||
_INTERNAL_TOOL_NAMES = {"create_reasoning_plan"}
|
||||
_LOG_ARGS_TEXT_LIMIT = 3_000
|
||||
_LOG_RESULT_TEXT_LIMIT = 5_000
|
||||
_LOG_TRUNCATION_SUFFIX = "... [truncated]"
|
||||
# Background memory saves can emit their start event just after kickoff returns.
|
||||
_MEMORY_SAVE_DRAIN_GRACE_SECONDS = 2.0
|
||||
|
||||
|
||||
def _is_save_to_memory_tool(tool_name: str | None) -> bool:
|
||||
return (tool_name or "").replace(" ", "_").lower() == "save_to_memory"
|
||||
|
||||
|
||||
def _truncate_log_text(value: Any, limit: int) -> str | None:
|
||||
if value is None:
|
||||
return None
|
||||
text = str(value)
|
||||
if len(text) <= limit:
|
||||
return text
|
||||
suffix = _LOG_TRUNCATION_SUFFIX
|
||||
return f"{text[: max(0, limit - len(suffix))]}{suffix}"
|
||||
|
||||
|
||||
def _enable_tracing_in_dotenv() -> None:
|
||||
@@ -538,8 +519,6 @@ FooterKey .footer-key--key {
|
||||
self._log_expanded: set[int] = set()
|
||||
self._log_scroll_needed: bool = False
|
||||
self._log_line_map: list[tuple[int, int, int]] = []
|
||||
self._suppressed_memory_save_event_ids: set[str] = set()
|
||||
self._memory_save_drain_timer: Any = None
|
||||
|
||||
self._event_handlers: list[tuple[type, Any]] = []
|
||||
|
||||
@@ -654,6 +633,7 @@ FooterKey .footer-key--key {
|
||||
self.call_from_thread(self._on_crew_failed, str(e))
|
||||
|
||||
def _on_crew_done(self, output: str | None) -> None:
|
||||
self._unsubscribe()
|
||||
with self._lock:
|
||||
self._status = "completed"
|
||||
self._final_output = output
|
||||
@@ -669,8 +649,6 @@ FooterKey .footer-key--key {
|
||||
now = time.time()
|
||||
for entry in self._log_entries:
|
||||
if entry["status"] == "running":
|
||||
if entry["tool_name"] == "memory_save":
|
||||
continue
|
||||
entry["status"] = "timeout"
|
||||
entry["error"] = "No result received before crew completed"
|
||||
entry["duration"] = now - entry["start_time"]
|
||||
@@ -702,9 +680,9 @@ FooterKey .footer-key--key {
|
||||
self.call_later(self._focus_activity_log)
|
||||
self._tick_timer.stop()
|
||||
self._tick_timer = self.set_interval(1 / 2, self._tick)
|
||||
self._unsubscribe_if_no_running_memory_save(wait_for_queued=True)
|
||||
|
||||
def _on_crew_failed(self, error: str) -> None:
|
||||
self._unsubscribe()
|
||||
with self._lock:
|
||||
self._status = "failed"
|
||||
self._error = error
|
||||
@@ -714,16 +692,12 @@ FooterKey .footer-key--key {
|
||||
now = time.time()
|
||||
for entry in self._log_entries:
|
||||
if entry["status"] == "running":
|
||||
if entry["tool_name"] == "memory_save":
|
||||
continue
|
||||
entry["status"] = "error"
|
||||
entry["error"] = "No result received before crew failed"
|
||||
entry["duration"] = now - entry["start_time"]
|
||||
self._tick()
|
||||
self.call_later(self._focus_activity_log)
|
||||
self._tick_timer.stop()
|
||||
self._tick_timer = self.set_interval(1 / 2, self._tick)
|
||||
self._unsubscribe_if_no_running_memory_save(wait_for_queued=True)
|
||||
|
||||
# ── Actions ─────────────────────────────────────────────
|
||||
|
||||
@@ -1540,53 +1514,6 @@ FooterKey .footer-key--key {
|
||||
pass
|
||||
self._event_handlers.clear()
|
||||
|
||||
def _has_running_memory_save_locked(self) -> bool:
|
||||
return any(
|
||||
entry["tool_name"] == "memory_save" and entry["status"] == "running"
|
||||
for entry in self._log_entries
|
||||
)
|
||||
|
||||
def _on_memory_save_drain_elapsed(self) -> None:
|
||||
self._memory_save_drain_timer = None
|
||||
self._unsubscribe_if_no_running_memory_save()
|
||||
|
||||
def _schedule_memory_save_drain_unsubscribe(self) -> bool:
|
||||
loop = getattr(self, "_loop", None)
|
||||
if loop is None:
|
||||
return False
|
||||
if getattr(self, "_thread_id", None) != threading.get_ident():
|
||||
try:
|
||||
loop.call_soon_threadsafe(self._schedule_memory_save_drain_unsubscribe)
|
||||
except RuntimeError:
|
||||
return False
|
||||
return True
|
||||
if self._memory_save_drain_timer is not None:
|
||||
self._memory_save_drain_timer.stop()
|
||||
self._memory_save_drain_timer = self.set_timer(
|
||||
_MEMORY_SAVE_DRAIN_GRACE_SECONDS,
|
||||
self._on_memory_save_drain_elapsed,
|
||||
name="memory-save-drain",
|
||||
)
|
||||
return True
|
||||
|
||||
def _unsubscribe_if_no_running_memory_save(
|
||||
self, *, wait_for_queued: bool = False
|
||||
) -> None:
|
||||
with self._lock:
|
||||
should_unsubscribe = (
|
||||
self._status
|
||||
in {
|
||||
"completed",
|
||||
"failed",
|
||||
}
|
||||
and not self._has_running_memory_save_locked()
|
||||
)
|
||||
|
||||
if should_unsubscribe:
|
||||
if wait_for_queued and self._schedule_memory_save_drain_unsubscribe():
|
||||
return
|
||||
self._unsubscribe()
|
||||
|
||||
def _subscribe(self) -> None:
|
||||
from crewai.events.event_bus import crewai_event_bus
|
||||
from crewai.events.types.crew_events import CrewKickoffStartedEvent
|
||||
@@ -1875,8 +1802,6 @@ FooterKey .footer-key--key {
|
||||
entry["status"] == "running"
|
||||
and entry["tool_name"] != event.tool_name
|
||||
):
|
||||
if entry["tool_name"] == "memory_save":
|
||||
continue
|
||||
entry["status"] = "timeout"
|
||||
entry["error"] = (
|
||||
"No result received before the next tool started"
|
||||
@@ -1905,7 +1830,6 @@ FooterKey .footer-key--key {
|
||||
"duration": None,
|
||||
"task_idx": self._current_task_idx,
|
||||
"plan_step_number": plan_step_number,
|
||||
"event_id": event.event_id,
|
||||
}
|
||||
)
|
||||
self._complete_step("teal", f"⚡ {event.tool_name}…")
|
||||
@@ -1999,178 +1923,8 @@ FooterKey .footer-key--key {
|
||||
MemoryRetrievalCompletedEvent,
|
||||
MemoryRetrievalFailedEvent,
|
||||
MemoryRetrievalStartedEvent,
|
||||
MemorySaveCompletedEvent,
|
||||
MemorySaveFailedEvent,
|
||||
MemorySaveStartedEvent,
|
||||
)
|
||||
|
||||
def is_nested_save_to_memory_event(event: Any) -> bool:
|
||||
if event.parent_event_id is None:
|
||||
return False
|
||||
state = crewai_event_bus.runtime_state
|
||||
if state is None:
|
||||
return False
|
||||
parent_node = state.event_record.nodes.get(event.parent_event_id)
|
||||
parent_event = getattr(parent_node, "event", None)
|
||||
return getattr(
|
||||
parent_event, "type", None
|
||||
) == "tool_usage_started" and _is_save_to_memory_tool(
|
||||
getattr(parent_event, "tool_name", None)
|
||||
)
|
||||
|
||||
@crewai_event_bus.on(MemorySaveStartedEvent)
|
||||
def on_memory_save_started(source: Any, event: MemorySaveStartedEvent) -> None:
|
||||
with self._lock:
|
||||
if is_nested_save_to_memory_event(event):
|
||||
self._suppressed_memory_save_event_ids.add(event.event_id)
|
||||
return
|
||||
for entry in reversed(self._log_entries):
|
||||
if (
|
||||
_is_save_to_memory_tool(entry["tool_name"])
|
||||
and entry.get("event_id") == event.parent_event_id
|
||||
):
|
||||
self._suppressed_memory_save_event_ids.add(event.event_id)
|
||||
return
|
||||
for entry in reversed(self._log_entries):
|
||||
if (
|
||||
entry["tool_name"] == "memory_save"
|
||||
and entry.get("started_event_id") == event.event_id
|
||||
):
|
||||
entry["args"] = _truncate_log_text(
|
||||
event.value, _LOG_ARGS_TEXT_LIMIT
|
||||
)
|
||||
return
|
||||
self._log_entries.append(
|
||||
{
|
||||
"tool_name": "memory_save",
|
||||
"status": "running",
|
||||
"args": _truncate_log_text(event.value, _LOG_ARGS_TEXT_LIMIT),
|
||||
"result": None,
|
||||
"error": None,
|
||||
"start_time": time.time(),
|
||||
"duration": None,
|
||||
"task_idx": self._current_task_idx,
|
||||
"event_id": event.event_id,
|
||||
}
|
||||
)
|
||||
|
||||
self._register_handler(MemorySaveStartedEvent, on_memory_save_started)
|
||||
|
||||
@crewai_event_bus.on(MemorySaveCompletedEvent)
|
||||
def on_memory_save_completed(
|
||||
source: Any, event: MemorySaveCompletedEvent
|
||||
) -> None:
|
||||
with self._lock:
|
||||
if (
|
||||
event.started_event_id in self._suppressed_memory_save_event_ids
|
||||
or is_nested_save_to_memory_event(event)
|
||||
):
|
||||
if event.started_event_id is not None:
|
||||
self._suppressed_memory_save_event_ids.discard(
|
||||
event.started_event_id
|
||||
)
|
||||
else:
|
||||
for entry in reversed(self._log_entries):
|
||||
has_started_event_match = (
|
||||
event.started_event_id is not None
|
||||
and (
|
||||
entry.get("event_id") == event.started_event_id
|
||||
or entry.get("started_event_id")
|
||||
== event.started_event_id
|
||||
)
|
||||
)
|
||||
has_running_event_without_id = (
|
||||
event.started_event_id is None
|
||||
and entry["status"] == "running"
|
||||
)
|
||||
if entry["tool_name"] == "memory_save" and (
|
||||
has_running_event_without_id or has_started_event_match
|
||||
):
|
||||
entry["status"] = "success"
|
||||
entry["duration"] = event.save_time_ms / 1000
|
||||
entry["result"] = _truncate_log_text(
|
||||
event.value, _LOG_RESULT_TEXT_LIMIT
|
||||
)
|
||||
entry["error"] = None
|
||||
entry["started_event_id"] = event.started_event_id
|
||||
break
|
||||
else:
|
||||
self._log_entries.append(
|
||||
{
|
||||
"tool_name": "memory_save",
|
||||
"status": "success",
|
||||
"args": None,
|
||||
"result": _truncate_log_text(
|
||||
event.value, _LOG_RESULT_TEXT_LIMIT
|
||||
),
|
||||
"error": None,
|
||||
"start_time": time.time(),
|
||||
"duration": event.save_time_ms / 1000,
|
||||
"task_idx": self._current_task_idx,
|
||||
"started_event_id": event.started_event_id,
|
||||
}
|
||||
)
|
||||
|
||||
self._unsubscribe_if_no_running_memory_save(wait_for_queued=True)
|
||||
|
||||
self._register_handler(MemorySaveCompletedEvent, on_memory_save_completed)
|
||||
|
||||
@crewai_event_bus.on(MemorySaveFailedEvent)
|
||||
def on_memory_save_failed(source: Any, event: MemorySaveFailedEvent) -> None:
|
||||
with self._lock:
|
||||
if (
|
||||
event.started_event_id in self._suppressed_memory_save_event_ids
|
||||
or is_nested_save_to_memory_event(event)
|
||||
):
|
||||
if event.started_event_id is not None:
|
||||
self._suppressed_memory_save_event_ids.discard(
|
||||
event.started_event_id
|
||||
)
|
||||
else:
|
||||
for idx, entry in reversed(list(enumerate(self._log_entries))):
|
||||
has_started_event_match = (
|
||||
event.started_event_id is not None
|
||||
and (
|
||||
entry.get("event_id") == event.started_event_id
|
||||
or entry.get("started_event_id")
|
||||
== event.started_event_id
|
||||
)
|
||||
)
|
||||
has_running_event_without_id = (
|
||||
event.started_event_id is None
|
||||
and entry["status"] == "running"
|
||||
)
|
||||
if entry["tool_name"] == "memory_save" and (
|
||||
has_running_event_without_id or has_started_event_match
|
||||
):
|
||||
entry["status"] = "error"
|
||||
entry["error"] = event.error
|
||||
entry["duration"] = time.time() - entry["start_time"]
|
||||
entry["started_event_id"] = event.started_event_id
|
||||
self._log_expanded.add(idx)
|
||||
break
|
||||
else:
|
||||
self._log_entries.append(
|
||||
{
|
||||
"tool_name": "memory_save",
|
||||
"status": "error",
|
||||
"args": _truncate_log_text(
|
||||
event.value, _LOG_ARGS_TEXT_LIMIT
|
||||
),
|
||||
"result": None,
|
||||
"error": event.error,
|
||||
"start_time": time.time(),
|
||||
"duration": 0,
|
||||
"task_idx": self._current_task_idx,
|
||||
"started_event_id": event.started_event_id,
|
||||
}
|
||||
)
|
||||
self._log_expanded.add(len(self._log_entries) - 1)
|
||||
|
||||
self._unsubscribe_if_no_running_memory_save(wait_for_queued=True)
|
||||
|
||||
self._register_handler(MemorySaveFailedEvent, on_memory_save_failed)
|
||||
|
||||
@crewai_event_bus.on(MemoryRetrievalStartedEvent)
|
||||
def on_memory_retrieval_started(
|
||||
source: Any, event: MemoryRetrievalStartedEvent
|
||||
|
||||
@@ -378,40 +378,12 @@ class SkillCommand(BaseCommand, PlusAPIMixin):
|
||||
|
||||
|
||||
def _safe_extractall(tf: tarfile.TarFile, dest: Path) -> None:
|
||||
"""Path-traversal-safe extraction for Python < 3.12.
|
||||
|
||||
Validates both the member's own path and, for symlink/hardlink members,
|
||||
the link target. Without the link-target check a malicious archive can
|
||||
plant a symlink that escapes ``dest`` (e.g. ``link -> /home/user/.ssh``)
|
||||
followed by a regular member written *through* that link
|
||||
(``link/authorized_keys``), escaping ``dest`` even though every member
|
||||
name resolves inside it. This mirrors the protection that
|
||||
``tarfile.extractall(..., filter="data")`` provides on Python >= 3.12.
|
||||
"""
|
||||
"""Path-traversal-safe extraction for Python < 3.12."""
|
||||
dest_resolved = dest.resolve()
|
||||
for member in tf.getmembers():
|
||||
member_path = (dest / member.name).resolve()
|
||||
if not member_path.is_relative_to(dest_resolved):
|
||||
raise ValueError(f"Blocked path traversal attempt: {member.name!r}")
|
||||
if member.ischr() or member.isblk() or member.isfifo():
|
||||
raise ValueError(f"Blocked special file type in archive: {member.name!r}")
|
||||
if member.issym() or member.islnk():
|
||||
link_target = member.linkname
|
||||
# Absolute link targets always escape the destination.
|
||||
if os.path.isabs(link_target):
|
||||
raise ValueError(
|
||||
f"Blocked link target escaping destination: "
|
||||
f"{member.name!r} -> {link_target!r}"
|
||||
)
|
||||
# Hardlink names are relative to the archive root; symlink
|
||||
# targets are relative to the member's own directory.
|
||||
anchor = dest if member.islnk() else (dest / member.name).parent
|
||||
resolved_target = (anchor / link_target).resolve()
|
||||
if not resolved_target.is_relative_to(dest_resolved):
|
||||
raise ValueError(
|
||||
f"Blocked link target escaping destination: "
|
||||
f"{member.name!r} -> {link_target!r}"
|
||||
)
|
||||
tf.extractall(dest) # noqa: S202
|
||||
|
||||
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Callable
|
||||
from contextlib import AbstractContextManager, nullcontext
|
||||
from enum import Enum
|
||||
import os
|
||||
@@ -8,9 +7,10 @@ from pathlib import Path
|
||||
import re
|
||||
import subprocess
|
||||
import sys
|
||||
from typing import TYPE_CHECKING, Any, cast
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
import click
|
||||
from crewai.project.json_loader import find_crew_json_file
|
||||
from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
|
||||
from packaging import version
|
||||
|
||||
@@ -38,15 +38,6 @@ class CrewType(Enum):
|
||||
_INPUT_PLACEHOLDER_RE = re.compile(r"(?<!{){([A-Za-z_][A-Za-z0-9_\-]*)}(?!})")
|
||||
_CREWAI_CLI_RUNNER_PACKAGE_DIR_ENV = "CREWAI_CLI_RUNNER_PACKAGE_DIR"
|
||||
_CREWAI_RUNNER_SOURCE_DIR_ENV = "CREWAI_RUNNER_SOURCE_DIR"
|
||||
_FULL_CREWAI_INSTALL_MESSAGE = """\
|
||||
CrewAI CLI is installed without the `crewai` package required to run crews.
|
||||
|
||||
Install the full CrewAI prerelease package:
|
||||
|
||||
uv tool install --force --prerelease=allow 'crewai[tools]==1.14.8a1'
|
||||
|
||||
The quotes are required in zsh so `crewai[tools]` is not treated as a glob.
|
||||
"""
|
||||
_JSON_CREW_RUNNER_CODE = """
|
||||
import importlib.util
|
||||
import os
|
||||
@@ -81,39 +72,12 @@ module_spec.loader.exec_module(module)
|
||||
|
||||
from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
|
||||
|
||||
try:
|
||||
module._run_json_crew(
|
||||
trained_agents_file=os.getenv(CREWAI_TRAINED_AGENTS_FILE_ENV)
|
||||
)
|
||||
except module.click.ClickException as exc:
|
||||
exc.show()
|
||||
raise SystemExit(exc.exit_code)
|
||||
module._run_json_crew(
|
||||
trained_agents_file=os.getenv(CREWAI_TRAINED_AGENTS_FILE_ENV)
|
||||
)
|
||||
""".strip()
|
||||
|
||||
|
||||
def _import_find_crew_json_file() -> Callable[[], Path | None]:
|
||||
from crewai.project.json_loader import find_crew_json_file as _find_crew_json_file
|
||||
|
||||
return cast("Callable[[], Path | None]", _find_crew_json_file)
|
||||
|
||||
|
||||
def _is_missing_crewai_package(exc: ModuleNotFoundError) -> bool:
|
||||
return bool(exc.name and exc.name.startswith("crewai"))
|
||||
|
||||
|
||||
def _full_crewai_install_error() -> click.ClickException:
|
||||
return click.ClickException(_FULL_CREWAI_INSTALL_MESSAGE)
|
||||
|
||||
|
||||
def find_crew_json_file() -> Path | None:
|
||||
try:
|
||||
return _import_find_crew_json_file()()
|
||||
except ModuleNotFoundError as exc:
|
||||
if _is_missing_crewai_package(exc):
|
||||
raise _full_crewai_install_error() from exc
|
||||
raise
|
||||
|
||||
|
||||
def _has_json_crew() -> bool:
|
||||
"""Check if this is a JSON-defined crew project.
|
||||
|
||||
|
||||
@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
|
||||
authors = [{ name = "Your Name", email = "you@example.com" }]
|
||||
requires-python = ">=3.10,<3.14"
|
||||
dependencies = [
|
||||
"crewai[tools]==1.14.8a2"
|
||||
"crewai[tools]==1.14.7"
|
||||
]
|
||||
|
||||
[project.scripts]
|
||||
|
||||
@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
|
||||
authors = [{ name = "Your Name", email = "you@example.com" }]
|
||||
requires-python = ">=3.10,<3.14"
|
||||
dependencies = [
|
||||
"crewai[tools]==1.14.8a2"
|
||||
"crewai[tools]==1.14.7"
|
||||
]
|
||||
|
||||
[project.scripts]
|
||||
|
||||
@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10,<3.14"
|
||||
dependencies = [
|
||||
"crewai[tools]==1.14.8a2"
|
||||
"crewai[tools]==1.14.7"
|
||||
]
|
||||
|
||||
[tool.crewai]
|
||||
|
||||
@@ -1,107 +0,0 @@
|
||||
"""Regression tests for path-traversal-safe archive extraction.
|
||||
|
||||
Guards against symlink/hardlink-based path traversal in the Python < 3.12
|
||||
extraction fallback (`_safe_extractall`). The 3.12+ path relies on
|
||||
`tarfile.extractall(..., filter="data")`; the fallback must provide the same
|
||||
protection by validating link targets, not just member names.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import tarfile
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from crewai_cli.experimental.skills.main import _safe_extractall
|
||||
|
||||
|
||||
def _tar_from_members(build) -> tarfile.TarFile:
|
||||
"""Build an in-memory tar archive via `build(tf)` and return it for reading."""
|
||||
buf = io.BytesIO()
|
||||
with tarfile.open(fileobj=buf, mode="w") as tf:
|
||||
build(tf)
|
||||
buf.seek(0)
|
||||
return tarfile.open(fileobj=buf, mode="r")
|
||||
|
||||
|
||||
def test_blocks_symlink_escaping_destination(tmp_path: Path) -> None:
|
||||
"""A symlink whose target escapes dest, plus a file written through it,
|
||||
must be rejected before anything is extracted."""
|
||||
outside = tmp_path / "outside"
|
||||
outside.mkdir()
|
||||
dest = tmp_path / "dest"
|
||||
dest.mkdir()
|
||||
|
||||
def build(tf: tarfile.TarFile) -> None:
|
||||
link = tarfile.TarInfo("link")
|
||||
link.type = tarfile.SYMTYPE
|
||||
link.linkname = str(outside) # absolute path outside dest
|
||||
tf.addfile(link)
|
||||
payload = b"pwned"
|
||||
info = tarfile.TarInfo("link/evil.txt")
|
||||
info.size = len(payload)
|
||||
tf.addfile(info, io.BytesIO(payload))
|
||||
|
||||
with _tar_from_members(build) as tf:
|
||||
with pytest.raises(ValueError, match="escaping destination"):
|
||||
_safe_extractall(tf, dest)
|
||||
|
||||
assert not (outside / "evil.txt").exists()
|
||||
|
||||
|
||||
def test_blocks_relative_symlink_escaping_destination(tmp_path: Path) -> None:
|
||||
"""A relative symlink (../..) that escapes dest is also rejected."""
|
||||
dest = tmp_path / "dest"
|
||||
dest.mkdir()
|
||||
|
||||
def build(tf: tarfile.TarFile) -> None:
|
||||
link = tarfile.TarInfo("sub/link")
|
||||
link.type = tarfile.SYMTYPE
|
||||
link.linkname = "../../outside" # escapes dest from sub/
|
||||
tf.addfile(link)
|
||||
|
||||
with _tar_from_members(build) as tf:
|
||||
with pytest.raises(ValueError, match="escaping destination"):
|
||||
_safe_extractall(tf, dest)
|
||||
|
||||
|
||||
def test_allows_benign_relative_symlink(tmp_path: Path) -> None:
|
||||
"""A symlink that stays within dest is permitted."""
|
||||
dest = tmp_path / "dest"
|
||||
dest.mkdir()
|
||||
|
||||
def build(tf: tarfile.TarFile) -> None:
|
||||
payload = b"hi"
|
||||
info = tarfile.TarInfo("real.txt")
|
||||
info.size = len(payload)
|
||||
tf.addfile(info, io.BytesIO(payload))
|
||||
link = tarfile.TarInfo("alias.txt")
|
||||
link.type = tarfile.SYMTYPE
|
||||
link.linkname = "real.txt" # stays inside dest
|
||||
tf.addfile(link)
|
||||
|
||||
with _tar_from_members(build) as tf:
|
||||
_safe_extractall(tf, dest)
|
||||
|
||||
assert (dest / "real.txt").read_bytes() == b"hi"
|
||||
|
||||
|
||||
def test_allows_benign_archive(tmp_path: Path) -> None:
|
||||
"""An ordinary archive of regular files extracts correctly."""
