# History core
------------------------------------------------------------------------
source
### hydrate_turns
``` python
def hydrate_turns(
cfg, turns
):
```
*Restore whole results and prompts from confined details files. A
missing or unreadable file leaves clipped text.*
------------------------------------------------------------------------
source
### request_title
``` python
def request_title(
prompt, n:int=80
):
```
*A session’s title from its first request: the first sentence of
[`request_body`](https://vedicreader.github.io/ramabana/history_core.html#request_body),
in at most `n` characters.*
------------------------------------------------------------------------
source
### request_body
``` python
def request_body(
prompt
):
```
*[`request_text`](https://vedicreader.github.io/ramabana/history_core.html#request_text)
without the harness’s blocks, or a `` tag a prompt cut
short kept.*
------------------------------------------------------------------------
source
### request_text
``` python
def request_text(
prompt
):
```
*The person’s request, without the notebook or screen context composed
around it.*
------------------------------------------------------------------------
source
### labeled_rows
``` python
def labeled_rows(
rows, legacy_n:int=0, legacy_last:NoneType=None, key:function=
):
```
*Yield `(session_id, item)` for each item of `rows` whose row is
`key(item)`, with legacy ids inferred and rows with invalid timestamps
skipped.*
------------------------------------------------------------------------
source
### history_rows
``` python
def history_rows(
path, offset:int=0
):
```
*Yield `(start, end, row)` for each complete object row from `offset`.*
A history index skips rows whose timestamps are not numeric.
``` python
rows = [
(0, 10, {'session': 'bad', 'at': 'later', 'prompt': 'skip me'}),
(10, 20, {'session': 'kept', 'at': 2, 'prompt': 'Keep this turn'}),
]
indexed = _index_rows(rows)
assert list(indexed) == ['kept']
indexed['kept']
```