Merge remote-tracking branch 'origin/master' into fs-tool-clean
# Conflicts: # docs/architecture.md # docs/cordis-catalog/events-and-services.md # docs/module-graph.md # packages/README.md
This commit is contained in:
Tianyi Cui
@@ -12,8 +12,9 @@ Packages are grouped by modular role at `packages/<group>/<pkg>/`. The group dir
|
||||
| [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable surface |
|
||||
| [`bash/`](bash/README.md) | Bash capability family: the executor seam, a local impl, and the model-facing tool | Product — stable surface |
|
||||
| [`fs/`](fs/README.md) | Filesystem capability family: the abstract seam, a local impl, and the model-facing file tools | Product — stable surface |
|
||||
| [`compact/`](compact/README.md) | Compaction capability family: the abstract seam (backend + tool deferred) | Product — stable surface |
|
||||
| [`compact/`](compact/README.md) | Compaction capability family: the abstract seam + a basic backend (tool deferred) | Product — stable surface |
|
||||
| [`subagent/`](subagent/README.md) | Subagent capability family: the provider-registry seam and the model-facing delegation tool | Product — stable surface |
|
||||
| [`todo/`](todo/README.md) | Todo/planning family: the model-facing `todo_write` tool (whole-list task tracking on the session log) | Product — stable surface |
|
||||
| [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface |
|
||||
| [`ui/`](ui/README.md) | Editor/client integration surfaces (the ACP bridge) | Product — stable surface |
|
||||
| [`support/`](support/README.md) | Dev/test/example infrastructure (invariants, stdio UI, replay adapter) | Support — lower compatibility expectations |
|
||||
@@ -30,7 +31,8 @@ dsh-bash ← dsh-brand (abstract executor seam; b
|
||||
dsh-session ← dsh-llm, dsh-brand
|
||||
dsh-system-prompt ← dsh-llm
|
||||
dsh-agent ← dsh-llm, dsh-session, dsh-brand
|
||||
dsh-compact ← dsh-session, dsh-llm (abstract compaction seam; backend + tool deferred)
|
||||
dsh-compact ← dsh-session, dsh-llm (abstract compaction seam; tool deferred)
|
||||
dsh-compact-basic ← dsh-compact, dsh-session, dsh-llm, dsh-agent (char/4 + token-budget retention backend)
|
||||
dsh-tools ← dsh-llm, dsh-system-prompt, dsh-agent
|
||||
dsh-bash-local ← dsh-bash (BashExecutor impl)
|
||||
dsh-tool-bash ← dsh-bash, dsh-tools (bash tool schemas)
|
||||
@@ -40,17 +42,19 @@ dsh-file-context ← dsh-fs (observed-state + freshnes
|
||||
dsh-tool-fs ← dsh-fs, dsh-tools (file tools + executor)
|
||||
dsh-llm-deepseek ← dsh-llm (DeepSeek adapter)
|
||||
dsh-llm-pi-ai ← dsh-llm (pi-ai-backed adapter)
|
||||
dsh-agent-loop ← dsh-llm, dsh-session, dsh-system-prompt, dsh-tools, dsh-agent
|
||||
dsh-agent-loop ← dsh-llm, dsh-session, dsh-session-persistence, dsh-system-prompt, dsh-tools, dsh-agent
|
||||
dsh-invariants ← dsh-llm, dsh-session, dsh-agent (dev-mode contract checks)
|
||||
dsh-acp ← dsh-agent, dsh-llm, dsh-session, dsh-session-persistence (ACP JSON-RPC bridge)
|
||||
dsh-acp ← dsh-agent, dsh-llm, dsh-session, dsh-session-persistence, dsh-tools (ACP JSON-RPC bridge)
|
||||
dsh-ui-stdio ← dsh-agent, dsh-llm, dsh-session (stdio readline UI plugin)
|
||||
dsh-llm-replay ← dsh-llm, dsh-session (record/replay adapter for keyless snapshot tests)
|
||||
dsh-subagent ← dsh-agent, dsh-llm, dsh-tools (abstract subagent provider-registry seam)
|
||||
dsh-subagent-mock ← dsh-subagent (scripted provider for tests)
|
||||
dsh-subagent-spawn ← dsh-subagent, dsh-agent, dsh-session, dsh-llm (in-process fresh child + shared run driver)
|
||||
dsh-subagent-fork ← dsh-subagent-spawn, dsh-agent, dsh-session (in-process child seeded from parent log)
|
||||
dsh-subagent-inprocess ← dsh-subagent, dsh-agent, dsh-session, dsh-llm (shared in-process run driver)
|
||||
dsh-subagent-mock ← dsh-subagent, dsh-agent, dsh-llm (scripted provider for tests)
|
||||
dsh-subagent-spawn ← dsh-subagent, dsh-subagent-inprocess (in-process fresh child backend)
|
||||
dsh-subagent-fork ← dsh-subagent, dsh-subagent-inprocess, dsh-agent, dsh-session (in-process child seeded from parent log)
|
||||
dsh-subagent-acp ← dsh-subagent, dsh-agent, dsh-llm, @agentclientprotocol/sdk (out-of-process child over ACP)
|
||||
dsh-tool-subagent ← dsh-subagent, dsh-tools, dsh-agent (model-facing delegation tool)
|
||||
dsh-tool-subagent ← dsh-subagent, dsh-tools, dsh-agent, dsh-llm (model-facing delegation tool)
|
||||
dsh-tool-todo ← dsh-tools, dsh-agent, dsh-session (model-facing todo_write tool; whole list on the session log)
|
||||
dsh-agent-core ← timer, dsh-llm, dsh-session, dsh-system-prompt, dsh-tools, dsh-agent, dsh-invariants, dsh-tool-bash, dsh-agent-loop (the providerless spine, as one bundle plugin)
|
||||
dsh-stdio-agent ← dsh-agent-core, dsh-ui-stdio, dsh-session-persistence-jsonl, dsh-agent, dsh-session (stdio chat APP + bin)
|
||||
dsh-acp-agent ← dsh-agent-core, dsh-acp, dsh-session-persistence-jsonl (ACP server APP + bin)
|
||||
@@ -77,6 +81,7 @@ The rule: **extension** plugins depend on interfaces, never on the concrete loop
|
||||
| `file-context/` | `fs` | Policy gate plugin: observed-state + read-before-edit + version-guarded write/edit via the `fs/*` event gate | (no service — `fs/*` listeners) |
|
||||
| `tool-fs/` | `fs` | Model-facing `read`/`write`/`edit` tools + executor (reads via `ctx.fs`, owns read windowing, dispatches `fs/*`) | (registers on `ctx.tools`) |
|
||||
| `compact/` | `compact` | Abstract compaction seam + `compact/*` events + `CompactionResult` | `ctx.compact` |
|
||||
| `compact-basic/` | `compact` | A backend: char/4 estimation + token-budget retention + `llm.stream()` summarization | (registers `ctx.compact`) |
