mirror of
https://github.com/openai/codex.git
synced 2026-04-28 16:45:54 +00:00
core: bundle settings diff updates into one dev/user envelope (#12417)
## Summary
- bundle contextual prompt injection into at most one developer message
plus one contextual user message in both:
- per-turn settings updates
- initial context insertion
- preserve `<model_switch>` across compaction by rebuilding it through
canonical initial-context injection, instead of relying on
strip/reattach hacks
- centralize contextual user fragment detection in one shared definition
table and reuse it for parsing/compaction logic
- keep `AGENTS.md` in its natural serialized format:
- `# AGENTS.md instructions for {dirname}`
- `<INSTRUCTIONS>...</INSTRUCTIONS>`
- simplify related tests/helpers and accept the expected snapshot/layout
updates from bundled multi-part messages
## Why
The goal is to converge toward a simpler, more intentional prompt shape
where contextual updates are consistently represented as one developer
envelope plus one contextual user envelope, while keeping parsing and
compaction behavior aligned with that representation.
## Notable details
- the temporary `SettingsUpdateEnvelope` wrapper was removed; these
paths now return `Vec<ResponseItem>` directly
- local/remote compaction no longer rely on model-switch strip/restore
helpers
- contextual user detection is now driven by shared fragment definitions
instead of ad hoc matcher assembly
- AGENTS/user instructions are still the same logical context; only the
synthetic `<user_instructions>` wrapper was replaced by the natural
AGENTS text format
## Testing
- `just fmt`
- `cargo test -p codex-app-server
codex_message_processor::tests::extract_conversation_summary_prefers_plain_user_messages
-- --exact`
- `cargo test -p codex-core
compact::tests::collect_user_messages_filters_session_prefix_entries
--lib -- --exact`
- `cargo test -p codex-core --test all
'suite::compact::snapshot_request_shape_pre_turn_compaction_strips_incoming_model_switch'
-- --exact`
- `cargo test -p codex-core --test all
'suite::compact_remote::snapshot_request_shape_remote_pre_turn_compaction_strips_incoming_model_switch'
-- --exact`
- `cargo test -p codex-core --test all
'suite::client::includes_apps_guidance_as_developer_message_when_enabled'
-- --exact`
- `cargo test -p codex-core --test all
'suite::client::includes_developer_instructions_message_in_request' --
--exact`
- `cargo test -p codex-core --test all
'suite::client::includes_user_instructions_message_in_request' --
--exact`
- `cargo test -p codex-core --test all
'suite::client::resume_includes_initial_messages_and_sends_prior_items'
-- --exact`
- `cargo test -p codex-core --test all
'suite::review::review_input_isolated_from_parent_history' -- --exact`
- `cargo test -p codex-exec --test all
'suite::resume::exec_resume_last_respects_cwd_filter_and_all_flag' --
--exact`
- `cargo test -p core_test_support
context_snapshot::tests::full_text_mode_preserves_unredacted_text --
--exact`
## Notes
- I also ran several targeted `compact`, `compact_remote`,
`prompt_caching`, `model_visible_layout`, and `event_mapping` tests
while iterating on prompt-shape changes.
- I have not claimed a clean full-workspace `cargo test` from this
environment because local sandbox/resource conditions have previously
produced unrelated failures in large workspace runs.
