Add Epiphany MVP status view
This commit is contained in:
Meta Vens
parent
9d18cdbe9f
commit
13ffbcf92f
9 changed files with 367 additions and 25 deletions
|
|
@ -10,7 +10,7 @@ The important question for this file is not "what is Epiphany supposed to become
|
|||
|
||||
Current Epiphany is a forked Codex harness with a typed modeling spine.
|
||||
|
||||
The spine exists in twenty-two live paths:
|
||||
The spine exists in twenty-three live paths:
|
||||
|
||||
- protocol state shape: `EpiphanyThreadState`, `RolloutItem::EpiphanyState`, retrieval summaries, and prompt tags live in [protocol.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/protocol/src/protocol.rs:103).
|
||||
- in-memory session state: `SessionState` stores an optional `EpiphanyThreadState`, and `Session` exposes thin async accessors over it in [state/session.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/core/src/state/session.rs:36) and [session/mod.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/core/src/session/mod.rs:1240).
|
||||
|
|
@ -31,6 +31,7 @@ The spine exists in twenty-two live paths:
|
|||
- context-pressure reflection: core token telemetry carries `model_auto_compact_token_limit` beside total/last usage and `model_context_window`; app-server declares experimental read-only `thread/epiphany/pressure`, reads live token usage or the latest stored rollout `TokenCount`, and derives `unknown`/`low`/`elevated`/`high`/`critical` pressure plus a non-acting compaction-prep recommendation without mutating Epiphany state or scheduling compaction in [protocol.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/protocol/src/protocol.rs:2237), [turn_context.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/core/src/session/turn_context.rs:103), [session/mod.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/core/src/session/mod.rs:2716), [common.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/common.rs:360), [v2.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/v2.rs:4361), [token_usage_replay.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server/src/codex_message_processor/token_usage_replay.rs:75), [codex_message_processor.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server/src/codex_message_processor.rs:4306), and [codex_message_processor.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server/src/codex_message_processor.rs:11028).
|
||||
- reorientation policy: app-server declares experimental read-only `thread/epiphany/reorient`, reuses the same live/stored thread view plus mapped pressure/freshness/watcher signals, and derives a bounded `resume`/`regather` verdict with checkpoint-path/frontier reasons without mutating, compacting, scheduling, notifying, or continuing work in [common.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/common.rs:365), [v2.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/v2.rs:4514), [codex_message_processor.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server/src/codex_message_processor.rs:4394), and [codex_message_processor.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server/src/codex_message_processor.rs:11424).
|
||||
- CRRC coordinator recommendation: app-server declares experimental read-only `thread/epiphany/crrc`, reuses the same pressure/freshness/watcher/reorientation mapping plus the fixed `reorient-worker` binding and result read-back helper, and returns one bounded recommendation such as continue, prepare checkpoint, launch worker, wait, review, accept, or regather manually without mutating, launching, accepting, compacting, notifying, scheduling, or silently continuing work in [common.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/common.rs:370), [v2.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/v2.rs:4661), and [codex_message_processor.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server/src/codex_message_processor.rs:4546).
|
||||
- MVP operator view: `tools/epiphany_mvp_status.py` launches app-server over stdio, starts or reads one thread, gathers scene, pressure, reorient, jobs, reorient result, and CRRC responses, and renders them as text or JSON so the loop can be dogfooded without reading Rust.
|
||||
- reorientation launch: app-server now declares experimental `thread/epiphany/reorientLaunch`, requires a loaded thread plus durable investigation checkpoint, consumes the live reorientation verdict, and launches one fixed `reorient-worker` binding through the existing job-control seam with explicit resume-versus-regather scope, checkpoint-derived payload, and structured-output expectations instead of pretending CRRC suddenly grew a scheduler in [common.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/common.rs:370), [v2.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/v2.rs:4575), and [codex_message_processor.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server/src/codex_message_processor.rs:4519).
