## What changed
Add `WorldStateSectionContribution::with_window_prefix()` to render extension developer fragments as separate messages before retained history when building a context window, including after compaction. Updates within an existing window still append to history. Ignore fragments with other roles for sections that opt in.
## Testing
Add a unit test for prefix placement and duplicate avoidance, plus local and remote compaction scenarios covering live updates, persisted replacement history, and rejection of non-developer fragments.
GitOrigin-RevId: 8621457c6eec17f1585ca8e6fa154b1bf3257330
## Why
Incremental-tool windows recorded base instructions only at setup, so a catalog refresh for the same model could leave active instructions stale. Instruction changes need to reach the model without rewriting the existing history prefix.
## What changed
- Track model identity and instruction content independently, appending a `model_instructions` developer message when either changes. Explicitly mark replacement or removal of base instructions, and avoid repeating unchanged updates.
- Start new windows after compaction with the latest model instructions while preserving custom base instructions.
- Preserve the recorded window base during local compaction retries, including empty instructions, and rebuild current model instructions when reconstructing child context.
## Testing
Add integration tests and request snapshots for catalog refreshes, instruction removal, model switches, compaction, restart, and forks. Extend regression coverage for legacy snapshots and local compaction retries.
GitOrigin-RevId: eeca69067b4d9cd91c817732d79b4d5c1faa18b9
## Why
Message roles and content classifications do not identify who supplied each context part. Source attribution needs to survive prompt assembly and history truncation, including messages that combine text from different producers.
## What changed
- Add per-part `ContentItemMetadata` for user input, developer instructions, `AGENTS.md`, skills, harness context, command hooks, and tool context with optional callable namespaces.
- Carry attribution alongside content and classifications through contextual fragments, extension prompts, hook output, and agent messages. Keep tool-provided context-window hints separate from harness text.
- Preserve the source of retained text slices during compaction and attribute generated truncation notices to the harness. Default missing historical attribution to unknown.
- Attribute host MCP calls using cached tool namespaces only when catalog revisions remain stable, without starting servers or refreshing catalogs for attribution.
- Send the new metadata to Responses Lite and strip it from requests to endpoints that do not support it.
## Testing
Extend compaction tests to cover mixed sources, missing or extra metadata entries, and discarded media. Update Responses Lite request assertions to verify endpoint-specific attribution handling.
GitOrigin-RevId: b0ebc929b7c60f3ec49d1affbf897312d63edcc8
## What changed
- Add the disabled-by-default `output_token_replay` feature to request `output.encrypted_content` from OpenAI providers.
- Preserve encrypted message and tool-call output, message and function-call status, and output-text `annotations` and `logprobs` through history and replay. Update the generated protocol schemas and SDK types.
- Strip output ciphertext from requests to other providers while retaining it in stored history, including after replay is disabled. Remove encrypted content from memory extraction inputs.
## Testing
Add integration coverage for the feature/provider combinations, metadata replay across follow-up requests, and history preservation when resuming with replay disabled.
GitOrigin-RevId: 77729a021b6771933402aebe74ece8eb39c057e2
## Why
Changing the incremental tools setting on resume should not move tool declarations and base instructions within an existing context window.
## What changed
- Determine the current window's tool declaration mode from its history, and apply the incremental tools setting when building a new window after compaction or a context reset.
- Use that mode consistently for sampling, remote compaction, startup prewarm, prompt debugging, and Guardian input budgeting.
- Preserve tool declarations alongside their comparison baseline in full-history agent forks, including compacted histories; remove them together when rebuilding context.
## Testing
Add request snapshots covering legacy resume, migration after remote compaction or a context reset, disabling incremental tools, and tool updates after restart. Extend agent fork and WebSocket startup prewarm tests to cover retained declarations and incremental tools.
GitOrigin-RevId: 7c46849a1788027a8435082e4d1f7e7f48d2700c
## What changed
- Record nonempty base instructions as a developer message after tool declarations at the start of each incremental tool context window, and omit the request-level `instructions` field.
- Preserve this prefix when rebuilding history after local or remote compaction, while keeping the compaction summary last.
- Count recorded base instructions once when estimating context usage and trimming tool outputs.
## Testing
Add regression coverage for instruction placement, omission of request-level instructions, compaction ordering, and token accounting. Exercise remote compaction trimming with both request-level and recorded base instructions.
GitOrigin-RevId: 6a6fda92c5c6eb33852a77b38d34c028cf78b164
## Why
Manual, pre-turn, and post-turn compaction previously deferred rebuilding initial context until the next turn. Their saved replacement history could omit refreshed instructions and skill catalogs.
## What changed
- Install initial context during local and remote compaction, before the last real user message or summary, keeping the compaction summary last.
