feat: expose passive request metadata and response links - #5519

* Preserve received response history on current v1

* feat: expose passive request metadata and response links (#5519)

Observe passive request metadata on repaired history

Co-authored-by: markstuart-oai <[email protected]>

---------

Co-authored-by: markstuart-oai <[email protected]>

* Preserve received response history on current v1

* fix: preserve trace context on repaired history base

* Preserve defined trace flags and manual action budgets

* Sequence trace regression tool replies before final model output

* feat: expose passive request metadata and response links (#5519)

Observe passive request metadata on repaired history

Co-authored-by: markstuart-oai <[email protected]>

* Validate native trace prefix widths and fresh-root controls

* Align manual continuation trace and observation arguments

* Fix worker deadline fixtures and Windows storage type checks

* Verify the winning reply when manual responses race

* Check complete trace handles and both MCP callback parents

* Observe child turns before testing unconfirmed cancellation

* Respect supported platforms in SQLite trace fixtures

* Distinguish caller exports from disabled child work

* Preserve native child callback tracing ownership

* Distinguish child trace exports and surface callback failures

* Keep remote trace ancestry separate from private SDK policy

* Preserve owned child tracing policy across native admission

* Avoid callback scheduling assumptions in trace policy test

* Separate session setup from concurrent trace policy admissions

* Account for split trace processor batches in loop-loss test

---------

Co-authored-by: markstuart-oai <[email protected]>

* Expose typed reasons for owned model output failures

* Handle the expected parser disconnect in the reason fixture

* Preserve received response history on current v1

* fix: preserve trace context on repaired history base

* Fix CI assumptions about child snapshots and temporary directories

* Preserve defined trace flags and manual action budgets

* Sequence trace regression tool replies before final model output

* feat: expose passive request metadata and response links (#5519)

Observe passive request metadata on repaired history

Co-authored-by: markstuart-oai <[email protected]>

* Keep integrity reason tests within the native enum contract

* Validate native trace prefix widths and fresh-root controls

* Align manual continuation trace and observation arguments

* Fix worker deadline fixtures and Windows storage type checks

* Verify the winning reply when manual responses race

* Check complete trace handles and both MCP callback parents

* Observe child turns before testing unconfirmed cancellation

* Respect supported platforms in SQLite trace fixtures

* Distinguish caller exports from disabled child work

* Preserve native child callback tracing ownership

* Distinguish child trace exports and surface callback failures

* Keep remote trace ancestry separate from private SDK policy

* Preserve owned child tracing policy across native admission

* Avoid callback scheduling assumptions in trace policy test

* Separate session setup from concurrent trace policy admissions

* Account for split trace processor batches in loop-loss test

* Wait for a pending observation read before cancellation

* Wait for asynchronous release command before checking child retirement

---------

Co-authored-by: markstuart-oai <[email protected]>

…5517)

* fix: report captured context limits and model defaults

* Expose typed reasons for owned model output failures

* Handle the expected parser disconnect in the reason fixture

* Report the compactor's context window on terminal overflow

* Preserve received response history on current v1

* Fill overflow usage from the model that sampled the request

* Import the types and assertions used by context metadata tests

* fix: preserve trace context on repaired history base

* Fix CI assumptions about child snapshots and temporary directories

* Preserve defined trace flags and manual action budgets

* Sequence trace regression tool replies before final model output

* feat: expose passive request metadata and response links (#5519)