|
||||
| `llm-deepseek/` | `llm` | DeepSeek API adapter (hand-rolled fetch/SSE) | (registers on `ctx.llm`) |
|
||||
| `llm-pi-ai/` | `llm` | DeepSeek adapter via `@earendil-works/pi-ai` (design twin) | (registers on `ctx.llm`) |
|
||||
| `session-persistence/` | `session-persistence` | Persistence seam + write coordinator | `ctx.sessionPersistence` |
|
||||
@@ -89,11 +94,13 @@ The rule: **extension** plugins depend on interfaces, never on the concrete loop
|
||||
| `ui-stdio/` | `support` | Minimal stdio (readline) UI plugin: renders `agent/*` events, feeds stdin lines to the agent | (drives `ctx.agents`) |
|
||||
| `llm-replay/` | `support` | Record/replay adapter: short-circuits `llm/stream` with chunks from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) |
|
||||
| `subagent/` | `subagent` | Abstract subagent seam: named-provider registry for delegating to child agents | `ctx.subagents` |
|
||||
| `subagent-spawn/` | `subagent` | In-process backend: a fresh child agent (+ the shared in-process run driver) | (registers on `ctx.subagents`) |
|
||||
| `subagent-inprocess/` | `subagent` | Shared in-process subagent run driver used by spawn/fork; pure library, registers nothing | (none) |
|
||||
| `subagent-spawn/` | `subagent` | In-process backend: a fresh child agent | (registers on `ctx.subagents`) |
|
||||
| `subagent-fork/` | `subagent` | In-process backend: a child agent seeded with the parent's completed-turn prefix | (registers on `ctx.subagents`) |
|
||||
| `subagent-acp/` | `subagent` | Out-of-process backend: a child agent in a spawned subprocess, driven over the Agent Client Protocol | (registers on `ctx.subagents`) |
|
||||
| `subagent-mock/` | `support` | Scripted `SubagentProvider` for testing the seam through the real load path | (registers on `ctx.subagents`) |
|
||||
| `tool-subagent/` | `subagent` | Model-facing `subagent` delegation tool over `ctx.subagents` | (registers on `ctx.tools`) |
|
||||
| `tool-todo/` | `todo` | Model-facing `todo_write` tool; writes the whole task list to the session log (`todo/write`) | (registers on `ctx.tools`) |
|
||||
| `brand/` | `util` | Type-only `Branded<B>` nominal-typing primitive (no runtime code, no harness deps) | (none — type-only) |
|
||||
|
||||
Each package has its own `README.md` with purpose, service API, events, extension points, and deliberate non-goals (TODOs).
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
# compact/ — compaction capability family
|
||||
|
||||
A three-package capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract compaction interface, a backend that summarizes, and the model-facing tool that consumes it. Only the interface tier exists today; the backend and consumer are deferred. All **product** packages.
|
||||
A three-package capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract compaction interface, a backend that summarizes, and the model-facing tool that consumes it. The interface and a first backend (`compact-basic/`) exist; the consumer tool is deferred. All **product** packages.
|
||||
|
||||
| Package | Role | ctx key |
|
||||
|---|---|---|
|
||||
| `compact/` | Abstract compaction seam (interface + `compact/*` events + `CompactionResult`) | `ctx.compact` |
|
||||
| `compact-basic/` (deferred) | A backend: char/4 estimation + token-budget retention + `llm.stream()` summarization | (registers `ctx.compact`) |
|
||||
| `compact-basic/` | A backend: char/4 estimation + token-budget retention + `llm.stream()` summarization | (registers `ctx.compact`) |
|
||||
| `tool-compact/` (deferred) | Model-facing `/compact` tool over `ctx.compact` | (registers on `ctx.tools`) |
|
||||
|
||||
The interface lives at `compact/compact/`. Unlike the bash seam, it depends on `dsh-session` and `dsh-llm` — its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so the contract cannot be expressed without naming them. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../docs/rfc/proposed/feature/2026-06-18-compaction-capability-seam.md). A tokenizer- or template-based backend would replace `compact-basic` without touching the interface or the tool.
|
||||
The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`. Unlike the bash seam, it depends on `dsh-session` and `dsh-llm` — its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so the contract cannot be expressed without naming them. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). A tokenizer- or template-based backend would replace `compact-basic` without touching the interface or the tool.
|
||||
|
||||
57
packages/compact/compact-basic/README.md
Normal file
57
packages/compact/compact-basic/README.md
Normal file
@@ -0,0 +1,57 @@
|
||||
# @deepseek-ai/dsh-compact-basic
|
||||
|
||||
The **basic compaction backend**: a `BasicCompactService` implementing the `@deepseek-ai/dsh-compact` seam with a char/4 token heuristic, token-budget retention, and summarization routed through the agent request pipeline.
|
||||
|
||||
This is the implementation tier of the compaction capability — see the [interface package](../compact/README.md) for the seam and the [capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) for the design.
|
||||
|
||||
## What it owns
|
||||
|
||||
The abstract contract states only WHAT compaction does; this backend owns every HOW decision:
|
||||
|
||||
- **Token estimation** — `estimateContentTokens()`: char/4 with per-block structural overhead (`text`/`reasoning` = `ceil(len/4) + 4`, `tool-call` from name + arguments, `tool-result` recursive, `image` = 85, unknown blocks via JSON length).