- Persist matching full world-state and turn-context baselines with every replacement instead of retaining only partial extension metadata.
- Build replacement context and recompute token usage for the current model even when the previous model performs compaction. Reuse that captured context for eligible current-model retries.
- Capture manual compaction context centrally and propagate preparation errors to the task runner.
## Testing
Update assertions and snapshots for context ordering, refreshed instructions, resume and fork history, current-model checkpoint baselines, and cloud skill catalog retention across compaction and resume.
GitOrigin-RevId: 8572a76c31c6884a3c580b3bbb350d49af876bd1
## Why
Configuration reloads must honor current managed restrictions without granting new enterprise MCP authority to existing sessions or overwriting newer configuration with stale snapshots.
## What changed
- Allow enterprise managed authentication only for configured MCP servers. Remove plugin `ema_auth` overlays from the schema and disable servers that still use them.
- Refresh ordinary MCP settings while preserving session settings and initially admitted enterprise registrations. Disable enterprise MCP when its registration changes, policy revokes access, or configuration loading or resolution fails; require a new session to restore enterprise authority.
- Publish refreshes only when their captured configuration is still current, with bounded retries in app-server reloads. Preserve updated managed restrictions even when a refresh is rejected.
- Finish processing other thread refreshes before `config/mcpServer/reload` reports a rejection, and document that an error can accompany partially applied changes.
## Testing
Add regression coverage for stale refreshes, bounded retries, managed-policy revocation, persistent enterprise disablement, ordinary MCP transport changes, and rejection of plugin enterprise authentication. Verify that denied enterprise servers receive no requests.
GitOrigin-RevId: 34429cd339c1ec152a2ee8697cb29f0cff5d9e5f
## Why
Local compaction flattened retained user messages into a single text part, losing their original content boundaries and per-part annotations.
## What changed
Preserve the original content parts and annotations for text-only user messages that fit within the token budget. Borrow the original messages until selected history entries are materialized, and rebuild only the text fallback for truncated messages or messages containing media.
## Testing
Extend unit coverage for text boundaries, empty parts, omitted media, and retained metadata. Update the compaction integration test to verify that a multipart user message survives unchanged in the next request and retains its content parts and annotations in persisted replacement history.
GitOrigin-RevId: 39d9df9ae5360506c2a4bdeac76d89198dbbd39c
## Why
The 32 KiB per-result cap and 128 KiB aggregate budget discard tool metadata even when the outgoing request has room to retain it.
## What changed
- Remove the per-result capture cap and raise the aggregate executed-tool metadata budget to 2 MiB.
- Apply a 15 MiB soft budget to serialized HTTP requests and WebSocket messages, using the actual WebSocket delta. Trim optional result metadata on the wire copy while preserving ordinary content and logical history.
- Prioritize `openai/resource_access` metadata during trimming, and include `overage_bytes` in omission markers.
- Record bytes removed by metadata budgets in `codex.tool_metadata.shed_bytes`, tagged by stage.
## Testing
Add coverage for HTTP and WebSocket message boundaries, resource preservation, residual marker removal, unchanged history, and shedding metrics. Update direct-tool and code-mode tests to verify metadata survives beyond the previous limits.
GitOrigin-RevId: ed00996b77945300f60db1e52eff22b4de2707c1
## Why
Exceeding the aggregate metadata budget previously replaced all tool result metadata with omission markers, discarding small results unnecessarily. Oversized results also lost resource-access evidence even when that evidence alone would fit.
## What changed
- Raise the executed-tool-call metadata budget per request from 32 KiB to 128 KiB while retaining the 32 KiB per-result limit.
- Reduce the largest result metadata first and stop once the request fits, preserving smaller results.
- Retain `openai/resource_access` when full metadata exceeds capture, request, or direct-call retained-history limits. Keep resource lists intact, and discard optional result metadata before sacrificing call records, source evidence, or completion markers.
## Testing
Add regression coverage for selective reduction, resource-access retention, serialized request size, and direct-call and Code Mode behavior. Update compaction and truncation tests for the larger request budget.
GitOrigin-RevId: 698e47dcbdd3351e9a031e45ea39053608a5a0e4
## What changed
Remove the session-level capture mode and make thread-owned retained context the default throughout history management. Simplify input ordering, compaction identity preservation, fork handling, and approval freshness checks by removing legacy capture branches.
Keep checkpoint compatibility review separate: unknown or incompatible checkpoints can still use legacy review while retaining user evidence. Set the already-removed `guardianv2.thread_context` feature's default to false and remove redundant opt-out test variants.
## Testing
Update checkpoint tests to exercise legacy review through restored checkpoint data. Adapt existing compaction, resume, rollback, and fork tests to use unconditional context capture.
