eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Upgrade PromptKit runtime baseline

Browse Source
This commit is contained in:
Eric Rakestraw
2026-09-25 21:49:44 +00:00
parent 31b48d2d5e
commit d29a5cecd3
7 changed files with 46 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
docs/operations.md
View File

@@ -352,7 +352,9 @@ Provider execution settings and the generation timeout come from the selected
PromptKit profile. The invocation-only **--reasoning-effort** and
**--clear-reasoning-effort** controls may replace or clear that profile setting
for all LLM-backed calls in one run without changing the profile. PromptKit
structural output repair happens within one structured-completion call. Its
v0.11.0 also retries eligible transient HTTP failures with its built-in default
of two additional attempts per generation. This retry work is separate from
structural output repair, which happens within one structured-completion call. Its
effective `structured_output_repair_attempts` limit is resolved from the
selected binding, then the pipeline, then the prompt declaration; see
[module bindings](config.md#module-bindings-and-validators). This is distinct
@@ -360,19 +362,20 @@ from Notarius binding **retries**, which rerun the complete module operation
and validation chain and do not consume or replenish the structural-repair
limit. The maintained production prompts declare one repair attempt, paid only
after a structural failure. One structured completion with repair budget **R**
makes at most **R + 1** serial provider calls. If one stage attempt performs
**C** structured completions, a binding with **retries: N** has a maximum of
**(N + 1) * C * (R + 1)** provider calls; LLM-backed validators have their own
corresponding invocation counts and budgets. This is an upper bound, not a
promise that every call reaches a provider.
contains at most **R + 1** serial generations. Each generation can now contain
more than one provider call when PromptKit retries an eligible transient
failure. LLM-backed validators have their own corresponding invocation and
repair budgets. These are bounds on attempted work, not a promise that every
call reaches a provider.
Timeouts are layered. Caller cancellation is the outer authority. A positive
effective generation timeout adds an inner request deadline, while zero
disables only that generation deadline. The HTTP client timeout remains a
transport-wide cap. Notarius does not add another timeout around PromptKit.
Repairs are serial within the same caller context, so their worst-case latency
and cost follow the provider-call bound above; provision run deadlines and
provider budgets accordingly. Credentials remain optional unless the selected
effective generation timeout adds an inner request deadline to each built-in
generation attempt, while zero disables only that generation deadline. The HTTP
client timeout remains a transport-wide cap. Notarius does not add another
timeout around PromptKit. Retries and repairs are serial within the same caller
context, so their worst-case latency and cost can exceed the structural-repair
bound above; provision run deadlines and provider budgets accordingly.
Credentials remain optional unless the selected
PromptKit profile requires one, in which case preparation fails before a
provider call when its configured credential is unavailable.
The pinned upstream boundary and profile-format links are in