|
||||
- **Retention policy** — `compactIfNeeded()` walks the surface nodes tail→head summing per-node token estimates, and retains the smallest tail-run of WHOLE units (a closed step, or a single no-step node such as a pre-step `user/message` or inter-step `steering/message`) whose total reaches `retainTokens`; everything older is compacted. Retention is **turn-agnostic** — turn boundaries play no role, so a single runaway turn that alone exceeds the window compacts its OWN early closed steps rather than being retained verbatim (the failure mode that motivated dropping turn-protection: a tool-heavy turn must stay compactable or the harness dies exactly when compaction is needed). The only structural guard is **tool-pairing balance**: the compacted region's edges are balanced cuts on the surface (no unanswered tool-call crosses either edge), so it never splits a step's `assistant/message` tool-calls from their `tool/result`s. When the only compactable content left is an un-splittable open tail step, it declines (returns `null`) and retries once an older step closes. **Single-unit overflow is out of scope, by design**: if one retained unit (a single closed step, or a large pasted `user/message`) ALONE exceeds the budget, compaction cannot help and the call may go out over-budget — bounding an individual unit's size is a separate concern. `compactRegion()` enforces tool-pairing balance strictly, throwing on a boundary that would split a step. `dsh-session` exports `isToolPairingBalanced` for the check.
|
||||
- **Dynamic convergence** — no static summary-length config pretends to bound what the model will write. If framing/estimator/system overhead leaves the compacted surface above threshold, `compactIfNeeded()` re-compacts the head checkpoint up to `compactionRetries` extra times; if it still cannot get below threshold, it throws. A summary whose estimated stored size is not smaller than the shadowed content fails closed before it mutates the surface.
|
||||
- **Summarization** — `summarize()`: a `GenerateOptions` request assembled via `BlockAssembler` with a fixed system prompt that asks for a structured checkpoint (Primary Request and Intent · Key Technical Concepts · Files and Code · Errors and Fixes · Pending Tasks · Current Work · Next Step · Critical Context), every section mandatory, exact paths/commands/identifiers preserved. The request runs through the `agent/request` waterfall before `ctx.llm.stream()`, so router agents that choose the concrete model there also route compaction summaries. `maxTokens` is the provider-side generation cap; only text blocks from the model's reply are kept before the checkpoint is stored (reasoning is dropped so private chain-of-thought never leaks into the durable summary, and a stray `tool-call` is dropped so the synthesized `user/message` summary cannot land an orphaned call with no matching `tool-result`). The compacted region is flattened to a plain-text transcript first: text and reasoning contribute their text, and every non-text block (image, tool-call, tool-result, plugin-added types) contributes a type-tagged placeholder (`[image]`, `[tool-call: name(args)]`, …) so the summarizer is told what existed rather than silently dropping it.
|
||||
- **Checkpoint framing** — the raw summary is not landed directly. `compactRegion()` wraps it in a checkpoint preamble (so a resuming model reads it as a checkpoint, not a fresh user request, and builds on the captured context rather than restating it) plus `<compacted-summary>…</compacted-summary>` tags. Because region compaction can be invoked manually, a surface may hold several checkpoints, so the framing does not claim everything after it is recent or verbatim. The tags make a prior checkpoint detectable in the transcript on the next compaction cycle: the summarization prompt then instructs the model to merge it in place (preserve still-true facts, drop stale ones) rather than re-summarize it verbatim — a cheap incremental merge that needs no extra log/event machinery. The unframed summary stays on the `compact/summary` provenance event.
|
||||
- **Surface mutation** — `compactRegion()` appends the `compact/start` → `compact/summary` → `compact/end` log records and the single `user/message` replace node carrying the framed summary (see the interface README).
|
||||
- **Auto-compaction** — an `agent/pre-step` listener delegates to `compactIfNeeded()` before every step (not just a turn's first — a tool-heavy turn grows the surface mid-turn, so a runaway turn still compacts, and per-step firing is the only moment to rescue it before overflow). `agent/pre-step` is a serial (awaited, in-order) surface-mutation checkpoint that fires after `turn/start` and BEFORE the step opens (`step/start`) and its request history is derived, so compaction mutates the surface — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives once from the result: no double-derive, and the listener cannot see (or need to rewrite) an already-assembled `messages` array. The listener owns no threshold logic of its own (the single token-pressure check lives in `compactIfNeeded()`); because Cordis `serial` bails early on non-void return values, the listener returns `void` and does not use the dispatcher's bail channel as a veto surface.
|
||||
- **Failure handling** — the `compact/start … compact/end` bracket is a log-recorded lock: it makes a crash mid-summarization a detectable orphan (a `compact/start` with no `compact/end`), records provenance, and prevents a concurrent compaction. Two failure paths: a **crash** (the loop dies mid-summarization) leaves a dangling `compact/start` that is inert — `compact/*` events are log-only, the surface replacement never landed, so the full history derives fine and generic turn-repair closes the turn; a **recoverable** failure (summarization throws but the loop survives) appends `compact/end` with its `error` field set, leaving the surface untouched so the call proceeds with full history. Core session repair stays compaction-agnostic by design — it never learns about `compact/*`.
|
||||
|
||||
`estimateContentTokens()` and `summarize()` are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the retention walk and surface plumbing.
|
||||
|
||||
## Config (`BasicCompactConfig`)
|
||||
|
||||
Every knob is **required** except `auto` — there is no concrete data yet to justify default thresholds/budgets, so a consumer states each value explicitly rather than inherit a guessed default. `auto` alone defaults to `true`.
|
||||
|
||||
| Key | Required | Meaning |
|
||||
|---|---|---|
|
||||
| `contextWindow` | yes | Context window size in tokens. |
|
||||
| `thresholdRatio` | yes | Compact when estimated usage exceeds this fraction of the window. |
|
||||
| `retainTokens` | yes | Tokens of recent context to keep intact. |
|
||||
| `summarizationModel` | yes | Model for summarization (`''` → use the agent's model). |
|
||||
| `maxTokens` | yes | Provider generation cap for the summarization call; may include reasoning tokens. |
|
||||
| `compactionRetries` | yes | Extra compaction attempts after the first if the compacted surface remains over threshold. |
|
||||
| `auto` | no (default `true`) | Register the `agent/pre-step` auto-compaction listener. Set `false` for manual-only. |
|
||||
|
||||
## Usage
|
||||
|
||||
```ts
|
||||
import type { Context } from 'cordis'
|
||||
import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
|
||||
|
||||
export const name = 'compact-basic'
|
||||
export const inject = ['llm']
|
||||
|
||||
export function apply(ctx: Context): void {
|
||||
ctx.plugin(BasicCompactService, {
|
||||
contextWindow: 128000,
|
||||
thresholdRatio: 0.8,
|
||||
retainTokens: 20480,
|
||||
summarizationModel: '',
|
||||
maxTokens: 8192,
|
||||
compactionRetries: 1,
|
||||
})
|
||||
}
|
||||
```
|
||||
|
||||
Loading the plugin registers `ctx.compact`. With `auto: true` (the default) it compacts automatically under token pressure; a consumer (a future `/compact` tool) can also call `ctx.compact.compactIfNeeded(...)` or `ctx.compact.compactRegion(...)` directly.