|
||||
dest = tmp_path / "dest"
|
||||
dest.mkdir()
|
||||
|
||||
def build(tf: tarfile.TarFile) -> None:
|
||||
for name, body in (("SKILL.md", b"# skill"), ("scripts/run.py", b"print(1)")):
|
||||
payload = body
|
||||
info = tarfile.TarInfo(name)
|
||||
info.size = len(payload)
|
||||
tf.addfile(info, io.BytesIO(payload))
|
||||
|
||||
with _tar_from_members(build) as tf:
|
||||
_safe_extractall(tf, dest)
|
||||
|
||||
assert (dest / "SKILL.md").read_bytes() == b"# skill"
|
||||
assert (dest / "scripts" / "run.py").read_bytes() == b"print(1)"
|
||||
@@ -5,10 +5,7 @@ from pathlib import Path
|
||||
from unittest import mock
|
||||
|
||||
import pytest
|
||||
import tomli
|
||||
from click.testing import CliRunner
|
||||
from packaging.requirements import Requirement
|
||||
from packaging.version import Version
|
||||
import crewai_cli.create_json_crew as json_crew
|
||||
import crewai_cli.tui_picker as tui_picker
|
||||
from crewai_cli.create_crew import create_crew, create_folder_structure
|
||||
@@ -715,14 +712,6 @@ def test_json_create_provider_preselects_default_model(tmp_path, monkeypatch):
|
||||
assert not (tmp_path / "json_crew" / "tests").exists()
|
||||
assert not (tmp_path / "json_crew" / "config.jsonc").exists()
|
||||
|
||||
pyproject = tomli.loads((tmp_path / "json_crew" / "pyproject.toml").read_text())
|
||||
dependency = pyproject["project"]["dependencies"][0]
|
||||
assert dependency == "crewai[tools]==1.14.8a1"
|
||||
assert Version("1.14.8a1") in Requirement(dependency).specifier
|
||||
assert pyproject["tool"]["hatch"]["build"]["targets"]["wheel"][
|
||||
"only-include"
|
||||
] == ["agents", "crew.jsonc", "tools", "knowledge", "skills"]
|
||||
|
||||
crew_template = (tmp_path / "json_crew" / "crew.jsonc").read_text()
|
||||
assert (
|
||||
'"guardrail": "Every factual claim needs context support."'
|
||||
|
||||
@@ -4,11 +4,6 @@ import time
|
||||
import pytest
|
||||
|
||||
from crewai.events.event_bus import crewai_event_bus
|
||||
from crewai.events.types.memory_events import (
|
||||
MemorySaveCompletedEvent,
|
||||
MemorySaveFailedEvent,
|
||||
MemorySaveStartedEvent,
|
||||
)
|
||||
from crewai.events.types.observation_events import (
|
||||
GoalAchievedEarlyEvent,
|
||||
PlanRefinementEvent,
|
||||
@@ -26,12 +21,7 @@ from crewai.events.types.tool_usage_events import (
|
||||
)
|
||||
from crewai_cli.command import AuthenticationRequiredError
|
||||
from crewai_cli import run_crew
|
||||
from crewai_cli.crew_run_tui import (
|
||||
CrewRunApp,
|
||||
_LOG_ARGS_TEXT_LIMIT,
|
||||
_LOG_RESULT_TEXT_LIMIT,
|
||||
_LOG_TRUNCATION_SUFFIX,
|
||||
)
|
||||
from crewai_cli.crew_run_tui import CrewRunApp
|
||||
|
||||
|
||||
def _app_with_plan() -> CrewRunApp:
|
||||
@@ -345,396 +335,6 @@ def test_internal_reasoning_function_call_is_hidden_from_activity_log() -> None:
|
||||
assert app._current_task_steps == []
|
||||
|
||||
|
||||
def test_memory_save_events_are_shown_in_activity_log() -> None:
|
||||
app = _app_with_plan()
|
||||
app._current_task_idx = 1
|
||||
app._subscribe()
|
||||
try:
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value="2 memories (background)",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
_emit_event(
|
||||
MemorySaveCompletedEvent(
|
||||
value="2 memories saved",
|
||||
metadata={},
|
||||
save_time_ms=123,
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert len(app._log_entries) == 1
|
||||
assert app._log_entries[0]["tool_name"] == "memory_save"
|
||||
assert app._log_entries[0]["status"] == "success"
|
||||
assert app._log_entries[0]["args"] == "2 memories (background)"
|
||||
assert app._log_entries[0]["result"] == "2 memories saved"
|
||||
assert app._log_entries[0]["error"] is None
|
||||
assert app._log_entries[0]["duration"] == 0.123
|
||||
assert app._log_entries[0]["task_idx"] == 1
|
||||
|
||||
|
||||
def test_nested_memory_save_event_is_hidden_for_save_to_memory_tool() -> None:
|
||||
app = _app_with_plan()
|
||||
app._subscribe()
|
||||
try:
|
||||
tool_args = {"contents": ["Fact to remember."]}
|
||||
_emit_event(
|
||||
ToolUsageStartedEvent(
|
||||
tool_name="save_to_memory",
|
||||
tool_args=tool_args,
|
||||
)
|
||||
)
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value="Fact to remember.",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
_emit_event(
|
||||
MemorySaveCompletedEvent(
|
||||
value="Fact to remember.",
|
||||
metadata={},
|
||||
save_time_ms=123,
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
now = datetime.now()
|
||||
_emit_event(
|
||||
ToolUsageFinishedEvent(
|
||||
tool_name="save_to_memory",
|
||||
tool_args=tool_args,
|
||||
started_at=now,
|
||||
finished_at=now,
|
||||
output="Saved to memory.",
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert len(app._log_entries) == 1
|
||||
assert app._log_entries[0]["tool_name"] == "save_to_memory"
|
||||
assert app._log_entries[0]["status"] == "success"
|
||||
assert app._log_entries[0]["result"] == "Saved to memory."
|
||||
|
||||
|
||||
def test_memory_save_failure_is_shown_in_activity_log() -> None:
|
||||
app = _app_with_plan()
|
||||
app._subscribe()
|
||||
try:
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value="background save",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
_emit_event(
|
||||
MemorySaveFailedEvent(
|
||||
value="background save",
|
||||
metadata={},
|
||||
error="embedding connection failed",
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert app._log_entries[0]["tool_name"] == "memory_save"
|
||||
assert app._log_entries[0]["status"] == "error"
|
||||
assert app._log_entries[0]["error"] == "embedding connection failed"
|
||||
assert app._log_expanded == {0}
|
||||
|
||||
|
||||
def test_memory_save_completion_updates_timed_out_row() -> None:
|
||||
app = _app_with_plan()
|
||||
app._subscribe()
|
||||
try:
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value="9 memories (background)",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
|
||||
app._log_entries[0]["status"] = "timeout"
|
||||
app._log_entries[0]["error"] = "No result received before crew completed"
|
||||
app._log_entries[0]["duration"] = 8.3
|
||||
|
||||
_emit_event(
|
||||
MemorySaveCompletedEvent(
|
||||
value="9 memories saved",
|
||||
metadata={},
|
||||
save_time_ms=8300,
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert len(app._log_entries) == 1
|
||||
assert app._log_entries[0]["tool_name"] == "memory_save"
|
||||
assert app._log_entries[0]["status"] == "success"
|
||||
assert app._log_entries[0]["result"] == "9 memories saved"
|
||||
assert app._log_entries[0]["error"] is None
|
||||
assert app._log_entries[0]["duration"] == 8.3
|
||||
|
||||
|
||||
def test_memory_save_completion_with_unmatched_id_does_not_update_running_row() -> None:
|
||||
app = _app_with_plan()
|
||||
app._subscribe()
|
||||
try:
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value="first background save",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
)
|
||||
)
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value="second background save",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
)
|
||||
)
|
||||
|
||||
_emit_event(
|
||||
MemorySaveCompletedEvent(
|
||||
value="orphan save completed",
|
||||
metadata={},
|
||||
save_time_ms=2800,
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
started_event_id="missing-memory-save-start",
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert [entry["status"] for entry in app._log_entries] == [
|
||||
"running",
|
||||
"running",
|
||||
"success",
|
||||
]
|
||||
assert app._log_entries[0]["args"] == "first background save"
|
||||
assert app._log_entries[1]["args"] == "second background save"
|
||||
assert app._log_entries[2]["result"] == "orphan save completed"
|
||||
assert app._log_entries[2]["started_event_id"] == "missing-memory-save-start"
|
||||
|
||||
|
||||
def test_memory_save_failure_with_unmatched_id_does_not_update_running_row() -> None:
|
||||
app = _app_with_plan()
|
||||
app._subscribe()
|
||||
try:
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value="first background save",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
)
|
||||
)
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value="second background save",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
)
|
||||
)
|
||||
|
||||
_emit_event(
|
||||
MemorySaveFailedEvent(
|
||||
value="orphan save failed",
|
||||
metadata={},
|
||||
error="embedding connection failed",
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
started_event_id="missing-memory-save-start",
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert [entry["status"] for entry in app._log_entries] == [
|
||||
"running",
|
||||
"running",
|
||||
"error",
|
||||
]
|
||||
assert app._log_entries[0]["args"] == "first background save"
|
||||
assert app._log_entries[1]["args"] == "second background save"
|
||||
assert app._log_entries[2]["args"] == "orphan save failed"
|
||||
assert app._log_entries[2]["error"] == "embedding connection failed"
|
||||
assert app._log_entries[2]["started_event_id"] == "missing-memory-save-start"
|
||||
assert app._log_expanded == {2}
|
||||
|
||||
|
||||
def test_memory_save_completion_without_id_does_not_update_stale_row() -> None:
|
||||
app = _app_with_plan()
|
||||
now = time.time()
|
||||
app._log_entries = [
|
||||
{
|
||||
"tool_name": "memory_save",
|
||||
"status": "running",
|
||||
"args": "current background save",
|
||||
"result": None,
|
||||
"error": None,
|
||||
"start_time": now,
|
||||
"duration": None,
|
||||
"task_idx": 1,
|
||||
},
|
||||
{
|
||||
"tool_name": "memory_save",
|
||||
"status": "success",
|
||||
"args": "stale background save",
|
||||
"result": "stale save completed",
|
||||
"error": None,
|
||||
"start_time": now - 10,
|
||||
"duration": 1.0,
|
||||
"task_idx": 1,
|
||||
},
|
||||
]
|
||||
|
||||
app._subscribe()
|
||||
try:
|
||||
_emit_event(
|
||||
MemorySaveCompletedEvent(
|
||||
value="current save completed",
|
||||
metadata={},
|
||||
save_time_ms=2800,
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert [entry["status"] for entry in app._log_entries] == [
|
||||
"success",
|
||||
"success",
|
||||
]
|
||||
assert app._log_entries[0]["args"] == "current background save"
|
||||
assert app._log_entries[0]["result"] == "current save completed"
|
||||
assert app._log_entries[1]["args"] == "stale background save"
|
||||
assert app._log_entries[1]["result"] == "stale save completed"
|
||||
|
||||
|
||||
def test_memory_save_failure_without_id_does_not_update_stale_row() -> None:
|
||||
app = _app_with_plan()
|
||||
now = time.time()
|
||||
app._log_entries = [
|
||||
{
|
||||
"tool_name": "memory_save",
|
||||
"status": "running",
|
||||
"args": "current background save",
|
||||
"result": None,
|
||||
"error": None,
|
||||
"start_time": now,
|
||||
"duration": None,
|
||||
"task_idx": 1,
|
||||
},
|
||||
{
|
||||
"tool_name": "memory_save",
|
||||
"status": "success",
|
||||
"args": "stale background save",
|
||||
"result": "stale save completed",
|
||||
"error": None,
|
||||
"start_time": now - 10,
|
||||
"duration": 1.0,
|
||||
"task_idx": 1,
|
||||
},
|
||||
]
|
||||
|
||||
app._subscribe()
|
||||
try:
|
||||
_emit_event(
|
||||
MemorySaveFailedEvent(
|
||||
value="current save failed",
|
||||
metadata={},
|
||||
error="embedding connection failed",
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert [entry["status"] for entry in app._log_entries] == ["error", "success"]
|
||||
assert app._log_entries[0]["args"] == "current background save"
|
||||
assert app._log_entries[0]["error"] == "embedding connection failed"
|
||||
assert app._log_entries[1]["args"] == "stale background save"
|
||||
assert app._log_entries[1]["result"] == "stale save completed"
|
||||
assert app._log_entries[1]["error"] is None
|
||||
assert app._log_expanded == {0}
|
||||
|
||||
|
||||
def test_memory_save_payloads_are_truncated_in_activity_log() -> None:
|
||||
app = _app_with_plan()
|
||||
long_args = "a" * (_LOG_ARGS_TEXT_LIMIT + 10)
|
||||
long_result = "r" * (_LOG_RESULT_TEXT_LIMIT + 10)
|
||||
|
||||
app._subscribe()
|
||||
try:
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value=long_args,
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
_emit_event(
|
||||
MemorySaveCompletedEvent(
|
||||
value=long_result,
|
||||
metadata={},
|
||||
save_time_ms=8300,
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert len(app._log_entries[0]["args"]) == _LOG_ARGS_TEXT_LIMIT
|
||||
assert app._log_entries[0]["args"].endswith(_LOG_TRUNCATION_SUFFIX)
|
||||
assert len(app._log_entries[0]["result"]) == _LOG_RESULT_TEXT_LIMIT
|
||||
assert app._log_entries[0]["result"].endswith(_LOG_TRUNCATION_SUFFIX)
|
||||
|
||||
|
||||
def test_starting_next_tool_does_not_timeout_memory_save() -> None:
|
||||
app = _app_with_plan()
|
||||
app._subscribe()
|
||||
try:
|
||||
_emit_event(
|
||||
MemorySaveStartedEvent(
|
||||
value="9 memories (background)",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
)
|
||||
)
|
||||
_emit_event(
|
||||
ToolUsageStartedEvent(
|
||||
tool_name="read_website_content",
|
||||
tool_args={"url": "https://example.com"},
|
||||
)
|
||||
)
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert app._log_entries[0]["tool_name"] == "memory_save"
|
||||
assert app._log_entries[0]["status"] == "running"
|
||||
assert app._log_entries[0]["error"] is None
|
||||
assert app._log_entries[1]["tool_name"] == "read_website_content"
|
||||
assert app._log_entries[1]["status"] == "running"
|
||||
|
||||
|
||||
def test_tool_failure_does_not_override_successful_plan_step_completion() -> None:
|
||||
app = _app_with_plan()
|
||||
app._subscribe()
|
||||
@@ -880,187 +480,6 @@ async def test_crew_done_does_not_mark_unfinished_tool_successful() -> None:
|
||||
assert app._plan_step_status == {1: "failed", 2: "done", 3: "done"}
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_crew_done_does_not_timeout_memory_save() -> None:
|
||||
app = _app_with_plan()
|
||||
|
||||
async with app.run_test(size=(100, 40)) as pilot:
|
||||
app._log_entries = [
|
||||
{
|
||||
"tool_name": "memory_save",
|
||||
"status": "running",
|
||||
"args": "9 memories (background)",
|
||||
"result": None,
|
||||
"error": None,
|
||||
"start_time": time.time() - 8,
|
||||
"duration": None,
|
||||
"task_idx": 1,
|
||||
},
|
||||
{
|
||||
"tool_name": "search",
|
||||
"status": "running",
|
||||
"args": '{"query": "CrewAI"}',
|
||||
"result": None,
|
||||
"error": None,
|
||||
"start_time": time.time() - 2,
|
||||
"duration": None,
|
||||
"task_idx": 1,
|
||||
},
|
||||
]
|
||||
|
||||
app._on_crew_done("final output")
|
||||
await pilot.pause()
|
||||
|
||||
assert app._log_entries[0]["status"] == "running"
|
||||
assert app._log_entries[0]["error"] is None
|
||||
assert app._log_entries[1]["status"] == "timeout"
|
||||
assert app._log_entries[1]["error"] == "No result received before crew completed"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_crew_done_keeps_memory_save_subscription_until_completion(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(
|
||||
"crewai_cli.crew_run_tui._MEMORY_SAVE_DRAIN_GRACE_SECONDS", 0.05
|
||||
)
|
||||
app = _app_with_plan()
|
||||
auto_unsubscribed = False
|
||||
|
||||
async with app.run_test(size=(100, 40)) as pilot:
|
||||
try:
|
||||
assert app._event_handlers
|
||||
started_event = MemorySaveStartedEvent(
|
||||
value="9 memories (background)",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
)
|
||||
_emit_event(started_event)
|
||||
|
||||
app._on_crew_done("final output")
|
||||
await pilot.pause()
|
||||
|
||||
assert app._log_entries[0]["status"] == "running"
|
||||
assert app._event_handlers
|
||||
|
||||
_emit_event(
|
||||
MemorySaveCompletedEvent(
|
||||
value="9 memories saved",
|
||||
metadata={},
|
||||
save_time_ms=8300,
|
||||
source_type="unified_memory",
|
||||
started_event_id=started_event.event_id,
|
||||
)
|
||||
)
|
||||
await pilot.pause()
|
||||
|
||||
assert app._event_handlers
|
||||
await pilot.pause(0.08)
|
||||
auto_unsubscribed = not app._event_handlers
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert app._log_entries[0]["tool_name"] == "memory_save"
|
||||
assert app._log_entries[0]["status"] == "success"
|
||||
assert app._log_entries[0]["result"] == "9 memories saved"
|
||||
assert app._log_entries[0]["error"] is None
|
||||
assert app._log_entries[0]["duration"] == 8.3
|
||||
assert auto_unsubscribed is True
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_crew_done_waits_for_queued_memory_save_events(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(
|
||||
"crewai_cli.crew_run_tui._MEMORY_SAVE_DRAIN_GRACE_SECONDS", 0.05
|
||||
)
|
||||
app = _app_with_plan()
|
||||
auto_unsubscribed = False
|
||||
|
||||
async with app.run_test(size=(100, 40)) as pilot:
|
||||
try:
|
||||
assert app._event_handlers
|
||||
|
||||
app._on_crew_done("final output")
|
||||
|
||||
assert app._event_handlers
|
||||
started_event = MemorySaveStartedEvent(
|
||||
value="9 memories (background)",
|
||||
metadata={},
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
)
|
||||
_emit_event(started_event)
|
||||
await pilot.pause()
|
||||
|
||||
assert app._log_entries[0]["tool_name"] == "memory_save"
|
||||
assert app._log_entries[0]["status"] == "running"
|
||||
|
||||
_emit_event(
|
||||
MemorySaveCompletedEvent(
|
||||
value="9 memories saved",
|
||||
metadata={},
|
||||
save_time_ms=8300,
|
||||
source_type="unified_memory",
|
||||
parent_event_id="manual-parent",
|
||||
started_event_id=started_event.event_id,
|
||||
)
|
||||
)
|
||||
await pilot.pause()
|
||||
|
||||
assert app._event_handlers
|
||||
await pilot.pause(0.08)
|
||||
auto_unsubscribed = not app._event_handlers
|
||||
finally:
|
||||
app._unsubscribe()
|
||||
|
||||
assert app._log_entries[0]["tool_name"] == "memory_save"
|
||||
assert app._log_entries[0]["status"] == "success"
|
||||
assert app._log_entries[0]["args"] == "9 memories (background)"
|
||||
assert app._log_entries[0]["result"] == "9 memories saved"
|
||||
assert app._log_entries[0]["error"] is None
|
||||
assert app._log_entries[0]["duration"] == 8.3
|
||||
assert auto_unsubscribed is True
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_crew_failed_does_not_timeout_memory_save() -> None:
|
||||
app = _app_with_plan()
|
||||
|
||||
async with app.run_test(size=(100, 40)) as pilot:
|
||||
app._log_entries = [
|
||||
{
|
||||
"tool_name": "memory_save",
|
||||
"status": "running",
|
||||
"args": "9 memories (background)",
|
||||
"result": None,
|
||||
"error": None,
|
||||
"start_time": time.time() - 8,
|
||||
"duration": None,
|
||||
"task_idx": 1,
|
||||
},
|
||||
{
|
||||
"tool_name": "search",
|
||||
"status": "running",
|
||||
"args": '{"query": "CrewAI"}',
|
||||
"result": None,
|
||||
"error": None,
|
||||
"start_time": time.time() - 2,
|
||||
"duration": None,
|
||||
"task_idx": 1,
|
||||
},
|
||||
]
|
||||
|
||||
app._on_crew_failed("boom")
|
||||
await pilot.pause()
|
||||
|
||||
assert app._log_entries[0]["status"] == "running"
|
||||
assert app._log_entries[0]["error"] is None
|
||||
assert app._log_entries[1]["status"] == "error"
|
||||
assert app._log_entries[1]["error"] == "No result received before crew failed"
|
||||
|
||||
|
||||
def test_streamed_step_observation_updates_named_step_only() -> None:
|
||||
app = _app_with_plan()
|
||||
|
||||
|
||||
@@ -5,33 +5,12 @@ from pathlib import Path
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
import click
|
||||
import pytest
|
||||
from crewai_core.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
|
||||
|
||||
import crewai_cli.run_crew as run_crew_module
|
||||
|
||||
|
||||
def test_missing_crewai_package_shows_full_install_hint(monkeypatch):
|
||||
def missing_crewai_package():
|
||||
raise ModuleNotFoundError("No module named 'crewai'", name="crewai")
|
||||
|
||||
monkeypatch.setattr(
|
||||
run_crew_module, "_import_find_crew_json_file", missing_crewai_package
|
||||
)
|
||||
|
||||
with pytest.raises(click.ClickException) as exc_info:
|
||||
run_crew_module.find_crew_json_file()
|
||||
|
||||
message = exc_info.value.message
|
||||
assert "CrewAI CLI is installed without the `crewai` package" in message
|
||||
assert (
|
||||
"uv tool install --force --prerelease=allow 'crewai[tools]==1.14.8a1'"
|
||||
in message
|
||||
)
|
||||
assert "quotes are required in zsh" in message
|
||||
|
||||
|
||||
def test_run_crew_forwards_trained_agents_file_to_json_crews(monkeypatch):
|
||||
"""crewai run -f must reach JSON crews, not only classic subprocess crews."""
|
||||
monkeypatch.setattr(run_crew_module, "_has_json_crew", lambda: True)
|
||||
|
||||
@@ -1 +1 @@
|
||||
__version__ = "1.14.8a2"
|
||||
__version__ = "1.14.7"
|
||||
|
||||
@@ -9,7 +9,7 @@ authors = [
|
||||
requires-python = ">=3.10, <3.14"
|
||||
dependencies = [
|
||||
"Pillow~=12.1.1",
|
||||
"pypdf~=6.13.3",
|
||||
"pypdf~=6.10.0",
|
||||
"python-magic>=0.4.27",
|
||||
"aiocache~=0.12.3",
|
||||
"aiofiles~=24.1.0",
|
||||
@@ -19,8 +19,6 @@ dependencies = [
|
||||
|
||||
[tool.uv]
|
||||
exclude-newer = "3 days"
|
||||
# pypdf 6.13.3 is a security fix newer than the global supply-chain cutoff.
|
||||
exclude-newer-package = { pypdf = "2026-06-18T00:00:00Z" }
|
||||
|
||||
[build-system]
|
||||
requires = ["hatchling"]
|
||||
|
||||
@@ -152,4 +152,4 @@ __all__ = [
|
||||
"wrap_file_source",
|
||||
]
|
||||
|
||||
__version__ = "1.14.8a2"
|
||||
__version__ = "1.14.7"
|
||||
|
||||
@@ -10,7 +10,7 @@ requires-python = ">=3.10, <3.14"
|
||||
dependencies = [
|
||||
"pytube~=15.0.0",
|
||||
"requests>=2.33.0,<3",
|
||||
"crewai==1.14.8a2",
|
||||
"crewai==1.14.7",
|
||||
"tiktoken>=0.8.0,<0.13",
|
||||
"beautifulsoup4~=4.13.4",
|
||||
"python-docx~=1.2.0",
|
||||
|
||||
@@ -330,4 +330,4 @@ __all__ = [
|
||||
"ZapierActionTools",
|
||||
]
|
||||
|
||||
__version__ = "1.14.8a2"
|
||||
__version__ = "1.14.7"
|
||||
|
||||
@@ -8,8 +8,8 @@ authors = [
|
||||
]
|
||||
requires-python = ">=3.10, <3.14"
|
||||
dependencies = [
|
||||
"crewai-core==1.14.8a2",
|
||||
"crewai-cli==1.14.8a2",
|
||||
"crewai-core==1.14.7",
|
||||
"crewai-cli==1.14.7",
|
||||
# Core Dependencies
|
||||
"pydantic>=2.11.9,<2.13",
|
||||
"openai>=2.30.0,<3",
|
||||
@@ -55,7 +55,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
|
||||
|
||||
[project.optional-dependencies]
|
||||
tools = [
|
||||
"crewai-tools==1.14.8a2",
|
||||
"crewai-tools==1.14.7",
|
||||
]
|
||||
embeddings = [
|
||||
"tiktoken>=0.8.0,<0.13"
|
||||
|
||||
@@ -48,7 +48,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
|
||||
|
||||
_suppress_pydantic_deprecation_warnings()
|
||||
|
||||
__version__ = "1.14.8a2"
|
||||
__version__ = "1.14.7"
|
||||
|
||||
_LAZY_IMPORTS: dict[str, tuple[str, str]] = {
|
||||
"Memory": ("crewai.memory.unified_memory", "Memory"),
|
||||
|
||||
@@ -9,7 +9,6 @@ from __future__ import annotations
|
||||
from datetime import datetime, timezone
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
from pathlib import Path
|
||||
import tarfile
|
||||
from typing import TypedDict
|
||||
@@ -128,40 +127,12 @@ class SkillCacheManager:
|
||||
|
||||
|
||||
def _safe_extractall(tf: tarfile.TarFile, dest: Path) -> None:
|
||||
"""Path-traversal-safe extraction for Python < 3.12.
