Skip to content

Automate browser based workflows with AI

copilot: document per-block-type output shape and null-guard in workflow KB (#5643)

Andrew Neilson2c6cd35b8ed7
diff --git a/skyvern/forge/prompts/skyvern/workflow_knowledge_base.txt b/skyvern/forge/prompts/skyvern/workflow_knowledge_base.txt
index 807492eb8..81a44a45e 100644
--- a/skyvern/forge/prompts/skyvern/workflow_knowledge_base.txt
+++ b/skyvern/forge/prompts/skyvern/workflow_knowledge_base.txt
@@ -618,6 +618,8 @@ prompt: <text_prompt> # Required: Prompt to run
parameter_keys: [] # Optional: Parameters used in this block
json_schema: <json_schema> # Optional: Structured output schema
+Referencing output from downstream blocks: fields live on the block directly, NOT under `.output`. Write `{{ summarize_notes.summary }}`, not `{{ summarize_notes.output.summary }}`. See PARAMETER TEMPLATING for the full per-block-type rule and the null-guard requirement.
+
Use Cases:
- Summarize extracted text or documents
- Normalize free-form content into a schema
@@ -716,10 +718,22 @@ There are TWO types of references:
Requires: parameter_keys list must include the param_key
2. BLOCK OUTPUTS - Reference output from a previous block by its label
- Syntax: {{ block_label.output }}
+ Syntax depends on the upstream block type; see below.
Requires: NOTHING - block outputs are automatically available, no parameter_keys needed
-IMPORTANT: Block outputs use the block's label directly (e.g., {{ block_1.output }}).
+IMPORTANT — block output shapes are NOT uniform across block types. Using the wrong shape either raises "dict object has no attribute 'output'" at render time or (worse) silently renders a None value into a URL field, producing `https://None` which fails with `net::ERR_NAME_NOT_RESOLVED`.
+
+* Browser-task blocks (navigation, extraction, goto_url, login, action, file_download):
+ - `{{ label.output }}` — the full TaskOutput envelope.
+ - `{{ label.output.extracted_information }}` — the extracted payload.
+ - Example: `{{ extract_items.output }}` inside a downstream prompt.
+
+* Non-task blocks (text_prompt, http_request, file_url_parser):
+ - `{{ label.<field> }}` — fields from the returned JSON are on the block directly; there is NO `.output` wrapper.
+ - Example: `{{ summarize_notes.summary }}` (NOT `{{ summarize_notes.output.summary }}`).
+ - Writing `{{ summarize_notes.output.summary }}` raises "dict object has no attribute 'output'" because `summarize_notes` IS the dict.
+
+NULL-GUARD RULE — when a downstream field may legitimately be null/empty (e.g., a text_prompt returned `{"store_url": null}` because no such link exists on the page), wrap the reference in a `conditional` block BEFORE using it as a URL. Unguarded `goto_url` with `url: "{{ x.field }}"` where `x.field` is None renders as `https://None` and is not recoverable by retrying the same workflow — it is a nullity bug, not a navigation bug.
Examples - Workflow Parameters:
@@ -733,7 +747,7 @@ parameter_keys: [product_name, category]
Examples - Block Outputs (no parameter_keys needed):
-* Send previous block output to webhook:
+* Send previous task-block output to webhook (task block → use .output):
blocks:
- block_type: navigation
label: get_data
@@ -747,7 +761,7 @@ blocks:
data: "{{ get_data.output }}"
parameter_keys: [] # Empty - block outputs don't need to be declared
-* Use extraction output in next block:
+* Use extraction output in next block (task block → use .output):
blocks:
- block_type: extraction
label: extract_items
@@ -756,6 +770,16 @@ blocks:
label: process_items
navigation_goal: "Process these items: {{ extract_items.output }}"
+* Use text_prompt output in next block (non-task block → reference fields directly, NO .output):
+blocks:
+ - block_type: text_prompt
+ label: summarize_notes
+ prompt: "Summarize ..."
+ json_schema: {type: object, properties: {summary: {type: string}}}
+ - block_type: navigation
+ label: use_summary
+ navigation_goal: "Act on: {{ summarize_notes.summary }}" # NOT {{ summarize_notes.output.summary }}
+
* In schemas (as descriptions):
data_schema:
type: object