|
||||
42
packages/compact/compact-basic/package.json
Normal file
42
packages/compact/compact-basic/package.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"name": "@deepseek-ai/dsh-compact-basic",
|
||||
"description": "Basic compaction backend (char/4 token estimation + token-budget retention + llm.generate() summarization) for the DeepSeek Harness",
|
||||
"version": "0.0.1",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"main": "lib/index.js",
|
||||
"types": "lib/types/index.d.ts",
|
||||
"exports": {
|
||||
".": {
|
||||
"types": "./lib/types/index.d.ts",
|
||||
"default": "./lib/index.js"
|
||||
},
|
||||
"./src/*": "./src/*",
|
||||
"./package.json": "./package.json"
|
||||
},
|
||||
"files": [
|
||||
"lib/index.js",
|
||||
"lib/types/**/*.d.ts",
|
||||
"lib/types/**/*.d.ts.map",
|
||||
"src"
|
||||
],
|
||||
"license": "BSD-3-Clause",
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "^0.0.1",
|
||||
"@deepseek-ai/dsh-compact": "^0.0.1",
|
||||
"@deepseek-ai/dsh-llm": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-loop": "workspace:^",
|
||||
"@deepseek-ai/dsh-compact": "workspace:^",
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"@deepseek-ai/dsh-tools": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
}
|
||||
}
|
||||
746
packages/compact/compact-basic/src/index.ts
Normal file
746
packages/compact/compact-basic/src/index.ts
Normal file
@@ -0,0 +1,746 @@
|
||||
/**
|
||||
* `BasicCompactService`: the first implementation of the
|
||||
* `@deepseek-ai/dsh-compact` seam. It owns the entire compaction strategy:
|
||||
*
|
||||
* - **Token estimation** — char/4 heuristic with per-block structural overhead.
|
||||
* - **Retention policy** — walk surface nodes tail→head, keep recent nodes up
|
||||
* to a token budget, compact everything older. The cutoff is snapped forward
|
||||
* to the next balanced tool-pairing boundary so a compacted region never
|
||||
* splits a step's tool-call/result pair (an open tail step is never crossed —
|
||||
* compaction declines and retries once it closes).
|
||||
* - **Summarization** — `ctx.llm.stream()` assembled via `BlockAssembler`
|
||||
* (the single model-call surface; same path the loop uses) with a fixed
|
||||
* condense-the-history system prompt routed through `agent/request`.
|
||||
* - **Surface mutation** — a single `user/message` replace node carries the
|
||||
* summary; `compact/*` events are log-only lock + provenance records.
|
||||
* - **Auto-compaction** — an `agent/pre-step` listener delegates to
|
||||
* {@link BasicCompactService.compactIfNeeded} before EVERY step (so a
|
||||
* tool-heavy turn that grows the surface mid-turn still compacts); it owns the
|
||||
* sole token-pressure check.
|
||||
*
|
||||
* A different backend (real tokenizer, template summarizer, turn-count
|
||||
* retention) either subclasses this and overrides the {@link
|
||||
* BasicCompactService.estimateContentTokens} / {@link
|
||||
* BasicCompactService.summarize} hooks, or implements the abstract
|
||||
* {@link CompactService} from scratch.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-compact-basic
|
||||
*/
|
||||
|
||||
import { Context } from 'cordis'
|
||||
import { CompactService } from '@deepseek-ai/dsh-compact'
|
||||
import type { CompactionResult } from '@deepseek-ai/dsh-compact'
|
||||
import { BlockAssembler } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock, FinishReason, GenerateOptions, Message } from '@deepseek-ai/dsh-llm'
|
||||
import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import { isToolPairingBalanced } from '@deepseek-ai/dsh-session'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import type { BasicCompactConfig, ResolvedConfig } from './types.ts'
|
||||
import { resolveConfig } from './types.ts'
|
||||
|
||||
export type { BasicCompactConfig, ResolvedConfig } from './types.ts'
|
||||
export { resolveConfig } from './types.ts'
|
||||
|
||||
/** Per-block structural overhead for JSON framing / type tag. */
|
||||
const BLOCK_OVERHEAD = 4
|
||||
|
||||
/** Heuristic token count for an image block (~85 tokens for low-res URL). */
|
||||
const IMAGE_TOKEN_COST = 85
|
||||
|
||||
/** Role-field framing overhead added per message in {@link BasicCompactService.estimateTokens}. */
|
||||
const ROLE_OVERHEAD = 4
|
||||
|
||||
/** Tags wrapping the structured summary inside the landed checkpoint node. */
|
||||
const SUMMARY_OPEN_TAG = '<compacted-summary>'
|
||||
const SUMMARY_CLOSE_TAG = '</compacted-summary>'
|
||||
|
||||
/**
|
||||
* The summarization system prompt: instructs the model to condense the
|
||||
* conversation into a fixed, fully-populated structure rather than freeform
|
||||
* bullets. The fixed structure guarantees coverage of the things a resuming
|
||||
* model needs (original intent, pending work, the next step, critical context)
|
||||
* and is stable across compaction cycles, so a prior checkpoint can be merged
|
||||
* in place. The final rule keys off {@link SUMMARY_OPEN_TAG}: when the
|
||||
* transcript already contains a prior checkpoint, the model consolidates rather
|
||||
* than re-summarizing it verbatim (a cheap incremental-merge that needs no
|
||||
* extra log/event machinery — the tag travels on the summary surface node).