GitOrigin-RevId: ab23a0d7aca71d5a103458cff8b0c68137dd9708
## Why
Compaction prompts omitted recorded Code Mode tool calls, leaving them without the nested tool inventory available to normal sampling requests.
## What changed
- Attach pending and retained Code Mode tool metadata to local and remote v2 compaction prompts, including updated result metadata and completeness markers.
- Bound Code Mode metadata separately while preserving captured direct tool records.
- Keep observations omitted from shortened compaction retries available if compaction fails and normal sampling resumes.
## Testing
Add regression coverage for metadata attachment, retry retention, independent budgeting, and binding validation. Extend local and remote compaction tests to check tool inventories with metadata enabled and disabled.
GitOrigin-RevId: 1dc012bd5838797c605d981a8fc1b0378a142227
## What changed
Represent images in `ContentItem` and `FunctionCallOutputContentItem` with `ImageReference::Inline`, flattened to preserve the existing `image_url` wire format. Update image producers and consumers and regenerate app-server schemas and SDK artifacts.
Preserve the Python SDK's `InputImageContentItem` and `InputImageFunctionCallOutputContentItem` class names during generation.
## Testing
Add a regression test for stable Python image class names and adapt existing image tests to the shared representation.
GitOrigin-RevId: c38a780ac3314c2ac2deb3afc1b93b94b6f93fec
## Why
Direct tool-call records need to stay associated with the invocation that produced each output, including when call IDs are reused. Completeness must describe the recorded call inventory, independently of tool success.
## What changed
- Attach direct-call records to outputs before they enter history, and set `tool_calls_complete` when the invocation's arguments are fully recorded.
- Bound pending recordings and retained metadata, release reservations on completion or cancellation, and invalidate pending records when capture is disabled.
- Apply request budgets to direct metadata and strip it from inference and compaction inputs when capture is disabled.
- Remove executed-call metadata from app-server raw response notifications and exclude its size from Guardian history retention budgets.
- Track call IDs that bypass dispatch so their reuse cannot incorrectly establish Code Mode completeness.
## Testing
Add regression coverage for direct-call attribution, malformed calls, metadata budgets, cancellation, configuration changes, compaction, notification filtering, and Guardian context isolation.
GitOrigin-RevId: 2ebd39c7f141d04788736491495109841656b4c0
## Why
Remote compaction already uses the normal Responses API, leaving the legacy `/responses/compact` runner unused.
## What changed
- Remove the legacy runner, endpoint client, request types, analytics variant, and obsolete test helpers and snapshots.
- Move tool-output trimming and its metadata tests into `compact_remote_history` for reuse by remote compaction v2.
- Consolidate retained-history filtering in the v2 implementation and remove redundant `RemoteCompactionV2` settings from tests.
## Testing
Extend the retained-history unit test to explicitly check that hook prompts survive compaction.
GitOrigin-RevId: 999bb1391aa22c3c281d6a96f98817d6c9e46ed9
## Why
Model changes during an active turn could leave context using the turn's initial model and settings, even after requests switched to the new model.
## What changed
- Build model, personality, approval, collaboration, app, plugin, and multi-agent instructions from captured step settings.
- Resolve multi-agent policy from the step's effective reasoning effort.
- Use the captured step's context window for full-context metadata and retain that step when rebuilding initial context for compaction.
## Testing
Add regression coverage for model switches updating context without duplicating updates, delegation policy following selected or model-default reasoning effort, and compaction preserving retained context after a model change.
GitOrigin-RevId: 3615c7a3f13f15fdcce9ad13d23311340e0aea88
## Why
Guardian review needs the original user instructions alongside verified answers, even after compaction, resume, or rollback. A summarized or legacy checkpoint cannot establish a complete instruction history.
## What changed
- Capture text user messages in retained context when `guardian_thread_context` is enabled, preserving their message identity through compaction and replay.
- Keep retained instructions and verified answers in arrival order, with independent size and completeness tracking for each family.
- Roll back retained evidence at the exact user-message boundary, including steers that share a turn ID, and apply the same semantics during rollout migration.
- Treat checkpoints without retained user messages as incomplete while preserving their verified answers.
## Testing
- Cover capture, compaction, resume, rollback, child forks, legacy checkpoints, storage bounds, and rollout migration.
GitOrigin-RevId: 72706731b54e5ac8645db61b446d2401afb42235
## Why
Remote compaction's retained-message budget counted text but not images, so
image-heavy history could retain more context than the budget represented.
## What changed
- Add the opt-in `compaction_image_budget` feature to charge retained images
using the existing image size estimate.
- Keep images and their adjacent labels atomic when truncating a boundary
message, while preserving existing text, audio, metadata, and
client-authored developer-message behavior.