|
||||
|
||||
Validates both the member's own path and, for symlink/hardlink members,
|
||||
the link target. Without the link-target check a malicious archive can
|
||||
plant a symlink that escapes ``dest`` (e.g. ``link -> /home/user/.ssh``)
|
||||
followed by a regular member written *through* that link
|
||||
(``link/authorized_keys``), escaping ``dest`` even though every member
|
||||
name resolves inside it. This mirrors the protection that
|
||||
``tarfile.extractall(..., filter="data")`` provides on Python >= 3.12.
|
||||
"""
|
||||
"""Path-traversal-safe extraction for Python < 3.12."""
|
||||
dest_resolved = dest.resolve()
|
||||
for member in tf.getmembers():
|
||||
member_path = (dest / member.name).resolve()
|
||||
if not member_path.is_relative_to(dest_resolved):
|
||||
raise ValueError(f"Blocked path traversal attempt: {member.name!r}")
|
||||
if member.ischr() or member.isblk() or member.isfifo():
|
||||
raise ValueError(f"Blocked special file type in archive: {member.name!r}")
|
||||
if member.issym() or member.islnk():
|
||||
link_target = member.linkname
|
||||
# Absolute link targets always escape the destination.
|
||||
if os.path.isabs(link_target):
|
||||
raise ValueError(
|
||||
f"Blocked link target escaping destination: "
|
||||
f"{member.name!r} -> {link_target!r}"
|
||||
)
|
||||
# Hardlink names are relative to the archive root; symlink
|
||||
# targets are relative to the member's own directory.
|
||||
anchor = dest if member.islnk() else (dest / member.name).parent
|
||||
resolved_target = (anchor / link_target).resolve()
|
||||
if not resolved_target.is_relative_to(dest_resolved):
|
||||
raise ValueError(
|
||||
f"Blocked link target escaping destination: "
|
||||
f"{member.name!r} -> {link_target!r}"
|
||||
)
|
||||
tf.extractall(dest) # noqa: S202
|
||||
|
||||
|
||||
|
||||
@@ -10,7 +10,6 @@ from crewai.flow.conversation import (
|
||||
ConversationalInputs,
|
||||
)
|
||||
from crewai.flow.dsl import HumanFeedbackResult, human_feedback
|
||||
from crewai.flow.expressions import Expression
|
||||
from crewai.flow.flow import Flow, and_, listen, or_, router, start
|
||||
from crewai.flow.flow_config import flow_config
|
||||
from crewai.flow.input_provider import InputProvider, InputResponse
|
||||
@@ -27,7 +26,6 @@ __all__ = [
|
||||
"ConsoleProvider",
|
||||
"ConversationalConfig",
|
||||
"ConversationalInputs",
|
||||
"Expression",
|
||||
"Flow",
|
||||
"FlowStructure",
|
||||
"HumanFeedbackPending",
|
||||
|
||||
@@ -14,6 +14,7 @@ from crewai.flow.flow_definition import (
|
||||
FlowConversationalDefinition,
|
||||
FlowConversationalRouterDefinition,
|
||||
FlowDefinition,
|
||||
FlowDefinitionDiagnostic,
|
||||
FlowDictStateDefinition,
|
||||
FlowHumanFeedbackDefinition,
|
||||
FlowMethodDefinition,
|
||||
@@ -22,7 +23,6 @@ from crewai.flow.flow_definition import (
|
||||
FlowStateDefinition,
|
||||
FlowUnknownStateDefinition,
|
||||
_object_ref,
|
||||
log_flow_definition_issues,
|
||||
)
|
||||
from crewai.flow.flow_wrappers import (
|
||||
FlowMethod,
|
||||
@@ -116,6 +116,7 @@ def _is_json_serializable(value: Any) -> bool:
|
||||
|
||||
def _serialize_static_value(
|
||||
value: Any,
|
||||
diagnostics: list[FlowDefinitionDiagnostic],
|
||||
path: str,
|
||||
) -> Any:
|
||||
if value is None or _is_json_serializable(value):
|
||||
@@ -147,11 +148,12 @@ def _serialize_static_value(
|
||||
)
|
||||
|
||||
ref = _object_ref(value)
|
||||
logger.warning(
|
||||
"Flow definition value at %s is not fully serializable; "
|
||||
"preserved import reference %s.",
|
||||
path,
|
||||
ref,
|
||||
diagnostics.append(
|
||||
FlowDefinitionDiagnostic(
|
||||
code="non_serializable_value",
|
||||
path=path,
|
||||
message=f"value is not fully serializable; preserved import reference {ref}",
|
||||
)
|
||||
)
|
||||
return {"ref": ref}
|
||||
|
||||
@@ -167,7 +169,10 @@ def _state_ref(value: Any) -> str | None:
|
||||
return None
|
||||
|
||||
|
||||
def _build_state_definition(flow_class: type) -> FlowStateDefinition | None:
|
||||
def _build_state_definition(
|
||||
flow_class: type,
|
||||
diagnostics: list[FlowDefinitionDiagnostic],
|
||||
) -> FlowStateDefinition | None:
|
||||
from pydantic import BaseModel as PydanticBaseModel
|
||||
|
||||
state_value = getattr(flow_class, "_initial_state_t", None)
|
||||
@@ -182,23 +187,29 @@ def _build_state_definition(flow_class: type) -> FlowStateDefinition | None:
|
||||
if state_value is dict or isinstance(state_value, dict):
|
||||
default = None
|
||||
if isinstance(state_value, dict):
|
||||
default = _serialize_static_value(state_value, "state.default")
|
||||
default = _serialize_static_value(state_value, diagnostics, "state.default")
|
||||
return FlowDictStateDefinition(default=default)
|
||||
if isinstance(state_value, type) and issubclass(state_value, PydanticBaseModel):
|
||||
return FlowPydanticStateDefinition(ref=_state_ref(state_value))
|
||||
if isinstance(state_value, PydanticBaseModel):
|
||||
return FlowPydanticStateDefinition(
|
||||
ref=_state_ref(state_value),
|
||||
default=_serialize_static_value(state_value, "state.default"),
|
||||
default=_serialize_static_value(state_value, diagnostics, "state.default"),
|
||||
)
|
||||
diagnostics.append(
|
||||
FlowDefinitionDiagnostic(
|
||||
code="unknown_state_type",
|
||||
path="state",
|
||||
message=f"could not serialize state type {_object_ref(state_value)}",
|
||||
)
|
||||
logger.warning(
|
||||
"Flow definition state could not serialize state type %s.",
|
||||
_object_ref(state_value),
|
||||
)
|
||||
return FlowUnknownStateDefinition(ref=_state_ref(state_value))
|
||||
|
||||
|
||||
def _build_config_definition(flow_class: type) -> FlowConfigDefinition:
|
||||
def _build_config_definition(
|
||||
flow_class: type,
|
||||
diagnostics: list[FlowDefinitionDiagnostic],
|
||||
) -> FlowConfigDefinition:
|
||||
config_field_names = set(FlowConfigDefinition.model_fields)
|
||||
field_defaults = {
|
||||
name: field.get_default(call_default_factory=True)
|
||||
@@ -214,12 +225,15 @@ def _build_config_definition(flow_class: type) -> FlowConfigDefinition:
|
||||
value if value is None or isinstance(value, str) else _object_ref(value)
|
||||
)
|
||||
else:
|
||||
values[field_name] = _serialize_static_value(value, f"config.{field_name}")
|
||||
values[field_name] = _serialize_static_value(
|
||||
value, diagnostics, f"config.{field_name}"
|
||||
)
|
||||
return FlowConfigDefinition(**values)
|
||||
|
||||
|
||||
def _build_human_feedback_definition(
|
||||
method: Any,
|
||||
diagnostics: list[FlowDefinitionDiagnostic],
|
||||
path: str,
|
||||
) -> FlowHumanFeedbackDefinition | None:
|
||||
config = getattr(method, "__human_feedback_config__", None)
|
||||
@@ -234,7 +248,7 @@ def _build_human_feedback_definition(
|
||||
llm=getattr(config, "llm", None),
|
||||
default_outcome=getattr(config, "default_outcome", None),
|
||||
metadata=_serialize_static_value(
|
||||
getattr(config, "metadata", None), f"{path}.metadata"
|
||||
getattr(config, "metadata", None), diagnostics, f"{path}.metadata"
|
||||
),
|
||||
provider=getattr(config, "provider", None),
|
||||
learn=bool(getattr(config, "learn", False)),
|
||||
@@ -259,6 +273,7 @@ def _build_persistence_definition(value: Any) -> FlowPersistenceDefinition | Non
|
||||
|
||||
def _build_conversational_router_definition(
|
||||
router_config: Any,
|
||||
diagnostics: list[FlowDefinitionDiagnostic],
|
||||
path: str,
|
||||
) -> FlowConversationalRouterDefinition | None:
|
||||
if router_config is None:
|
||||
@@ -269,9 +284,12 @@ def _build_conversational_router_definition(
|
||||
prompt=getattr(router_config, "prompt", None),
|
||||
response_format=_serialize_static_value(
|
||||
getattr(router_config, "response_format", None),
|
||||
diagnostics,
|
||||
f"{path}.response_format",
|
||||
),
|
||||
llm=_serialize_static_value(getattr(router_config, "llm", None), f"{path}.llm"),
|
||||
llm=_serialize_static_value(
|
||||
getattr(router_config, "llm", None), diagnostics, f"{path}.llm"
|
||||
),
|
||||
routes=[str(route) for route in routes] if routes is not None else None,
|
||||
route_descriptions=getattr(router_config, "route_descriptions", None),
|
||||
default_intent=getattr(router_config, "default_intent", "converse"),
|
||||
@@ -282,6 +300,7 @@ def _build_conversational_router_definition(
|
||||
|
||||
def _build_conversational_definition(
|
||||
flow_class: type,
|
||||
diagnostics: list[FlowDefinitionDiagnostic],
|
||||
) -> FlowConversationalDefinition | None:
|
||||
if not _is_conversational_flow(flow_class):
|
||||
return None
|
||||
@@ -305,9 +324,12 @@ def _build_conversational_definition(
|
||||
return FlowConversationalDefinition(
|
||||
enabled=True,
|
||||
system_prompt=getattr(config, "system_prompt", None),
|
||||
llm=_serialize_static_value(getattr(config, "llm", None), "conversational.llm"),
|
||||
llm=_serialize_static_value(
|
||||
getattr(config, "llm", None), diagnostics, "conversational.llm"
|
||||
),
|
||||
router=_build_conversational_router_definition(
|
||||
getattr(config, "router", None),
|
||||
diagnostics,
|
||||
"conversational.router",
|
||||
),
|
||||
answer_from_history_prompt=getattr(config, "answer_from_history_prompt", None),
|
||||
@@ -318,10 +340,12 @@ def _build_conversational_definition(
|
||||
),
|
||||
intent_llm=_serialize_static_value(
|
||||
getattr(config, "intent_llm", None),
|
||||
diagnostics,
|
||||
"conversational.intent_llm",
|
||||
),
|
||||
answer_from_history_llm=_serialize_static_value(
|
||||
getattr(config, "answer_from_history_llm", None),
|
||||
diagnostics,
|
||||
"conversational.answer_from_history_llm",
|
||||
),
|
||||
visible_agent_outputs=(
|
||||
@@ -341,6 +365,7 @@ def _build_conversational_definition(
|
||||
|
||||
def _build_method_definition(
|
||||
method: Any,
|
||||
diagnostics: list[FlowDefinitionDiagnostic],
|
||||
path: str,
|
||||
) -> FlowMethodDefinition:
|
||||
fragment = _get_flow_method_definition(method)
|
||||
@@ -351,7 +376,9 @@ def _build_method_definition(
|
||||
deep=True, update={"do": _method_action(method)}
|
||||
)
|
||||
|
||||
human_feedback = _build_human_feedback_definition(method, f"{path}.human_feedback")
|
||||
human_feedback = _build_human_feedback_definition(
|
||||
method, diagnostics, f"{path}.human_feedback"
|
||||
)
|
||||
if human_feedback is not None:
|
||||
method_definition.human_feedback = human_feedback
|
||||
if human_feedback.emit:
|
||||
@@ -417,6 +444,7 @@ def _build_flow_definition_from_class(
|
||||
flow_class: type,
|
||||
namespace: dict[str, Any] | None = None,
|
||||
) -> FlowDefinition:
|
||||
diagnostics: list[FlowDefinitionDiagnostic] = []
|
||||
methods: dict[str, FlowMethodDefinition] = {}
|
||||
flow_methods = _iter_flow_methods(flow_class)
|
||||
if namespace is not None:
|
||||
@@ -428,7 +456,7 @@ def _build_flow_definition_from_class(
|
||||
|
||||
for method_name, method in flow_methods.items():
|
||||
methods[method_name] = _build_method_definition(
|
||||
method, f"methods.{method_name}"
|
||||
method, diagnostics, f"methods.{method_name}"
|
||||
)
|
||||
|
||||
description = None
|
||||
@@ -439,13 +467,15 @@ def _build_flow_definition_from_class(
|
||||
definition = FlowDefinition(
|
||||
name=getattr(flow_class, "__name__", "Flow"),
|
||||
description=description,
|
||||
state=_build_state_definition(flow_class),
|
||||
config=_build_config_definition(flow_class),
|
||||
state=_build_state_definition(flow_class, diagnostics),
|
||||
config=_build_config_definition(flow_class, diagnostics),
|
||||
persist=_build_persistence_definition(flow_class),
|
||||
conversational=_build_conversational_definition(flow_class),
|
||||
conversational=_build_conversational_definition(flow_class, diagnostics),
|
||||
methods=methods,
|
||||
diagnostics=diagnostics,
|
||||
)
|
||||
log_flow_definition_issues(definition)
|
||||
definition.diagnostics.extend(definition.validate_contract())
|
||||
definition.log_diagnostics()
|
||||
return definition
|
||||
|
||||
|
||||
|
||||
@@ -1,329 +0,0 @@
|
||||
"""Runtime expression support for FlowDefinition CEL expressions."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Iterable
|
||||
import json
|
||||
from typing import TYPE_CHECKING, Any, TypeAlias, cast
|
||||
|
||||
from crewai.utilities.serialization import to_serializable
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from crewai.flow.runtime import Flow
|
||||
else:
|
||||
from typing_extensions import TypeAliasType
|
||||
|
||||
|
||||
_CEL_MACROS_WITH_LOCAL_BINDINGS = frozenset(
|
||||
{"all", "exists", "exists_one", "filter", "map"}
|
||||
)
|
||||
if TYPE_CHECKING:
|
||||
ExpressionData: TypeAlias = (
|
||||
str
|
||||
| int
|
||||
| float
|
||||
| bool
|
||||
| None
|
||||
| list["ExpressionData"]
|
||||
| dict[str, "ExpressionData"]
|
||||
)
|
||||
else:
|
||||
ExpressionData = TypeAliasType(
|
||||
"ExpressionData",
|
||||
str
|
||||
| int
|
||||
| float
|
||||
| bool
|
||||
| None
|
||||
| list["ExpressionData"]
|
||||
| dict[str, "ExpressionData"],
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"Expression",
|
||||
"ExpressionData",
|
||||
"ExpressionError",
|
||||
]
|
||||
|
||||
|
||||
class ExpressionError(ValueError):
|
||||
"""An expression failed to parse, validate, render, or evaluate."""
|
||||
|
||||
|
||||
class Expression:
|
||||
"""CEL expression helper used for definition-time checks and runtime rendering."""
|
||||
|
||||
def __init__(
|
||||
self, value: ExpressionData, *, context: dict[str, Any] | None = None
|
||||
) -> None:
|
||||
self.value = value
|
||||
self.context = context
|
||||
|
||||
@classmethod
|
||||
def from_flow(
|
||||
cls,
|
||||
value: ExpressionData,
|
||||
flow: Flow[Any],
|
||||
*,
|
||||
local_context: dict[str, Any] | None = None,
|
||||
) -> Expression:
|
||||
"""Build an expression with the standard Flow runtime context."""
|
||||
return cls(value, context=cls._flow_context(flow, local_context=local_context))
|
||||
|
||||
def validate_expression(
|
||||
self,
|
||||
*,
|
||||
allowed_roots: Iterable[str],
|
||||
source: str = "CEL expression",
|
||||
) -> None:
|
||||
"""Validate a full CEL expression without evaluating it."""
|
||||
allowed = frozenset(allowed_roots)
|
||||
expression = self._require_cel_source(cast(str, self.value), source=source)
|
||||
roots = self._collect_root_identifiers(
|
||||
self._compile_cel(expression, source=source)
|
||||
)
|
||||
unknown = sorted(root for root in roots if root not in allowed)
|
||||
if unknown:
|
||||
allowed_list = ", ".join(sorted(allowed))
|
||||
unknown_list = ", ".join(repr(root) for root in unknown)
|
||||
raise ExpressionError(
|
||||
f"unknown CEL root at {source}: {unknown_list}; "
|
||||
f"allowed roots: {allowed_list}. Reference flow data through one "
|
||||
"of those roots, for example state.field or outputs.step_name."
|
||||
)
|
||||
|
||||
def validate_template(
|
||||
self,
|
||||
*,
|
||||
allowed_roots: Iterable[str],
|
||||
source: str = "with block",
|
||||
) -> None:
|
||||
"""Validate nested strings fully wrapped in ``${...}`` as CEL."""
|
||||
self._validate_template_value(
|
||||
self.value, allowed_roots=allowed_roots, source=source
|
||||
)
|
||||
|
||||
def evaluate(self, context: dict[str, Any] | None = None) -> Any:
|
||||
"""Evaluate this value as a full CEL expression."""
|
||||
resolved_context = self.context if context is None else context
|
||||
return self._evaluate_cel(
|
||||
self._require_cel_source(cast(str, self.value)),
|
||||
resolved_context or {},
|
||||
)
|
||||
|
||||
def render_template(self, context: dict[str, Any] | None = None) -> Any:
|
||||
"""Evaluate nested strings fully wrapped in ``${...}`` as CEL."""
|
||||
resolved_context = self.context if context is None else context
|
||||
return self._render_template_value(self.value, resolved_context or {})
|
||||
|
||||
@staticmethod
|
||||
def _validate_template_value(
|
||||
value: ExpressionData,
|
||||
*,
|
||||
allowed_roots: Iterable[str],
|
||||
source: str,
|
||||
) -> None:
|
||||
if isinstance(value, str):
|
||||
expression = Expression._expression_marker_source(value, source=source)
|
||||
if expression is not None:
|
||||
Expression(expression).validate_expression(
|
||||
allowed_roots=allowed_roots, source=source
|
||||
)
|
||||
return
|
||||
if isinstance(value, dict):
|
||||
for key, item in value.items():
|
||||
item_source = f"{source}.{key}" if isinstance(key, str) else source
|
||||
Expression._validate_template_value(
|
||||
item, allowed_roots=allowed_roots, source=item_source
|
||||
)
|
||||
return
|
||||
if isinstance(value, list):
|
||||
for index, item in enumerate(value):
|
||||
Expression._validate_template_value(
|
||||
item,
|
||||
allowed_roots=allowed_roots,
|
||||
source=f"{source}[{index}]",
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _flow_context(
|
||||
flow: Flow[Any], local_context: dict[str, Any] | None = None
|
||||
) -> dict[str, Any]:
|
||||
from crewai.flow.runtime._outputs import outputs_by_name
|
||||
|
||||
local_outputs = local_context.get("outputs") if local_context else None
|
||||
outputs = outputs_by_name(
|
||||
flow._method_outputs,
|
||||
local_outputs=local_outputs,
|
||||
serialize=True,
|
||||
)
|
||||
context: dict[str, Any] = {
|
||||
"state": flow._copy_and_serialize_state(),
|
||||
"outputs": outputs,
|
||||
}
|
||||
if local_context:
|
||||
context.update(
|
||||
{
|
||||
key: to_serializable(value, max_depth=0)
|
||||
for key, value in local_context.items()
|
||||
if key not in {"outputs", "state"}
|
||||
}
|
||||
)
|
||||
return context
|
||||
|
||||
@staticmethod
|
||||
def _render_template_value(value: ExpressionData, context: dict[str, Any]) -> Any:
|
||||
if isinstance(value, str):
|
||||
return Expression._render_template_string(value, context)
|
||||
if isinstance(value, dict):
|
||||
return {
|
||||
key: Expression._render_template_value(item, context)
|
||||
for key, item in value.items()
|
||||
}
|
||||
if isinstance(value, list):
|
||||
return [Expression._render_template_value(item, context) for item in value]
|
||||
return value
|
||||
|
||||
@staticmethod
|
||||
def _render_template_string(value: str, context: dict[str, Any]) -> Any:
|
||||
expression = Expression._expression_marker_source(value)
|
||||
if expression is None:
|
||||
return value
|
||||
return Expression._evaluate_cel(expression, context)
|
||||
|
||||
@staticmethod
|
||||
def _expression_marker_source(
|
||||
value: str, *, source: str | None = None
|
||||
) -> str | None:
|
||||
"""Return CEL source when the trimmed string starts with ``${`` and ends with ``}``."""
|
||||
stripped = value.strip()
|
||||
if not stripped.startswith("${"):
|
||||
return None
|
||||
if not stripped.endswith("}"):
|
||||
return None
|
||||
|
||||
expression = stripped[2:-1].strip()
|
||||
if not expression:
|
||||
if source is None:
|
||||
raise ExpressionError("empty CEL expression in with block")
|
||||
raise ExpressionError(f"empty CEL expression at {source}")
|
||||
return expression
|
||||
|
||||
@staticmethod
|
||||
def _evaluate_cel(expression: str, context: dict[str, Any]) -> Any:
|
||||
try:
|
||||
from celpy import Environment
|
||||
from celpy.adapter import CELJSONEncoder, json_to_cel
|
||||
from celpy.evaluation import Context
|
||||
|
||||
environment = Environment()
|
||||
program = environment.program(
|
||||
Expression._compile_cel(expression, environment=environment)
|
||||
)
|
||||
result = program.evaluate(cast(Context, json_to_cel(context)))
|
||||
return json.loads(json.dumps(result, cls=CELJSONEncoder))
|
||||
except Exception as e:
|
||||
raise ExpressionError(
|
||||
f"failed to evaluate CEL expression {expression!r}: {e}"
|
||||
) from e
|
||||
|
||||
@staticmethod
|
||||
def _compile_cel(
|
||||
expression: str,
|
||||
*,
|
||||
source: str | None = None,
|
||||
environment: Any | None = None,
|
||||
) -> Any:
|
||||
if environment is None:
|
||||
from celpy import Environment
|
||||
|
||||
environment = Environment()
|
||||
try:
|
||||
return environment.compile(expression)
|
||||
except Exception as e:
|
||||
if source is None:
|
||||
raise
|
||||
raise ExpressionError(
|
||||
f"invalid CEL expression at {source}: {expression!r}. "
|
||||
f"Check the CEL syntax. Parser details: {e}"
|
||||
) from e
|
||||
|
||||
@staticmethod
|
||||
def _require_cel_source(value: str, *, source: str | None = None) -> str:
|
||||
expression = value.strip()
|
||||
if expression.startswith("${") and expression.endswith("}"):
|
||||
expression = expression[2:-1].strip()
|
||||
if expression:
|
||||
return expression
|
||||
if source is None:
|
||||
raise ExpressionError("empty CEL expression")
|
||||
raise ExpressionError(
|
||||
f"empty CEL expression at {source}. Provide a CEL expression such as "
|
||||
"state.topic or outputs.step_name."