|
||||
*/
|
||||
const SUMMARIZE_SYSTEM_PROMPT = [
|
||||
'You are a compaction engine for an AI coding assistant. Condense the conversation transcript into a structured checkpoint that lets another model resume the work with no loss of essential context.',
|
||||
'',
|
||||
'Output EXACTLY the Markdown structure below: keep every section, in order. Use terse bullets, not prose paragraphs. Write "(none)" for an empty section — never drop a section.',
|
||||
'',
|
||||
'## Primary Request and Intent',
|
||||
"- [the user's original and evolving goals; quote verbatim where the exact wording matters]",
|
||||
'',
|
||||
'## Key Technical Concepts',
|
||||
'- [technologies, frameworks, patterns, and conventions in play]',
|
||||
'',
|
||||
'## Files and Code',
|
||||
'- [exact path: why it matters, key changes or snippets]',
|
||||
'',
|
||||
'## Errors and Fixes',
|
||||
'- [error: how it was resolved, plus any related user feedback]',
|
||||
'',
|
||||
'## Pending Tasks',
|
||||
'- [explicitly requested work not yet completed]',
|
||||
'',
|
||||
'## Current Work',
|
||||
'- [precisely what was in progress at this checkpoint]',
|
||||
'',
|
||||
'## Next Step',
|
||||
'- [the single next action, directly in line with the most recent request, or "(none)"]',
|
||||
'',
|
||||
'## Critical Context',
|
||||
'- [decisions and their rationale, constraints, user preferences, open questions, data needed to continue]',
|
||||
'',
|
||||
'Rules:',
|
||||
'- Preserve exact file paths, commands, error strings, identifiers, and function signatures.',
|
||||
'- Capture user feedback and explicit instructions faithfully, especially corrections.',
|
||||
'- Do NOT mention this summarization process or that the context was compacted.',
|
||||
`- If the transcript already contains a ${SUMMARY_OPEN_TAG} block, it is a PRIOR checkpoint. Do not copy it forward verbatim: preserve still-true facts, drop stale ones, and merge newer information into a single consolidated summary under the same structure.`,
|
||||
].join('\n')
|
||||
|
||||
/**
|
||||
* Framing prepended to the landed summary so a resuming model reads it as a
|
||||
* checkpoint rather than a fresh user request, and continues the task from it.
|
||||
* It summarizes an earlier span of the conversation; the messages that follow
|
||||
* are the continuation. Because region compaction can be invoked manually, a
|
||||
* surface may hold several checkpoints, so the framing does NOT claim that
|
||||
* everything after it is recent or verbatim — only that the captured context
|
||||
* should be built on, not restated.
|
||||
*/
|
||||
const CHECKPOINT_PREAMBLE =
|
||||
'This is an automatically generated checkpoint condensing an earlier span of the conversation to free up context. Treat the captured context as established background and build on it without restating it. Continue the task directly from the messages that follow, without acknowledging this checkpoint.'
|
||||
|
||||
/**
|
||||
* Map a terminal `FinishReason` to the error a SUMMARIZATION must throw, or
|
||||
* `undefined` for an acceptable finish. `FinishReason` is merge-extensible.
|
||||
*
|
||||
* Compaction fails CLOSED on a truncated summary: `error`, `aborted`, AND
|
||||
* `max-tokens` all raise. Unlike an ordinary agent turn — where `max-tokens` is
|
||||
* a normal "the model hit its budget" outcome the loop keeps — a summary cut off
|
||||
* at the token cap is an INCOMPLETE checkpoint, and committing it would shadow
|
||||
* (discard) the real history it summarizes. Raising here keeps the original
|
||||
* surface intact (the caller appends `compact/end` with the error and the auto
|
||||
* path proceeds with full history). `stop`/future kinds are accepted.
|
||||
*/
|
||||
function finishError(finish: FinishReason): Error | undefined {
|
||||
switch (finish.kind) {
|
||||
case 'error': {
|
||||
const error = new Error(finish.message) as Error & { code?: string }
|
||||
if (finish.code !== undefined) error.code = finish.code
|
||||
return error
|
||||
}
|
||||
case 'aborted': {
|
||||
const error = new Error('summarization stream aborted') as Error & { code?: string }
|
||||
error.code = 'ABORTED'
|
||||
return error
|
||||
}
|
||||
case 'max-tokens': {
|
||||
const error = new Error('summarization truncated at the token cap (incomplete checkpoint)') as Error & { code?: string }
|
||||
error.code = 'MAX_TOKENS'
|
||||
return error
|
||||
}
|
||||
default:
|
||||
return undefined
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Basic, dependency-light compaction backend. Defaults target a 128K context
|
||||
* window, compacting at 80% utilization and retaining ~20K tokens of recent
|
||||
* context.
|
||||
*/
|
||||
export class BasicCompactService extends CompactService {
|
||||
static inject = ['llm']
|
||||
|
||||
/** Resolved configuration (`auto` defaulted). */
|
||||
readonly config: ResolvedConfig
|
||||
|
||||
constructor(ctx: Context, config: BasicCompactConfig) {
|
||||
super(ctx)
|
||||
this.config = resolveConfig(config)
|
||||
|
||||
if (this.config.auto) {
|
||||
// Auto-compaction: delegate to compactIfNeeded before EVERY step. This is
|
||||
// LOAD-BEARING for runaway-turn survival: a tool-heavy ReAct turn appends
|
||||
// an assistant/message and a tool/result per step, so the surface (and the
|
||||
// derived token count) grows WITHIN a turn. The only moment to rescue a
|
||||
// turn that alone approaches the window is the next step's pre-step
|
||||
// checkpoint; gating to a turn's first step would let a runaway turn
|
||||
// overflow before the next turn's check. The listener owns NO threshold
|
||||
// logic — compactIfNeeded is the single place that decides whether to
|
||||
// compact, and its in-progress lock serializes concurrent attempts.
|
||||
//
|
||||
// It runs on `agent/pre-step` (a serial surface-mutation checkpoint fired
|
||||
// AFTER turn/start but BEFORE step/start), NOT `agent/request`: compaction
|
||||
// mutates the session surface, and the loop derives the request `messages`
|
||||
// AFTER this fires — so a single derive already reflects the compaction,
|
||||
// with no double-derive and no need to rewrite an already-assembled
|
||||
// `messages` array. Firing pre-step (outside any open step) keeps the
|
||||
// log-only `compact/*` records and the replacement node cleanly outside a
|
||||
// step, so a crash mid-compaction leaves an inert orphan the turn-repair
|
||||
// closes — never a half-open step.