- Stop backfilling older messages when an image at the truncation boundary
does not fit.
## Testing
- Add unit coverage for image boundaries, annotations, audio, text-only
messages, and client-authored developer messages.
- Add an integration test covering repeated remote compaction with the feature
enabled, disabled, and left at its default.
GitOrigin-RevId: 88868bbd09d2858939dbae3f8402e1f497b4e3c6
## Why
Local compaction rebuilds preserved user input as a single text item. Carrying
over the original per-item content kinds can leave its annotation metadata out
of sync with the rebuilt content.
## What changed
- Set the rebuilt item's content kind to `user.text` when the original message
had content-kind metadata.
- Preserve the remaining message and harness metadata.
## Testing
- Cover metadata normalization in compacted history.
- Verify persisted replacement history contains the merged text and a matching
`user.text` content kind.
GitOrigin-RevId: cd10b8ec68ef8ec2a272a90182e69875b60dc35c
## What changed
- Wrap response items with optional harness-owned metadata while keeping the persisted response payload shape backward compatible.
- Store compacted-history metadata in an aligned sidecar and reject malformed sidecars.
- Carry metadata through history normalization, compaction, resume, fork, truncation, migration, and rollout recording without sending it to model providers.
## Testing
- Cover legacy rollout compatibility, metadata serialization and validation, compaction retention, and resume/fork reconstruction.
GitOrigin-RevId: 17a6127c9048ff984cb4df4d97c0751a38c29f5f
## What changed
- Add `ResponseItemEnvelope` as the history-owned wrapper for a `ResponseItem`.
- Store envelopes in `ContextManager` while keeping raw-item iteration and consuming APIs for existing callers.
- Preserve envelopes when compaction and history normalization rewrite retained items, and wrap newly synthesized items.
## Testing
- Cover envelope access, mutation, and conversion back to raw response items.
- Cover annotated history replacement and annotated user-message collection for compaction.
GitOrigin-RevId: 3fa2e7bdd981b08cc7aec410c80deccaecdabab4
## What changed
- Add provider-owned remote compaction capabilities for unsupported, v1, and v2 protocols.
- Mark Amazon Bedrock as v1-only so manual and automatic compaction use `/v1/responses/compact`, even when the v2 feature is enabled.
- Preserve v2 support for OpenAI and Azure Responses providers and local compaction for unsupported providers.
## Testing
- Cover Amazon Bedrock manual and automatic remote compaction, including endpoint selection, authentication headers, model selection, and reuse of the compacted summary.
GitOrigin-RevId: d58093178605d1f8155b93d9a161408177f6ac72
## Why
The `<current_date>` in environment context could diverge from the clock used by current-time features, especially when a host provides an external clock.
## What changed
- Read the current time from the session's time provider whenever world state is built, and render its local date in environment context.
- Use each session's own thread ID for clock reads, including guardian sessions.
- Propagate clock-read failures through turn error events and stop before model inference.
## Testing
- Cover date updates across turns and app-server requests.
- Verify guardian clock reads use the corresponding root or guardian thread ID and do not run during prewarm.
- Verify clock failures emit an error without sending an inference request.
GitOrigin-RevId: bb7f32ccc0229b7bc6f14d7356db00bcce78066d
## What changed
- Retain bounded, non-completion agent messages in remote v2 compaction history so delegated tasks remain available on follow-up turns.
- Account for encrypted agent-message content when estimating token usage and place restored initial context before the latest real user or agent message.
- Exclude child completion messages from retained follow-up history and strip inherited parent agent messages when forking a child.
## Testing
- Extend compaction, history-estimation, and agent-fork tests to cover encrypted delegated tasks, child completions, context ordering, and fork sanitization.
GitOrigin-RevId: ba4392e9cfdf4ecbcdc9c7d8581d58a8d2d78260
## What changed
- Add protocol types and `ResponseItem` helpers for attaching and clearing
locally recorded tool-call names and arguments.
- Bound serialized metadata across a prompt, replacing oversized arguments and
omitted calls with trusted truncation details.
- Prevent deserialized response items or model-provided arguments from forging
locally generated tool-call and truncation metadata.
## Testing
- Cover prompt-wide size limits, omission accounting, idempotent bounding, and
forged truncation markers.
GitOrigin-RevId: 960a223437ce81fe6b4cbb5fc7a9774408b2755b
## What changed
- Make `McpRuntime` own the published MCP configuration, connections, elicitation routing, and selected capability roots for a thread.
- Capture immutable MCP bindings for model steps and tool calls so in-flight work keeps a consistent connection set and approval authority while refreshed state is published atomically.
- Mark MCP state dirty when relevant configuration, plugins, environments, authentication, or elicitation capabilities change, then rebuild it before the next sampling request or out-of-band MCP operation.