|
||||
- reorientation result read-back: app-server now declares experimental read-only `thread/epiphany/reorientResult`, defaults to the fixed `reorient-worker` binding, resolves that binding through the current `agent_jobs` backend when available, reads the single backend item result, and projects a reviewable finding with mode, summary, next safe move, checkpoint-validity flag, inspected files, frontier ids, evidence ids, raw result, and any job/item errors without mutating state, promoting evidence, or scheduling follow-up work in [common.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/common.rs:374), [v2.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/v2.rs:4610), and [codex_message_processor.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server/src/codex_message_processor.rs:4684).
|
||||
- reorientation finding acceptance: app-server now declares experimental `thread/epiphany/reorientAccept`, requires a loaded thread and a completed `reorient-worker` backend result, appends accepted observation/evidence records, optionally banks the finding into scratch and the durable investigation checkpoint, persists through the normal typed update path, and emits `thread/epiphany/stateUpdated` with source `reorientAccept` without accepting pending work, auto-promoting arbitrary worker output, launching follow-up work, or silently continuing implementation in [common.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/common.rs:378), [v2.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server-protocol/src/protocol/v2.rs:4635), and [codex_message_processor.rs](E:/Projects/EpiphanyAgent/vendor/codex/codex-rs/app-server/src/codex_message_processor.rs:4885).
|
||||
|
|
@ -1335,7 +1336,7 @@ stored Epiphany state
|
|||
-> successful writes emit thread/epiphany/stateUpdated
|
||||
```
|
||||
|
||||
The current remaining missing organ is not the red pen, not the first chewing motion, not the first state-change bell, not the first client-shaped scene, not the first job/progress reflection, not the first live bound-job notification, not the first freshness lens, not the first watcher-backed invalidation read, not the first targeted graph/evidence context read, not the first context-pressure gauge, not the first durable investigation checkpoint packet, not the first bounded reorientation verdict, not the first thin launcher seam, not the first explicit launch/interrupt authority surface over that seam, not the first runtime consumer that can act on the reorientation verdict without becoming a hidden tyrant, not the first read-back surface for that worker's findings, not the first explicit acceptance write for completed findings, and no longer the first read-only CRRC coordinator recommendation. Those exist. Proposal now has the first bits of map memory, focus, and selection hygiene: it can auto-select a bounded evidence-backed observation cluster when ids are omitted, requires accepting recent evidence behind selected observations, prioritizes stronger selected observations for proposal wording, reuses existing architecture nodes by concrete code-ref/path/id checks before creating new path nodes, can rescue unanchored graph nodes through strict unique semantic overlap, follows graph links and incident edges into the frontier, and reports match-kind-aware churn pressure from the actual proposal shape. Distillation now also has the first source-output-aware teeth for tool/model summaries. Promotion now notices risky deltas instead of just checking the shape of the envelope, treats graph expansion as risky even if the patch tries to mumble "low pressure" while dragging a new wall into the blueprint, token-matches strong verifier kinds so `contest` cannot sneak past as `test`, and validates investigation checkpoints against known evidence before the packet can be inked. Successful update/promote writes now emit `thread/epiphany/stateUpdated` with `source: "update"` or `source: "promote"`, event-level revision, and typed changed fields so clients no longer need to poll blindly, infer the cause from timing, or diff the whole state to know which top-level sections moved. Runtime `agent_job_progress` background events now also emit `thread/epiphany/jobsUpdated` with changed bound-job payloads so clients no longer need to poll `thread/epiphany/jobs` just to watch one real owner move, the bound jobs now reflect launcher id, authority scope, and backend kind/job id instead of treating raw runtime pointers as the architecture, `jobLaunch` / `jobInterrupt` can create or tear down those bindings without pretending reflection is authority, `reorientLaunch` can launch one fixed `reorient-worker` job from the checkpoint verdict without turning the verdict itself into a writer, `reorientResult` can read the worker's structured output back as a reviewable finding without promoting it, `reorientAccept` can explicitly bank a completed finding into typed observation/evidence plus optional scratch/checkpoint state, and `crrc` can recommend the next explicit action over that loop without doing the action itself. The scene, jobs, freshness, context, pressure, reorient, crrc, and reorient-result surfaces give clients compact or bounded read-only views without making the GUI/client authoritative, scene/context surface the checkpoint packet back out without becoming writers, freshness surfaces watcher telemetry without becoming a hidden worker, reorient turns those signals into an explicit wakeup verdict that one explicit launch surface can consume on purpose, and crrc now tells the operator whether to continue, checkpoint, launch, wait, review, accept, or regather manually. The remaining missing organs are a second backend if `agent_jobs` stops being enough, a dogfood-facing operator view over the landed loop, and eventually role-scoped specialist ownership without silently auto-promoting anything.