|
||||
ctx.on('agent/pre-step', async (agent: Agent, turn: number, step: number, fullSystemPrompt: string, signal: AbortSignal) => {
|
||||
try {
|
||||
const result = await this.compactIfNeeded(agent, turn, step, fullSystemPrompt, signal)
|
||||
if (result) {
|
||||
const after = this.estimateTokens(agent.session.deriveMessages(), fullSystemPrompt)
|
||||
ctx.logger.info(
|
||||
`compaction: shadowed ${result.shadowedSeqs.length} surface nodes ` +
|
||||
`(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` +
|
||||
`~${result.shadowedTokenCount} tokens) ` +
|
||||
`→ ${after} estimated tokens after compaction`,
|
||||
)
|
||||
}
|
||||
} catch (error: unknown) {
|
||||
// A failed compaction must not prevent the model call — the surface is
|
||||
// untouched on failure, so the loop derives the full history and the
|
||||
// call proceeds.
|
||||
const msg = error instanceof Error ? error.message : String(error)
|
||||
ctx.logger.warn(`compaction failed: ${msg}; proceeding with full history`)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// ---- Token estimation (overridable hooks) ----
|
||||
|
||||
// TODO: char/4 is a coarse heuristic. Replace with an exact count — a real
|
||||
// tokenizer, or the provider's post-response `usage` (input tokens) fed back
|
||||
// as a correction — so threshold decisions match the model's actual budget.
|
||||
/**
|
||||
* Estimate the token count of content blocks — char/4 with per-block
|
||||
* overhead. Override in a subclass to plug in a real tokenizer.
|
||||
*/
|
||||
estimateContentTokens(blocks: readonly ContentBlock[]): number {
|
||||
let tokens = 0
|
||||
for (const block of blocks) {
|
||||
switch (block.type) {
|
||||
case 'text':
|
||||
case 'reasoning':
|
||||
tokens += Math.ceil(block.text.length / 4) + BLOCK_OVERHEAD
|
||||
break
|
||||
case 'tool-call':
|
||||
tokens += Math.ceil(block.name.length / 4)
|
||||
+ Math.ceil(block.arguments.length / 4)
|
||||
+ BLOCK_OVERHEAD
|
||||
break
|
||||
case 'tool-result':
|
||||
tokens += this.estimateContentTokens(block.content) + BLOCK_OVERHEAD
|
||||
break
|
||||
case 'image':
|
||||
tokens += IMAGE_TOKEN_COST
|
||||
break
|
||||
default:
|
||||
// Unknown block types (merge-extensible ContentBlockMap):
|
||||
// estimate conservatively via JSON stringify.
|
||||
tokens += BLOCK_OVERHEAD + Math.ceil(JSON.stringify(block).length / 4)
|
||||
}
|
||||
}
|
||||
return tokens
|
||||
}
|
||||
|
||||
/**
|
||||
* Estimate token count for a single session event. Returns 0 for non-message
|
||||
* event types (boundaries, chunks, usage, errors, compact markers).
|
||||
*/
|
||||
estimateEventTokens(event: SessionEvent): number {
|
||||
switch (event.type) {
|
||||
case 'user/message':
|
||||
case 'assistant/message':
|
||||
case 'context/message':
|
||||
case 'steering/message':
|
||||
case 'tool/result':
|
||||
return this.estimateContentTokens(event.data.content)
|
||||
default:
|
||||
return 0
|
||||
}
|
||||
}
|
||||
|
||||
/** Estimate total tokens across a list of messages plus optional system prompt. */
|
||||
estimateTokens(messages: readonly Message[], systemPrompt?: string): number {
|
||||
let total = 0
|
||||
for (const msg of messages) {
|
||||
total += this.estimateContentTokens(msg.content)
|
||||
total += ROLE_OVERHEAD
|
||||
}
|
||||
if (systemPrompt) total += Math.ceil(systemPrompt.length / 4)
|
||||
return total
|
||||
}
|
||||
|
||||
/**
|
||||
* Summarize conversation text into content blocks via `agent/request` plus
|
||||
* `ctx.llm.stream()` assembled through a `BlockAssembler` (the single
|
||||
* model-call surface).
|
||||
* Override in a subclass for a template or remote summarizer.
|
||||
*
|
||||
* Honors the adapter failure contract: an adapter may report a model failure
|
||||
* by throwing from `stream()` (propagated here) OR by ending the stream with
|
||||
* a `finish {kind:'error'|'aborted'}` chunk — the latter is re-thrown so a
|
||||
* provider error never yields an empty summary.
|
||||
*
|
||||
* Forwards `signal` into `GenerateOptions.signal` so an abort/dispose tears
|
||||
* down the in-flight summarization rather than orphaning the model call.
|
||||
*/
|
||||
async summarize(text: string, agent: Agent, turn: number, step: number, signal?: AbortSignal): Promise<ContentBlock[]> {
|
||||
const assembler = new BlockAssembler()
|
||||
const options: GenerateOptions = {
|
||||
model: this.config.summarizationModel || agent.options.model || '',
|
||||
messages: [{
|
||||
role: 'user',
|
||||
content: [{ type: 'text', text: `Summarize this conversation history:\n\n${text}\n\nSummary:` }],
|
||||
}],
|
||||
system: SUMMARIZE_SYSTEM_PROMPT,
|
||||
maxTokens: this.config.maxTokens,
|
||||
sessionId: agent.session.id,
|
||||
}
|
||||
// exactOptionalPropertyTypes: only set `signal` when present — assigning
|
||||
// `undefined` to an optional `signal?: AbortSignal` is a type error.
|
||||
if (signal) options.signal = signal
|
||||
const request = await this.ctx.waterfall('agent/request', agent, turn, step, options, () => Promise.resolve(options))
|
||||
if (!request.model) {
|
||||
throw new Error('no model available for summarization: set BasicCompactConfig.summarizationModel, AgentOptions.model, or supply one via the agent/request waterfall')
|
||||
}
|
||||
for await (const chunk of this.ctx.llm.stream(request)) {
|
||||
assembler.push(chunk)
|
||||
}
|
||||
|
||||
const error = finishError(assembler.finish)
|
||||
if (error) throw error
|
||||
|
||||
const summary = this._textOnly(assembler.message().content)
|
||||
if (!summary.some(block => block.type === 'text' && block.text.trim().length > 0)) {
|
||||
throw new Error('summarization produced no text summary content')
|
||||
}
|
||||
|
||||
return summary
|
||||
}
|
||||
|
||||
// ---- Core API (implements the abstract contract) ----
|
||||
|
||||
/**
|
||||
* The sole token-pressure gate: estimate the current surface-derived history,
|
||||
* and if it exceeds the threshold (`contextWindow * thresholdRatio`), compact
|
||||
* the oldest surface nodes outside the `retainTokens` budget. The auto-
|
||||
* compaction listener delegates here rather than pre-checking, so this is the
|
||||
* only place the decision lives.