- Separate config reloads from server invalidation: `ReloadMcpConfig` applies resolved MCP inputs, while `RefreshMcpServers` requests reinitialization from the thread's latest state.
## Testing
- Cover refreshed state visibility for existing turns, stable step bindings, current approval authority, cancelled refresh retries, resource-client reconciliation, and Apps recovery between sampling requests.
GitOrigin-RevId: 59eabb1aa8dc083426bd18ef4d3630508f376401
## What changed
- Add the `supports_standalone_web_search` model-provider setting, defaulting to `false`, and preserve it in remote thread configuration.
- Enable the standalone `web.run` tool for opted-in custom Responses providers when web search is enabled and the runtime provider supports it.
- Send standalone search requests through the custom provider's endpoint and authentication.
## Testing
- Cover opt-in, default-off, disabled-search, and unsupported-provider behavior.
- Verify custom-provider search request routing and authorization through the app server.
GitOrigin-RevId: 7c5f96b0ce924ad2b9715c45bfc635e89fc39cff
## What changed
- Remove the step-scoped `ExtensionData` argument from context, turn-input, and tool contributors.
- Pass the host's optional `McpResourceClient` through `ThreadStartInput` so extensions can retain session capabilities explicitly.
- Keep the MCP resource client in skills-owned session state for catalog loading and skill tools.
GitOrigin-RevId: bafa77bcd998aff408d6a396c5fd9ac268c4cce4
## What changed
- Add an `ExtensionData` store to each `StepContext`.
- Pass the step store to context, world-state, turn-input, and tool contributors so extensions can use capabilities bound to the current sampling step.
- Preserve the captured step context when rebuilding initial context during compaction.
GitOrigin-RevId: 51f3105d3a793f60534f122f9be8247c131c2ca5
## What changed
- Add a `ResponseItemId` type that generates item-specific prefixes with UUIDv7 suffixes and use it across response items.
- Keep deserialization permissive for legacy histories, but omit empty or unprefixed item IDs from HTTP and WebSocket requests.
- Export the new type in the generated TypeScript protocol schema.
## Testing
- Cover prefixed ID generation, legacy deserialization, prefix recognition, and outbound request filtering.
GitOrigin-RevId: 0209fe430c826d0ae88bc4648652c4ebf390c4a4
## Why
With deferred executors, a turn can begin before a remote environment
attaches. AGENTS.md discovery previously ran only during session setup,
so instructions from a later environment never reached the model or the
session instruction sources.
WorldState persistence has now landed, so this uses the durable
model-visible baseline directly instead of carrying a temporary
resume/fork compatibility path.
## What
- Add an `AgentsMdManager` in `SessionServices` to own host
instructions, loaded state, and refresh caching.
- When `DeferredExecutor` is enabled, refresh AGENTS.md when attached
environment selections change and freeze the result in the corresponding
`StepContext`.
- Represent AGENTS.md as a persisted WorldState section for every
session, with bounded initial, replacement, and removal updates.
- Remove duplicate AGENTS.md state and rendering from
`SessionConfiguration` and `TurnContext`.
- Build initial context, per-request updates, and compaction context
from the same step-scoped value.
- On resume and fork, compare current instructions with the restored
WorldState baseline and inject a replacement exactly once when they
differ.
Builds on #29833, #29835, and #29837.
## Tests
- Covers a remote environment becoming ready mid-turn, with AGENTS.md
appearing on the next request exactly once and updating canonical
instruction sources.
- Covers full, unchanged, replaced, and removed AGENTS.md WorldState
rendering.
- Covers changed instructions across cold resume and fork without
duplicate reinjection.
- Covers remote-v2 compaction retaining creation-time instructions in
the live session and cold resume appending one replacement when the
source changed.
- Ran focused `codex-core` AGENTS.md, WorldState, and context-update
test suites.
## Why
Follow-up to #29249 and its [compaction review
thread](https://github.com/openai/codex/pull/29249#discussion_r3455055101).
During a turn, environment readiness can change between sampling
requests. Inline compaction must render the same model-visible
`WorldState` used by the request it follows. Rebuilding that state
during compaction can observe a newer environment, make replacement
history disagree with what the model saw, and suppress the next
environment update.
## What changed
- Make `run_turn` own the current `Arc<WorldState>` and replace it only
between sampling requests.
- Build each state from an explicitly chosen environment snapshot, diff
deferred-executor steps against the turn-owned state, and retain the
latest state in `ContextManager` only for cross-turn and resume
tracking.
- Pass the exact turn-owned state into inline compaction and explicit
new-context-window replacement.
- Carry that state with
`InitialContextInjection::BeforeLastUserMessage`, so replacement context
and its stored baseline cannot come from different snapshots.