|
||||
The current remaining missing organ is not the red pen, not the first chewing motion, not the first state-change bell, not the first client-shaped scene, not the first job/progress reflection, not the first live bound-job notification, not the first freshness lens, not the first watcher-backed invalidation read, not the first targeted graph/evidence context read, not the first context-pressure gauge, not the first durable investigation checkpoint packet, not the first bounded reorientation verdict, not the first thin launcher seam, not the first explicit launch/interrupt authority surface over that seam, not the first runtime consumer that can act on the reorientation verdict without becoming a hidden tyrant, not the first read-back surface for that worker's findings, not the first explicit acceptance write for completed findings, not the first read-only CRRC coordinator recommendation, and no longer the first dogfood-facing operator view over the landed loop. Those exist. Proposal now has the first bits of map memory, focus, and selection hygiene: it can auto-select a bounded evidence-backed observation cluster when ids are omitted, requires accepting recent evidence behind selected observations, prioritizes stronger selected observations for proposal wording, reuses existing architecture nodes by concrete code-ref/path/id checks before creating new path nodes, can rescue unanchored graph nodes through strict unique semantic overlap, follows graph links and incident edges into the frontier, and reports match-kind-aware churn pressure from the actual proposal shape. Distillation now also has the first source-output-aware teeth for tool/model summaries. Promotion now notices risky deltas instead of just checking the shape of the envelope, treats graph expansion as risky even if the patch tries to mumble "low pressure" while dragging a new wall into the blueprint, token-matches strong verifier kinds so `contest` cannot sneak past as `test`, and validates investigation checkpoints against known evidence before the packet can be inked. Successful update/promote writes now emit `thread/epiphany/stateUpdated` with `source: "update"` or `source: "promote"`, event-level revision, and typed changed fields so clients no longer need to poll blindly, infer the cause from timing, or diff the whole state to know which top-level sections moved. Runtime `agent_job_progress` background events now also emit `thread/epiphany/jobsUpdated` with changed bound-job payloads so clients no longer need to poll `thread/epiphany/jobs` just to watch one real owner move, the bound jobs now reflect launcher id, authority scope, and backend kind/job id instead of treating raw runtime pointers as the architecture, `jobLaunch` / `jobInterrupt` can create or tear down those bindings without pretending reflection is authority, `reorientLaunch` can launch one fixed `reorient-worker` job from the checkpoint verdict without turning the verdict itself into a writer, `reorientResult` can read the worker's structured output back as a reviewable finding without promoting it, `reorientAccept` can explicitly bank a completed finding into typed observation/evidence plus optional scratch/checkpoint state, and `crrc` can recommend the next explicit action over that loop without doing the action itself. The scene, jobs, freshness, context, pressure, reorient, crrc, reorient-result, and MVP status surfaces give clients compact or bounded read-only views without making the GUI/client authoritative, scene/context surface the checkpoint packet back out without becoming writers, freshness surfaces watcher telemetry without becoming a hidden worker, reorient turns those signals into an explicit wakeup verdict that one explicit launch surface can consume on purpose, crrc tells the operator whether to continue, checkpoint, launch, wait, review, accept, or regather manually, and the status tool prints the answer without requiring a Rust spelunk. The remaining missing organs are a second backend if `agent_jobs` stops being enough and eventually role-scoped specialist ownership without silently auto-promoting anything.
