vrr/Pulse
2
0
Fork 0
mirror of https://github.com/rcourtman/Pulse.git synced 2026-10-04 13:52:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

docs(ai): record prompt-cache transport contract

Browse source 
Add the ai-runtime contract section for the Anthropic stable-system-prefix
prompt-cache reuse and its focused proof. This completes the contract obligation
for the runtime repair in 248ada3cc6 without rewriting that reviewed commit.

Change-source: pulse-maintainer
This commit is contained in:
pulse-triage[bot] 2026-09-19 22:02:04 +01:00
parent 248ada3cc6
commit f08b96b968
1 changed files with 25 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

25
docs/release-control/v6/internal/subsystems/ai-runtime.md
View file

@ -877,6 +877,31 @@ outcome requires from current evidence, and explicitly grants no tool choice,
mutation, approval, or policy authority. This is the retained-intent seam from
cheap local detection into model-owned diagnosis and governed action.
### Anthropic prompt-cache reuse of the stable system prefix (19 September 2026)
Provider-neutral `ChatRequest.System` stays the full system prompt. The optional
`SystemCacheablePrefix` marks its stable leading portion; the agentic loop
(`internal/ai/chat/agentic_prompt.go`) supplies the frozen base plus execution
mode text there and keeps the per-turn clock and accumulated knowledge after it,
so multi-turn runs can reuse the prompt instead of repaying it every turn
(#2118). When the prefix is an exact prefix of `System`, the Anthropic transport
(`internal/ai/providers/anthropic.go`) serializes `system` as content blocks with
an `ephemeral` cache breakpoint on the stable block and the volatile remainder as
an uncached block; otherwise it sends the plain string form. Anthropic caches in
tools then system then messages order, so the system breakpoint already covers
the tool definitions and the per-tool breakpoint is omitted when the block form
is used; providers without prompt caching ignore the field and send `System`
unchanged. The prefix is applied only when it is an exact prefix of the possibly
sanitized `System`, so a redacted secret cannot be reintroduced through the block
form; a mismatch falls back to the plain string. Cache creation/read counters are
logged at Info for production visibility. Proof: `TestBuildAnthropicSystem`,
`TestAnthropicClient_Chat_CacheableSystemPrefix`,
`TestAnthropicClient_ChatStream_CacheableSystemPrefix`,
`TestAnthropicClient_Chat_KeepsToolBreakpointWithoutCacheableSystem`, and
`TestAgenticLoop_SystemPromptPartsSeparateStablePrefix`. This does not change
model-facing content, tool exposure, or approval authority, and it does not claim
a measured cost reduction or installed-deployment cache-read rate.
## Canonical Files
- `pkg/reporting/evidence.go`: measured retained-history evidence contract for model-facing summaries, with no report narrator or heuristic health judgement.