- Remove obsolete state-recapture helpers and ambiguous TurnContext-only
WorldState builders.
- Add an integration test that moves an environment from starting to
ready during a paused turn, triggers compaction, and verifies the next
request receives the readiness update exactly once.
## Test plan
- `just test -p codex-core
deferred_executor_compaction_preserves_then_updates_environment_once`
- `just test -p codex-core process_compacted_history`
- `just test -p codex-core mid_turn_continuation_compaction`
- `just test -p codex-core build_initial_context`
- `just test -p codex-core
ignores_session_prefix_messages_when_truncating`
## Description
This PR cuts Codex over from generic `ResponseItem.metadata` (introduced
here: https://github.com/openai/codex/pull/28355) to
`ResponseItem.internal_chat_message_metadata_passthrough`, which is the
blessed path and has strongly-typed keys.
For now we have to drop this MAv2 usage of `metadata`:
https://github.com/openai/codex/pull/28561 until we figure out where
that should live.
## Why
`ResponseItem` variants do not have a consistent internal ID shape: some
variants carry required IDs, some carry optional IDs, and some cannot
represent an ID at all. The existing fields also use inconsistent serde,
TypeScript, and JSON-schema annotations. A single enum-level access path
is needed before history recording can assign and retain IDs.
This PR establishes that internal model only. It intentionally does not
generate or serialize IDs; allocation and wire persistence are isolated
in the stacked follow-up.
## What changed
- Give every concrete `ResponseItem` variant an `Option<String>` ID
field.
- Apply the same internal-only annotations to every ID field:
`#[serde(default, skip_serializing)]`, `#[ts(skip)]`, and
`#[schemars(skip)]`.
- Add `ResponseItem::id()` and `ResponseItem::set_id()` as the shared
accessors.
- Preserve IDs when history items are rewritten for truncation.
- Adapt consumers that previously assumed reasoning and image-generation
IDs were required.
- Regenerate app-server schemas so the hidden fields are represented
consistently.
The serde catch-all `ResponseItem::Other` remains ID-less because it
must remain a unit variant.
## Test plan
- `cargo check --tests -p codex-core -p codex-api -p codex-rollout-trace
-p codex-image-generation-extension`
- `just test -p codex-protocol`
- `just test -p codex-app-server-protocol`
- `just test -p codex-api -p codex-rollout-trace -p
codex-image-generation-extension`
- `just test -p codex-core event_mapping`
## Summary
This keeps inter-agent communication on the existing raw response item
path and adds a join key for MAv2 tool calls.
MAv2 `spawn_agent`, `send_message`, and `followup_task` now stamp the
originating tool call id into `ResponseItemMetadata.source_call_id` on
the raw `ResponseItem::AgentMessage`. App-server clients can join that
raw item back to the existing tool/activity event by call id, while
using the raw agent message's existing sender, receiver, and content
fields.
No new app-server `ThreadItem` or notification type is added.
## Tests
- `just fmt`
- `just write-app-server-schema`
- `just test -p codex-protocol`
- `just test -p codex-app-server-protocol`
- `just test -p codex-core
multi_agent_v2_spawn_returns_path_and_send_message_accepts_relative_path`
- `just test -p codex-core
multi_agent_v2_followup_task_completion_notifies_parent_on_every_turn`
- `just fix -p codex-protocol`
- `just fix -p codex-app-server-protocol`
- `just fix -p codex-core`
## Description
This PR adds an optional `metadata` field to `ResponseItem` for
Responses API calls. Only mechanical plumbing, no actual values
populated and sent yet. Turns out just adding a new field to
`ResponseItem` has quite a large blast radius already.
This change is backwards compatible because `metadata` is optional and
omitted when absent, so existing response items and rollout history
without it still deserialize and requests that do not set it keep the
same wire shape. For provider compatibility, we strip out `metadata`
before non-OpenAI Responses requests so Azure and AWS Bedrock never see
this field.
My followup PR here will actually make use of it to start storing and
passing along `turn_id`: https://github.com/openai/codex/pull/28360
## What changed
- Added `ResponseItemMetadata` with optional `turn_id`, plus optional
`metadata` on Responses API item variants and inter-agent communication.
- Preserved item metadata through response-item rewrites such as
truncation, missing tool-output synthesis, compaction history
rebuilding, visible-history conversion, rollout/resume, and generated
app-server schemas/types.
- Strip item metadata from non-OpenAI Responses requests while
preserving it for OpenAI-shaped requests.
- Updated the mechanical fixture/test construction churn required by the
new optional field.
