apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-06-13 08:15:21 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: add default initial context variables

Browse source
This commit is contained in:
Abhishek Kumar 2026-04-02 14:32:43 +05:30
parent f368fe5134
commit 96c90376c3
8 changed files with 112 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

21
docs/core-concepts/context-and-variables.mdx
View file

@ -45,6 +45,27 @@ whether they'd like to continue.
When the call starts, Dograh substitutes the values before sending the prompt to the LLM — so the agent speaks naturally as if it already knows the contact.
### Built-in template variables
Dograh provides built-in variables for current time and weekday that you can use in any prompt without setting up `initial_context`.
| Variable | Description | Example output |
|---|---|---|
| `{{current_time}}` | Current time in UTC (or inferred timezone) | `2026-04-02 14:30:45 UTC` |
| `{{current_time_<TIMEZONE>}}` | Current time in the specified timezone | `2026-04-02 20:00:45 IST` |
| `{{current_weekday}}` | Current weekday name in UTC (or inferred timezone) | `Thursday` |
| `{{current_weekday_<TIMEZONE>}}` | Current weekday name in the specified timezone | `Thursday` |
Replace `<TIMEZONE>` with an [IANA timezone name](https://en.wikipedia.org/wiki/List_of_tz_database_time_zones) such as `Asia/Kolkata`, `America/New_York`, or `Europe/London`.
```
Today is {{current_weekday}} and the current time is {{current_time_America/New_York}}.
```
<Note>
When you use a timezone suffix on **either** `current_time` or `current_weekday`, the other variable without a suffix will automatically use the same timezone instead of UTC. For example, if your prompt contains both `{{current_time_Asia/Kolkata}}` and `{{current_weekday}}`, the weekday will also be resolved in `Asia/Kolkata`.
</Note>
### gathered_context
Data the agent collects *during* the call. You configure what to extract in the agent node's extraction settings — each variable has a name, type, and a prompt that tells the LLM what to look for.