Observe passive request metadata on repaired history

Co-authored-by: markstuart-oai <[email protected]>

* Keep integrity reason tests within the native enum contract

* Validate native trace prefix widths and fresh-root controls

* Align manual continuation trace and observation arguments

* Fix worker deadline fixtures and Windows storage type checks

* Verify the winning reply when manual responses race

* Check complete trace handles and both MCP callback parents

* Observe child turns before testing unconfirmed cancellation

* Respect supported platforms in SQLite trace fixtures

* Distinguish caller exports from disabled child work

* Preserve native child callback tracing ownership

* Distinguish child trace exports and surface callback failures

* Keep remote trace ancestry separate from private SDK policy

* Preserve owned child tracing policy across native admission

* Avoid callback scheduling assumptions in trace policy test

* Separate session setup from concurrent trace policy admissions

* Account for split trace processor batches in loop-loss test

---------

Co-authored-by: markstuart-oai <[email protected]>

* fix: report captured context limits and model defaults

* feat: edit detached native sampling requests

* Expose typed reasons for owned model output failures

* Report prepared-request mid-turn compaction failures

* Handle the expected parser disconnect in the reason fixture

* Report the compactor's context window on terminal overflow

* Borrow the sampling prompt when no request editor is active

* Preserve received response history on current v1

* Fill overflow usage from the model that sampled the request

* Import the types and assertions used by context metadata tests

* fix: preserve trace context on repaired history base

* Validate prepared requests against the selected tool roster

* Fix CI assumptions about child snapshots and temporary directories

* Preserve defined trace flags and manual action budgets

* Sequence trace regression tool replies before final model output

* Preserve explicit provider overrides in request editor preflight

* Keep request editor forwarding optional for run_sync overrides

* feat: expose passive request metadata and response links (#5519)

Observe passive request metadata on repaired history

Co-authored-by: markstuart-oai <[email protected]>

* Keep integrity reason tests within the native enum contract

* Let the turn report fatal prepared-request compaction once

* Validate native trace prefix widths and fresh-root controls

* Validate sampled manual tools and retain request callback tracing

* Align manual continuation trace and observation arguments

* Fix worker deadline fixtures and Windows storage type checks

* Preserve existing submit overrides on ordinary agent runs

* Verify the winning reply when manual responses race

* Check complete trace handles and both MCP callback parents

* Observe child turns before testing unconfirmed cancellation

* Respect supported platforms in SQLite trace fixtures

* Distinguish caller exports from disabled child work

* Preserve native child callback tracing ownership

* Distinguish child trace exports and surface callback failures

* Keep remote trace ancestry separate from private SDK policy

* Preserve owned child tracing policy across native admission

* Avoid callback scheduling assumptions in trace policy test

* Separate session setup from concurrent trace policy admissions

* Account for split trace processor batches in loop-loss test

* fix: preserve completed answers when request editing skips compaction

---------

Co-authored-by: markstuart-oai <[email protected]>

#5516)

* Stop sampling retries after terminal authentication failure

* fix: report captured context limits and model defaults

* feat: edit detached native sampling requests

* Expose typed reasons for owned model output failures

* Report prepared-request mid-turn compaction failures

* Initialize the receipt field in the protocol test fixture

* Handle the expected parser disconnect in the reason fixture

* Report the compactor's context window on terminal overflow

* Borrow the sampling prompt when no request editor is active

* Preserve received response history on current v1

* Fill overflow usage from the model that sampled the request

* Share bounded authentication recovery across fallback

* Import the types and assertions used by context metadata tests

* fix: preserve trace context on repaired history base

* Validate prepared requests against the selected tool roster

* Validate rotated credentials in native recovery tests

* Fix CI assumptions about child snapshots and temporary directories

* Preserve defined trace flags and manual action budgets

* Sequence trace regression tool replies before final model output

* Distinguish preconnect and sampling authentication recovery tests

* Preserve explicit provider overrides in request editor preflight

* Keep request editor forwarding optional for run_sync overrides

* feat: expose passive request metadata and response links (#5519)

Observe passive request metadata on repaired history

Co-authored-by: markstuart-oai <[email protected]>

* Keep integrity reason tests within the native enum contract

* Let the turn report fatal prepared-request compaction once

* Validate native trace prefix widths and fresh-root controls

* Validate sampled manual tools and retain request callback tracing

* Align manual continuation trace and observation arguments

* Fix worker deadline fixtures and Windows storage type checks

* Preserve existing submit overrides on ordinary agent runs

* Verify the winning reply when manual responses race

* Check complete trace handles and both MCP callback parents

* Observe child turns before testing unconfirmed cancellation

* Respect supported platforms in SQLite trace fixtures

* Distinguish caller exports from disabled child work

* Preserve native child callback tracing ownership

* Distinguish child trace exports and surface callback failures

* Keep remote trace ancestry separate from private SDK policy

* Preserve owned child tracing policy across native admission

* Avoid callback scheduling assumptions in trace policy test

* Separate session setup from concurrent trace policy admissions

* Account for split trace processor batches in loop-loss test

* fix: preserve completed answers when request editing skips compaction

---------

Co-authored-by: markstuart-oai <[email protected]>