core: snapshot tests for compaction requests, post-compaction layout, some additional compaction tests (#11487)

This PR keeps compaction context-layout test coverage separate from
runtime compaction behavior changes, so runtime logic review can stay
focused.

## Included
- Adds reusable context snapshot helpers in
`core/tests/common/context_snapshot.rs` for rendering model-visible
request/history shapes.
- Standardizes helper naming for readability:
  - `format_request_input_snapshot`
  - `format_response_items_snapshot`
  - `format_labeled_requests_snapshot`
  - `format_labeled_items_snapshot`
- Expands snapshot coverage for both local and remote compaction flows:
  - pre-turn auto-compaction
  - pre-turn failure/context-window-exceeded paths
  - mid-turn continuation compaction
  - manual `/compact` with and without prior user turns
- Captures both sides where relevant:
  - compaction request shape
  - post-compaction history layout shape
- Adds/uses shared request-inspection helpers so assertions target
structured request content instead of ad-hoc JSON string parsing.
- Aligns snapshots/assertions to current behavior and leaves explicit
`TODO(ccunningham)` notes where behavior is known and intentionally
deferred.

## Not Included
- No runtime compaction logic changes.
- No model-visible context/state behavior changes.
This commit is contained in:
Charley Cunningham
2026-02-14 19:57:10 -08:00
committed by GitHub
parent fce4ad9cf4
commit 85034b189e
20 changed files with 1594 additions and 221 deletions

View File

@@ -0,0 +1,21 @@
---
source: core/tests/suite/compact.rs
expression: "format_labeled_requests_snapshot(\"Manual /compact with prior user history compacts existing history and the follow-up turn includes the compact summary plus new user message.\",\n&[(\"Local Compaction Request\", &requests[1]),\n(\"Local Post-Compaction History Layout\", &requests[2]),])"
---
Scenario: Manual /compact with prior user history compacts existing history and the follow-up turn includes the compact summary plus new user message.
## Local Compaction Request
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:first manual turn
04:message/assistant:FIRST_REPLY
05:message/user:<SUMMARIZATION_PROMPT>
## Local Post-Compaction History Layout
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:first manual turn
04:message/user:<COMPACTION_SUMMARY>\nFIRST_MANUAL_SUMMARY
05:message/user:second manual turn

View File

@@ -0,0 +1,18 @@
---
source: core/tests/suite/compact.rs
expression: "format_labeled_requests_snapshot(\"Manual /compact with no prior user turn currently still issues a compaction request; follow-up turn carries canonical context and the new user message.\",\n&[(\"Local Compaction Request\", &requests[0]),\n(\"Local Post-Compaction History Layout\", &requests[1]),])"
---
Scenario: Manual /compact with no prior user turn currently still issues a compaction request; follow-up turn carries canonical context and the new user message.
## Local Compaction Request
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:<SUMMARIZATION_PROMPT>
## Local Post-Compaction History Layout
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:<COMPACTION_SUMMARY>\nMANUAL_EMPTY_SUMMARY
04:message/user:AFTER_MANUAL_EMPTY_COMPACT

View File

@@ -0,0 +1,22 @@
---
source: core/tests/suite/compact.rs
assertion_line: 2646
expression: "format_labeled_requests_snapshot(\"True mid-turn continuation compaction after tool output: compact request includes tool artifacts, and the continuation request includes the summary in the same turn.\",\n&[(\"Local Compaction Request\", &auto_compact_mock.single_request()),\n(\"Local Post-Compaction History Layout\",\n&post_auto_compact_mock.single_request()),])"
---
Scenario: True mid-turn continuation compaction after tool output: compact request includes tool artifacts, and the continuation request includes the summary in the same turn.
## Local Compaction Request
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:function call limit push
04:function_call/test_tool
05:function_call_output:unsupported call: test_tool
06:message/user:<SUMMARIZATION_PROMPT>
## Local Post-Compaction History Layout
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:function call limit push
04:message/user:<COMPACTION_SUMMARY>\nAUTO_SUMMARY