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _collect_root_identifiers(
|
||||
tree: Any, local_roots: frozenset[str] = frozenset()
|
||||
) -> set[str]:
|
||||
"""Collect CEL root identifiers, excluding receiver macro local variables."""
|
||||
data = getattr(tree, "data", None)
|
||||
children = list(getattr(tree, "children", []) or [])
|
||||
|
||||
if data == "ident" and children:
|
||||
name = str(children[0])
|
||||
return set() if name in local_roots else {name}
|
||||
|
||||
if data == "ident_arg":
|
||||
return Expression._collect_root_identifiers_from(
|
||||
children[1:], local_roots=local_roots
|
||||
)
|
||||
|
||||
if data == "member_dot_arg":
|
||||
roots = (
|
||||
Expression._collect_root_identifiers(children[0], local_roots)
|
||||
if children
|
||||
else set()
|
||||
)
|
||||
nested_locals = frozenset(
|
||||
{*local_roots, *Expression._receiver_macro_local_roots(children)}
|
||||
)
|
||||
roots.update(
|
||||
Expression._collect_root_identifiers_from(
|
||||
children[2:], local_roots=nested_locals
|
||||
)
|
||||
)
|
||||
return roots
|
||||
|
||||
return Expression._collect_root_identifiers_from(
|
||||
children, local_roots=local_roots
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _collect_root_identifiers_from(
|
||||
trees: Iterable[Any], *, local_roots: frozenset[str]
|
||||
) -> set[str]:
|
||||
return set().union(
|
||||
*(Expression._collect_root_identifiers(tree, local_roots) for tree in trees)
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _receiver_macro_local_roots(children: list[Any]) -> set[str]:
|
||||
if len(children) < 3 or str(children[1]) not in _CEL_MACROS_WITH_LOCAL_BINDINGS:
|
||||
return set()
|
||||
exprlist = children[2]
|
||||
exprs = list(getattr(exprlist, "children", []) or [])
|
||||
if exprs and (name := Expression._single_identifier_name(exprs[0])):
|
||||
return {name}
|
||||
return set()
|
||||
|
||||
@staticmethod
|
||||
def _single_identifier_name(tree: Any) -> str | None:
|
||||
data = getattr(tree, "data", None)
|
||||
children = list(getattr(tree, "children", []) or [])
|
||||
if data == "ident" and children:
|
||||
return str(children[0])
|
||||
if len(children) != 1:
|
||||
return None
|
||||
return Expression._single_identifier_name(children[0])
|
||||
@@ -12,12 +12,13 @@ from __future__ import annotations
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
from typing import Annotated, Any, Literal, TypeAlias, cast
|
||||
from typing import Annotated, Any, Literal as TypingLiteral, TypeAlias
|
||||
|
||||
from pydantic import (
|
||||
BaseModel,
|
||||
ConfigDict,
|
||||
Field,
|
||||
RootModel,
|
||||
field_serializer,
|
||||
model_validator,
|
||||
)
|
||||
@@ -27,21 +28,16 @@ from crewai.flow.conversational_definition import (
|
||||
FlowConversationalDefinition,
|
||||
FlowConversationalRouterDefinition,
|
||||
)
|
||||
from crewai.flow.expressions import ExpressionData
|
||||
from crewai.project.crew_definition import AgentDefinition, CrewDefinition
|
||||
from crewai.project.crew_definition import CrewDefinition
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
FlowDefinitionCondition = str | dict[str, Any]
|
||||
_STEP_NAME_PATTERN = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
|
||||
_BASE_CEL_ROOTS = frozenset({"outputs", "state"})
|
||||
_EACH_STEP_CEL_ROOTS = frozenset({"item", "outputs", "state"})
|
||||
|
||||
__all__ = [
|
||||
"FlowActionDefinition",
|
||||
"FlowAgentActionDefinition",
|
||||
"FlowAtomicActionDefinition",
|
||||
"FlowCodeActionDefinition",
|
||||
"FlowConfigDefinition",
|
||||
"FlowConversationalDefinition",
|
||||
@@ -49,16 +45,16 @@ __all__ = [
|
||||
"FlowCrewActionDefinition",
|
||||
"FlowDefinition",
|
||||
"FlowDefinitionCondition",
|
||||
"FlowDefinitionDiagnostic",
|
||||
"FlowDictStateDefinition",
|
||||
"FlowEachActionDefinition",
|
||||
"FlowEachStepDefinition",
|
||||
"FlowEachInnerActionDefinition",
|
||||
"FlowExpressionActionDefinition",
|
||||
"FlowHumanFeedbackDefinition",
|
||||
"FlowJsonSchemaStateDefinition",
|
||||
"FlowMethodDefinition",
|
||||
"FlowPersistenceDefinition",
|
||||
"FlowPydanticStateDefinition",
|
||||
"FlowScriptActionDefinition",
|
||||
"FlowStateDefinition",
|
||||
"FlowToolActionDefinition",
|
||||
"FlowUnknownStateDefinition",
|
||||
@@ -73,12 +69,21 @@ def _object_ref(value: Any) -> str:
|
||||
return f"{module}:{qualname}" if module and qualname else repr(value)
|
||||
|
||||
|
||||
class FlowDefinitionDiagnostic(BaseModel):
|
||||
"""A non-fatal Flow Definition build or validation diagnostic."""
|
||||
|
||||
code: str
|
||||
message: str
|
||||
severity: TypingLiteral["warning", "error"] = "warning"
|
||||
path: str | None = None
|
||||
|
||||
|
||||
class FlowDictStateDefinition(BaseModel):
|
||||
"""Static description of a plain dictionary Flow state contract."""
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
type: Literal["dict"] = Field(
|
||||
type: TypingLiteral["dict"] = Field(
|
||||
default="dict",
|
||||
description="Plain dictionary state with optional default values.",
|
||||
examples=["dict"],
|
||||
@@ -95,7 +100,7 @@ class FlowPydanticStateDefinition(BaseModel):
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
type: Literal["pydantic"] = Field(
|
||||
type: TypingLiteral["pydantic"] = Field(
|
||||
default="pydantic",
|
||||
description="Importable Pydantic model used as the Flow state type.",
|
||||
examples=["pydantic"],
|
||||
@@ -130,7 +135,7 @@ class FlowJsonSchemaStateDefinition(BaseModel):
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
type: Literal["json_schema"] = Field(
|
||||
type: TypingLiteral["json_schema"] = Field(
|
||||
default="json_schema",
|
||||
description="Inline JSON Schema used as the Flow state contract.",
|
||||
examples=["json_schema"],
|
||||
@@ -157,7 +162,7 @@ class FlowUnknownStateDefinition(BaseModel):
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
type: Literal["unknown"] = Field(
|
||||
type: TypingLiteral["unknown"] = Field(
|
||||
default="unknown",
|
||||
description="Unknown state representation; runtime falls back to dictionary state.",
|
||||
examples=["unknown"],
|
||||
@@ -186,46 +191,14 @@ FlowStateDefinition: TypeAlias = Annotated[
|
||||
class FlowConfigDefinition(BaseModel):
|
||||
"""Serializable Flow-level configuration."""
|
||||
|
||||
tracing: bool | None = Field(
|
||||
default=None,
|
||||
description="Override for flow tracing; when omitted, runtime defaults apply.",
|
||||
examples=[True],
|
||||
)
|
||||
stream: bool = Field(
|
||||
default=False,
|
||||
description="Whether the flow should emit streaming events when supported.",
|
||||
examples=[True],
|
||||
)
|
||||
memory: dict[str, Any] | None = Field(
|
||||
default=None,
|
||||
description="Serializable memory configuration passed to flow execution.",
|
||||
examples=[{"enabled": True}],
|
||||
)
|
||||
input_provider: str | None = Field(
|
||||
default=None,
|
||||
description="Import reference or provider key used to supply flow inputs.",
|
||||
examples=["my_project.inputs:load_inputs"],
|
||||
)
|
||||
suppress_flow_events: bool = Field(
|
||||
default=False,
|
||||
description="Disable flow event emission for this definition.",
|
||||
examples=[False],
|
||||
)
|
||||
max_method_calls: int = Field(
|
||||
default=100,
|
||||
description="Maximum number of method executions allowed during one kickoff.",
|
||||
examples=[20],
|
||||
)
|
||||
defer_trace_finalization: bool = Field(
|
||||
default=False,
|
||||
description="Defer trace finalization so callers can complete tracing later.",
|
||||
examples=[False],
|
||||
)
|
||||
checkpoint: bool | dict[str, Any] | None = Field(
|
||||
default=None,
|
||||
description="Checkpointing configuration, or true to use default checkpointing.",
|
||||
examples=[True, {"enabled": True}],
|
||||
)
|
||||
tracing: bool | None = None
|
||||
stream: bool = False
|
||||
memory: dict[str, Any] | None = None
|
||||
input_provider: str | None = None
|
||||
suppress_flow_events: bool = False
|
||||
max_method_calls: int = 100
|
||||
defer_trace_finalization: bool = False
|
||||
checkpoint: bool | dict[str, Any] | None = None
|
||||
|
||||
|
||||
class FlowPersistenceDefinition(BaseModel):
|
||||
@@ -237,21 +210,9 @@ class FlowPersistenceDefinition(BaseModel):
|
||||
serialized config.
|
||||
"""
|
||||
|
||||
enabled: bool = Field(
|
||||
default=False,
|
||||
description="Whether persistence is enabled for this flow or method.",
|
||||
examples=[True],
|
||||
)
|
||||
verbose: bool = Field(
|
||||
default=False,
|
||||
description="Whether persistence should emit verbose diagnostic output.",
|
||||
examples=[False],
|
||||
)
|
||||
persistence: Any = Field(
|
||||
default=None,
|
||||
description="Persistence backend configuration or import reference.",
|
||||
examples=[{"ref": "my_project.persistence:FlowStore"}],
|
||||
)
|
||||
enabled: bool = False
|
||||
verbose: bool = False
|
||||
persistence: Any = None
|
||||
|
||||
@field_serializer("persistence", when_used="json")
|
||||
def _serialize_persistence(self, value: Any) -> Any:
|
||||
@@ -277,53 +238,15 @@ class FlowHumanFeedbackDefinition(BaseModel):
|
||||
a serialized config (``llm``) or a ``module:qualname`` ref (``provider``).
|
||||
"""
|
||||
|
||||
message: str = Field(
|
||||
description="Prompt shown to the human reviewer when feedback is requested.",
|
||||
examples=["Review the research summary before publishing."],
|
||||
)
|
||||
emit: list[str] | None = Field(
|
||||
default=None,
|
||||
description=(
|
||||
"Allowed feedback outcomes. When set, the method routes like a router "
|
||||
"using the selected outcome."
|
||||
),
|
||||
examples=[["approved", "revise"]],
|
||||
)
|
||||
llm: Any = Field(
|
||||
default="gpt-4o-mini",
|
||||
description="LLM configuration used to assist or process human feedback.",
|
||||
examples=["gpt-4o-mini"],
|
||||
)
|
||||
default_outcome: str | None = Field(
|
||||
default=None,
|
||||
description="Outcome to use when feedback cannot be collected.",
|
||||
examples=["revise"],
|
||||
)
|
||||
metadata: dict[str, Any] | None = Field(
|
||||
default=None,
|
||||
description="Serializable metadata attached to the feedback request.",
|
||||
examples=[{"team": "research"}],
|
||||
)
|
||||
provider: Any = Field(
|
||||
default=None,
|
||||
description="Feedback provider configuration or import reference.",
|
||||
examples=["my_project.feedback:provider"],
|
||||
)
|
||||
learn: bool = Field(
|
||||
default=False,
|
||||
description="Whether feedback should be recorded for later learning workflows.",
|
||||
examples=[True],
|
||||
)
|
||||
learn_source: str = Field(
|
||||
default="hitl",
|
||||
description="Source label attached to learned feedback records.",
|
||||
examples=["hitl"],
|
||||
)
|
||||
learn_strict: bool = Field(
|
||||
default=False,
|
||||
description="Whether learning should enforce strict validation of feedback data.",
|
||||
examples=[False],
|
||||
)
|
||||
message: str
|
||||
emit: list[str] | None = None
|
||||
llm: Any = "gpt-4o-mini"
|
||||
default_outcome: str | None = None
|
||||
metadata: dict[str, Any] | None = None
|
||||
provider: Any = None
|
||||
learn: bool = False
|
||||
learn_source: str = "hitl"
|
||||
learn_strict: bool = False
|
||||
|
||||
@field_serializer("llm", when_used="json")
|
||||
def _serialize_llm(self, value: Any) -> dict[str, Any] | str | None:
|
||||
@@ -343,124 +266,30 @@ class FlowHumanFeedbackDefinition(BaseModel):
|
||||
class FlowCodeActionDefinition(BaseModel):
|
||||
"""A Flow method action that executes importable Python code."""
|
||||
|
||||
model_config = ConfigDict(
|
||||
populate_by_name=True,
|
||||
extra="forbid",
|
||||
)
|
||||
model_config = ConfigDict(populate_by_name=True, extra="forbid")
|
||||
|
||||
call: Literal["code"] = Field(
|
||||
default="code",
|
||||
description="Action discriminator. Use code to call importable Python.",
|
||||
examples=["code"],
|
||||
)
|
||||
ref: str = Field(
|
||||
description="Import reference for the callable, formatted as module:qualname.",
|
||||
examples=["my_project.flows:normalize_topic"],
|
||||
)
|
||||
with_: dict[str, ExpressionData] | None = Field(
|
||||
default=None,
|
||||
alias="with",
|
||||
description=(
|
||||
"Keyword arguments passed to the callable. String values are evaluated "
|
||||
"as CEL only when the trimmed value starts with ${ and ends with }; "
|
||||
"all other values are literal."
|
||||
),
|
||||
examples=[{"topic": "${state.topic}"}],
|
||||
)
|
||||
call: TypingLiteral["code"] = "code"
|
||||
ref: str
|
||||
with_: dict[str, Any] | None = Field(default=None, alias="with")
|
||||
|
||||
|
||||
class FlowToolActionDefinition(BaseModel):
|
||||
"""A Flow method action that invokes a CrewAI tool."""
|
||||
|
||||
model_config = ConfigDict(
|
||||
populate_by_name=True,
|
||||
extra="forbid",
|
||||
)
|
||||
model_config = ConfigDict(populate_by_name=True, extra="forbid")
|
||||
|
||||
call: Literal["tool"] = Field(
|
||||
description="Action discriminator. Use tool to instantiate and run a CrewAI tool.",
|
||||
examples=["tool"],
|
||||
)
|
||||
ref: str = Field(
|
||||
description="Import reference for a BaseTool class, formatted as module:qualname.",
|
||||
examples=["my_project.tools:SearchTool"],
|
||||
)
|
||||
with_: dict[str, ExpressionData] | None = Field(
|
||||
default=None,
|
||||
alias="with",
|
||||
description=(
|
||||
"Tool input arguments. String values are evaluated as CEL only when "
|
||||
"the trimmed value starts with ${ and ends with }; all other values "
|
||||
"are literal."
|
||||
),
|
||||
examples=[{"query": "${outputs.normalize_topic}", "limit": 5}],
|
||||
)
|
||||
call: TypingLiteral["tool"]
|
||||
ref: str
|
||||
with_: dict[str, Any] | None = Field(default=None, alias="with")
|
||||
|
||||
|
||||
class FlowCrewActionDefinition(BaseModel):
|
||||
"""A Flow method action that builds and kicks off a CrewAI crew."""
|
||||
|
||||
model_config = ConfigDict(
|
||||
populate_by_name=True,
|
||||
extra="forbid",
|
||||
)
|
||||
model_config = ConfigDict(populate_by_name=True, extra="forbid")
|
||||
|
||||
call: Literal["crew"] = Field(
|
||||
description="Action discriminator. Use crew to run an inline Crew definition.",
|
||||
examples=["crew"],
|
||||
)
|
||||
with_: CrewDefinition = Field(
|
||||
alias="with",
|
||||
description="Inline Crew definition to load and execute for this action.",
|
||||
examples=[
|
||||
{
|
||||
"name": "inline_research",
|
||||
"agents": {
|
||||
"researcher": {
|
||||
"role": "Researcher",
|
||||
"goal": "Research {topic}",
|
||||
"backstory": "Knows the domain.",
|
||||
}
|
||||
},
|
||||
"tasks": [
|
||||
{
|
||||
"name": "research_task",
|
||||
"description": "Research {topic}",
|
||||
"expected_output": "Findings about {topic}",
|
||||
"agent": "researcher",
|
||||
}
|
||||
],
|
||||
"inputs": {"topic": "${state.topic}"},
|
||||
}
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
class FlowAgentActionDefinition(BaseModel):
|
||||
"""A Flow method action that builds and kicks off a CrewAI agent."""
|
||||
|
||||
model_config = ConfigDict(
|
||||
populate_by_name=True,
|
||||
extra="forbid",
|
||||
)
|
||||
|
||||
call: Literal["agent"] = Field(
|
||||
description="Action discriminator. Use agent to run an inline Agent definition.",
|
||||
examples=["agent"],
|
||||
)
|
||||
with_: AgentDefinition = Field(
|
||||
alias="with",
|
||||
description="Inline Agent definition to load and execute for this action.",
|
||||
examples=[
|
||||
{
|
||||
"role": "Analyst",
|
||||
"goal": "Answer user questions",
|
||||
"backstory": "Precise and concise.",
|
||||
"settings": {"llm": "openai/gpt-4o-mini"},
|
||||
"input": "${state.question}",
|
||||
}
|
||||
],
|
||||
)
|
||||
call: TypingLiteral["crew"]
|
||||
with_: CrewDefinition = Field(alias="with")
|
||||
|
||||
|
||||
class FlowExpressionActionDefinition(BaseModel):
|
||||
@@ -468,143 +297,66 @@ class FlowExpressionActionDefinition(BaseModel):
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
call: Literal["expression"] = Field(
|
||||
description="Action discriminator. Use expression to evaluate a CEL expression.",
|
||||
examples=["expression"],
|
||||
)
|
||||
expr: str = Field(
|
||||
description="CEL expression evaluated against state, outputs, and local context.",
|
||||
examples=["state.topic", "outputs.normalize_topic"],
|
||||
)
|
||||
call: TypingLiteral["expression"]
|
||||
expr: str
|
||||
|
||||
|
||||
class FlowScriptActionDefinition(BaseModel):
|
||||
"""A Flow method action that executes trusted inline Python."""
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
call: Literal["script"] = Field(
|
||||
description="Action discriminator. Use script to execute trusted inline Python.",
|
||||
examples=["script"],
|
||||
)
|
||||
code: str = Field(
|
||||
description=(
|
||||
"Trusted Python source executed as a generated function. Runtime values are "
|
||||
"passed as state, outputs, input, and item; they are not interpolated into "
|
||||
"the source. This is not sandboxed."
|
||||
),
|
||||
examples=[
|
||||
"state['normalized_topic'] = input.strip()\n"
|
||||
"return state['normalized_topic']"
|
||||
],
|
||||
)
|
||||
language: Literal["python"] = Field(
|
||||
default="python",
|
||||
description="Script language. Only python is currently supported.",
|
||||
examples=["python"],
|
||||
)
|
||||
|
||||
|
||||
FlowAtomicActionDefinition: TypeAlias = Annotated[
|
||||
FlowInnerActionDefinition = (
|
||||
FlowCodeActionDefinition
|
||||
| FlowToolActionDefinition
|
||||
| FlowCrewActionDefinition
|
||||
| FlowAgentActionDefinition
|
||||
| FlowExpressionActionDefinition
|
||||
| FlowScriptActionDefinition,
|
||||
Field(discriminator="call"),
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
class FlowEachStepDefinition(BaseModel):
|
||||
"""One named step inside an ``each`` composite action."""
|
||||
|
||||
model_config = ConfigDict(
|
||||
populate_by_name=True,
|
||||
extra="forbid",
|
||||
)
|
||||
|
||||
name: str = Field(
|
||||
description="Step name used to reference this step's output.",
|
||||
examples=["clean"],
|
||||
)
|
||||
if_: str | None = Field(
|
||||
default=None,
|
||||
alias="if",
|
||||
description=(
|
||||
"Optional CEL expression evaluated against state, outputs, and local "
|
||||
"context. When present, the step runs only if the expression evaluates "
|
||||
"to true."
|
||||
),
|
||||
examples=["item.kind == 'invoice'"],
|
||||
)
|
||||
action: FlowAtomicActionDefinition = Field(
|
||||
description="Atomic action to run for this step.",
|
||||
examples=[{"call": "script", "code": "return item.strip()"}],
|
||||
)
|
||||
class FlowEachInnerActionDefinition(RootModel[dict[str, FlowInnerActionDefinition]]):
|
||||
"""One named action inside an ``each`` composite action."""
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _validate_step_name(self) -> FlowEachStepDefinition:
|
||||
_validate_step_name(self.name, field="each.do step names")
|
||||
def _validate_action_mapping(self) -> FlowEachInnerActionDefinition:
|
||||
if len(self.root) != 1:
|
||||
raise ValueError("each.do entries must be one-key mappings")
|
||||
_validate_step_name(self.name, field="each.do action names")
|
||||
return self
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
return next(iter(self.root))
|
||||
|
||||
@property
|
||||
def action(self) -> FlowInnerActionDefinition:
|
||||
return next(iter(self.root.values()))
|
||||
|
||||
|
||||
class FlowEachActionDefinition(BaseModel):
|
||||
"""A composite action that runs a sequential mini-pipeline for each item."""
|
||||
|
||||
model_config = ConfigDict(
|
||||
populate_by_name=True,
|
||||
extra="forbid",
|
||||
)
|
||||
model_config = ConfigDict(populate_by_name=True, extra="forbid")
|
||||
|
||||
call: Literal["each"] = Field(
|
||||
description=(
|
||||
"Action discriminator. Use each to run a sequence of actions for every "
|
||||
"item in an input list."
|
||||
),
|
||||
examples=["each"],
|
||||
)
|
||||
in_: str = Field(
|
||||
alias="in",
|
||||
description="CEL expression that must evaluate to the list to iterate.",
|
||||
examples=["state.rows"],
|
||||
)
|
||||
do: list[FlowEachStepDefinition] = Field(
|
||||
description=(
|
||||
"Ordered steps to run for each item. Each step has a name, optional "
|
||||
"if expression, and atomic action."
|
||||
),
|
||||
examples=[
|
||||
[
|
||||
{
|
||||
"name": "clean",
|
||||
"action": {"call": "script", "code": "return item.strip()"},
|
||||
},
|
||||
{
|
||||
"name": "tag",
|
||||
"if": "outputs.clean != ''",
|
||||
"action": {"call": "expression", "expr": "outputs.clean"},
|
||||
},
|
||||
]
|
||||
],
|
||||
)
|
||||
call: TypingLiteral["each"]
|
||||
in_: str = Field(alias="in")
|
||||
do: list[FlowEachInnerActionDefinition]
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _validate_step_list(self) -> FlowEachActionDefinition:
|
||||
def _validate_inner_action_list(self) -> FlowEachActionDefinition:
|
||||
if not self.do:
|
||||
raise ValueError("each.do must contain at least one step")
|
||||
raise ValueError("each.do must contain at least one action")
|
||||
|
||||
seen: set[str] = set()
|
||||
for inner_action in self.do:
|
||||
name = inner_action.name
|
||||
if name in seen:
|
||||
raise ValueError(f"each.do action names must be unique: {name!r}")
|
||||
seen.add(name)
|
||||
|
||||
_validate_step_list(self.do, field="each.do")
|
||||
return self
|
||||
|
||||
|
||||
FlowActionDefinition: TypeAlias = (
|
||||
FlowActionDefinition = (
|
||||
FlowCodeActionDefinition
|
||||
| FlowToolActionDefinition
|
||||
| FlowCrewActionDefinition
|
||||
| FlowAgentActionDefinition
|
||||
| FlowExpressionActionDefinition
|
||||
| FlowScriptActionDefinition
|
||||
| FlowEachActionDefinition
|
||||
)
|
||||
|
||||
@@ -612,48 +364,14 @@ FlowActionDefinition: TypeAlias = (
|
||||
class FlowMethodDefinition(BaseModel):
|
||||
"""Static definition of one Flow method and its execution roles."""
|
||||
|
||||
description: str | None = Field(
|
||||
default=None,
|
||||
description="Human-readable summary of what this method does.",
|
||||
examples=["Normalize the incoming topic."],
|
||||
)
|
||||
do: FlowActionDefinition = Field(
|
||||
description="Action executed when this method runs.",
|
||||
examples=[{"call": "script", "code": "return input.strip()"}],
|
||||
)
|
||||
start: bool | FlowDefinitionCondition | None = Field(
|
||||
default=None,
|
||||
description=(
|
||||
"Marks a start method. True starts unconditionally; a condition starts "
|
||||
"when the kickoff inputs or events satisfy it."
|
||||
),
|
||||
examples=[True],
|
||||
)
|
||||
listen: FlowDefinitionCondition | None = Field(
|
||||
default=None,
|
||||
description="Trigger condition that runs this method after upstream events.",
|
||||
examples=["seed", {"or": ["approved", "revise"]}],
|
||||
)
|
||||
router: bool = Field(
|
||||
default=False,
|
||||
description="Whether the method output should be treated as the next event name.",
|
||||
examples=[True],
|
||||
)
|
||||
emit: list[str] | None = Field(
|
||||
default=None,
|
||||
description="Declared router events this method may emit.",
|
||||
examples=[["approved", "revise"]],
|
||||
)
|
||||
human_feedback: FlowHumanFeedbackDefinition | None = Field(
|
||||
default=None,
|
||||
description="Optional human feedback step applied after the method action.",
|
||||
examples=[{"message": "Review the research summary before publishing."}],
|
||||
)
|
||||
persist: FlowPersistenceDefinition | None = Field(
|
||||
default=None,
|
||||
description="Method-level persistence override.",
|
||||
examples=[{"enabled": True}],
|
||||
)
|
||||
description: str | None = None
|
||||
do: FlowActionDefinition
|
||||
start: bool | FlowDefinitionCondition | None = None
|
||||
listen: FlowDefinitionCondition | None = None
|
||||
router: bool = False
|
||||
emit: list[str] | None = None
|
||||
human_feedback: FlowHumanFeedbackDefinition | None = None
|
||||
persist: FlowPersistenceDefinition | None = None
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _canonicalize_human_feedback_routing(self) -> FlowMethodDefinition:
|
||||
@@ -679,57 +397,19 @@ class FlowMethodDefinition(BaseModel):
|
||||
class FlowDefinition(BaseModel):
|
||||
"""Static, serializable definition of a Flow."""