## Summary
- snapshot `comp_hash` into `TurnContext` when the turn is created and
use that snapshot as the downstream source of truth
- persist the turn hash in rollout context and recover it into
previous-turn settings during resume and fork replay
- compact existing history with the previous model only when both
adjacent turns provide hashes and the values differ
- record `comp_hash_changed` as the compaction reason
- cover ordinary transitions, resume, and missing-hash compatibility
with end-to-end tests
## Why
History produced under one compaction-compatible model configuration may
not be safe to carry directly into another. Compacting at the turn
boundary converts that history before context updates and the new user
message are added. Persisting the turn snapshot in `TurnContextItem`
makes the same protection work after resuming a rollout.
A missing hash is not treated as evidence of incompatibility. `None →
Some`, `Some → None`, and `None → None` do not trigger compaction; only
`Some(previous) → Some(current)` with unequal values does.
## Stack
- depends on #27532
- #27532 is based directly on `main`
## Testing
- `just test -p codex-core pre_sampling_compact_` — 6 passed
- `just test -p codex-core
turn_context_item_uses_turn_context_comp_hash_snapshot` — passed
- `just fix -p codex-core -p codex-protocol -p codex-analytics -p
codex-models-manager`
## Why
Older sessions can contain model-warning records persisted as `user`
messages, including the unified exec process-limit warning, the
`apply_patch`-via-`exec_command` warning, and the model-mismatch
high-risk cyber fallback warning. Those warnings are no longer produced
as conversation history items, but when old sessions compact they should
still be recognized as injected context rather than preserved as real
user turns.
## What changed
- Removed `record_model_warning` and the production paths that emitted
these warning messages into conversation history.
- Added `LegacyUnifiedExecProcessLimitWarning`,
`LegacyApplyPatchExecCommandWarning`, and `LegacyModelMismatchWarning`
contextual fragments that are used only for matching old persisted
messages.
- Registered the legacy fragments with contextual user message detection
so compaction filters them through the existing fragment path.
- Added focused compaction coverage for old warning messages being
dropped during compacted-history processing.
## Testing
- `cargo test -p codex-core warning`
- `just fix -p codex-core`
## Why
Dogfooder feedback exposed two correctness gaps in normal-loop overflow
recovery:
1. a sampling request that hit `ContextWindowExceeded` could keep
re-entering auto-compaction indefinitely if the compacted retry still
did not fit, and
2. local compact-history rebuilds flattened user messages down to text,
so an overflowing `[image, "what is this?"]` turn could be retried
without the image after compaction.
That means recovery could either fail to terminate cleanly or proceed
with a materially weakened version of the user request.
## What changed
- Move normal-loop `ContextWindowExceeded` handling into the sampling
retry loop, so successful rescue compaction consumes the provider retry
budget instead of creating an unbounded outer-turn loop.
- Keep compacted user-history rebuilds structured:
`collect_user_messages` now carries user `UserInput` content rather than
flattened strings, and `build_compacted_history` reconstructs full user
messages from that structured representation.
- Preserve image inputs while retaining the existing text-budget
truncation behavior for compacted user history.
- Preserve existing compaction-task failure handling and client-session
reset behavior while bounding repeated overflow retries.
- Add focused regression coverage for:
- recovery after a normal-loop overflow,
- retry-budget exhaustion after repeated overflow,
- local recovery preserving image + text input,
- remote recovery preserving image + text input,
- remote compaction v2 preserving image + text input, and
- compaction failure still terminating cleanly.
The main behavior changes are in `codex-rs/core/src/session/turn.rs` and
`codex-rs/core/src/compact.rs`.
## Verification
- Not run locally; relying on PR CI for this update.
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
API-key-auth remote compaction requests should not inherit
`service_tier` from normal `/responses` turns. This path needs to match
API auth expectations, while ChatGPT-auth remote compaction should keep
reusing the shared request fields that still apply there.
This change keeps the decision inline in
`codex-rs/core/src/compact_remote.rs` only. Under API key auth, the
classic remote `/responses/compact` path now omits `service_tier`; under
ChatGPT auth, it keeps reusing the configured tier.
`codex-rs/core/src/compact_remote_v2.rs` is unchanged. The remote
compaction parity coverage and snapshots were updated to assert the
API-key omission and preserve the ChatGPT-auth behavior.
## Testing
- Updated remote compaction parity coverage in
`codex-rs/core/tests/suite/compact_remote.rs` and the corresponding
snapshots.
## Why
Codex needs a first-class `amazon-bedrock` model provider so users can
select Bedrock without copying a full provider definition into
`config.toml`. The provider has Codex-owned defaults for the pieces that
should stay consistent across users: the display `name`, Bedrock
`base_url`, and `wire_api`.