View File

@@ -0,0 +1,31 @@
---
source: core/tests/suite/compact.rs
assertion_line: 1773
expression: "format_labeled_requests_snapshot(\"Pre-sampling compaction on model switch to a smaller context window: current behavior compacts using prior-turn history only (incoming user message excluded), and the follow-up request carries compacted history plus the new user message.\",\n&[(\"Initial Request (Previous Model)\", &requests[0]),\n(\"Pre-sampling Compaction Request\", &requests[1]),\n(\"Post-Compaction Follow-up Request (Next Model)\", &requests[2]),])"
---
Scenario: Pre-sampling compaction on model switch to a smaller context window: current behavior compacts using prior-turn history only (incoming user message excluded), and the follow-up request carries compacted history plus the new user message.
## Initial Request (Previous Model)
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/developer:<PERMISSIONS_INSTRUCTIONS>
04:message/user:before switch
## Pre-sampling Compaction Request
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/developer:<PERMISSIONS_INSTRUCTIONS>
04:message/user:before switch
05:message/assistant:before switch
06:message/user:<SUMMARIZATION_PROMPT>
## Post-Compaction Follow-up Request (Next Model)
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:before switch
04:message/user:<COMPACTION_SUMMARY>\nPRE_SAMPLING_SUMMARY
05:message/developer:<model_switch>\nThe user was previously using a different model....
06:message/user:after switch

View File

@@ -0,0 +1,13 @@
---
source: core/tests/suite/compact.rs
expression: "format_labeled_requests_snapshot(\"Pre-turn auto-compaction context-window failure: compaction request excludes the incoming user message and the turn errors.\",\n&[(\"Local Compaction Request (Incoming User Excluded)\", &requests[1]),])"
---
Scenario: Pre-turn auto-compaction context-window failure: compaction request excludes the incoming user message and the turn errors.
## Local Compaction Request (Incoming User Excluded)
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:USER_ONE
04:message/assistant:FIRST_REPLY
05:message/user:<SUMMARIZATION_PROMPT>

View File

@@ -0,0 +1,25 @@
---
source: core/tests/suite/compact.rs
expression: "format_labeled_requests_snapshot(\"Pre-turn auto-compaction with a context override emits the context diff in the compact request while the incoming user message is still excluded.\",\n&[(\"Local Compaction Request\", &requests[2]),\n(\"Local Post-Compaction History Layout\", &requests[3]),])"
---
Scenario: Pre-turn auto-compaction with a context override emits the context diff in the compact request while the incoming user message is still excluded.
## Local Compaction Request
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:USER_ONE
04:message/assistant:FIRST_REPLY
05:message/user:USER_TWO
06:message/assistant:SECOND_REPLY
07:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
08:message/user:<SUMMARIZATION_PROMPT>
## Local Post-Compaction History Layout
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
03:message/user:USER_ONE
04:message/user:USER_TWO
05:message/user:<COMPACTION_SUMMARY>\nPRE_TURN_SUMMARY
06:message/user:<image> | <input_image:image_url> | </image> | USER_THREE

View File

@@ -0,0 +1,21 @@
---
source: core/tests/suite/compact_remote.rs
assertion_line: 178
expression: "format_labeled_requests_snapshot(\"Remote manual /compact where remote compact output is summary-only: follow-up layout uses returned summary plus new user message.\",\n&[(\"Remote Compaction Request\", &compact_request),\n(\"Remote Post-Compaction History Layout\", follow_up_request),])"
---
Scenario: Remote manual /compact where remote compact output is summary-only: follow-up layout uses returned summary plus new user message.
## Remote Compaction Request
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:hello remote compact
04:message/assistant:FIRST_REMOTE_REPLY
## Remote Post-Compaction History Layout
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:REMOTE_COMPACTED_SUMMARY
04:compaction:encrypted=true
05:message/user:after compact