|
||||
|
||||
model_config = ConfigDict(
|
||||
populate_by_name=True,
|
||||
arbitrary_types_allowed=True,
|
||||
)
|
||||
model_config = ConfigDict(populate_by_name=True, arbitrary_types_allowed=True)
|
||||
|
||||
schema_: Literal["crewai.flow/v1"] = Field(
|
||||
default="crewai.flow/v1",
|
||||
alias="schema",
|
||||
description="Flow Definition schema identifier and version.",
|
||||
examples=["crewai.flow/v1"],
|
||||
)
|
||||
name: str = Field(
|
||||
description="Unique flow name used in logs, events, and traces.",
|
||||
examples=["ResearchFlow"],
|
||||
)
|
||||
description: str | None = Field(
|
||||
default=None,
|
||||
description="Human-readable summary of the flow.",
|
||||
examples=["Normalize a topic and prepare it for research."],
|
||||
)
|
||||
state: FlowStateDefinition | None = Field(
|
||||
default=None,
|
||||
description="State contract for kickoff inputs and runtime state.",
|
||||
examples=[{"type": "dict", "default": {"topic": "AI agents"}}],
|
||||
)
|
||||
config: FlowConfigDefinition = Field(
|
||||
default_factory=FlowConfigDefinition,
|
||||
description="Serializable flow-level runtime configuration.",
|
||||
examples=[{"stream": True, "max_method_calls": 20}],
|
||||
)
|
||||
persist: FlowPersistenceDefinition | None = Field(
|
||||
default=None,
|
||||
description="Flow-level persistence configuration.",
|
||||
examples=[{"enabled": True}],
|
||||
)
|
||||
conversational: FlowConversationalDefinition | None = Field(
|
||||
default=None,
|
||||
description="Conversational flow configuration, when the flow supports chat.",
|
||||
)
|
||||
methods: dict[str, FlowMethodDefinition] = Field(
|
||||
default_factory=dict,
|
||||
description="Mapping of method names to method definitions.",
|
||||
examples=[
|
||||
{
|
||||
"seed": {
|
||||
"start": True,
|
||||
"do": {"call": "expression", "expr": "state.topic"},
|
||||
}
|
||||
}
|
||||
],
|
||||
schema_: TypingLiteral["crewai.flow/v1"] = Field(
|
||||
default="crewai.flow/v1", alias="schema"
|
||||
)
|
||||
name: str
|
||||
description: str | None = None
|
||||
state: FlowStateDefinition | None = None
|
||||
config: FlowConfigDefinition = Field(default_factory=FlowConfigDefinition)
|
||||
persist: FlowPersistenceDefinition | None = None
|
||||
conversational: FlowConversationalDefinition | None = None
|
||||
methods: dict[str, FlowMethodDefinition] = Field(default_factory=dict)
|
||||
diagnostics: list[FlowDefinitionDiagnostic] = Field(default_factory=list)
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _validate_method_names(self) -> FlowDefinition:
|
||||
@@ -737,16 +417,6 @@ class FlowDefinition(BaseModel):
|
||||
_validate_step_name(method_name, field="Flow method names")
|
||||
return self
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _validate_cel_expressions(self) -> FlowDefinition:
|
||||
for method_name, method in self.methods.items():
|
||||
_validate_action_cel(
|
||||
method.do,
|
||||
path=f"methods.{method_name}.do",
|
||||
allowed_roots=_BASE_CEL_ROOTS,
|
||||
)
|
||||
return self
|
||||
|
||||
def to_dict(self, *, exclude_none: bool = True) -> dict[str, Any]:
|
||||
"""Serialize the definition to a JSON/YAML-ready dictionary."""
|
||||
return self.model_dump(by_alias=True, exclude_none=exclude_none, mode="json")
|
||||
@@ -766,9 +436,13 @@ class FlowDefinition(BaseModel):
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: dict[str, Any]) -> FlowDefinition:
|
||||
"""Load a definition from a dictionary."""
|
||||
"""Load a definition from a dictionary and attach diagnostics."""
|
||||
serialized_diagnostics = _deserialize_diagnostics(data.get("diagnostics", []))
|
||||
definition = cls.model_validate(data)
|
||||
log_flow_definition_issues(definition)
|
||||
definition.diagnostics = _merge_diagnostics(
|
||||
serialized_diagnostics, definition.validate_contract()
|
||||
)
|
||||
definition.log_diagnostics()
|
||||
return definition
|
||||
|
||||
@classmethod
|
||||
@@ -789,153 +463,122 @@ class FlowDefinition(BaseModel):
|
||||
"""Return the JSON Schema for the Flow Definition contract."""
|
||||
return cls.model_json_schema(by_alias=True)
|
||||
|
||||
def validate_contract(self) -> list[FlowDefinitionDiagnostic]:
|
||||
"""Validate the static contract without rejecting dynamic routing."""
|
||||
diagnostics: list[FlowDefinitionDiagnostic] = []
|
||||
for method_name, method in self.methods.items():
|
||||
path = f"methods.{method_name}"
|
||||
if method.router and not method.is_start and method.listen is None:
|
||||
diagnostics.append(
|
||||
FlowDefinitionDiagnostic(
|
||||
code="router_without_trigger",
|
||||
severity="error",
|
||||
path=path,
|
||||
message="router: true requires either start or listen",
|
||||
)
|
||||
)
|
||||
if method.emit and not method.router:
|
||||
diagnostics.append(
|
||||
FlowDefinitionDiagnostic(
|
||||
code="emit_without_router",
|
||||
path=f"{path}.emit",
|
||||
message="emit is only used by routers to declare downstream events",
|
||||
)
|
||||
)
|
||||
if method.human_feedback:
|
||||
human_feedback_config = method.human_feedback
|
||||
if human_feedback_config.emit and not human_feedback_config.llm:
|
||||
diagnostics.append(
|
||||
FlowDefinitionDiagnostic(
|
||||
code="human_feedback_llm_required",
|
||||
severity="error",
|
||||
path=f"{path}.human_feedback.llm",
|
||||
message="llm is required when human_feedback.emit is set",
|
||||
)
|
||||
)
|
||||
if (
|
||||
human_feedback_config.default_outcome is not None
|
||||
and not human_feedback_config.emit
|
||||
):
|
||||
diagnostics.append(
|
||||
FlowDefinitionDiagnostic(
|
||||
code="human_feedback_default_requires_emit",
|
||||
severity="error",
|
||||
path=f"{path}.human_feedback.default_outcome",
|
||||
message="default_outcome requires human_feedback.emit",
|
||||
)
|
||||
)
|
||||
elif (
|
||||
human_feedback_config.default_outcome is not None
|
||||
and human_feedback_config.emit
|
||||
):
|
||||
if (
|
||||
human_feedback_config.default_outcome
|
||||
not in human_feedback_config.emit
|
||||
):
|
||||
diagnostics.append(
|
||||
FlowDefinitionDiagnostic(
|
||||
code="human_feedback_default_not_in_emit",
|
||||
severity="error",
|
||||
path=f"{path}.human_feedback.default_outcome",
|
||||
message="default_outcome must be one of human_feedback.emit",
|
||||
)
|
||||
)
|
||||
|
||||
return diagnostics
|
||||
|
||||
def with_diagnostics(self) -> FlowDefinition:
|
||||
"""Attach fresh diagnostics and return this definition."""
|
||||
self.diagnostics = self.validate_contract()
|
||||
self.log_diagnostics()
|
||||
return self
|
||||
|
||||
def log_diagnostics(self) -> None:
|
||||
"""Emit all attached diagnostics through the flow definition logger."""
|
||||
_log_flow_definition_diagnostics(self.name, self.diagnostics)
|
||||
|
||||
|
||||
def _log_flow_definition_diagnostics(
|
||||
definition_name: str,
|
||||
diagnostics: list[FlowDefinitionDiagnostic],
|
||||
) -> None:
|
||||
for diagnostic in diagnostics:
|
||||
level = logging.ERROR if diagnostic.severity == "error" else logging.WARNING
|
||||
path = f" at {diagnostic.path}" if diagnostic.path else ""
|
||||
logger.log(
|
||||
level,
|
||||
"Flow definition diagnostic for %s%s [%s]: %s",
|
||||
definition_name,
|
||||
path,
|
||||
diagnostic.code,
|
||||
diagnostic.message,
|
||||
)
|
||||
|
||||
|
||||
def _deserialize_diagnostics(value: Any) -> list[FlowDefinitionDiagnostic]:
|
||||
return [FlowDefinitionDiagnostic.model_validate(item) for item in value or []]
|
||||
|
||||
|
||||
def _validate_step_name(name: str, *, field: str) -> None:
|
||||
if not isinstance(name, str) or not _STEP_NAME_PATTERN.fullmatch(name):
|
||||
raise ValueError(f"{field} must match {_STEP_NAME_PATTERN.pattern}")
|
||||
|
||||
|
||||
def _validate_step_list(steps: list[FlowEachStepDefinition], *, field: str) -> None:
|
||||
seen: set[str] = set()
|
||||
for step in steps:
|
||||
name = step.name
|
||||
if name in seen:
|
||||
raise ValueError(f"{field} step names must be unique: {name!r}")
|
||||
seen.add(name)
|
||||
|
||||
|
||||
def _validate_action_cel(
|
||||
action: FlowActionDefinition,
|
||||
*,
|
||||
path: str,
|
||||
allowed_roots: frozenset[str],
|
||||
) -> None:
|
||||
from crewai.flow.expressions import Expression
|
||||
|
||||
if isinstance(action, FlowExpressionActionDefinition):
|
||||
Expression(action.expr).validate_expression(
|
||||
allowed_roots=allowed_roots, source=f"{path}.expr"
|
||||
)
|
||||
return
|
||||
|
||||
if isinstance(action, (FlowCodeActionDefinition, FlowToolActionDefinition)):
|
||||
if action.with_ is not None:
|
||||
Expression(action.with_).validate_template(
|
||||
allowed_roots=allowed_roots, source=f"{path}.with"
|
||||
def _merge_diagnostics(
|
||||
*diagnostic_groups: list[FlowDefinitionDiagnostic],
|
||||
) -> list[FlowDefinitionDiagnostic]:
|
||||
diagnostics: list[FlowDefinitionDiagnostic] = []
|
||||
seen: set[tuple[str, str, str | None, str]] = set()
|
||||
for group in diagnostic_groups:
|
||||
for diagnostic in group:
|
||||
key = (
|
||||
diagnostic.code,
|
||||
diagnostic.severity,
|
||||
diagnostic.path,
|
||||
diagnostic.message,
|
||||
)
|
||||
return
|
||||
|
||||
if isinstance(action, FlowCrewActionDefinition):
|
||||
Expression(cast(ExpressionData, action.with_.inputs)).validate_template(
|
||||
allowed_roots=allowed_roots,
|
||||
source=f"{path}.with.inputs",
|
||||
)
|
||||
return
|
||||
|
||||
if isinstance(action, FlowAgentActionDefinition):
|
||||
Expression(cast(ExpressionData, action.with_.input)).validate_template(
|
||||
allowed_roots=allowed_roots,
|
||||
source=f"{path}.with.input",
|
||||
)
|
||||
return
|
||||
|
||||
if isinstance(action, FlowEachActionDefinition):
|
||||
Expression(action.in_).validate_expression(
|
||||
allowed_roots=_BASE_CEL_ROOTS,
|
||||
source=f"{path}.in",
|
||||
)
|
||||
for index, step in enumerate(action.do):
|
||||
step_path = f"{path}.do[{index}]"
|
||||
if step.if_ is not None:
|
||||
Expression(step.if_).validate_expression(
|
||||
allowed_roots=_EACH_STEP_CEL_ROOTS,
|
||||
source=f"{step_path}.if",
|
||||
)
|
||||
_validate_action_cel(
|
||||
step.action,
|
||||
path=f"{step_path}.action",
|
||||
allowed_roots=_EACH_STEP_CEL_ROOTS,
|
||||
)
|
||||
return
|
||||
|
||||
if isinstance(action, FlowScriptActionDefinition):
|
||||
return
|
||||
|
||||
raise TypeError(
|
||||
f"no CEL validation defined for action type {type(action).__name__} at "
|
||||
f"{path}; add a branch to _validate_action_cel for it."
|
||||
)
|
||||
|
||||
|
||||
def log_flow_definition_issues(definition: FlowDefinition) -> None:
|
||||
for method_name, method in definition.methods.items():
|
||||
path = f"methods.{method_name}"
|
||||
if method.router and not method.is_start and method.listen is None:
|
||||
_log_flow_definition_issue(
|
||||
definition.name,
|
||||
code="router_without_trigger",
|
||||
severity="error",
|
||||
path=path,
|
||||
message="router: true requires either start or listen",
|
||||
)
|
||||
if method.emit and not method.router:
|
||||
_log_flow_definition_issue(
|
||||
definition.name,
|
||||
code="emit_without_router",
|
||||
path=f"{path}.emit",
|
||||
message="emit is only used by routers to declare downstream events",
|
||||
)
|
||||
if method.human_feedback:
|
||||
human_feedback_config = method.human_feedback
|
||||
if human_feedback_config.emit and not human_feedback_config.llm:
|
||||
_log_flow_definition_issue(
|
||||
definition.name,
|
||||
code="human_feedback_llm_required",
|
||||
severity="error",
|
||||
path=f"{path}.human_feedback.llm",
|
||||
message="llm is required when human_feedback.emit is set",
|
||||
)
|
||||
if (
|
||||
human_feedback_config.default_outcome is not None
|
||||
and not human_feedback_config.emit
|
||||
):
|
||||
_log_flow_definition_issue(
|
||||
definition.name,
|
||||
code="human_feedback_default_requires_emit",
|
||||
severity="error",
|
||||
path=f"{path}.human_feedback.default_outcome",
|
||||
message="default_outcome requires human_feedback.emit",
|
||||
)
|
||||
elif (
|
||||
human_feedback_config.default_outcome is not None
|
||||
and human_feedback_config.emit
|
||||
and human_feedback_config.default_outcome
|
||||
not in human_feedback_config.emit
|
||||
):
|
||||
_log_flow_definition_issue(
|
||||
definition.name,
|
||||
code="human_feedback_default_not_in_emit",
|
||||
severity="error",
|
||||
path=f"{path}.human_feedback.default_outcome",
|
||||
message="default_outcome must be one of human_feedback.emit",
|
||||
)
|
||||
|
||||
|
||||
def _log_flow_definition_issue(
|
||||
definition_name: str,
|
||||
*,
|
||||
code: str,
|
||||
message: str,
|
||||
severity: Literal["warning", "error"] = "warning",
|
||||
path: str | None = None,
|
||||
) -> None:
|
||||
level = logging.ERROR if severity == "error" else logging.WARNING
|
||||
location = f" at {path}" if path else ""
|
||||
logger.log(
|
||||
level,
|
||||
"Flow definition issue for %s%s [%s]: %s",
|
||||
definition_name,
|
||||
location,
|
||||
code,
|
||||
message,
|
||||
)
|
||||
if key in seen:
|
||||
continue
|
||||
seen.add(key)
|
||||
diagnostics.append(diagnostic)
|
||||
return diagnostics
|
||||
|
||||
@@ -121,7 +121,7 @@ from crewai.flow.human_feedback import (
|
||||
)
|
||||
from crewai.flow.input_provider import InputProvider
|
||||
from crewai.flow.persistence.base import FlowPersistence
|
||||
from crewai.flow.runtime._actions import FlowScriptExecutionDisabledError, build_action
|
||||
from crewai.flow.runtime._actions import build_action
|
||||
from crewai.flow.runtime._refs import resolve_instance_ref, resolve_ref
|
||||
from crewai.flow.types import (
|
||||
FlowExecutionData,
|
||||
@@ -1090,8 +1090,6 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
|
||||
def build(name: str, definition: FlowMethodDefinition) -> Callable[..., Any]:
|
||||
try:
|
||||
return build_action(self, definition.do)
|
||||
except FlowScriptExecutionDisabledError:
|
||||
raise
|
||||
except Exception as e:
|
||||
unresolved.append(f"{name}: {e}")
|
||||
return lambda *args, **kwargs: None
|
||||
|
||||
@@ -2,27 +2,22 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import ast
|
||||
import asyncio
|
||||
from collections.abc import Awaitable, Callable
|
||||
from collections.abc import Callable
|
||||
import contextvars
|
||||
import inspect
|
||||
import os
|
||||
from typing import TYPE_CHECKING, Any, Protocol, cast
|
||||
|
||||
from crewai.flow.expressions import Expression, ExpressionData
|
||||
from crewai.flow.flow_definition import (
|
||||
FlowActionDefinition,
|
||||
FlowAgentActionDefinition,
|
||||
FlowCodeActionDefinition,
|
||||
FlowCrewActionDefinition,
|
||||
FlowEachActionDefinition,
|
||||
FlowEachStepDefinition,
|
||||
FlowEachInnerActionDefinition,
|
||||
FlowExpressionActionDefinition,
|
||||
FlowScriptActionDefinition,
|
||||
FlowToolActionDefinition,
|
||||
)
|
||||
from crewai.flow.runtime._outputs import outputs_by_name
|
||||
from crewai.flow.runtime._expressions import evaluate_expression, render_with_block
|
||||
from crewai.flow.runtime._refs import InvalidRefError, resolve_ref
|
||||
|
||||
|
||||
@@ -30,18 +25,10 @@ if TYPE_CHECKING:
|
||||
from crewai.flow.runtime import Flow
|
||||
|
||||
|
||||
__all__ = ["FlowScriptExecutionDisabledError", "build_action"]
|
||||
__all__ = ["build_action"]
|
||||
|
||||
LocalContext = dict[str, Any]
|
||||
NestedStepRunner = Callable[[LocalContext], Awaitable[Any]]
|
||||
NestedStep = tuple[str, str | None, NestedStepRunner]
|
||||
_LOCAL_CONTEXT_KWARG = "__flow_definition_local_context"
|
||||
_ALLOW_SCRIPT_EXECUTION_ENV_VAR = "CREWAI_ALLOW_FLOW_SCRIPT_EXECUTION"
|
||||
_TRUSTED_SCRIPT_EXECUTION_VALUES = frozenset({"1", "true", "yes"})
|
||||
|
||||
|
||||
class FlowScriptExecutionDisabledError(RuntimeError):
|
||||
"""Raised when a flow definition tries to execute inline script code."""
|
||||
|
||||
|
||||
class _BuiltAction(Protocol):
|
||||
@@ -68,9 +55,9 @@ class CodeAction:
|
||||
if self.definition.with_ is None:
|
||||
return self.handler(*args, **kwargs)
|
||||
return self.handler(
|
||||
**Expression.from_flow(
|
||||
self.definition.with_, self.flow, local_context=local_context
|
||||
).render_template()
|
||||
**render_with_block(
|
||||
self.flow, self.definition.with_, local_context=local_context
|
||||
)
|
||||
)
|
||||
|
||||
def _resolve_handler(self) -> Callable[..., Any]:
|
||||
@@ -96,9 +83,7 @@ class ToolAction:
|
||||
def run(self, *_args: Any, **kwargs: Any) -> Any:
|
||||
local_context = _pop_local_context(kwargs)
|
||||
return self.tool.run(
|
||||
**Expression.from_flow(
|
||||
self.kwargs, self.flow, local_context=local_context
|
||||
).render_template()
|
||||
**render_with_block(self.flow, self.kwargs, local_context=local_context)
|
||||
)
|
||||
|
||||
def _build_tool(self) -> Any:
|
||||
@@ -132,44 +117,13 @@ class CrewAction:
|
||||
|
||||
local_context = _pop_local_context(kwargs)
|
||||
crew_definition = self.definition.with_
|
||||
inputs = Expression.from_flow(
|
||||
cast(ExpressionData, crew_definition.inputs),
|
||||
self.flow,
|
||||
local_context=local_context,
|
||||
).render_template()
|
||||
inputs = render_with_block(
|
||||
self.flow, crew_definition.inputs, local_context=local_context
|
||||
)
|
||||
crew, _ = load_crew_from_definition(crew_definition, source="crew action")
|
||||
return await crew.kickoff_async(inputs=inputs)
|
||||
|
||||
|
||||
class AgentAction:
|
||||
definition_type = FlowAgentActionDefinition
|
||||
|
||||
def __init__(self, flow: Flow[Any], definition: FlowAgentActionDefinition) -> None:
|
||||
self.flow = flow
|
||||
self.definition = definition
|
||||
|
||||
async def run(self, *_args: Any, **kwargs: Any) -> Any:
|
||||
from crewai.project.json_loader import load_agent_from_definition
|
||||
|
||||
local_context = _pop_local_context(kwargs)
|
||||
rendered_input = Expression.from_flow(
|
||||
cast(ExpressionData, self.definition.with_.input),
|
||||
self.flow,
|
||||
local_context=local_context,
|
||||
).render_template()
|
||||
if not isinstance(rendered_input, str):
|
||||
raise ValueError("agent input must render to a string")
|
||||
|
||||
agent, response_format = load_agent_from_definition(
|
||||
self.definition.with_,
|
||||
source="agent action",
|
||||
)
|
||||
return await agent.kickoff_async(
|
||||
rendered_input,
|
||||
response_format=response_format,
|
||||
)
|
||||
|
||||
|
||||
class ExpressionAction:
|
||||
definition_type = FlowExpressionActionDefinition
|
||||
|
||||
@@ -181,71 +135,10 @@ class ExpressionAction:
|
||||
|
||||
def run(self, *_args: Any, **kwargs: Any) -> Any:
|
||||
local_context = _pop_local_context(kwargs)
|
||||
return Expression.from_flow(
|
||||
self.definition.expr, self.flow, local_context=local_context
|
||||
).evaluate()
|
||||
|
||||
|
||||
class ScriptAction:
|
||||
definition_type = FlowScriptActionDefinition
|
||||
|
||||
def __init__(self, flow: Flow[Any], definition: FlowScriptActionDefinition) -> None:
|
||||
self.flow = flow
|
||||
self.definition = definition
|
||||
self.handler = self._compile_handler()
|
||||
|
||||
def run(self, *args: Any, **kwargs: Any) -> Any:
|
||||
local_context = _pop_local_context(kwargs)
|
||||
return self.handler(
|
||||
state=self.flow.state,
|
||||
outputs=outputs_by_name(
|
||||
self.flow._method_outputs,
|
||||
local_outputs=local_context.get("outputs") if local_context else None,
|
||||
),
|
||||
input=args[0] if args else None,
|
||||
item=local_context.get("item") if local_context else None,
|
||||
return evaluate_expression(
|
||||
self.flow, self.definition.expr, local_context=local_context
|
||||
)
|
||||
|
||||
def _compile_handler(self) -> Callable[..., Any]:
|
||||
raw = os.environ.get(_ALLOW_SCRIPT_EXECUTION_ENV_VAR, "")
|
||||
if raw.strip().lower() not in _TRUSTED_SCRIPT_EXECUTION_VALUES:
|
||||
raise FlowScriptExecutionDisabledError(
|
||||
"Flow script execution is disabled by default. "
|
||||
f"Set {_ALLOW_SCRIPT_EXECUTION_ENV_VAR}=1 to enable it only for "
|
||||
"trusted flow definitions."
|
||||
)
|
||||
|
||||
filename = f"crewai.flow.script.{self.flow._definition.name}"
|
||||
module = ast.parse(self.definition.code, filename=filename)
|
||||
function = ast.FunctionDef(
|
||||
name="_flow_script",
|
||||
args=ast.arguments(
|
||||
posonlyargs=[],
|
||||
args=[ast.arg(arg) for arg in ("state", "outputs", "input", "item")],
|
||||
vararg=None,
|
||||
kwonlyargs=[],
|
||||
kw_defaults=[],
|
||||
kwarg=None,
|
||||
defaults=[],
|
||||
),
|
||||
body=module.body or [ast.Pass()],
|
||||
decorator_list=[],
|
||||
returns=None,
|
||||
type_comment=None,
|
||||
type_params=[],
|
||||
)
|
||||
module.body = [function]
|
||||
ast.fix_missing_locations(module)
|
||||
|
||||
# The YAML here is trusted project source authored by the code owner,
|
||||
# so this has the same trust boundary as using custom tools. We
|
||||
# intentionally do not interpolate user input and runtime values are passed
|
||||
# as function arguments. This is still arbitrary trusted Python execution,
|
||||
# so it remains disabled by default behind `CREWAI_ALLOW_FLOW_SCRIPT_EXECUTION`
|
||||
namespace: dict[str, Any] = {"__name__": filename}
|
||||
exec(compile(module, filename, "exec"), namespace) # nosec B102 # noqa: S102
|
||||
return cast(Callable[..., Any], namespace["_flow_script"])
|
||||
|
||||
|
||||
class EachAction:
|
||||
definition_type = FlowEachActionDefinition
|
||||
@@ -253,13 +146,13 @@ class EachAction:
|
||||
def __init__(self, flow: Flow[Any], definition: FlowEachActionDefinition) -> None:
|
||||
self.flow = flow
|
||||
self.definition = definition
|
||||
self.steps: list[NestedStep] = [
|
||||
(step.name, step.if_, self._build_step_action(step))
|
||||
for step in definition.do
|
||||
self.inner_actions = [
|
||||
(inner_action.name, self._build_inner_action(inner_action))
|
||||
for inner_action in definition.do
|
||||
]
|
||||
|
||||
async def run(self, *_args: Any, **_kwargs: Any) -> list[Any]:
|
||||
items = Expression.from_flow(self.definition.in_, self.flow).evaluate()
|
||||
items = evaluate_expression(self.flow, self.definition.in_)
|
||||
if not isinstance(items, list):
|
||||
raise ValueError("each.in must evaluate to an array")
|
||||
|
||||
@@ -267,32 +160,22 @@ class EachAction:
|
||||
|
||||
for item in items:
|
||||
local_outputs: dict[str, Any] = {}
|
||||
local_context = {"item": item, "outputs": local_outputs}
|
||||
last_output: Any = None
|
||||
for name, condition, run_step_action in self.steps:
|
||||
if condition is not None and not self._condition_matches(
|
||||
condition, local_context
|
||||
):
|
||||
continue
|
||||
|
||||
last_output = await run_step_action(local_context)
|
||||
for name, run_inner_action in self.inner_actions:
|
||||
last_output = await run_inner_action(
|
||||
{"item": item, "outputs": local_outputs}
|
||||
)
|
||||
local_outputs[name] = last_output
|
||||
results.append(last_output)
|
||||
|
||||
return results
|
||||
|
||||
def _condition_matches(self, condition: str, local_context: LocalContext) -> bool:
|
||||
result = Expression.from_flow(
|
||||
condition, self.flow, local_context=local_context
|
||||
).evaluate()
|
||||
if not isinstance(result, bool):
|
||||
raise ValueError("if expression must evaluate to a boolean")
|
||||
return result
|
||||
def _build_inner_action(
|
||||
self, inner_action: FlowEachInnerActionDefinition
|
||||
) -> Callable[[LocalContext], Any]:
|
||||
run_action = build_action(self.flow, inner_action.action)
|
||||
|
||||
def _build_step_action(self, step: FlowEachStepDefinition) -> NestedStepRunner:
|
||||
run_action = build_action(self.flow, step.action)
|
||||
|
||||
async def run_step_action(local_context: LocalContext) -> Any:
|
||||
async def run_inner_action(local_context: LocalContext) -> Any:
|
||||
kwargs = {_LOCAL_CONTEXT_KWARG: local_context}
|
||||
if inspect.iscoroutinefunction(run_action):
|
||||
result = run_action(**kwargs)
|
||||
@@ -307,17 +190,15 @@ class EachAction:
|
||||
result = await result
|
||||
return result
|
||||
|
||||
return run_step_action
|
||||
return run_inner_action
|
||||
|
||||
|
||||
_ACTION_TYPES: tuple[_ActionType, ...] = (
|
||||
EachAction,
|
||||
CodeAction,
|
||||
ToolAction,
|
||||
AgentAction,
|
||||
CrewAction,
|
||||
ExpressionAction,
|
||||
ScriptAction,
|
||||
)
|
||||
|
||||
|
||||
|
||||
157
lib/crewai/src/crewai/flow/runtime/_expressions.py
Normal file
157
lib/crewai/src/crewai/flow/runtime/_expressions.py
Normal file
@@ -0,0 +1,157 @@
|
||||
"""Runtime expression support for FlowDefinition CEL expressions."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from itertools import pairwise
|
||||
import json
|
||||
import re
|
||||
from typing import TYPE_CHECKING, Any, cast
|
||||
|
||||
from crewai.utilities.serialization import to_serializable
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from crewai.flow.runtime import Flow
|
||||
|
||||
|
||||
_EXPRESSION_PATTERN = re.compile(r"\$\{([^{}]*)\}")
|
||||
|
||||
__all__ = ["FlowExpressionError", "evaluate_expression", "render_with_block"]
|
||||
|
||||
|
||||
class FlowExpressionError(ValueError):
|
||||
"""A FlowDefinition expression failed to parse or evaluate."""