This commit is contained in:
committed by
GitHub
parent
28bfbb8f2b
commit
07aefffb1f
@@ -6,16 +6,18 @@ Scenario: Manual /compact with prior user history compacts existing history and
|
||||
|
||||
## 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>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:first manual turn
|
||||
03:message/assistant:FIRST_REPLY
|
||||
04:message/user:<SUMMARIZATION_PROMPT>
|
||||
|
||||
## Local Post-Compaction History Layout
|
||||
00:message/user:first manual turn
|
||||
01:message/user:<COMPACTION_SUMMARY>\nFIRST_MANUAL_SUMMARY
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user:<AGENTS_MD>
|
||||
04:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
05:message/user:second manual turn
|
||||
03:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
04:message/user:second manual turn
|
||||
|
||||
@@ -6,13 +6,15 @@ Scenario: Manual /compact with no prior user turn currently still issues a compa
|
||||
|
||||
## 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>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:<SUMMARIZATION_PROMPT>
|
||||
|
||||
## Local Post-Compaction History Layout
|
||||
00:message/user:<COMPACTION_SUMMARY>\nMANUAL_EMPTY_SUMMARY
|
||||
01:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
02:message/user:<AGENTS_MD>
|
||||
03:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
04:message/user:AFTER_MANUAL_EMPTY_COMPACT
|
||||
02:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
03:message/user:AFTER_MANUAL_EMPTY_COMPACT
|
||||
|
||||
@@ -1,22 +1,23 @@
|
||||
---
|
||||
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>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:function call limit push
|
||||
03:function_call/test_tool
|
||||
04:function_call_output:unsupported call: test_tool
|
||||
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:function call limit push
|
||||
04:message/user:<COMPACTION_SUMMARY>\nAUTO_SUMMARY
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:function call limit push
|
||||
03:message/user:<COMPACTION_SUMMARY>\nAUTO_SUMMARY
|
||||
|
||||
@@ -1,30 +1,35 @@
|
||||
---
|
||||
source: core/tests/suite/compact.rs
|
||||
assertion_line: 1791
|
||||
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
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03: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>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user:before switch
|
||||
04:message/assistant:before switch
|
||||
05:message/user:<SUMMARIZATION_PROMPT>
|
||||
|
||||
## Post-Compaction Follow-up Request (Next Model)
|
||||
00:message/user:before switch
|
||||
01:message/user:<COMPACTION_SUMMARY>\nPRE_SAMPLING_SUMMARY
|
||||
02:message/developer:<model_switch>\nThe user was previously using a different model....
|
||||
03:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
04:message/user:<AGENTS_MD>
|
||||
05:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
06:message/user:after switch
|
||||
02:message/developer[2]:
|
||||
[01] <model_switch>\nThe user was previously using a different model....
|
||||
[02] <PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
04:message/user:after switch
|
||||
|
||||
@@ -6,8 +6,9 @@ Scenario: Pre-turn auto-compaction context-window failure: compaction request ex
|
||||
|
||||
## 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>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:USER_ONE
|
||||
03:message/assistant:FIRST_REPLY
|
||||
04:message/user:<SUMMARIZATION_PROMPT>
|
||||
|
||||
@@ -6,19 +6,25 @@ Scenario: Pre-turn auto-compaction with a context override emits the context dif
|
||||
|
||||
## 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:<SUMMARIZATION_PROMPT>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:USER_ONE
|
||||
03:message/assistant:FIRST_REPLY
|
||||
04:message/user:USER_TWO
|
||||
05:message/assistant:SECOND_REPLY
|
||||
06:message/user:<SUMMARIZATION_PROMPT>
|
||||
|
||||
## Local Post-Compaction History Layout
|
||||
00:message/user:USER_ONE
|
||||
01:message/user:USER_TWO
|
||||
02:message/user:<COMPACTION_SUMMARY>\nPRE_TURN_SUMMARY
|
||||
03:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
04:message/user:<AGENTS_MD>
|
||||
05:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
|
||||
06:message/user:<image> | <input_image:image_url> | </image> | USER_THREE
|
||||
04:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
|
||||
05:message/user[4]:
|
||||
[01] <image>
|
||||
[02] <input_image:image_url>
|
||||
[03] </image>
|
||||
[04] USER_THREE
|
||||
|
||||
@@ -1,31 +1,36 @@
|
||||
---
|
||||
source: core/tests/suite/compact.rs
|
||||
assertion_line: 3188
|
||||
expression: "format_labeled_requests_snapshot(\"Pre-turn compaction during model switch (without pre-sampling model-switch compaction): current behavior strips incoming <model_switch> from the compact request and restores it in the post-compaction follow-up request.\",\n&[(\"Initial Request (Previous Model)\", &requests[0]),\n(\"Local Compaction Request\", &requests[1]),\n(\"Local Post-Compaction History Layout\", &requests[2]),])"
|
||||
---
|
||||
Scenario: Pre-turn compaction during model switch (without pre-sampling model-switch compaction): current behavior strips incoming <model_switch> from the compact request and restores it in the post-compaction follow-up request.
