diff --git a/notes/fresh-workspace-handoff.md b/notes/fresh-workspace-handoff.md index 7ef407d9..2826cef7 100644 --- a/notes/fresh-workspace-handoff.md +++ b/notes/fresh-workspace-handoff.md @@ -610,6 +610,9 @@ The Codex-core re-export husks for `epiphany_distillation`, `epiphany_promotion` `codex-core` now re-exports those native types/functions directly from `epiphany-core`, and `CodexThread` calls `epiphany_core::retrieve_workspace` / `index_workspace` / `retrieval_state_for_workspace` directly. +The `epiphany_rollout` husk is gone too; `codex-core::lib` keeps only the +one host-boundary function that passes Codex's turn-boundary predicate into +`epiphany-core`. The runtime-spine job-opening mechanism for heartbeat/specialist launches has also been pulled into `epiphany-core` as `open_runtime_spine_heartbeat_job`. diff --git a/state/ledgers.msgpack b/state/ledgers.msgpack index 9bc995fa..bef56b9f 100644 Binary files a/state/ledgers.msgpack and b/state/ledgers.msgpack differ diff --git a/state/map.yaml b/state/map.yaml index 68d6f6ea..29d6444c 100644 --- a/state/map.yaml +++ b/state/map.yaml @@ -279,5 +279,5 @@ rejected_paths: reason: making Epiphany cleaner inside Codex still preserves the wrong organ; Codex must be starved down to OpenAI subscription auth/model transport, while Epiphany data and subsystem communication move to typed CultCache/CultNet. current_status: - summary: The Codex starvation pass has five typing receipts, eighteen processor cuts, a real physical extraction in `epiphany-codex-bridge`, a source-grounded Codex auth spine inventory, the native `epiphany-openai-adapter` document boundary, a buildable Codex auth/model wrapper in `epiphany-openai-codex-spine`, the first native runtime caller in `epiphany-openai-runtime`, native heartbeat launch planning/job opening in `epiphany-core`, native state-update contract/validation/application in `epiphany-core`, and the route-facing mutation service in `epiphany-codex-bridge`. The bridge owns Codex-facing Epiphany adapters for scene, jobs, context/planning/graph query, retrieval/indexing projection, result projection, runtime-spine result adaptation, launch/prompt doctrine, mutation document mechanics, mutation service update/promote/role-accept/reorient-accept/role-launch/reorient-launch/job-launch/job-interrupt application, live-state projection, pressure/pre-compaction rendering, freshness/reorientation projection, CRRC/coordinator/role-board projection, and acceptance/evidence signal helpers. Vendored app-server now retains only `epiphany_invalidation.rs` as a root Epiphany module because watcher lifecycle is still app-server machinery; `codex_message_processor.rs` still contains route dispatch, JSON-RPC response shaping, watcher registration/snapshotting, and notification emission. The processor is about 10,339 lines, `epiphany_mutation_routes.rs` is about 691 lines after the route-load/notification helper cut and index projection move, `epiphany_state_helpers.rs` is down to a 19-line rollout-state loader, and `codex_thread.rs` is about 1,425 lines after state-update law moved native. `epiphany-openai-adapter` defines CultCache `DatabaseEntry` request/event/receipt/auth-status documents with no Codex app-server or generic JSON dependency. `epiphany-openai-codex-spine` projects `AuthManager` / `CodexAuth` into typed `EpiphanyOpenAiAdapterStatus`, maps typed `EpiphanyOpenAiModelRequest` into Codex API `ResponsesApiRequest`, resolves auth/provider through keeper Codex crates, opens HTTP Responses streams through `codex-api`, maps deltas / completion into typed stream events and receipts, and no longer directly depends on `codex-app-server-protocol` just to name auth mode. `epiphany-openai-runtime` writes OpenAI status/request/stream-event/receipt records plus runtime sessions/jobs/results/events into `epiphany-core::runtime_spine_cache`, can emit the assistant text artifact for legacy result consumers, is now the default executor for startup-only repo birth specialists, and now has `run-worker` to load a durable `EpiphanyRuntimeWorkerLaunchRequest`, call the typed OpenAI runtime, persist typed `EpiphanyRuntimeRoleWorkerResult` / `EpiphanyRuntimeReorientWorkerResult` documents, and complete the original heartbeat/specialist runtime job without Codex worker execution; `codex exec` survives only as explicit fallback in repo-birth startup. `epiphany-mvp-coordinator` now invokes `epiphany-openai-runtime run-worker` for launched runtime job ids