|
||||
|
||||
|
||||
def render_with_block(
|
||||
flow: Flow[Any], value: Any, local_context: dict[str, Any] | None = None
|
||||
) -> Any:
|
||||
"""Render CEL expressions inside a FlowDefinition ``with:`` payload."""
|
||||
context = _expression_context(flow, local_context=local_context)
|
||||
return _render_value(value, context)
|
||||
|
||||
|
||||
def evaluate_expression(
|
||||
flow: Flow[Any], expression: str, local_context: dict[str, Any] | None = None
|
||||
) -> Any:
|
||||
"""Evaluate a FlowDefinition CEL expression against runtime context."""
|
||||
expression = expression.strip()
|
||||
if not expression:
|
||||
raise FlowExpressionError("empty CEL expression")
|
||||
return _eval_cel(expression, _expression_context(flow, local_context=local_context))
|
||||
|
||||
|
||||
def _expression_context(
|
||||
flow: Flow[Any], local_context: dict[str, Any] | None = None
|
||||
) -> dict[str, Any]:
|
||||
outputs = _outputs_by_name(flow._method_outputs)
|
||||
context: dict[str, Any] = {
|
||||
"state": flow._copy_and_serialize_state(),
|
||||
"outputs": outputs,
|
||||
}
|
||||
if local_context:
|
||||
local_values = {
|
||||
key: to_serializable(value, max_depth=0)
|
||||
for key, value in local_context.items()
|
||||
}
|
||||
local_outputs = local_values.pop("outputs", None)
|
||||
local_values.pop("state", None)
|
||||
context.update(local_values)
|
||||
if local_outputs is not None:
|
||||
if not isinstance(local_outputs, dict):
|
||||
raise TypeError("flow definition local outputs must be a mapping")
|
||||
context["outputs"] = {**outputs, **local_outputs}
|
||||
return context
|
||||
|
||||
|
||||
def _outputs_by_name(method_outputs: list[Any]) -> dict[str, Any]:
|
||||
outputs: dict[str, Any] = {}
|
||||
for entry in method_outputs:
|
||||
method = ""
|
||||
output = entry
|
||||
if isinstance(entry, dict) and "output" in entry:
|
||||
method = str(entry.get("method", ""))
|
||||
output = entry["output"]
|
||||
outputs[method] = to_serializable(output, max_depth=0)
|
||||
return outputs
|
||||
|
||||
|
||||
def _render_value(value: Any, context: dict[str, Any]) -> Any:
|
||||
if isinstance(value, str):
|
||||
return _render_string(value, context)
|
||||
if isinstance(value, dict):
|
||||
return {key: _render_value(item, context) for key, item in value.items()}
|
||||
if isinstance(value, list):
|
||||
return [_render_value(item, context) for item in value]
|
||||
return value
|
||||
|
||||
|
||||
def _render_string(value: str, context: dict[str, Any]) -> Any:
|
||||
matches = list(_EXPRESSION_PATTERN.finditer(value))
|
||||
if not matches:
|
||||
_raise_for_invalid_interpolation(value)
|
||||
return value
|
||||
|
||||
_raise_for_literal_braces(value[: matches[0].start()])
|
||||
for previous, current in pairwise(matches):
|
||||
_raise_for_literal_braces(value[previous.end() : current.start()])
|
||||
_raise_for_literal_braces(value[matches[-1].end() :])
|
||||
|
||||
if len(matches) == 1 and matches[0].span() == (0, len(value)):
|
||||
expression = matches[0].group(1).strip()
|
||||
if not expression:
|
||||
raise FlowExpressionError("empty CEL expression in with block")
|
||||
return _eval_cel(expression, context)
|
||||
|
||||
rendered: list[str] = []
|
||||
position = 0
|
||||
for match in matches:
|
||||
start, end = match.span()
|
||||
literal = value[position:start]
|
||||
rendered.append(literal)
|
||||
|
||||
expression = match.group(1).strip()
|
||||
if not expression:
|
||||
raise FlowExpressionError("empty CEL expression in with block")
|
||||
result = _eval_cel(expression, context)
|
||||
rendered.append(result if isinstance(result, str) else json.dumps(result))
|
||||
position = end
|
||||
|
||||
literal = value[position:]
|
||||
rendered.append(literal)
|
||||
|
||||
return "".join(rendered)
|
||||
|
||||
|
||||
def _raise_for_invalid_interpolation(value: str) -> None:
|
||||
if "${" not in value:
|
||||
return
|
||||
raise FlowExpressionError(
|
||||
"invalid CEL interpolation in with block: expressions must be enclosed "
|
||||
"as ${...} and cannot contain braces"
|
||||
)
|
||||
|
||||
|
||||
def _raise_for_literal_braces(value: str) -> None:
|
||||
if "{" not in value and "}" not in value:
|
||||
return
|
||||
raise FlowExpressionError(
|
||||
"invalid CEL interpolation in with block: expressions must be enclosed "
|
||||
"as ${...} and cannot contain braces"
|
||||
)
|
||||
|
||||
|
||||
def _eval_cel(expression: str, context: dict[str, Any]) -> Any:
|
||||
try:
|
||||
from celpy import Environment
|
||||
from celpy.adapter import CELJSONEncoder, json_to_cel
|
||||
from celpy.evaluation import Context
|
||||
|
||||
environment = Environment()
|
||||
program = environment.program(environment.compile(expression))
|
||||
result = program.evaluate(cast(Context, json_to_cel(context)))
|
||||
return json.loads(json.dumps(result, cls=CELJSONEncoder))
|
||||
except Exception as e:
|
||||
raise FlowExpressionError(
|
||||
f"failed to evaluate CEL expression {expression!r}: {e}"
|
||||
) from e
|
||||
@@ -1,40 +0,0 @@
|
||||
"""Shared FlowDefinition runtime output helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Mapping
|
||||
from typing import Any, TypedDict
|
||||
|
||||
from crewai.utilities.serialization import to_serializable
|
||||
|
||||
|
||||
class _MethodOutput(TypedDict):
|
||||
method: str
|
||||
output: Any
|
||||
|
||||
|
||||
def outputs_by_name(
|
||||
method_outputs: list[_MethodOutput],
|
||||
*,
|
||||
local_outputs: Mapping[str, Any] | None = None,
|
||||
serialize: bool = False,
|
||||
) -> dict[str, Any]:
|
||||
outputs: dict[str, Any] = {}
|
||||
for entry in method_outputs:
|
||||
outputs[entry["method"]] = _output_value(entry["output"], serialize=serialize)
|
||||
|
||||
if local_outputs is not None:
|
||||
outputs.update(
|
||||
{
|
||||
key: _output_value(output, serialize=serialize)
|
||||
for key, output in local_outputs.items()
|
||||
}
|
||||
)
|
||||
|
||||
return outputs
|
||||
|
||||
|
||||
def _output_value(value: Any, *, serialize: bool) -> Any:
|
||||
if not serialize:
|
||||
return value
|
||||
return to_serializable(value, max_depth=0)
|
||||
@@ -3,9 +3,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from concurrent.futures import Future, ThreadPoolExecutor
|
||||
from contextlib import suppress
|
||||
import contextvars
|
||||
import copy
|
||||
from datetime import datetime
|
||||
import threading
|
||||
import time
|
||||
@@ -55,24 +53,6 @@ def _default_embedder() -> OpenAIEmbeddingFunction:
|
||||
return build_embedder(spec)
|
||||
|
||||
|
||||
def _non_streaming_analysis_llm(llm: Any) -> Any:
|
||||
"""Return an isolated non-streaming LLM for internal memory analysis."""
|
||||
if not isinstance(llm, BaseLLM):
|
||||
return llm
|
||||
|
||||
try:
|
||||
analysis_llm = copy.copy(llm)
|
||||
except Exception:
|
||||
try:
|
||||
analysis_llm = llm.model_copy(deep=False)
|
||||
except Exception:
|
||||
return llm
|
||||
|
||||
with suppress(Exception):
|
||||
analysis_llm.stream = False
|
||||
return analysis_llm
|
||||
|
||||
|
||||
class Memory(BaseModel):
|
||||
"""Unified memory: standalone, LLM-analyzed, with intelligent recall flow.
|
||||
|
||||
@@ -220,9 +200,7 @@ class Memory(BaseModel):
|
||||
query_analysis_threshold=self.query_analysis_threshold,
|
||||
)
|
||||
|
||||
self._llm_instance = (
|
||||
None if isinstance(self.llm, str) else _non_streaming_analysis_llm(self.llm)
|
||||
)
|
||||
self._llm_instance = None if isinstance(self.llm, str) else self.llm
|
||||
self._embedder_instance = (
|
||||
self.embedder
|
||||
if (self.embedder is not None and not isinstance(self.embedder, dict))
|
||||
|
||||
@@ -15,22 +15,16 @@ from crewai.project.annotations import (
|
||||
)
|
||||
from crewai.project.crew_base import CrewBase
|
||||
from crewai.project.crew_definition import (
|
||||
AgentDefinition,
|
||||
CrewAgentDefinition,
|
||||
CrewDefinition,
|
||||
CrewTaskDefinition,
|
||||
PythonReferenceDefinition,
|
||||
)
|
||||
from crewai.project.crew_loader import load_crew, load_crew_and_kickoff
|
||||
from crewai.project.json_loader import (
|
||||
load_agent,
|
||||
load_agent_from_definition,
|
||||
strip_jsonc_comments,
|
||||
)
|
||||
from crewai.project.json_loader import load_agent, strip_jsonc_comments
|
||||
|
||||
|
||||
__all__ = [
|
||||
"AgentDefinition",
|
||||
"CrewAgentDefinition",
|
||||
"CrewBase",
|
||||
"CrewDefinition",
|
||||
@@ -44,7 +38,6 @@ __all__ = [
|
||||
"crew",
|
||||
"llm",
|
||||
"load_agent",
|
||||
"load_agent_from_definition",
|
||||
"load_crew",
|
||||
"load_crew_and_kickoff",
|
||||
"output_json",
|
||||
|
||||
@@ -8,7 +8,6 @@ from pydantic import BaseModel, ConfigDict, Field, field_validator, model_valida
|
||||
|
||||
|
||||
__all__ = [
|
||||
"AgentDefinition",
|
||||
"CrewAgentDefinition",
|
||||
"CrewDefinition",
|
||||
"CrewTaskDefinition",
|
||||
@@ -54,20 +53,6 @@ class CrewAgentDefinition(BaseModel):
|
||||
return value or {}
|
||||
|
||||
|
||||
class AgentDefinition(CrewAgentDefinition):
|
||||
"""Inline agent definition used by a Flow agent action."""
|
||||
|
||||
input: str
|
||||
response_format: PythonReferenceDefinition | None = None
|
||||
|
||||
@field_validator("input", mode="before")
|
||||
@classmethod
|
||||
def _validate_input(cls, value: Any) -> Any:
|
||||
if not isinstance(value, str):
|
||||
raise ValueError("agent.input must be a string")
|
||||
return value
|
||||
|
||||
|
||||
class CrewTaskDefinition(BaseModel):
|
||||
"""Task definition used by a crew definition."""
|
||||
|
||||
|
||||
@@ -207,18 +207,19 @@ def load_jsonc_file(source: str | Path) -> Any:
|
||||
return parse_jsonc(path.read_text(encoding="utf-8"), source=path)
|
||||
|
||||
|
||||
def _instantiate_agent_from_data(
|
||||
defn: dict[str, Any], source_label: str, root: Path
|
||||
) -> Any:
|
||||
"""Resolve the agent class and kwargs from definition data and instantiate it."""
|
||||
def load_agent(source: str | Path) -> Any:
|
||||
"""Load an existing ``Agent`` from a ``.json`` / ``.jsonc`` definition file."""
|
||||
path = Path(source)
|
||||
defn = _expect_object(load_jsonc_file(path), path)
|
||||
root = path.parent.parent if path.parent.name == "agents" else path.parent
|
||||
agent_class = _agent_class_from_definition(
|
||||
defn,
|
||||
f"{source_label}: type",
|
||||
f"{path}: type",
|
||||
project_root=root,
|
||||
)
|
||||
agent_kwargs = _agent_kwargs_from_definition(
|
||||
defn,
|
||||
source_label,
|
||||
path,
|
||||
agent_class=agent_class,
|
||||
project_root=root,
|
||||
)
|
||||
@@ -226,50 +227,9 @@ def _instantiate_agent_from_data(
|
||||
try:
|
||||
return agent_class(**agent_kwargs)
|
||||
except ValidationError as exc:
|
||||
raise JSONProjectError(_format_validation_error(source_label, exc)) from exc
|
||||
raise JSONProjectError(_format_validation_error(path, exc)) from exc
|
||||
except Exception as exc:
|
||||
raise JSONProjectError(f"{source_label}: failed to load agent: {exc}") from exc
|
||||
|
||||
|
||||
def load_agent(source: str | Path) -> Any:
|
||||
"""Load an existing ``Agent`` from a ``.json`` / ``.jsonc`` definition file."""
|
||||
path = Path(source)
|
||||
defn = _expect_object(load_jsonc_file(path), path)
|
||||
root = path.parent.parent if path.parent.name == "agents" else path.parent
|
||||
return _instantiate_agent_from_data(defn, str(path), root)
|
||||
|
||||
|
||||
def load_agent_from_definition(
|
||||
definition: dict[str, Any] | Any,
|
||||
*,
|
||||
source: str | Path = "<inline agent>",
|
||||
project_root: str | Path | None = None,
|
||||
) -> tuple[Any, type[BaseModel] | None]:
|
||||
"""Load an ``Agent`` and optional kickoff response model from an inline definition."""
|
||||
from crewai.project.crew_definition import AgentDefinition
|
||||
|
||||
root = Path(project_root) if project_root is not None else Path.cwd()
|
||||
source_label = str(source)
|
||||
agent_definition = (
|
||||
definition
|
||||
if isinstance(definition, AgentDefinition)
|
||||
else AgentDefinition.model_validate(definition)
|
||||
)
|
||||
definition_data = agent_definition.model_dump(mode="python", exclude_none=True)
|
||||
response_format_ref = definition_data.pop("response_format", None)
|
||||
definition_data.pop("input", None)
|
||||
|
||||
agent = _instantiate_agent_from_data(definition_data, source_label, root)
|
||||
|
||||
response_format = None
|
||||
if response_format_ref is not None:
|
||||
response_format = _resolve_model_class(
|
||||
response_format_ref,
|
||||
f"{source_label}: response_format",
|
||||
root,
|
||||
)
|
||||
|
||||
return agent, response_format
|
||||
raise JSONProjectError(f"{path}: failed to load agent: {exc}") from exc
|
||||
|
||||
|
||||
def validate_crew_project(
|
||||
|
||||
@@ -1,136 +0,0 @@
|
||||
"""Regression tests for path-traversal-safe archive extraction in the cache.
|
||||
|
||||
Guards against symlink/hardlink-based path traversal in the Python < 3.12
|
||||
extraction fallback (`_safe_extractall`) used by `SkillCacheManager.store`.
|
||||
The 3.12+ path relies on `tarfile.extractall(..., filter="data")`; the
|
||||
fallback must provide the same protection by validating link targets, not
|
||||
just member names.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import tarfile
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from crewai.experimental.skills.cache import _safe_extractall
|
||||
|
||||
|
||||
def _tar_from_members(build) -> tarfile.TarFile:
|
||||
"""Build an in-memory tar archive via `build(tf)` and return it for reading."""
|
||||
buf = io.BytesIO()
|
||||
with tarfile.open(fileobj=buf, mode="w") as tf:
|
||||
build(tf)
|
||||
buf.seek(0)
|
||||
return tarfile.open(fileobj=buf, mode="r")
|
||||
|
||||
|
||||
def test_blocks_symlink_escaping_destination(tmp_path: Path) -> None:
|
||||
"""A symlink whose target escapes dest, plus a file written through it,
|
||||
must be rejected before anything is extracted."""
|
||||
outside = tmp_path / "outside"
|
||||
outside.mkdir()
|
||||
dest = tmp_path / "dest"
|
||||
dest.mkdir()
|
||||
|
||||
def build(tf: tarfile.TarFile) -> None:
|
||||
link = tarfile.TarInfo("link")
|
||||
link.type = tarfile.SYMTYPE
|
||||
link.linkname = str(outside) # absolute path outside dest
|
||||
tf.addfile(link)
|
||||
payload = b"pwned"
|
||||
info = tarfile.TarInfo("link/evil.txt")
|
||||
info.size = len(payload)
|
||||
tf.addfile(info, io.BytesIO(payload))
|
||||
|
||||
with _tar_from_members(build) as tf:
|
||||
with pytest.raises(ValueError, match="escaping destination"):
|
||||
_safe_extractall(tf, dest)
|
||||
|
||||
assert not (outside / "evil.txt").exists()
|
||||
|
||||
|
||||
def test_blocks_relative_symlink_escaping_destination(tmp_path: Path) -> None:
|
||||
"""A relative symlink (../..) that escapes dest is also rejected."""
|
||||
dest = tmp_path / "dest"
|
||||
dest.mkdir()
|
||||
|
||||
def build(tf: tarfile.TarFile) -> None:
|
||||
link = tarfile.TarInfo("sub/link")
|
||||
link.type = tarfile.SYMTYPE
|
||||
link.linkname = "../../outside" # escapes dest from sub/
|
||||
tf.addfile(link)
|
||||
|
||||
with _tar_from_members(build) as tf:
|
||||
with pytest.raises(ValueError, match="escaping destination"):
|
||||
_safe_extractall(tf, dest)
|
||||
|
||||
|
||||
def test_allows_benign_relative_symlink(tmp_path: Path) -> None:
|
||||
"""A symlink that stays within dest is permitted."""
|
||||
dest = tmp_path / "dest"
|
||||
dest.mkdir()
|
||||
|
||||
def build(tf: tarfile.TarFile) -> None:
|
||||
payload = b"hi"
|
||||
info = tarfile.TarInfo("real.txt")
|
||||
info.size = len(payload)
|
||||
tf.addfile(info, io.BytesIO(payload))
|
||||
link = tarfile.TarInfo("alias.txt")
|
||||
link.type = tarfile.SYMTYPE
|
||||
link.linkname = "real.txt" # stays inside dest
|
||||
tf.addfile(link)
|
||||
|
||||
with _tar_from_members(build) as tf:
|
||||
_safe_extractall(tf, dest)
|
||||
|
||||
assert (dest / "real.txt").read_bytes() == b"hi"
|
||||
|
||||
|
||||
def test_allows_benign_archive(tmp_path: Path) -> None:
|
||||
"""An ordinary archive of regular files extracts correctly."""
|
||||
dest = tmp_path / "dest"
|
||||
dest.mkdir()
|
||||
|
||||
def build(tf: tarfile.TarFile) -> None:
|
||||
for name, body in (("SKILL.md", b"# skill"), ("scripts/run.py", b"print(1)")):
|
||||
payload = body
|
||||
info = tarfile.TarInfo(name)
|
||||
info.size = len(payload)
|
||||
tf.addfile(info, io.BytesIO(payload))
|
||||
|
||||
with _tar_from_members(build) as tf:
|
||||
_safe_extractall(tf, dest)
|
||||
|
||||
assert (dest / "SKILL.md").read_bytes() == b"# skill"
|
||||
assert (dest / "scripts" / "run.py").read_bytes() == b"print(1)"
|
||||
|
||||
|
||||
def test_blocks_hardlink_escaping_destination(tmp_path: Path) -> None:
|
||||
"""A hardlink whose target escapes dest must be rejected."""
|
||||
outside = tmp_path / "outside"
|
||||
outside.mkdir()
|
||||
victim = outside / "victim.txt"
|
||||
victim.write_bytes(b"safe")
|
||||
|
||||
dest = tmp_path / "dest"
|
||||
dest.mkdir()
|
||||
|
||||
def build(tf: tarfile.TarFile) -> None:
|
||||
link = tarfile.TarInfo("victim.txt")
|
||||
link.type = tarfile.LNKTYPE
|
||||
link.linkname = str(victim) # absolute path outside dest
|
||||
tf.addfile(link)
|
||||
|
||||
payload = b"pwned"
|
||||
info = tarfile.TarInfo("victim.txt")
|
||||
info.size = len(payload)
|
||||
tf.addfile(info, io.BytesIO(payload))
|
||||
|
||||
with _tar_from_members(build) as tf:
|
||||
with pytest.raises(ValueError, match="escaping destination"):
|
||||
_safe_extractall(tf, dest)
|
||||
|
||||
assert victim.read_bytes() == b"safe"
|
||||
@@ -19,39 +19,6 @@ from crewai.memory.types import (
|
||||
)
|
||||
|
||||
|
||||
def test_memory_analysis_llm_is_isolated_from_streaming_agent_llm(
|
||||
tmp_path: Path,
|
||||
) -> None:
|
||||
"""Memory analysis should not share a mutable streaming LLM with the agent UI."""