|
||||
|
||||
## 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_USER
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user:BEFORE_SWITCH_USER
|
||||
|
||||
## Local 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_USER
|
||||
05:message/assistant:BEFORE_SWITCH_REPLY
|
||||
06:message/user:<SUMMARIZATION_PROMPT>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user:BEFORE_SWITCH_USER
|
||||
04:message/assistant:BEFORE_SWITCH_REPLY
|
||||
05:message/user:<SUMMARIZATION_PROMPT>
|
||||
|
||||
## Local Post-Compaction History Layout
|
||||
00:message/user:BEFORE_SWITCH_USER
|
||||
01:message/user:<COMPACTION_SUMMARY>\nPRETURN_SWITCH_SUMMARY
|
||||
02:message/developer:<model_switch>\nThe user was previously using a different model....
|
||||
03:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
04:message/developer:<personality_spec> The user has requested a new communication st...
|
||||
05:message/user:<AGENTS_MD>
|
||||
06:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
07:message/user:AFTER_SWITCH_USER
|
||||
02:message/developer[3]:
|
||||
[01] <model_switch>\nThe user was previously using a different model....
|
||||
[02] <PERMISSIONS_INSTRUCTIONS>
|
||||
[03] <personality_spec> The user has requested a new communication st...
|
||||
03:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
04:message/user:AFTER_SWITCH_USER
|
||||
|
||||
@@ -6,14 +6,16 @@ Scenario: Remote manual /compact where remote compact output is compaction-only:
|
||||
|
||||
## 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
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:hello remote compact
|
||||
03:message/assistant:FIRST_REMOTE_REPLY
|
||||
|
||||
## Remote Post-Compaction History Layout
|
||||
00:compaction:encrypted=true
|
||||
01:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
02:message/user:<AGENTS_MD>
|
||||
03:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
04:message/user:after compact
|
||||
02:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
03:message/user:after compact
|
||||
|
||||
@@ -6,11 +6,13 @@ Scenario: Remote manual /compact with no prior user turn still issues a compact
|
||||
|
||||
## Remote Compaction Request
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <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
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:USER_ONE
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
---
|
||||
source: core/tests/suite/compact_remote.rs
|
||||
assertion_line: 1876
|
||||
expression: "format_labeled_requests_snapshot(\"After a prior manual /compact produced an older remote compaction item, the next turn hits remote auto-compaction before the next sampling request. The compact request carries forward that earlier compaction item, and the next sampling request shows the latest compaction item with context reinjected before USER_TWO.\",\n&[(\"Remote Compaction Request\", &compact_request),\n(\"Second Turn Request (After Compaction)\", &second_turn_request),])"
|
||||
---
|
||||
Scenario: After a prior manual /compact produced an older remote compaction item, the next turn hits remote auto-compaction before the next sampling request. The compact request carries forward that earlier compaction item, and the next sampling request shows the latest compaction item with context reinjected before USER_TWO.
|
||||
@@ -13,6 +12,7 @@ Scenario: After a prior manual /compact produced an older remote compaction item
|
||||
00:message/user:USER_ONE
|
||||
01:compaction:encrypted=true
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user:<AGENTS_MD>
|
||||
04:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
05:message/user:USER_TWO
|
||||
03:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
04:message/user:USER_TWO
|
||||
|
||||
@@ -6,15 +6,17 @@ Scenario: Remote mid-turn continuation compaction after tool output: compact req
|
||||
|
||||
## 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
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:USER_ONE
|
||||
03:function_call/test_tool
|
||||
04:function_call_output:unsupported call: test_tool
|
||||
|
||||
## 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
|
||||
04:compaction:encrypted=true
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:USER_ONE
|
||||
03:compaction:encrypted=true
|
||||
|
||||
@@ -1,19 +1,21 @@
|
||||
---
|
||||
source: core/tests/suite/compact_remote.rs
|
||||
expression: "format_labeled_requests_snapshot(\"Remote mid-turn compaction where compact output has only a compaction item: continuation layout reinjects context before that compaction item.\",\n&[(\"Remote Compaction Request\", &compact_request),\n(\"Remote Post-Compaction History Layout\", &requests[1]),])"
|
||||
expression: "format_labeled_requests_snapshot(\"Remote mid-turn compaction where compact output has only a compaction item: continuation layout reinjects context before that compaction item.\",\n&[(\"Remote Compaction Request\", &compact_request),\n(\"Remote Post-Compaction History Layout\", &post_compact_turn_request),])"
|
||||
---
|
||||
Scenario: Remote mid-turn compaction where compact output has only a compaction item: continuation layout reinjects context before that compaction item.