At the same time, users still need a way to choose the AWS credential
profile used by their local environment. This change makes
`amazon-bedrock` a partially modifiable built-in provider: code owns the
provider identity and endpoint defaults, while user config can set
`model_providers.amazon-bedrock.aws.profile`.
For example:
```toml
model_provider = "amazon-bedrock"
[model_providers.amazon-bedrock.aws]
profile = "codex-bedrock"
```
## What Changed
- Added `amazon-bedrock` to the built-in model provider map with:
- `name = "Amazon Bedrock"`
- `base_url = "https://bedrock-mantle.us-east-1.api.aws/v1"`
- `wire_api = "responses"`
- Added AWS provider auth config with a profile-only shape:
`model_providers.<id>.aws.profile`.
- Kept AWS auth config restricted to `amazon-bedrock`; custom providers
that set `aws` are rejected.
- Allowed `model_providers.amazon-bedrock` through reserved-provider
validation so it can act as a partial override.
- During config loading, only `aws.profile` is copied from the
user-provided `amazon-bedrock` entry onto the built-in provider. Other
Bedrock provider fields remain hard-coded by the built-in definition.
- Updated the generated config schema for the new provider AWS profile
config.
Azure Responses providers were still falling back to local compaction
because the compaction gate only checked
`ModelProviderInfo::is_openai()`.
Move the capability check onto `ModelProviderInfo` with
`supports_remote_compaction()`, backed by the existing Azure Responses
endpoint detection used in `codex-api`, and have `core::compact`
delegate to that helper.
Add regression coverage for:
- OpenAI providers using remote compaction
- Azure providers using remote compaction
- non-OpenAI/non-Azure providers staying on the local path
resolves#17773
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
## Why
`argument-comment-lint` was green in CI even though the repo still had
many uncommented literal arguments. The main gap was target coverage:
the repo wrapper did not force Cargo to inspect test-only call sites, so
examples like the `latest_session_lookup_params(true, ...)` tests in
`codex-rs/tui_app_server/src/lib.rs` never entered the blocking CI path.
This change cleans up the existing backlog, makes the default repo lint
path cover all Cargo targets, and starts rolling that stricter CI
enforcement out on the platform where it is currently validated.
## What changed
- mechanically fixed existing `argument-comment-lint` violations across
the `codex-rs` workspace, including tests, examples, and benches
- updated `tools/argument-comment-lint/run-prebuilt-linter.sh` and
`tools/argument-comment-lint/run.sh` so non-`--fix` runs default to
`--all-targets` unless the caller explicitly narrows the target set
- fixed both wrappers so forwarded cargo arguments after `--` are
preserved with a single separator
- documented the new default behavior in
`tools/argument-comment-lint/README.md`
- updated `rust-ci` so the macOS lint lane keeps the plain wrapper
invocation and therefore enforces `--all-targets`, while Linux and
Windows temporarily pass `-- --lib --bins`
That temporary CI split keeps the stricter all-targets check where it is
already cleaned up, while leaving room to finish the remaining Linux-
and Windows-specific target-gated cleanup before enabling
`--all-targets` on those runners. The Linux and Windows failures on the
intermediate revision were caused by the wrapper forwarding bug, not by
additional lint findings in those lanes.
## Validation
- `bash -n tools/argument-comment-lint/run.sh`
- `bash -n tools/argument-comment-lint/run-prebuilt-linter.sh`
- shell-level wrapper forwarding check for `-- --lib --bins`
- shell-level wrapper forwarding check for `-- --tests`
- `just argument-comment-lint`
- `cargo test` in `tools/argument-comment-lint`
- `cargo test -p codex-terminal-detection`
## Follow-up
- Clean up remaining Linux-only target-gated callsites, then switch the
Linux lint lane back to the plain wrapper invocation.
- Clean up remaining Windows-only target-gated callsites, then switch
the Windows lint lane back to the plain wrapper invocation.
## Why
PR #13783 moved the `codex.rs` unit tests into `codex_tests.rs`. This
applies the same extraction pattern across the rest of `codex-rs/core`
so the production modules stay focused on runtime code instead of large
inline test blocks.
Keeping the tests in sibling files also makes follow-up edits easier to
review because product changes no longer have to share a file with
hundreds or thousands of lines of test scaffolding.
## What changed
- replaced each inline `mod tests { ... }` in `codex-rs/core/src/**`
with a path-based module declaration
- moved each extracted unit test module into a sibling `*_tests.rs`
file, using `mod_tests.rs` for `mod.rs` modules
- preserved the existing `cfg(...)` guards and module-local structure so
the refactor remains structural rather than behavioral
## Testing
- `cargo test -p codex-core --lib` (`1653 passed; 0 failed; 5 ignored`)
- `just fix -p codex-core`
- `cargo fmt --check`
- `cargo shear`
Francis Chalissery