|
||||
from crewai.llms.base_llm import BaseLLM
|
||||
from crewai.memory.unified_memory import Memory
|
||||
from crewai.utilities.types import LLMMessage
|
||||
|
||||
class FakeStreamingLLM(BaseLLM):
|
||||
def call(
|
||||
self,
|
||||
messages: str | list[LLMMessage],
|
||||
tools: list[dict] | None = None,
|
||||
callbacks: list | None = None,
|
||||
available_functions: dict | None = None,
|
||||
from_task: object | None = None,
|
||||
from_agent: object | None = None,
|
||||
response_model: type | None = None,
|
||||
) -> str:
|
||||
return ""
|
||||
|
||||
agent_llm = FakeStreamingLLM(model="fake-model", stream=True)
|
||||
mem = Memory(
|
||||
storage=str(tmp_path / "db"),
|
||||
llm=agent_llm,
|
||||
embedder=lambda texts: [[0.1] for _ in texts],
|
||||
)
|
||||
|
||||
assert mem._llm is not agent_llm
|
||||
assert mem._llm.stream is False
|
||||
|
||||
agent_llm.stream = True
|
||||
assert mem._llm.stream is False
|
||||
|
||||
|
||||
def test_memory_record_defaults() -> None:
|
||||
|
||||
@@ -7,7 +7,6 @@ from pathlib import Path
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
from pydantic import BaseModel
|
||||
|
||||
from crewai.llms.base_llm import BaseLLM
|
||||
from crewai.project.json_loader import (
|
||||
@@ -15,7 +14,6 @@ from crewai.project.json_loader import (
|
||||
_looks_like_windows_absolute_path,
|
||||
find_json_project_file,
|
||||
load_agent,
|
||||
load_agent_from_definition,
|
||||
strip_jsonc_comments,
|
||||
)
|
||||
|
||||
@@ -360,30 +358,6 @@ class TestLoadAgent:
|
||||
load_agent(Path("/nonexistent/agent.json"))
|
||||
|
||||
|
||||
class TestLoadAgentFromDefinition:
|
||||
def test_resolves_response_format_from_project_module(self, tmp_path: Path):
|
||||
(tmp_path / "models.py").write_text(
|
||||
"from pydantic import BaseModel\n"
|
||||
"class AnswerModel(BaseModel):\n"
|
||||
" answer: str\n"
|
||||
)
|
||||
|
||||
_, response_format = load_agent_from_definition(
|
||||
{
|
||||
"role": "Analyst",
|
||||
"goal": "Analyze data",
|
||||
"backstory": "Data expert.",
|
||||
"input": "Summarize this",
|
||||
"response_format": {"python": "models.AnswerModel"},
|
||||
},
|
||||
source="agent action",
|
||||
project_root=tmp_path,
|
||||
)
|
||||
|
||||
assert issubclass(response_format, BaseModel)
|
||||
assert response_format.__name__ == "AnswerModel"
|
||||
|
||||
|
||||
class TestResolveTools:
|
||||
def test_unknown_tool_raises_with_guidance(self):
|
||||
from crewai.project.json_loader import JSONProjectError, _resolve_tools
|
||||
|
||||
@@ -631,7 +631,7 @@ class TestLegacyMethodOutputsRestore:
|
||||
assert restored.method_outputs == ["first", "second"]
|
||||
|
||||
def test_restore_legacy_outputs_evaluates_expressions(self) -> None:
|
||||
from crewai.flow.expressions import Expression
|
||||
from crewai.flow.runtime._expressions import _expression_context
|
||||
|
||||
flow = Flow()
|
||||
flow._method_outputs = ["legacy"]
|
||||
@@ -642,14 +642,17 @@ class TestLegacyMethodOutputsRestore:
|
||||
cfg = CheckpointConfig(restore_from=loc)
|
||||
restored = Flow.from_checkpoint(cfg)
|
||||
|
||||
context = Expression._flow_context(restored)
|
||||
context = _expression_context(restored)
|
||||
assert context["outputs"] == {"": "legacy"}
|
||||
|
||||
def test_raw_legacy_outputs_property_remains_readable(self) -> None:
|
||||
def test_raw_legacy_outputs_remain_readable(self) -> None:
|
||||
from crewai.flow.runtime._expressions import _expression_context
|
||||
|
||||
flow = Flow()
|
||||
flow._method_outputs = ["legacy"]
|
||||
|
||||
assert flow.method_outputs == ["legacy"]
|
||||
assert _expression_context(flow)["outputs"] == {"": "legacy"}
|
||||
|
||||
|
||||
class TestAgentCheckpoint:
|
||||
|
||||
@@ -37,8 +37,6 @@ def test_flow_public_exports_are_explicit():
|
||||
}
|
||||
assert set(flow_definition.__all__) == {
|
||||
"FlowActionDefinition",
|
||||
"FlowAgentActionDefinition",
|
||||
"FlowAtomicActionDefinition",
|
||||
"FlowCodeActionDefinition",
|
||||
"FlowConfigDefinition",
|
||||
"FlowConversationalDefinition",
|
||||
@@ -46,16 +44,16 @@ def test_flow_public_exports_are_explicit():
|
||||
"FlowCrewActionDefinition",
|
||||
"FlowDefinition",
|
||||
"FlowDefinitionCondition",
|
||||
"FlowDefinitionDiagnostic",
|
||||
"FlowDictStateDefinition",
|
||||
"FlowEachActionDefinition",
|
||||
"FlowEachStepDefinition",
|
||||
"FlowEachInnerActionDefinition",
|
||||
"FlowExpressionActionDefinition",
|
||||
"FlowHumanFeedbackDefinition",
|
||||
"FlowJsonSchemaStateDefinition",
|
||||
"FlowMethodDefinition",
|
||||
"FlowPersistenceDefinition",
|
||||
"FlowPydanticStateDefinition",
|
||||
"FlowScriptActionDefinition",
|
||||
"FlowStateDefinition",
|
||||
"FlowToolActionDefinition",
|
||||
"FlowUnknownStateDefinition",
|
||||
@@ -64,126 +62,6 @@ def test_flow_public_exports_are_explicit():
|
||||
assert "calculate_node_levels" not in flow_visualization.__all__
|
||||
|
||||
|
||||
def test_flow_definition_json_schema_carries_reference_descriptions():
|
||||
schema = flow_definition.FlowDefinition.json_schema()
|
||||
defs = schema["$defs"]
|
||||
|
||||
assert schema["properties"]["schema"]["description"]
|
||||
assert schema["properties"]["methods"]["description"]
|
||||
assert "diagnostics" not in schema["properties"]
|
||||
|
||||
method_properties = defs["FlowMethodDefinition"]["properties"]
|
||||
assert method_properties["do"]["description"] == "Action executed when this method runs."
|
||||
assert "Trigger condition" in method_properties["listen"]["description"]
|
||||
|
||||
script_properties = defs["FlowScriptActionDefinition"]["properties"]
|
||||
assert "trusted inline Python" in script_properties["call"]["description"]
|
||||
assert "not interpolated" in script_properties["code"]["description"]
|
||||
assert "not sandboxed" in script_properties["code"]["description"]
|
||||
|
||||
agent_properties = defs["FlowAgentActionDefinition"]["properties"]
|
||||
assert "Inline Agent definition" in agent_properties["with"]["description"]
|
||||
assert "run an inline Agent" in agent_properties["call"]["description"]
|
||||
|
||||
state_schema = next(
|
||||
branch
|
||||
for branch in schema["properties"]["state"]["anyOf"]
|
||||
if "discriminator" in branch
|
||||
)
|
||||
assert state_schema["discriminator"]["propertyName"] == "type"
|
||||
assert state_schema["discriminator"]["mapping"] == {
|
||||
"dict": "#/$defs/FlowDictStateDefinition",
|
||||
"json_schema": "#/$defs/FlowJsonSchemaStateDefinition",
|
||||
"pydantic": "#/$defs/FlowPydanticStateDefinition",
|
||||
"unknown": "#/$defs/FlowUnknownStateDefinition",
|
||||
}
|
||||
|
||||
dict_state_properties = defs["FlowDictStateDefinition"]["properties"]
|
||||
assert dict_state_properties["type"]["description"]
|
||||
assert "ref" not in dict_state_properties
|
||||
|
||||
json_schema_state_properties = defs["FlowJsonSchemaStateDefinition"]["properties"]
|
||||
assert json_schema_state_properties["json_schema"]["description"]
|
||||
assert "json_schema" in defs["FlowJsonSchemaStateDefinition"]["required"]
|
||||
|
||||
pydantic_state_properties = defs["FlowPydanticStateDefinition"]["properties"]
|
||||
assert "Fallback JSON Schema" in pydantic_state_properties["json_schema"][
|
||||
"description"
|
||||
]
|
||||
|
||||
each_properties = defs["FlowEachActionDefinition"]["properties"]
|
||||
assert "list to iterate" in each_properties["in"]["description"]
|
||||
assert "Ordered steps" in each_properties["do"]["description"]
|
||||
|
||||
step_properties = defs["FlowEachStepDefinition"]["properties"]
|
||||
assert "runs only if" in step_properties["if"]["description"]
|
||||
|
||||
|
||||
def test_flow_definition_json_schema_carries_field_examples_only():
|
||||
schema = flow_definition.FlowDefinition.json_schema()
|
||||
defs = schema["$defs"]
|
||||
|
||||
for model_name in [
|
||||
"FlowDefinition",
|
||||
"FlowCodeActionDefinition",
|
||||
"FlowToolActionDefinition",
|
||||
"FlowAgentActionDefinition",
|
||||
"FlowCrewActionDefinition",
|
||||
"FlowExpressionActionDefinition",
|
||||
"FlowScriptActionDefinition",
|
||||
"FlowEachActionDefinition",
|
||||
"FlowEachStepDefinition",
|
||||
"FlowMethodDefinition",
|
||||
"FlowDictStateDefinition",
|
||||
"FlowJsonSchemaStateDefinition",
|
||||
"FlowPydanticStateDefinition",
|
||||
"FlowUnknownStateDefinition",
|
||||
"FlowConfigDefinition",
|
||||
"FlowPersistenceDefinition",
|
||||
"FlowHumanFeedbackDefinition",
|
||||
]:
|
||||
model_schema = schema if model_name == "FlowDefinition" else defs[model_name]
|
||||
assert "examples" not in model_schema
|
||||
|
||||
assert schema["properties"]["name"]["examples"] == ["ResearchFlow"]
|
||||
assert schema["properties"]["schema"]["examples"] == ["crewai.flow/v1"]
|
||||
assert schema["properties"]["methods"]["examples"][0]["seed"]["do"] == {
|
||||
"call": "expression",
|
||||
"expr": "state.topic",
|
||||
}
|
||||
|
||||
script_properties = defs["FlowScriptActionDefinition"]["properties"]
|
||||
assert script_properties["call"]["examples"] == ["script"]
|
||||
assert "input.strip()" in script_properties["code"]["examples"][0]
|
||||
assert script_properties["language"]["examples"] == ["python"]
|
||||
|
||||
action_properties = defs["FlowCodeActionDefinition"]["properties"]
|
||||
assert action_properties["ref"]["examples"] == [
|
||||
"my_project.flows:normalize_topic"
|
||||
]
|
||||
assert action_properties["with"]["examples"] == [{"topic": "${state.topic}"}]
|
||||
|
||||
agent_properties = defs["FlowAgentActionDefinition"]["properties"]
|
||||
assert agent_properties["call"]["examples"] == ["agent"]
|
||||
assert agent_properties["with"]["examples"][0]["input"] == "${state.question}"
|
||||
|
||||
each_properties = defs["FlowEachActionDefinition"]["properties"]
|
||||
assert each_properties["in"]["examples"] == ["state.rows"]
|
||||
assert each_properties["do"]["examples"][0][0]["name"] == "clean"
|
||||
assert each_properties["do"]["examples"][0][0]["action"]["call"] == "script"
|
||||
assert each_properties["do"]["examples"][0][1]["if"] == "outputs.clean != ''"
|
||||
|
||||
step_properties = defs["FlowEachStepDefinition"]["properties"]
|
||||
assert step_properties["if"]["examples"] == ["item.kind == 'invoice'"]
|
||||
|
||||
method_properties = defs["FlowMethodDefinition"]["properties"]
|
||||
assert method_properties["listen"]["examples"] == [
|
||||
"seed",
|
||||
{"or": ["approved", "revise"]},
|
||||
]
|
||||
assert method_properties["emit"]["examples"] == [["approved", "revise"]]
|
||||
|
||||
|
||||
def test_flow_state_definition_uses_discriminated_branches():
|
||||
definition = flow_definition.FlowDefinition.model_validate(
|
||||
{
|
||||
@@ -355,7 +233,7 @@ def test_flow_definition_maps_dsl_to_static_contract():
|
||||
assert review.human_feedback.learn_strict is True
|
||||
|
||||
assert definition.methods["audit"].listen == {"and": ["begin", "process"]}
|
||||
assert "diagnostics" not in definition.to_dict()
|
||||
assert definition.diagnostics == []
|
||||
|
||||
|
||||
def test_flow_definition_excludes_conversational_builtins_for_regular_flows():
|
||||
@@ -437,8 +315,7 @@ def test_flow_definition_uses_collapsed_conversational_router_start():
|
||||
assert methods["route_conversation"].router is True
|
||||
|
||||
|
||||
def test_flow_definition_serializes_human_feedback_metadata(caplog):
|
||||
caplog.set_level(logging.WARNING, logger="crewai.flow.dsl._utils")
|
||||
def test_flow_definition_serializes_human_feedback_metadata():
|
||||
marker = object()
|
||||
|
||||
class MetadataFlow(Flow):
|
||||
@@ -457,9 +334,9 @@ def test_flow_definition_serializes_human_feedback_metadata(caplog):
|
||||
assert review.human_feedback is not None
|
||||
assert review.human_feedback.metadata == {"ref": "builtins:dict"}
|
||||
assert any(
|
||||
"methods.review.human_feedback.metadata" in record.message
|
||||
and "not fully serializable" in record.message
|
||||
for record in caplog.records
|
||||
diagnostic.code == "non_serializable_value"
|
||||
and diagnostic.path == "methods.review.human_feedback.metadata"
|
||||
for diagnostic in definition.diagnostics
|
||||
)
|
||||
definition.to_json()
|
||||
|
||||
@@ -604,16 +481,14 @@ def test_each_action_round_trips_json_and_yaml():
|
||||
"in": "state.rows",
|
||||
"do": [
|
||||
{
|
||||
"name": "normalize",
|
||||
"action": {
|
||||
"normalize": {
|
||||
"call": "tool",
|
||||
"ref": "my_tools:NormalizeRowTool",
|
||||
"with": {"row": "${ item }"},
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "save",
|
||||
"action": {
|
||||
"save": {
|
||||
"call": "code",
|
||||
"ref": "my_flow:save_row",
|
||||
"with": {
|
||||
@@ -700,6 +575,7 @@ def test_flow_definition_allows_dynamic_router_emit():
|
||||
definition = DynamicRouterFlow.flow_definition()
|
||||
|
||||
assert definition.methods["decide"].emit is None
|
||||
assert definition.diagnostics == []
|
||||
|
||||
|
||||
def test_flow_definition_infers_literal_router_emit():
|
||||
@@ -852,15 +728,16 @@ def test_flow_definition_accepts_explicit_router_events():
|
||||
assert definition.methods["decide"].emit == ["left", "right"]
|
||||
|
||||
|
||||
def test_flow_definition_ignores_legacy_diagnostics_loaded_from_contract():
|
||||
def test_flow_definition_preserves_diagnostics_loaded_from_contract():
|
||||
definition = flow_definition.FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
"name": "LoadedDiagnosticsFlow",
|
||||
"methods": {
|
||||
"begin": {
|
||||
"do": {"ref": "loaded_flows:LoadedDiagnosticsFlow.begin"},
|
||||
"start": True,
|
||||
"decision": {
|
||||
"do": {"ref": "loaded_flows:LoadedDiagnosticsFlow.decision"},
|
||||
"router": True,
|
||||
"emit": ["continue"],
|
||||
}
|
||||
},
|
||||
"diagnostics": [
|
||||
@@ -880,13 +757,13 @@ def test_flow_definition_ignores_legacy_diagnostics_loaded_from_contract():
|
||||
}
|
||||
)
|
||||
|
||||
assert "diagnostics" not in definition.to_dict()
|
||||
codes = [diagnostic.code for diagnostic in definition.diagnostics]
|
||||
assert "serialized_warning" in codes
|
||||
assert codes.count("router_without_trigger") == 1
|
||||
|
||||
|
||||
def test_router_start_false_without_listen_logs_missing_trigger(caplog):
|
||||
caplog.set_level(logging.ERROR, logger="crewai.flow.flow_definition")
|
||||
|
||||
flow_definition.FlowDefinition.from_dict(
|
||||
def test_router_start_false_without_listen_reports_missing_trigger():
|
||||
definition = flow_definition.FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
"name": "LoadedFlow",
|
||||
@@ -902,10 +779,9 @@ def test_router_start_false_without_listen_logs_missing_trigger(caplog):
|
||||
)
|
||||
|
||||
assert any(
|
||||
record.levelno == logging.ERROR
|
||||
and "router_without_trigger" in record.message
|
||||
and "methods.decision" in record.message
|
||||
for record in caplog.records
|
||||
diagnostic.code == "router_without_trigger"
|
||||
and diagnostic.path == "methods.decision"
|
||||
for diagnostic in definition.diagnostics
|
||||
)
|
||||
|
||||
|
||||
@@ -933,7 +809,7 @@ def test_router_human_feedback_preserves_existing_router_metadata():
|
||||
assert method.human_feedback is not None
|
||||
|
||||
|
||||
def test_dynamic_router_flow_definition_allows_dynamic_emit():
|
||||
def test_dynamic_router_flow_definition_has_no_diagnostics():
|
||||
class LazyDynamicRouterFlow(Flow):
|
||||
@start()
|
||||
def begin(self):
|
||||
@@ -944,7 +820,7 @@ def test_dynamic_router_flow_definition_allows_dynamic_emit():
|
||||
return self.state["dynamic_event"]
|
||||
|
||||
definition = LazyDynamicRouterFlow.flow_definition()
|
||||
assert definition.methods["decide"].emit is None
|
||||
assert definition.diagnostics == []
|
||||
|
||||
|
||||
def test_dynamic_router_string_listener_is_valid_contract():
|
||||
@@ -963,7 +839,7 @@ def test_dynamic_router_string_listener_is_valid_contract():
|
||||
|
||||
definition = DynamicRouterListenerFlow.flow_definition()
|
||||
|
||||
assert definition.methods["handle"].listen == "dynamic_event"
|
||||
assert definition.diagnostics == []
|
||||
|
||||
|
||||
def test_static_string_listener_is_allowed_by_contract():
|
||||
@@ -983,7 +859,7 @@ def test_static_string_listener_is_allowed_by_contract():
|
||||
},
|
||||
}
|
||||
)
|
||||
assert definition.methods["handle"].listen == "begni"
|
||||
assert definition.diagnostics == []
|
||||
|
||||
|
||||
def test_start_false_not_classified_as_start_method():
|
||||
@@ -1048,10 +924,10 @@ def test_flow_definition_cache_is_not_reused_by_subclasses():
|
||||
assert set(child_definition.methods) == {"child_step"}
|
||||
|
||||
|
||||
def test_flow_definition_logs_validation_issues_when_loaded_from_contract(caplog):
|
||||
def test_flow_definition_logs_diagnostics_when_loaded_from_contract(caplog):
|
||||
caplog.set_level(logging.WARNING, logger="crewai.flow.flow_definition")
|
||||
|
||||
flow_definition.FlowDefinition.from_dict(
|
||||
definition = flow_definition.FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
"name": "LoadedFlow",
|
||||
@@ -1065,6 +941,10 @@ def test_flow_definition_logs_validation_issues_when_loaded_from_contract(caplog
|
||||
}
|
||||
)
|
||||
|
||||
assert any(
|
||||
diagnostic.code == "router_without_trigger"
|
||||
for diagnostic in definition.diagnostics
|
||||
)
|
||||
assert any(
|
||||
record.levelno == logging.ERROR
|
||||
and "LoadedFlow" in record.message
|
||||
|
||||
@@ -26,7 +26,6 @@ from crewai.flow.flow_config import flow_config
|
||||
from crewai.flow.flow_definition import FlowConfigDefinition, FlowDefinition
|
||||
from crewai.flow.persistence import persist
|
||||
from crewai.flow.persistence.base import FlowPersistence
|
||||
from crewai.flow.runtime._actions import FlowScriptExecutionDisabledError
|
||||
from crewai.state.checkpoint_config import CheckpointConfig
|
||||
from crewai.tools import BaseTool
|
||||
from crewai.types.streaming import FlowStreamingOutput
|
||||
@@ -114,7 +113,7 @@ class EachActionFlow(Flow):
|
||||
except RuntimeError:
|
||||
pass
|
||||
else:
|
||||
raise RuntimeError("each step ran on the event loop")
|
||||
raise RuntimeError("inner action ran on the event loop")
|
||||
|
||||
from crewai.flow.flow_context import current_flow_method_name
|
||||
|
||||
@@ -644,7 +643,7 @@ methods:
|
||||
assert flow.kickoff(inputs={"topic": "ai"}) == "found:ai agents"
|
||||
|
||||
|
||||
def test_tool_action_treats_embedded_cel_marker_as_literal():
|
||||
def test_tool_action_rejects_braces_in_embedded_cel_input():
|
||||
definition = FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
@@ -660,62 +659,16 @@ def test_tool_action_treats_embedded_cel_marker_as_literal():
|
||||
"prefix": "${'p}x'}",
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
assert Flow.from_definition(definition).kickoff() == "p}x:wrapped ${'a}b'} value"
|
||||
with pytest.raises(ValueError, match="cannot contain braces"):
|
||||
Flow.from_definition(definition).kickoff()
|
||||
|
||||
|
||||
def test_tool_action_treats_marker_with_trailing_text_as_literal():
|
||||
definition = FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
"name": "ToolFlow",
|
||||
"methods": {
|
||||
"search": {
|
||||
"start": True,
|
||||
"do": {
|
||||
"call": "tool",
|
||||
"ref": f"{__name__}:StaticSearchTool",
|
||||
"with": {
|
||||
"search_query": "${state.topic} extra",
|
||||
"prefix": "p",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
assert Flow.from_definition(definition).kickoff() == "p:${state.topic} extra"
|
||||
|
||||
|
||||
def test_tool_action_rejects_adjacent_markers_as_invalid_cel():
|
||||
with pytest.raises(ValidationError, match="invalid CEL expression"):
|
||||
FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
"name": "ToolFlow",
|
||||
"methods": {
|
||||
"search": {
|
||||
"start": True,
|
||||
"do": {
|
||||
"call": "tool",
|
||||
"ref": f"{__name__}:StaticSearchTool",
|
||||
"with": {
|
||||
"search_query": "${'a'}${'b'}",
|
||||
"prefix": "p",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def test_tool_action_accepts_braces_in_full_cel_marker():
|
||||
def test_tool_action_rejects_braces_in_full_cel_input():
|
||||
definition = FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
@@ -728,15 +681,16 @@ def test_tool_action_accepts_braces_in_full_cel_marker():
|
||||
"ref": f"{__name__}:StaticSearchTool",
|
||||
"with": {
|
||||
"search_query": "${{'query': 'ai agents'}.query}",
|
||||
"prefix": "${'p}x'}",
|
||||
"prefix": "found",
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
assert Flow.from_definition(definition).kickoff() == "p}x:ai agents"
|
||||
with pytest.raises(ValueError, match="cannot contain braces"):
|
||||
Flow.from_definition(definition).kickoff()
|
||||
|
||||
|
||||
def test_tool_action_renders_latest_output_by_method_name():
|
||||
@@ -811,166 +765,6 @@ methods:
|
||||
)
|
||||
|
||||
|
||||
def test_agent_action_runs_inline_yaml_definition(monkeypatch: pytest.MonkeyPatch):
|
||||
from crewai import Agent
|
||||
|
||||
async def fake_kickoff_async(
|
||||
self: Agent, messages: str, **_kwargs: Any
|
||||
) -> dict[str, Any]:
|
||||
return {"agent": self.role, "input": messages}
|
||||
|
||||
monkeypatch.setattr(Agent, "kickoff_async", fake_kickoff_async)
|
||||
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: AgentFlow
|
||||
methods:
|
||||
answer:
|
||||
do:
|
||||
call: agent
|
||||
with:
|
||||
role: Analyst
|
||||
goal: Answer questions
|
||||
backstory: Knows things.
|
||||
input: "${state.question}"
|
||||
start: true
|
||||
"""
|
||||
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
assert flow.kickoff(inputs={"question": "What is CrewAI?"}) == {
|
||||
"agent": "Analyst",
|
||||
"input": "What is CrewAI?",
|
||||
}
|
||||
|
||||
|
||||
def test_agent_action_runs_inside_each(monkeypatch: pytest.MonkeyPatch):
|
||||
from crewai import Agent
|
||||
|
||||
async def fake_kickoff_async(
|
||||
self: Agent, messages: str, **_kwargs: Any
|
||||
) -> str:
|
||||
return f"{self.role}:{messages}"
|
||||
|
||||
monkeypatch.setattr(Agent, "kickoff_async", fake_kickoff_async)
|
||||
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: AgentEachFlow
|
||||
methods:
|
||||
answer_each:
|
||||
do:
|
||||
call: each
|
||||
in: state.questions
|
||||
do:
|
||||
- name: answer
|
||||
action:
|
||||
call: agent
|
||||
with:
|
||||
role: Analyst
|
||||
goal: Answer questions
|
||||
backstory: Knows things.
|
||||
input: "${item}"
|
||||
start: true
|
||||
"""
|
||||
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
assert flow.kickoff(inputs={"questions": ["one", "two"]}) == [
|
||||
"Analyst:one",
|
||||
"Analyst:two",
|
||||
]
|
||||
|
||||
|
||||
def test_agent_action_round_trips_with_inline_definition():
|
||||
definition = FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
"name": "AgentFlow",
|
||||
"methods": {
|
||||
"answer": {
|
||||
"start": True,
|
||||
"do": {
|
||||
"call": "agent",
|
||||
"with": {
|
||||
"role": "Analyst",
|
||||
"goal": "Answer questions",
|
||||
"backstory": "Knows things.",
|
||||
"settings": {"verbose": True},
|
||||
"input": "${state.question}",
|
||||
},
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
round_trip = FlowDefinition.from_yaml(definition.to_yaml())
|
||||
action = round_trip.to_dict()["methods"]["answer"]["do"]
|
||||
|
||||
assert action["call"] == "agent"
|
||||
assert action["with"]["role"] == "Analyst"
|
||||
assert action["with"]["input"] == "${state.question}"
|
||||
assert action["with"]["settings"] == {"verbose": True}
|
||||
|
||||
|
||||
def test_agent_action_json_schema_describes_inline_agent_definitions():
|
||||
schema_defs = FlowDefinition.json_schema()["$defs"]
|
||||
|
||||
assert set(schema_defs["AgentDefinition"]["properties"]) >= {
|
||||
"role",
|
||||
"goal",
|
||||
"backstory",
|
||||
"settings",
|
||||
"input",
|
||||
"response_format",
|
||||
}
|
||||
|
||||
|
||||
def test_agent_action_rejects_non_string_input_in_definition():
|
||||
with pytest.raises(ValidationError, match="agent.input must be a string"):
|
||||
FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
"name": "AgentFlow",
|
||||
"methods": {
|
||||
"answer": {
|
||||
"start": True,
|
||||
"do": {
|
||||
"call": "agent",
|
||||
"with": {
|
||||
"role": "Analyst",
|
||||
"goal": "Answer questions",
|
||||
"backstory": "Knows things.",
|
||||
"input": 123,
|
||||
},
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def test_agent_action_reports_invalid_cel_expression():
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: AgentFlow
|
||||
methods:
|
||||
answer:
|
||||
do:
|
||||
call: agent
|
||||
with:
|
||||
role: Analyst
|
||||
goal: Answer questions
|
||||
backstory: Knows things.