|
||||
|
||||
## 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
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:USER_ONE
|
||||
03:function_call/test_tool
|
||||
04:function_call_output:unsupported call: test_tool
|
||||
|
||||
## Remote Post-Compaction History Layout
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
03:compaction:encrypted=true
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:compaction:encrypted=true
|
||||
|
||||
@@ -6,7 +6,8 @@ Scenario: Remote pre-turn auto-compaction context-window failure: compaction req
|
||||
|
||||
## 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
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:USER_ONE
|
||||
03:message/assistant:REMOTE_FIRST_REPLY
|
||||
|
||||
@@ -6,7 +6,8 @@ Scenario: Remote pre-turn auto-compaction parse failure: compaction request excl
|
||||
|
||||
## 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
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:turn that exceeds token threshold
|
||||
03:message/assistant:initial turn complete
|
||||
|
||||
@@ -6,18 +6,20 @@ Scenario: Remote pre-turn auto-compaction with a context override emits the cont
|
||||
|
||||
## 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
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:USER_ONE
|
||||
03:message/assistant:REMOTE_FIRST_REPLY
|
||||
04:message/user:USER_TWO
|
||||
05:message/assistant:REMOTE_SECOND_REPLY
|
||||
|
||||
## Remote Post-Compaction History Layout
|
||||
00:message/user:USER_ONE
|
||||
01:message/user:USER_TWO
|
||||
02:compaction:encrypted=true
|
||||
03:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
04:message/user:<AGENTS_MD>
|
||||
05:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
|
||||
06:message/user:USER_THREE
|
||||
04:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
|
||||
05:message/user:USER_THREE
|
||||
|
||||
@@ -1,28 +1,33 @@
|
||||
---
|
||||
source: core/tests/suite/compact_remote.rs
|
||||
assertion_line: 1514
|
||||
expression: "format_labeled_requests_snapshot(\"Remote pre-turn compaction during model switch currently excludes incoming user input, strips incoming <model_switch> from the compact request payload, and restores it in the post-compaction follow-up request.\",\n&[(\"Initial Request (Previous Model)\", &initial_turn_request),\n(\"Remote Compaction Request\", &compact_request),\n(\"Remote Post-Compaction History Layout\", &post_compact_turn_request),])"
|
||||
---
|
||||
Scenario: Remote pre-turn compaction during model switch currently excludes incoming user input, strips incoming <model_switch> from the compact request payload, and restores it in the post-compaction follow-up request.
|
||||
|
||||
## Initial Request (Previous Model)
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
03:message/user:BEFORE_SWITCH_USER
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:BEFORE_SWITCH_USER
|
||||
|
||||
## Remote Compaction Request
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
03:message/user:BEFORE_SWITCH_USER
|
||||
04:message/assistant:BEFORE_SWITCH_REPLY
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:BEFORE_SWITCH_USER
|
||||
03:message/assistant:BEFORE_SWITCH_REPLY
|
||||
|
||||
## Remote Post-Compaction History Layout
|
||||
00:message/user:BEFORE_SWITCH_USER
|
||||
01:compaction:encrypted=true
|
||||
02:message/developer:<model_switch>\nThe user was previously using a different model....
|
||||
03:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
04:message/developer:<personality_spec> The user has requested a new communication st...
|
||||
05:message/user:<AGENTS_MD>
|
||||
06:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
07:message/user:AFTER_SWITCH_USER
|
||||
02:message/developer[3]:
|
||||
[01] <model_switch>\nThe user was previously using a different model....
|
||||
[02] <PERMISSIONS_INSTRUCTIONS>
|
||||
[03] <personality_spec> The user has requested a new communication st...