|
||||
*
|
||||
* Retention is a UNIFORM tail→head walk over the whole surface — turn
|
||||
* boundaries play NO role. Walking node-by-node from the tail and summing
|
||||
* token estimates, once the retained total reaches `retainTokens` the cutoff
|
||||
* is rounded to a balanced tool-pairing boundary: if the cut before the
|
||||
* retained node is unbalanced (an unanswered tool-call sits before it — i.e.
|
||||
* it is mid-step), the walk continues head-ward until the cut is balanced so
|
||||
* the whole step is retained (never splitting a step's tool-calls from their
|
||||
* results); if it stopped on a free node (a node belonging to no step), that
|
||||
* cut is already balanced. This always rounds toward retaining MORE (retained
|
||||
* ≥ `retainTokens`) and is boundary-safe by construction — no separate snap
|
||||
* pass.
|
||||
*
|
||||
* The compacted range is always anchored at the surface HEAD (`nodes[0]`):
|
||||
* auto-compaction re-consolidates any prior head checkpoint into one fresh
|
||||
* checkpoint. Declines (`null`) when nothing is over threshold, when the whole
|
||||
* surface fits the retain budget, or when no balanced cutoff exists in the
|
||||
* compactable range (its only content is an open tail step — retry once it
|
||||
* closes).
|
||||
*/
|
||||
override async compactIfNeeded(
|
||||
agent: Agent,
|
||||
turn: number,
|
||||
step: number,
|
||||
fullSystemPrompt: string,
|
||||
signal: AbortSignal,
|
||||
): Promise<CompactionResult | null> {
|
||||
const session = agent.session
|
||||
const threshold = Math.floor(this.config.contextWindow * this.config.thresholdRatio)
|
||||
let result: CompactionResult | null = null
|
||||
for (let attempt = 0; attempt <= this.config.compactionRetries; attempt++) {
|
||||
const totalTokens = this.estimateTokens(session.deriveMessages(), fullSystemPrompt)
|
||||
if (totalTokens < threshold) return result
|
||||
|
||||
const range = this._compactableRange(session)
|
||||
if (range === null) {
|
||||
/* v8 ignore else -- defensive for non-standard subclass mutations; the concrete replace keeps a compactable head checkpoint. */
|
||||
if (result === null) return null
|
||||
/* v8 ignore next -- paired with the ignored defensive branch above. */
|
||||
break
|
||||
}
|
||||
|
||||
result = await this.compactRegion(session, range.start, range.end, agent, turn, step, signal)
|
||||
}
|
||||
|
||||
const totalTokens = this.estimateTokens(session.deriveMessages(), fullSystemPrompt)
|
||||
if (totalTokens < threshold) return result
|
||||
|
||||
throw new Error(
|
||||
`compaction still above threshold after ${this.config.compactionRetries + 1} compaction attempts `
|
||||
+ `(${totalTokens} estimated tokens >= threshold ${threshold})`,
|
||||
)
|
||||
}
|
||||
|
||||
override async compactRegion(
|
||||
session: Session,
|
||||
start: number,
|
||||
end: number,
|
||||
agent: Agent,
|
||||
turn: number,
|
||||
step: number,
|
||||
signal?: AbortSignal,
|
||||
): Promise<CompactionResult> {
|
||||
// Resolve the range by surface POSITION, not numeric seq interval. A prior
|
||||
// replace lands a fresh high-seq summary node AT the shadowed range's
|
||||
// position, so the surface order (head→tail) no longer tracks seq order —
|
||||
// `[newSummarySeq, olderRetainedSeq, …]` is normal. Indexing into the
|
||||
// ordered node list and slicing it is the only correct way to read a range;
|
||||
// a `node.seq >= start && node.seq <= end` interval test would mis-collect
|
||||
// nodes (and `start > end` would falsely reject) once that happens.
|
||||
const nodes = session.surface.nodes
|
||||
const startIdx = nodes.findIndex(n => n.seq === start)
|
||||
const endIdx = nodes.findIndex(n => n.seq === end)
|
||||
if (startIdx === -1) throw new Error(`compactRegion: start seq ${start} not found in surface`)
|
||||
if (endIdx === -1) throw new Error(`compactRegion: end seq ${end} not found in surface`)
|
||||
if (startIdx > endIdx) {
|
||||
throw new Error(`compactRegion: start seq ${start} (position ${startIdx}) is after end seq ${end} (position ${endIdx}) on the surface`)
|
||||
}
|
||||
|
||||
// The region must never split a step's assistant-message tool-calls from
|
||||
// their tool/results (which would orphan one side and produce a transcript
|
||||
// every provider rejects). A region is safe iff BOTH its edges are balanced
|
||||
// cuts: the cut before `start`, and the cut after `end`. A node that belongs
|
||||
// to no step (pre-step user message, inter-step steering, injection context)
|
||||
// is a balanced (free) boundary; an `end` inside an open (unclosed) tail step
|
||||
// leaves the cut after it unbalanced (the open tool-call has no result yet),
|
||||
// so it is rejected. See dsh-session's tool-pairing balance check.
|
||||
const events = session.events
|
||||
if (!isToolPairingBalanced(nodes, events, start)) {
|
||||
throw new Error(`compactRegion: start seq ${start} is not a balanced boundary (would split a step's tool-call/result pair)`)
|
||||
}
|
||||
// The cut after `end` is named by `end`'s surface successor, or `null` when
|
||||
// `end` is the tail.