View File

@@ -0,0 +1,16 @@
---
source: core/tests/suite/compact_remote.rs
expression: "format_labeled_requests_snapshot(\"Remote manual /compact with no prior user turn still issues a compact request; follow-up turn carries canonical context and new user message.\",\n&[(\"Remote Compaction Request\", &compact_request),\n(\"Remote Post-Compaction History Layout\", &follow_up_request),])"
---
Scenario: Remote manual /compact with no prior user turn still issues a compact request; follow-up turn carries canonical context and new user message.
## Remote Compaction Request
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
## Remote Post-Compaction History Layout
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:USER_ONE

View File

@@ -0,0 +1,20 @@
---
source: core/tests/suite/compact_remote.rs
expression: "format_labeled_requests_snapshot(\"Remote mid-turn continuation compaction after tool output: compact request includes tool artifacts and follow-up request includes the summary.\",\n&[(\"Remote Compaction Request\", &compact_request),\n(\"Remote Post-Compaction History Layout\", &requests[1]),])"
---
Scenario: Remote mid-turn continuation compaction after tool output: compact request includes tool artifacts and follow-up request includes the summary.
## Remote Compaction Request
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:USER_ONE
04:function_call/test_tool
05:function_call_output:unsupported call: test_tool
## Remote Post-Compaction History Layout
00:message/user:USER_ONE
01:message/developer:<PERMISSIONS_INSTRUCTIONS>
02:message/user:<AGENTS_MD>
03:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
04:message/user:<COMPACTION_SUMMARY>\nREMOTE_MID_TURN_SUMMARY

View File

@@ -0,0 +1,12 @@
---
source: core/tests/suite/compact_remote.rs
expression: "format_labeled_requests_snapshot(\"Remote pre-turn auto-compaction context-window failure: compaction request excludes the incoming user message and the turn errors.\",\n&[(\"Remote Compaction Request (Incoming User Excluded)\",\n&include_attempt_request),])"
---
Scenario: Remote pre-turn auto-compaction context-window failure: compaction request excludes the incoming user message and the turn errors.
## Remote Compaction Request (Incoming User Excluded)
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:USER_ONE
04:message/assistant:REMOTE_FIRST_REPLY

View File

@@ -0,0 +1,12 @@
---
source: core/tests/suite/compact_remote.rs
expression: "format_labeled_requests_snapshot(\"Remote pre-turn auto-compaction parse failure: compaction request excludes the incoming user message and the turn stops.\",\n&[(\"Remote Compaction Request (Incoming User Excluded)\",\n&first_compact_mock.single_request()),])"
---
Scenario: Remote pre-turn auto-compaction parse failure: compaction request excludes the incoming user message and the turn stops.
## Remote Compaction Request (Incoming User Excluded)
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:turn that exceeds token threshold
04:message/assistant:initial turn complete

View File

@@ -0,0 +1,24 @@
---
source: core/tests/suite/compact_remote.rs
expression: "format_labeled_requests_snapshot(\"Remote pre-turn auto-compaction with a context override emits the context diff in the compact request while excluding the incoming user message.\",\n&[(\"Remote Compaction Request\", &compact_request),\n(\"Remote Post-Compaction History Layout\", &requests[2]),])"
---
Scenario: Remote pre-turn auto-compaction with a context override emits the context diff in the compact request while excluding the incoming user message.
## Remote Compaction Request
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user:<AGENTS_MD>
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:USER_ONE
04:message/assistant:REMOTE_FIRST_REPLY
05:message/user:USER_TWO
06:message/assistant:REMOTE_SECOND_REPLY
07:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
## Remote Post-Compaction History Layout
00:message/user:USER_ONE
01:message/user:USER_TWO
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
03:message/user:<AGENTS_MD>
04:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
05:message/user:<COMPACTION_SUMMARY>\nREMOTE_PRE_TURN_SUMMARY
06:message/user:USER_THREE