|
||||
input: "${state.}"
|
||||
start: true
|
||||
"""
|
||||
|
||||
with pytest.raises(ValidationError, match="invalid CEL expression"):
|
||||
FlowDefinition.from_yaml(yaml_str)
|
||||
|
||||
|
||||
def test_crew_action_runs_inline_yaml_definition(monkeypatch: pytest.MonkeyPatch):
|
||||
from crewai import Crew
|
||||
|
||||
@@ -1231,8 +1025,10 @@ methods:
|
||||
start: true
|
||||
"""
|
||||
|
||||
with pytest.raises(ValidationError, match="invalid CEL expression"):
|
||||
FlowDefinition.from_yaml(yaml_str)
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
with pytest.raises(ValueError, match="failed to evaluate CEL expression"):
|
||||
flow.kickoff()
|
||||
|
||||
|
||||
def test_code_action_renders_keyword_inputs():
|
||||
@@ -1284,8 +1080,7 @@ methods:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: normalize
|
||||
action:
|
||||
- normalize:
|
||||
call: code
|
||||
ref: {__name__}:EachActionFlow.normalize_row
|
||||
with:
|
||||
@@ -1301,7 +1096,7 @@ methods:
|
||||
]
|
||||
|
||||
|
||||
def test_each_action_runs_sync_steps_off_event_loop_with_context():
|
||||
def test_each_action_runs_sync_inner_actions_off_event_loop_with_context():
|
||||
yaml_str = f"""
|
||||
schema: crewai.flow/v1
|
||||
name: EachFlow
|
||||
@@ -1311,8 +1106,7 @@ methods:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: threaded
|
||||
action:
|
||||
- threaded:
|
||||
call: code
|
||||
ref: {__name__}:EachActionFlow.require_threaded_context
|
||||
with:
|
||||
@@ -1328,7 +1122,7 @@ methods:
|
||||
assert flow.inner_thread_id != caller_thread_id
|
||||
|
||||
|
||||
def test_each_action_runs_async_tool_results_from_sync_steps():
|
||||
def test_each_action_runs_async_tool_results_from_sync_inner_actions():
|
||||
yaml_str = f"""
|
||||
schema: crewai.flow/v1
|
||||
name: EachFlow
|
||||
@@ -1338,8 +1132,7 @@ methods:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: async_tool
|
||||
action:
|
||||
- async_tool:
|
||||
call: tool
|
||||
ref: {__name__}:AsyncResultTool
|
||||
with:
|
||||
@@ -1352,120 +1145,7 @@ methods:
|
||||
assert flow.kickoff(inputs={"rows": ["a", "b"]}) == ["async:a", "async:b"]
|
||||
|
||||
|
||||
def test_script_action_requires_explicit_opt_in():
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: ScriptFlow
|
||||
methods:
|
||||
normalize:
|
||||
do:
|
||||
call: script
|
||||
code: |
|
||||
return "blocked"
|
||||
start: true
|
||||
"""
|
||||
|
||||
with pytest.raises(
|
||||
FlowScriptExecutionDisabledError,
|
||||
match="CREWAI_ALLOW_FLOW_SCRIPT_EXECUTION=1",
|
||||
) as exc_info:
|
||||
Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
assert "methods with unresolvable actions" not in str(exc_info.value)
|
||||
|
||||
|
||||
def test_script_action_runs_python_imports_mutates_state_and_returns_value(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
):
|
||||
monkeypatch.setenv("CREWAI_ALLOW_FLOW_SCRIPT_EXECUTION", "1")
|
||||
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: ScriptFlow
|
||||
methods:
|
||||
normalize:
|
||||
do:
|
||||
call: script
|
||||
code: |
|
||||
import math
|
||||
|
||||
state["rounded"] = math.ceil(state["raw_score"])
|
||||
return f"rounded:{state['rounded']}"
|
||||
start: true
|
||||
"""
|
||||
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
assert flow.kickoff(inputs={"raw_score": 3.2}) == "rounded:4"
|
||||
assert flow.state["rounded"] == 4
|
||||
|
||||
|
||||
def test_script_listener_reads_trigger_input_and_outputs(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
):
|
||||
monkeypatch.setenv("CREWAI_ALLOW_FLOW_SCRIPT_EXECUTION", "1")
|
||||
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: ScriptFlow
|
||||
methods:
|
||||
seed:
|
||||
do:
|
||||
call: expression
|
||||
expr: "'alpha'"
|
||||
start: true
|
||||
combine:
|
||||
do:
|
||||
call: script
|
||||
code: |
|
||||
state["input_matches_output"] = input == outputs["seed"]
|
||||
return f"{outputs['seed']}:{input}"
|
||||
listen: seed
|
||||
"""
|
||||
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
assert flow.kickoff() == "alpha:alpha"
|
||||
assert flow.state["input_matches_output"] is True
|
||||
|
||||
|
||||
def test_script_each_action_reads_item_and_step_outputs(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
):
|
||||
monkeypatch.setenv("CREWAI_ALLOW_FLOW_SCRIPT_EXECUTION", "1")
|
||||
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: ScriptEachFlow
|
||||
methods:
|
||||
seed:
|
||||
do:
|
||||
call: expression
|
||||
expr: "'global'"
|
||||
start: true
|
||||
process_rows:
|
||||
do:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: clean
|
||||
action:
|
||||
call: script
|
||||
code: |
|
||||
return item.strip()
|
||||
- name: tag
|
||||
action:
|
||||
call: script
|
||||
code: |
|
||||
return f"{outputs['seed']}:{outputs['clean']}"
|
||||
listen: seed
|
||||
"""
|
||||
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
assert flow.kickoff(inputs={"rows": [" a ", " b "]}) == ["global:a", "global:b"]
|
||||
|
||||
|
||||
def test_each_action_uses_iteration_outputs_between_steps():
|
||||
def test_each_action_uses_iteration_outputs_between_nested_actions():
|
||||
yaml_str = f"""
|
||||
schema: crewai.flow/v1
|
||||
name: EachFlow
|
||||
@@ -1475,15 +1155,13 @@ methods:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: normalize
|
||||
action:
|
||||
- normalize:
|
||||
call: code
|
||||
ref: {__name__}:EachActionFlow.normalize_row
|
||||
with:
|
||||
row: "${{item}}"
|
||||
prefix: saved
|
||||
- name: save
|
||||
action:
|
||||
- save:
|
||||
call: code
|
||||
ref: {__name__}:EachActionFlow.save_row
|
||||
with:
|
||||
@@ -1500,7 +1178,7 @@ methods:
|
||||
]
|
||||
|
||||
|
||||
def test_each_action_resets_step_outputs_between_iterations():
|
||||
def test_each_action_resets_inner_outputs_between_iterations():
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: EachFlow
|
||||
@@ -1510,12 +1188,10 @@ methods:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: leak_check
|
||||
action:
|
||||
- leak_check:
|
||||
call: expression
|
||||
expr: "has(outputs.previous) ? outputs.previous : 'empty'"
|
||||
- name: previous
|
||||
action:
|
||||
- previous:
|
||||
call: expression
|
||||
expr: item
|
||||
start: true
|
||||
@@ -1529,7 +1205,7 @@ methods:
|
||||
]
|
||||
|
||||
|
||||
def test_each_action_preserves_flow_outputs_and_prefers_step_outputs():
|
||||
def test_each_action_preserves_flow_outputs_and_prefers_inner_outputs():
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: EachFlow
|
||||
@@ -1544,16 +1220,13 @@ methods:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: before_shadow
|
||||
action:
|
||||
- before_shadow:
|
||||
call: expression
|
||||
expr: "outputs.seed + ':' + item"
|
||||
- name: seed
|
||||
action:
|
||||
- seed:
|
||||
call: expression
|
||||
expr: "'local:' + item"
|
||||
- name: after_shadow
|
||||
action:
|
||||
- after_shadow:
|
||||
call: expression
|
||||
expr: "outputs.seed"
|
||||
listen: seed
|
||||
@@ -1571,130 +1244,6 @@ methods:
|
||||
]
|
||||
|
||||
|
||||
def test_each_action_runs_simple_if_clauses():
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: EachIfFlow
|
||||
methods:
|
||||
process_rows:
|
||||
do:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: kind
|
||||
action:
|
||||
call: expression
|
||||
expr: item.kind
|
||||
- name: kept
|
||||
if: "outputs.kind == 'keep'"
|
||||
action:
|
||||
call: expression
|
||||
expr: "'kept:' + item.value"
|
||||
- name: skipped
|
||||
if: "outputs.kind != 'keep'"
|
||||
action:
|
||||
call: expression
|
||||
expr: "'skipped:' + item.value"
|
||||
start: true
|
||||
"""
|
||||
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
assert flow.kickoff(
|
||||
inputs={
|
||||
"rows": [
|
||||
{"kind": "keep", "value": "a"},
|
||||
{"kind": "drop", "value": "b"},
|
||||
]
|
||||
}
|
||||
) == ["kept:a", "skipped:b"]
|
||||
|
||||
|
||||
def test_each_action_accepts_expression_markers_in_explicit_cel_fields():
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: EachIfFlow
|
||||
methods:
|
||||
process_rows:
|
||||
do:
|
||||
call: each
|
||||
in: "${state.rows}"
|
||||
do:
|
||||
- name: kind
|
||||
action:
|
||||
call: expression
|
||||
expr: "${item.kind}"
|
||||
- name: kept
|
||||
if: "${outputs.kind == 'keep'}"
|
||||
action:
|
||||
call: expression
|
||||
expr: "${item.value}"
|
||||
start: true
|
||||
"""
|
||||
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
assert flow.kickoff(inputs={"rows": [{"kind": "keep", "value": "a"}]}) == ["a"]
|
||||
|
||||
|
||||
def test_each_action_skipped_if_keeps_previous_output():
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: EachIfFlow
|
||||
methods:
|
||||
process_rows:
|
||||
do:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: original
|
||||
action:
|
||||
call: expression
|
||||
expr: item.value
|
||||
- name: maybe_included
|
||||
if: item.include
|
||||
action:
|
||||
call: expression
|
||||
expr: "'included:' + item.value"
|
||||
start: true
|
||||
"""
|
||||
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
assert flow.kickoff(
|
||||
inputs={
|
||||
"rows": [
|
||||
{"include": True, "value": "a"},
|
||||
{"include": False, "value": "b"},
|
||||
]
|
||||
}
|
||||
) == ["included:a", "b"]
|
||||
|
||||
|
||||
def test_each_action_if_condition_must_be_boolean():
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: EachIfFlow
|
||||
methods:
|
||||
process_rows:
|
||||
do:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: value
|
||||
if: item.value
|
||||
action:
|
||||
call: expression
|
||||
expr: item.value
|
||||
start: true
|
||||
"""
|
||||
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
with pytest.raises(ValueError, match="if expression must evaluate to a boolean"):
|
||||
flow.kickoff(inputs={"rows": [{"value": "truthy"}]})
|
||||
|
||||
|
||||
def test_each_action_empty_list_returns_empty_and_listener_runs_once():
|
||||
yaml_str = f"""
|
||||
schema: crewai.flow/v1
|
||||
@@ -1705,8 +1254,7 @@ methods:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: normalize
|
||||
action:
|
||||
- normalize:
|
||||
call: code
|
||||
ref: {__name__}:EachActionFlow.normalize_row
|
||||
with:
|
||||
@@ -1755,12 +1303,7 @@ def test_each_action_rejects_non_list_inputs(expr, inputs):
|
||||
"do": {
|
||||
"call": "each",
|
||||
"in": expr,
|
||||
"do": [
|
||||
{
|
||||
"name": "value",
|
||||
"action": {"call": "expression", "expr": "item"},
|
||||
}
|
||||
],
|
||||
"do": [{"value": {"call": "expression", "expr": "item"}}],
|
||||
},
|
||||
}
|
||||
},
|
||||
@@ -1776,25 +1319,15 @@ def test_each_action_rejects_non_list_inputs(expr, inputs):
|
||||
"action_do",
|
||||
[
|
||||
[],
|
||||
[{"value": {"call": "expression", "expr": "item"}}],
|
||||
[{"name": "1bad", "action": {"call": "expression", "expr": "item"}}],
|
||||
[{"name": "missing_action"}],
|
||||
[{"action": {"call": "expression", "expr": "item"}}],
|
||||
[{"first": {"call": "expression", "expr": "item"}, "second": {"call": "expression", "expr": "item"}}],
|
||||
[{"1bad": {"call": "expression", "expr": "item"}}],
|
||||
[
|
||||
{
|
||||
"name": "value",
|
||||
"if": "true",
|
||||
"then": [],
|
||||
"action": {"call": "expression", "expr": "item"},
|
||||
}
|
||||
],
|
||||
[
|
||||
{"name": "same", "action": {"call": "expression", "expr": "item"}},
|
||||
{"name": "same", "action": {"call": "expression", "expr": "item"}},
|
||||
{"same": {"call": "expression", "expr": "item"}},
|
||||
{"same": {"call": "expression", "expr": "item"}},
|
||||
],
|
||||
],
|
||||
)
|
||||
def test_each_action_validates_step_shape(action_do):
|
||||
def test_each_action_validates_inner_action_shape(action_do):
|
||||
with pytest.raises(ValidationError):
|
||||
FlowDefinition.from_dict(
|
||||
{
|
||||
@@ -1814,26 +1347,6 @@ def test_each_action_validates_step_shape(action_do):
|
||||
)
|
||||
|
||||
|
||||
def test_if_clauses_are_rejected_at_method_level():
|
||||
with pytest.raises(ValidationError):
|
||||
FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
"name": "TopLevelIfFlow",
|
||||
"methods": {
|
||||
"process": {
|
||||
"start": True,
|
||||
"do": {
|
||||
"call": "expression",
|
||||
"if": "true",
|
||||
"expr": "'ok'",
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def test_each_action_rejects_nested_each_actions():
|
||||
with pytest.raises(ValidationError):
|
||||
FlowDefinition.from_dict(
|
||||
@@ -1848,14 +1361,12 @@ def test_each_action_rejects_nested_each_actions():
|
||||
"in": "state.rows",
|
||||
"do": [
|
||||
{
|
||||
"name": "nested",
|
||||
"action": {
|
||||
"nested": {
|
||||
"call": "each",
|
||||
"in": "state.children",
|
||||
"do": [
|
||||
{
|
||||
"name": "child",
|
||||
"action": {
|
||||
"child": {
|
||||
"call": "expression",
|
||||
"expr": "item",
|
||||
}
|
||||
@@ -1881,8 +1392,7 @@ methods:
|
||||
call: each
|
||||
in: state.rows
|
||||
do:
|
||||
- name: validate
|
||||
action:
|
||||
- validate:
|
||||
call: code
|
||||
ref: {__name__}:EachActionFlow.fail_on_bad_row
|
||||
with:
|
||||
@@ -1920,28 +1430,8 @@ def test_expression_action_round_trips():
|
||||
assert Flow.from_definition(definition).kickoff(inputs={"score": 90}) == "qualified"
|
||||
|
||||
|
||||
def test_explicit_cel_fields_accept_expression_markers():
|
||||
definition = FlowDefinition.from_dict(
|
||||
{
|
||||
"schema": "crewai.flow/v1",
|
||||
"name": "ExpressionFlow",
|
||||
"methods": {
|
||||
"classify": {
|
||||
"start": True,
|
||||
"do": {
|
||||
"call": "expression",
|
||||
"expr": "${state.score >= 80 ? 'qualified' : 'nurture'}",
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
assert Flow.from_definition(definition).kickoff(inputs={"score": 90}) == "qualified"
|
||||
|
||||
|
||||
def test_expression_local_context_recurses_into_dataclass_values():
|
||||
from crewai.flow.expressions import Expression
|
||||
from crewai.flow.runtime._expressions import evaluate_expression
|
||||
|
||||
class Payload(BaseModel):
|
||||
name: str
|
||||
@@ -1951,37 +1441,15 @@ def test_expression_local_context_recurses_into_dataclass_values():
|
||||
payload: Payload
|
||||
|
||||
assert (
|
||||
Expression.from_flow(
|
||||
"item.payload.name",
|
||||
evaluate_expression(
|
||||
Flow(),
|
||||
"item.payload.name",
|
||||
local_context={"item": Row(payload=Payload(name="qualified"))},
|
||||
).evaluate()
|
||||
)
|
||||
== "qualified"
|
||||
)
|
||||
|
||||
|
||||
def test_expression_empty_context_overrides_stored_context():
|
||||
from crewai.flow.expressions import Expression, ExpressionError
|
||||
|
||||
expression = Expression("state.score", context={"state": {"score": 90}})
|
||||
|
||||
assert expression.evaluate() == 90
|
||||
with pytest.raises(ExpressionError):
|
||||
expression.evaluate({})
|
||||
|
||||
|
||||
def test_expression_template_empty_context_overrides_stored_context():
|
||||
from crewai.flow.expressions import Expression, ExpressionError
|
||||
|
||||
expression = Expression(
|
||||
{"score": "${state.score}"}, context={"state": {"score": 90}}
|
||||
)
|
||||
|
||||
assert expression.render_template() == {"score": 90}
|
||||
with pytest.raises(ExpressionError):
|
||||
expression.render_template({})
|
||||
|
||||
|
||||
def test_expression_action_can_route_like_if_else():
|
||||
yaml_str = f"""
|
||||
schema: crewai.flow/v1
|
||||
@@ -2033,24 +1501,10 @@ methods:
|
||||
start: true
|
||||
"""
|
||||
|
||||
with pytest.raises(ValidationError, match="invalid CEL expression"):
|
||||
FlowDefinition.from_yaml(yaml_str)
|
||||
flow = Flow.from_definition(FlowDefinition.from_yaml(yaml_str))
|
||||
|
||||
|
||||
def test_expression_action_rejects_unknown_cel_root():
|
||||
yaml_str = """
|
||||
schema: crewai.flow/v1
|
||||
name: ExpressionFlow
|
||||
methods:
|
||||
classify:
|
||||
do:
|
||||
call: expression
|
||||
expr: "score >= 80"
|
||||
start: true
|
||||
"""
|
||||
|
||||
with pytest.raises(ValidationError, match="unknown CEL root"):
|
||||
FlowDefinition.from_yaml(yaml_str)
|
||||
with pytest.raises(ValueError, match="failed to evaluate CEL expression"):
|
||||
flow.kickoff()
|
||||
|
||||
|
||||
def test_tool_action_requires_module_qualname_ref():
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
"""CrewAI development tools."""
|
||||
|
||||
__version__ = "1.14.8a2"
|
||||
__version__ = "1.14.7"
|
||||
|
||||
@@ -171,8 +171,6 @@ info = "Commits must follow Conventional Commits 1.0.0."
|
||||
|
||||
[tool.uv]
|
||||
exclude-newer = "3 days"
|
||||
# pypdf 6.13.3 is a security fix newer than the global supply-chain cutoff.
|
||||
exclude-newer-package = { pypdf = "2026-06-18T00:00:00Z" }
|
||||
|
||||
# composio-core pins rich<14 but textual requires rich>=14.
|
||||
# onnxruntime 1.24+ dropped Python 3.10 wheels; cap it so qdrant[fastembed] resolves on 3.10.
|
||||
@@ -182,8 +180,7 @@ exclude-newer-package = { pypdf = "2026-06-18T00:00:00Z" }
|
||||
# langchain-text-splitters <1.1.2 has GHSA-fv5p-p927-qmxr (SSRF bypass in split_text_from_url).
|
||||
# transformers 4.57.6 has CVE-2026-1839; force 5.4+ (docling 2.84 allows huggingface-hub>=1).
|
||||
# cryptography 46.0.6 has CVE-2026-39892; force 46.0.7+.
|
||||
# pypdf <6.10.2 has GHSA-4pxv-j86v-mhcw, GHSA-7gw9-cf7v-778f, GHSA-x284-j5p8-9c5p.
|
||||
# pypdf <6.13.3 has GHSA-jm82-fx9c-mx94; force 6.13.3+.
|
||||
# pypdf <6.10.2 has GHSA-4pxv-j86v-mhcw, GHSA-7gw9-cf7v-778f, GHSA-x284-j5p8-9c5p; force 6.10.2+.
|
||||
# uv <0.11.15 has GHSA-4gg8-gxpx-9rph (and earlier GHSA-pjjw-68hj-v9mw); force 0.11.15+.
|
||||
# python-multipart <0.0.27 has GHSA-pp6c-gr5w-3c5g (DoS via unbounded multipart headers).
|
||||
# gitpython <3.1.50 has GHSA-mv93-w799-cj2w (config_writer newline injection bypassing the 3.1.49 patch -> RCE via core.hooksPath).
|
||||
@@ -208,7 +205,7 @@ override-dependencies = [
|
||||
"urllib3>=2.7.0",
|
||||
"transformers>=5.4.0; python_version >= '3.10'",
|
||||
"cryptography>=46.0.7",
|
||||
"pypdf>=6.13.3,<7",
|
||||
"pypdf>=6.10.2,<7",
|
||||
"uv>=0.11.15,<1",
|
||||
"python-multipart>=0.0.27,<1",
|
||||
"gitpython>=3.1.50,<4",
|
||||
|
||||
13
uv.lock
generated
13
uv.lock
generated
@@ -16,9 +16,6 @@ resolution-markers = [
|
||||
exclude-newer = "0001-01-01T00:00:00Z" # This has no effect and is included for backwards compatibility when using relative exclude-newer values.
|
||||
exclude-newer-span = "P3D"
|
||||
|
||||
[options.exclude-newer-package]
|
||||
pypdf = "2026-06-18T00:00:00Z"
|
||||
|
||||
[manifest]
|
||||
members = [
|
||||
"crewai",
|
||||
@@ -43,7 +40,7 @@ overrides = [
|
||||
{ name = "pillow", specifier = ">=12.1.1" },
|
||||
{ name = "pip", specifier = ">=26.1.2" },
|
||||
{ name = "pydantic-settings", specifier = ">=2.14.0" },
|
||||
{ name = "pypdf", specifier = ">=6.13.3,<7" },
|
||||
{ name = "pypdf", specifier = ">=6.10.2,<7" },
|
||||
{ name = "python-multipart", specifier = ">=0.0.27,<1" },
|
||||
{ name = "rich", specifier = ">=13.7.1" },
|
||||
{ name = "starlette", specifier = ">=1.3.1" },
|
||||
@@ -1587,7 +1584,7 @@ requires-dist = [
|
||||
{ name = "aiofiles", specifier = "~=24.1.0" },
|
||||
{ name = "av", specifier = "~=13.0.0" },
|
||||
{ name = "pillow", specifier = "~=12.1.1" },
|
||||
{ name = "pypdf", specifier = "~=6.13.3" },
|
||||
{ name = "pypdf", specifier = "~=6.10.0" },
|
||||
{ name = "python-magic", specifier = ">=0.4.27" },
|
||||
{ name = "tinytag", specifier = "~=2.2.1" },
|
||||
]
|
||||
@@ -7191,14 +7188,14 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "pypdf"
|
||||
version = "6.13.3"
|
||||
version = "6.13.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "typing-extensions", marker = "python_full_version < '3.11'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/17/18/9947cc201af9ccf76720fd3347bf4f70eb882ce3fcf4cb05f7443e4cf871/pypdf-6.13.3.tar.gz", hash = "sha256:f3cb822769725f1bac658c406cfc9460399043f3750c2d3e4650e0a85eacabd7", size = 6484063, upload-time = "2026-06-17T15:22:00.898Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/15/d9/9d12fa0d9660d03320725ff686c961b645a4218940a82296e1272d9e1ff0/pypdf-6.13.1.tar.gz", hash = "sha256:4841d8a4c1589e5833915dc0c7ddfacff80a2e0bcbeb5d1e681fecaa1674b03a", size = 6477811, upload-time = "2026-06-08T11:01:49.344Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/94/56/2967e621598987905fb8cdfadd8f8de6b5c68c9351f0523c4df8409f28f1/pypdf-6.13.3-py3-none-any.whl", hash = "sha256:c6e3f86afb625791510b02ad5480e94b63970bb957df75d44657c282ecc52224", size = 347288, upload-time = "2026-06-17T15:21:59.512Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/fe/dd/8f03e0a5788a5d1feb4550617c3e6db5e9099eaee248a3e482ddaeacbbb0/pypdf-6.13.1-py3-none-any.whl", hash = "sha256:e555e4ce3f561ef069307622f1374136ba964ca6ca24f24158701decaf83ed9b", size = 346259, upload-time = "2026-06-08T11:01:47.741Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
Reference in New Issue
Block a user