and no longer creates a second coordinator-owned shadow runtime job/result as a compensator. `epiphany-core::plan_runtime_spine_heartbeat_launch` validates launch contracts/conflicts and projects durable job bindings/runtime links; `epiphany-core::open_runtime_spine_heartbeat_job` owns the initialize-runtime/ensure-session/create-job sequence and now persists `EpiphanyRuntimeWorkerLaunchRequest` CultCache records keyed by runtime job id, with indexed kind/contract fields plus MessagePack-encoded typed launch documents instead of discarding work intent after queue receipt creation; `roleResult` and `reorientResult` now prefer typed worker result documents and fall back only to generic job summaries for older receipts; `epiphany-core::EpiphanyStateUpdate`, `epiphany_state_update_validation_errors`, and `apply_epiphany_state_update` own state-update document shape and mutation law while `codex-core` calls them for compatibility. Vendored `CodexThread::epiphany_launch_job` is now mostly revision check, persistence validation, launch request handoff, and rollout/session writeback for the compatibility route. Vendored `codex-core` no longer has `epiphany_distillation`, `epiphany_promotion`, `epiphany_proposal`, or `epiphany_retrieval` husk modules; it re-exports those native surfaces from `epiphany-core` directly, and `CodexThread` calls core retrieval functions without a vendored wrapper. `epiphany-runtime-spine` advertises OpenAI adapter status/model-request/stream-event/receipt CultNet schemas and mutation contracts, so the native caller now has a real storage route instead of only JSON-RPC. MCP itself is correctly JSON at its protocol edge; the target is typed Epiphany intent/result/receipt wrappers around MCP, not replacing MCP JSON. The current OpenAI spine still pulls `codex-api` and a large transport dependency stack, so its next cut is dependency starvation after richer live callers move. + summary: The Codex starvation pass has five typing receipts, eighteen processor cuts, a real physical extraction in `epiphany-codex-bridge`, a source-grounded Codex auth spine inventory, the native `epiphany-openai-adapter` document boundary, a buildable Codex auth/model wrapper in `epiphany-openai-codex-spine`, the first native runtime caller in `epiphany-openai-runtime`, native heartbeat launch planning/job opening in `epiphany-core`, native state-update contract/validation/application in `epiphany-core`, and the route-facing mutation service in `epiphany-codex-bridge`. The bridge owns Codex-facing Epiphany adapters for scene, jobs, context/planning/graph query, retrieval/indexing projection, result projection, runtime-spine result adaptation, launch/prompt doctrine, mutation document mechanics, mutation service update/promote/role-accept/reorient-accept/role-launch/reorient-launch/job-launch/job-interrupt application, live-state projection, pressure/pre-compaction rendering, freshness/reorientation projection, CRRC/coordinator/role-board projection, and acceptance/evidence signal helpers. Vendored app-server now retains only `epiphany_invalidation.rs` as a root Epiphany module because watcher lifecycle is still app-server machinery; `codex_message_processor.rs` still contains route dispatch, JSON-RPC response shaping, watcher registration/snapshotting, and notification emission. The processor is about 10,339 lines, `epiphany_mutation_routes.rs` is about 691 lines after the route-load/notification helper cut and index projection move, `epiphany_state_helpers.rs` is down to a 19-line rollout-state loader, and `codex_thread.rs` is about 1,425 lines after state-update law moved native. `epiphany-openai-adapter` defines CultCache `DatabaseEntry` request/event/receipt/auth-status documents with no Codex app-server or generic JSON dependency. `epiphany-openai-codex-spine` projects `AuthManager` / `CodexAuth` into typed `EpiphanyOpenAiAdapterStatus`, maps typed `EpiphanyOpenAiModelRequest` into Codex API `ResponsesApiRequest`, resolves auth/provider through keeper Codex crates, opens HTTP Responses streams through `codex-api`, maps deltas / completion into typed stream events and receipts, and no longer directly depends on `codex-app-server-protocol` just to name auth mode. `epiphany-openai-runtime` writes OpenAI status/request/stream-event/receipt records plus runtime sessions/jobs/results/events into `epiphany-core::runtime_spine_cache`, can emit the assistant text artifact for legacy result consumers, is now the default