|
||||
|
||||
```text
|
||||
model/tool observations
|
||||
|
|
@ -1349,7 +1350,7 @@ model/tool observations
|
|||
|
||||
The typed write path exists, the first deterministic observation/evidence distillation path exists, source-output-aware distillation now summarizes noisy tool/model output into typed evidence with final result/error/finished lines ahead of generic warnings, the first deterministic map/churn proposal path exists, proposal-quality hardening now auto-selects bounded observation clusters when ids are omitted, requires accepting recent evidence, reuses existing graph nodes by observed code refs, prioritizes stronger selected observations, rescues unanchored graph nodes by strict semantic overlap, focuses linked frontier context, reports match-kind-aware map-delta pressure, and the first verifier-backed promotion gate exists. The first map/churn safety layer also exists: promotion can reject state replacement patches that are not tied to explicit observations/evidence, that contain structurally broken subgoal, invariant, graph, frontier, checkpoint, investigation-checkpoint, or churn fields, that try to promote risky churn without a warning and stronger verifier evidence, that claim a graph expansion is low-pressure to dodge the warning gate, or that rely on substring verifier-kind accidents. The first live state notification layer also exists: accepted writes publish updated typed state plus event-level revision and typed changed fields; rejected promotions stay quiet.
|
||||
|
||||
In natural language: current Epiphany can preserve a map, show a map, project a compact scene from the map, project derived job/progress slots from the map and retrieval summary, reflect a thin launcher seam over bound work, explicitly launch or interrupt that bound work through a bounded authority surface, emit live bound-job progress notifications from runtime `agent_job_progress` events, project a read-only freshness lens over retrieval and graph staleness, layer watcher-backed invalidation telemetry onto that lens for loaded threads, project a targeted graph/evidence context shard from the map, project context pressure from token telemetry, bank an in-flight investigation packet in durable typed state, reflect that packet back into prompt/scene/context, turn those signals into a read-only resume-versus-regather verdict, recommend the next explicit CRRC action over the verdict and worker/result state, explicitly launch one bounded `reorient-worker` job from that verdict, read its result back for review, explicitly accept a completed finding into typed state, retrieve evidence for the map, draft one explicit observation/evidence patch, derive a bounded graph/frontier/churn candidate from verified evidence-backed observations with code refs, choose a small coherent observation set when the caller does not provide one, favor the strongest selected observation when drafting that candidate, reject or accept a verified candidate, apply explicit map/evidence/churn edits, notify clients after successful writes, and sanity-check those edits before they hit the ledger. It still does not invalidate stale graph regions automatically, execute Epiphany-owned long-running jobs beyond the borrowed runtime `agent_jobs` backend, show the whole loop in a humane dogfood surface, or coordinate broad specialist ownership. Teeth are installed; chewing is supervised; the first bell rings; the first wall board exists; the first shift board exists; the first freshness clipboard exists; the first door sensor now exists too; the first binder lens exists; the first pressure gauge exists; the first ember packet exists; the first verdict slip now exists too; the first bounded launch lever and stop switch now exist too; the first explicit wakeup-hand now exists too; the first coordinator clipboard now exists too. The next slices are about making the wakeup legible and giving real roles real ownership, not jawbones.
