DeepSeek/deepseek-harness
1
0
Fork 0
mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'codex/simp-ui-identity-residue' into codex/simp-hide-concrete-agent-loop

Browse Source 
# Conflicts:
#	packages/core/agent-loop/README.md
This commit is contained in:
Tianyi Cui
2026-07-14 10:35:15 +08:00
parent 50d96689ac cf21e252fa
commit 0c19d69507
13 changed files with 105 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/config-catalog.md
View File

@@ -119,7 +119,7 @@ export interface Config {
agents: (AgentOptions & {
/** Stable config label used in logs and as the fresh combined-id prefix. */
id: string
/** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */
/** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */
sessionId?: SessionId
/** Optional workspace for a fresh session. */
cwd?: string

10
docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md
View File

@@ -4,19 +4,19 @@ Status: implemented
## Problem
The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately.
A live agent/session pair needs one identity for registry routing, event sourcing, and persistence. Giving the factory independent `agentId` and `sessionId` inputs would permit pairings no production path can use, while forcing every consumer to choose or translate between two names for the same lifecycle.
ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids.
ACP uses the same value for both identities. Stdio and hooks also operate on the session event stream and need the corresponding live agent directly; no production path reattaches one live agent object to several sessions or drives one session through several agent ids.
The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle.
The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) uses one `AgentCreationTransaction` for create and resume, and agent/session entries share the same final-entry collision rule. A second identity would not represent separate liveness, rollback, or quiescence; it would only add API and translation state around the same transaction.
Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes.
Session identity likewise has one home in `Session.header.id`; `Session.id` is a derived accessor rather than independent state that needs duplicate validation.
## Decision
An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone.
The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start normally mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; a coupled app may pre-mint and pass the exact fresh `sessionId`, while `resumeSessionId` supplies the exact combined identity to load and register. The two exact-id inputs are mutually exclusive. Stdio uses this narrow escape hatch so its config-created agent and UI share one opaque identity instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`.
The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. An ordinary fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide. A coupled app may pre-mint and pass an exact `sessionId`: first use creates it, while an AgentLoop remount with an already-present persistence service resumes materialized history under that same identity. `resumeSessionId` instead requires an existing persisted identity. The two exact-id inputs are mutually exclusive. Stdio uses the resume-or-create form so its config-created agent and UI share one opaque identity across loop reloads instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`.
`agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search.

2
docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md
View File

@@ -42,4 +42,4 @@ Not touched:
## Consequences
A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event` and filters `assistant/chunk` (the `Agent` handle, if needed, is recovered from a session-id→agent map built from `agent/created`/`agent/disposed`, exactly as boundary consumers already do). No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made.
A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event`, filters `assistant/chunk`, and looks up the corresponding live handle directly with `ctx.agents.get(session.id)` when needed. No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made.