executor for startup-only repo birth specialists, and now has `run-worker` to load a durable `EpiphanyRuntimeWorkerLaunchRequest`, call the typed OpenAI runtime, persist typed `EpiphanyRuntimeRoleWorkerResult` / `EpiphanyRuntimeReorientWorkerResult` documents, and complete the original heartbeat/specialist runtime job without Codex worker execution; `codex exec` survives only as explicit fallback in repo-birth startup. `epiphany-mvp-coordinator` now invokes `epiphany-openai-runtime run-worker` for launched runtime job ids and no longer creates a second coordinator-owned shadow runtime job/result as a compensator. `epiphany-core::plan_runtime_spine_heartbeat_launch` validates launch contracts/conflicts and projects durable job bindings/runtime links; `epiphany-core::open_runtime_spine_heartbeat_job` owns the initialize-runtime/ensure-session/create-job sequence and now persists `EpiphanyRuntimeWorkerLaunchRequest` CultCache records keyed by runtime job id, with indexed kind/contract fields plus MessagePack-encoded typed launch documents instead of discarding work intent after queue receipt creation; `roleResult` and `reorientResult` now prefer typed worker result documents and fall back only to generic job summaries for older receipts; `epiphany-core::EpiphanyStateUpdate`, `epiphany_state_update_validation_errors`, and `apply_epiphany_state_update` own state-update document shape and mutation law while `codex-core` calls them for compatibility. Vendored `CodexThread::epiphany_launch_job` is now mostly revision check, persistence validation, launch request handoff, and rollout/session writeback for the compatibility route. Vendored `codex-core` no longer has `epiphany_distillation`, `epiphany_promotion`, `epiphany_proposal`, `epiphany_retrieval`, or `epiphany_rollout` husk modules; it re-exports native surfaces from `epiphany-core` directly, and the only rollout adapter left is the real host seam that supplies Codex's turn-boundary predicate. `epiphany-runtime-spine` advertises OpenAI adapter status/model-request/stream-event/receipt CultNet schemas and mutation contracts, so the native caller now has a real storage route instead of only JSON-RPC. MCP itself is correctly JSON at its protocol edge; the target is typed Epiphany intent/result/receipt wrappers around MCP, not replacing MCP JSON. The current OpenAI spine still pulls `codex-api` and a large transport dependency stack, so its next cut is dependency starvation after richer live callers move. next_action: Move remaining coordinator/runtime execution and operator surfaces off app-server JSON-RPC where possible, then shrink the surviving Codex dependency surface to credential refresh, provider/model routing, and the smallest OpenAI Responses call required for Codex subscription compatibility. diff --git a/vendor/codex/codex-rs/core/src/epiphany_rollout.rs b/vendor/codex/codex-rs/core/src/epiphany_rollout.rs deleted file mode 100644 index 47ae1f28..00000000 --- a/vendor/codex/codex-rs/core/src/epiphany_rollout.rs +++ /dev/null @@ -1,9 +0,0 @@ -use crate::context_manager::is_user_turn_boundary; -use codex_protocol::protocol::EpiphanyThreadState; -use codex_protocol::protocol::RolloutItem; - -pub fn latest_epiphany_state_from_rollout_items( - rollout_items: &[RolloutItem], -) -> Option { - epiphany_core::latest_epiphany_state_from_rollout_items(rollout_items, is_user_turn_boundary) -} diff --git a/vendor/codex/codex-rs/core/src/lib.rs b/vendor/codex/codex-rs/core/src/lib.rs index 8febe708..eabe4e8b 100644 --- a/vendor/codex/codex-rs/core/src/lib.rs +++ b/vendor/codex/codex-rs/core/src/lib.rs @@ -17,7 +17,6 @@ pub(crate) mod session; pub use session::SteerInputError; mod codex_thread; mod compact_remote; -mod epiphany_rollout; pub use codex_thread::CodexThread; pub use codex_thread::CodexThreadTurnContextOverrides; pub use codex_thread::EpiphanyJobInterruptRequest; @@ -39,8 +38,17 @@ pub use epiphany_core::EpiphanyStateUpdate; pub use epiphany_core::distill_observation; pub use epiphany_core::evaluate_promotion; pub use epiphany_core::propose_map_update; -pub use epiphany_rollout::latest_epiphany_state_from_rollout_items; mod agent; + +pub fn latest_epiphany_state_from_rollout_items( + rollout_items: &[codex_protocol::protocol::RolloutItem], +) -> Option { + epiphany_core::latest_epiphany_state_from_rollout_items( + rollout_items, + context_manager::is_user_turn_boundary, + ) +} + mod codex_delegate; mod command_canonicalization; mod commit_attribution;