|
||||
In natural language: current Epiphany can preserve a map, show a map, project a compact scene from the map, project derived job/progress slots from the map and retrieval summary, reflect a thin launcher seam over bound work, explicitly launch or interrupt that bound work through a bounded authority surface, emit live bound-job progress notifications from runtime `agent_job_progress` events, project a read-only freshness lens over retrieval and graph staleness, layer watcher-backed invalidation telemetry onto that lens for loaded threads, project a targeted graph/evidence context shard from the map, project context pressure from token telemetry, bank an in-flight investigation packet in durable typed state, reflect that packet back into prompt/scene/context, turn those signals into a read-only resume-versus-regather verdict, recommend the next explicit CRRC action over the verdict and worker/result state, print that recommendation in a dogfood operator view, explicitly launch one bounded `reorient-worker` job from that verdict, read its result back for review, explicitly accept a completed finding into typed state, retrieve evidence for the map, draft one explicit observation/evidence patch, derive a bounded graph/frontier/churn candidate from verified evidence-backed observations with code refs, choose a small coherent observation set when the caller does not provide one, favor the strongest selected observation when drafting that candidate, reject or accept a verified candidate, apply explicit map/evidence/churn edits, notify clients after successful writes, and sanity-check those edits before they hit the ledger. It still does not invalidate stale graph regions automatically, execute Epiphany-owned long-running jobs beyond the borrowed runtime `agent_jobs` backend, or coordinate broad specialist ownership. Teeth are installed; chewing is supervised; the first bell rings; the first wall board exists; the first shift board exists; the first freshness clipboard exists; the first door sensor now exists too; the first binder lens exists; the first pressure gauge exists; the first ember packet exists; the first verdict slip now exists too; the first bounded launch lever and stop switch now exist too; the first explicit wakeup-hand now exists too; the first coordinator clipboard now exists too; the first operator readout exists too. The next slices are about giving real roles real ownership, not jawbones.
|
||||
|
||||
## Verification Hooks
|
||||
|
||||
|
|
@ -1375,7 +1376,8 @@ Current tests cover the landed flows at useful seams:
|
|||
- live app-server smoke for the first Phase 6 context boundary in `tools/epiphany_phase6_context_smoke.py`.
|
||||
- live app-server smoke for the first Phase 6 pressure boundary in `tools/epiphany_phase6_pressure_smoke.py`.
|
||||
- live app-server smoke for the first Phase 6 reorientation policy boundary in `tools/epiphany_phase6_reorient_smoke.py`.
|
||||
- live app-server smoke for the first bounded reorient-launch runtime consumer in `tools/epiphany_phase6_reorient_launch_smoke.py`.
|
||||
- live app-server smoke for the first bounded reorient-launch runtime consumer plus CRRC coordinator recommendations in `tools/epiphany_phase6_reorient_launch_smoke.py`.
|
||||
- live app-server smoke for the first MVP operator status view in `tools/epiphany_mvp_status_smoke.py`.
|
||||
- live app-server smoke for the first Phase 6 job-control boundary in `tools/epiphany_phase6_job_control_smoke.py`.
|
||||
|
||||
Useful commands:
|
||||
|
|
@ -1394,5 +1396,6 @@ $env:CARGO_TARGET_DIR='C:\Users\Meta\.cargo-target-codex'; cargo test -p codex-a
|
|||
& 'C:\Users\Meta\.cache\codex-runtimes\codex-primary-runtime\dependencies\python\python.exe' '.\tools\epiphany_phase6_pressure_smoke.py'
|
||||
& 'C:\Users\Meta\.cache\codex-runtimes\codex-primary-runtime\dependencies\python\python.exe' '.\tools\epiphany_phase6_reorient_smoke.py'
|
||||
& 'C:\Users\Meta\.cache\codex-runtimes\codex-primary-runtime\dependencies\python\python.exe' '.\tools\epiphany_phase6_reorient_launch_smoke.py'
|
||||
& 'C:\Users\Meta\.cache\codex-runtimes\codex-primary-runtime\dependencies\python\python.exe' '.\tools\epiphany_mvp_status_smoke.py'
|
||||
& 'C:\Users\Meta\.cache\codex-runtimes\codex-primary-runtime\dependencies\python\python.exe' '.\tools\epiphany_phase6_job_control_smoke.py'
|
||||
```
|
||||
|
|
|
|||
Reference in a new issue