|
||||
03:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
04:message/user:AFTER_SWITCH_USER
|
||||
|
||||
@@ -6,19 +6,21 @@ Scenario: Second turn changes cwd to a directory with different AGENTS.md; curre
|
||||
|
||||
## First Request (agents_one)
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
04:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
05:message/user:first turn in agents_one
|
||||
04:message/user:first turn in agents_one
|
||||
|
||||
## Second Request (agents_two cwd)
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
04:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
05:message/user:first turn in agents_one
|
||||
06:message/assistant:turn one complete
|
||||
07:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
08:message/user:second turn in agents_two
|
||||
04:message/user:first turn in agents_one
|
||||
05:message/assistant:turn one complete
|
||||
06:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
07:message/user:second turn in agents_two
|
||||
|
||||
@@ -1,21 +1,22 @@
|
||||
---
|
||||
source: core/tests/suite/model_visible_layout.rs
|
||||
assertion_line: 435
|
||||
expression: "format_labeled_requests_snapshot(\"First post-resume turn where pre-turn override sets model to rollout model; no model-switch update should appear.\",\n&[(\"Last Request Before Resume\", &initial_request),\n(\"First Request After Resume + Override\", &resumed_request),])"
|
||||
---
|
||||
Scenario: First post-resume turn where pre-turn override sets model to rollout model; no model-switch update should appear.
|
||||
|
||||
## Last Request Before Resume
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
03:message/user:seed resume history
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:seed resume history
|
||||
|
||||
## First Request After Resume + Override
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
03:message/user:seed resume history
|
||||
04:message/assistant:recorded before resume
|
||||
05:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
|
||||
06:message/user:first resumed turn after model override
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:seed resume history
|
||||
03:message/assistant:recorded before resume
|
||||
04:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
|
||||
05:message/user:first resumed turn after model override
|
||||
|
||||
@@ -1,23 +1,25 @@
|
||||
---
|
||||
source: core/tests/suite/model_visible_layout.rs
|
||||
assertion_line: 337
|
||||
expression: "format_labeled_requests_snapshot(\"First post-resume turn where resumed config model differs from rollout and personality changes.\",\n&[(\"Last Request Before Resume\", &initial_request),\n(\"First Request After Resume\", &resumed_request),])"
|
||||
---
|
||||
Scenario: First post-resume turn where resumed config model differs from rollout and personality changes.
|
||||
|
||||
## Last Request Before Resume
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
03:message/user:seed resume history
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:seed resume history
|
||||
|
||||
## First Request After Resume
|
||||
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
01:message/user:<AGENTS_MD>
|
||||
02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
03:message/user:seed resume history
|
||||
04:message/assistant:recorded before resume
|
||||
05:message/developer:<model_switch>\nThe user was previously using a different model. Please continue the conversatio...
|
||||
06:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
|
||||
07:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
08:message/user:resume and change personality
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/user:seed resume history
|
||||
03:message/assistant:recorded before resume
|
||||
04:message/developer[2]:
|
||||
[01] <model_switch>\nThe user was previously using a different model. Please continue the conversatio...
|
||||
[02] <PERMISSIONS_INSTRUCTIONS>
|
||||
05:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
|
||||
06:message/user:resume and change personality
|
||||
|
||||
@@ -6,19 +6,22 @@ Scenario: Second turn changes cwd, approval policy, and personality while keepin
|
||||
|
||||
## First Request (Baseline)
|
||||
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:first turn
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user:first turn
|
||||
|
||||
## Second Request (Turn Overrides)
|
||||
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:first turn
|
||||
05:message/assistant:turn one complete
|
||||
01:message/user[2]:
|
||||
[01] <AGENTS_MD>
|
||||
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
|
||||
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
03:message/user:first turn
|
||||
04:message/assistant:turn one complete
|
||||
05:message/developer[2]:
|
||||
[01] <PERMISSIONS_INSTRUCTIONS>
|
||||
[02] <personality_spec> The user has requested a new communication style. Future messages should adhe...
|
||||
06:message/user:<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>
|
||||
07:message/developer:<PERMISSIONS_INSTRUCTIONS>
|
||||
08:message/developer:<personality_spec> The user has requested a new communication style. Future messages should adhe...
|
||||
09:message/user:second turn with context updates
|
||||
07:message/user:second turn with context updates
|
||||
|
||||
Reference in New Issue
Block a user