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
|
||||
const afterEnd: number | null = nodes[endIdx]!.next
|
||||
if (!isToolPairingBalanced(nodes, events, afterEnd)) {
|
||||
throw new Error(`compactRegion: end seq ${end} is not a balanced boundary (would split a step, or the step is still open)`)
|
||||
}
|
||||
|
||||
if (this._isCompactionInProgress(session)) {
|
||||
throw new Error('compaction already in progress')
|
||||
}
|
||||
|
||||
// Compaction's events (compact/* and the replacement user/message) must be
|
||||
// turn-enclosed: the session-log contract rejects any plugin event appended
|
||||
// outside an open turn. Auto-compaction satisfies this — it runs on the
|
||||
// `agent/pre-step` seam, after `turn/start` and before `step/start`, so
|
||||
// strictly inside the open turn (but outside any step). A manual call on a
|
||||
// fully-closed session has no turn to enclose the events, so reject rather
|
||||
// than emit an un-enclosed run.
|
||||
const openTurn = this._openTurn(session)
|
||||
if (openTurn === null) {
|
||||
throw new Error('compactRegion: no open turn — compaction events must be enclosed in a turn')
|
||||
}
|
||||
// Slice the ordered surface nodes [startIdx, endIdx] inclusive — the
|
||||
// shadowed range is positional, so this is the set the replace op covers.
|
||||
const shadowedSeqs = nodes.slice(startIdx, endIdx + 1).map(n => n.seq)
|
||||
|
||||
// --- Acquire lock ---
|
||||
const startEvent = session.append('compact/start', { turn: openTurn })
|
||||
|
||||
try {
|
||||
// --- Extract text and summarize ---
|
||||
const text = this._extractText(session, shadowedSeqs)
|
||||
const summary = await this.summarize(text, agent, turn, step, signal)
|
||||
|
||||
// Estimate token count of the shadowed content for provenance.
|
||||
let shadowedTokenCount = 0
|
||||
for (const seq of shadowedSeqs) {
|
||||
// seq comes from a surface node — always a valid log index by construction.
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
|
||||
shadowedTokenCount += this.estimateEventTokens(session.events[seq]!)
|
||||
}
|
||||
const framedSummary = this._frameSummary(summary)
|
||||
const framedSummaryTokenCount = this.estimateContentTokens(framedSummary)
|
||||
if (framedSummaryTokenCount >= shadowedTokenCount) {
|
||||
throw new Error(
|
||||
`summary is not smaller than the shadowed content (${framedSummaryTokenCount} estimated framed tokens >= ${shadowedTokenCount})`,
|
||||
)
|
||||
}
|
||||
// --- Provenance record (log-only) ---
|
||||
const summaryEvent = session.append('compact/summary', {
|
||||
summary,
|
||||
shadowedRange: { start, end },
|
||||
shadowedSeqs,
|
||||
shadowedTokenCount,
|
||||
})
|
||||
|
||||
// --- Surface replacement ---
|
||||
// The user/message directly shadows all compacted surface nodes with a
|
||||
// single replace op. It is the ONLY surface event in the compaction
|
||||
// sequence — compact/start, compact/summary, and compact/end are log-only
|
||||
// (surfaceOp is rejected by the compiler for non-SurfaceEventType).
|
||||
// The landed content is FRAMED (checkpoint preamble + tag-wrapped summary);
|
||||
// the compact/summary provenance event above holds the raw model output.
|
||||
session.append('user/message', {
|
||||
content: framedSummary,
|
||||
source: { kind: 'plugin', plugin: 'compact' },
|
||||
}, {
|
||||
surfaceOp: { op: 'replace', start, end },
|
||||
sourceEventSeqs: [startEvent.seq, summaryEvent.seq, ...shadowedSeqs],
|
||||
})
|
||||
|
||||
// --- Release lock (log-only) ---
|
||||
// Appended LAST so the lock brackets the WHOLE operation: a crash between
|
||||
// compact/start and here leaves a detectable orphaned lock (a compact/start
|
||||
// with no matching compact/end) rather than a compact/end that falsely
|
||||
// claims compaction finished before the surface replacement landed.
|
||||
const endEvent = session.append('compact/end', { turn: openTurn })
|
||||
|
||||
return {
|
||||
startSeq: startEvent.seq,
|
||||
summarySeq: summaryEvent.seq,
|
||||
endSeq: endEvent.seq,
|
||||
summary,
|
||||
shadowedRange: { start, end },
|
||||
shadowedSeqs,
|
||||
shadowedTokenCount,
|
||||
}
|
||||
} catch (error: unknown) {
|
||||
// Always release the lock — append compact/end with the error so a
|
||||
// wedged lock is impossible.
|
||||
const msg = error instanceof Error ? error.message : String(error)
|
||||
session.append('compact/end', { turn: openTurn, error: msg })
|
||||
throw error
|
||||
}
|
||||
}
|
||||
|
||||
// ---- Internal helpers ----
|
||||
|
||||
/**
|
||||
* Frame the raw summary blocks into the content that lands on the surface:
|
||||
* a checkpoint preamble (so a resuming model reads it as a checkpoint, not a
|
||||
* fresh user request) followed by the summary wrapped in
|
||||
* {@link SUMMARY_OPEN_TAG}/{@link SUMMARY_CLOSE_TAG}. The tags make a prior
|
||||
* checkpoint detectable in the transcript on the next compaction cycle, which
|
||||
* triggers the merge rule in the summarization prompt. The raw, unframed
|
||||
* `summary` is preserved separately on the `compact/summary` provenance event.
|
||||
*/
|
||||
private _frameSummary(summary: readonly ContentBlock[]): ContentBlock[] {
|
||||
return [
|
||||
{ type: 'text', text: `${CHECKPOINT_PREAMBLE}\n\n${SUMMARY_OPEN_TAG}` },
|
||||
...summary,
|
||||
{ type: 'text', text: SUMMARY_CLOSE_TAG },
|
||||
]
|
||||
}
|
||||
|
||||
/**
|
||||
* Whether a compaction is currently in progress for `session` — an unmatched
|
||||
* `compact/start` (no later `compact/end`) WITHIN the current turn.
|
||||
*
|
||||
* The scan is scoped to the current turn: walking back from the tail it stops
|
||||
* at the first `turn/end` (the boundary closing the prior turn). A
|
||||
* `compact/start` left orphaned by a crash mid-compaction lives in a turn that
|
||||
* persistence repair then closes with a synthetic `turn/end`; scoping here so
|
||||
* that a stale orphan from a PAST turn cannot wedge compaction forever (it sits
|
||||
* before the nearest `turn/end`, so the scan never reaches it). An in-progress
|
||||
* compaction's `compact/start` is always in the still-open current turn,
|
||||
* before any `turn/end`, so it is still detected.
|
||||
*/
|
||||
private _isCompactionInProgress(session: Session): boolean {
|
||||
const events = session.events
|
||||
for (let i = events.length - 1; i >= 0; i--) {
|
||||
// Index bounded by i >= 0 and i < events.length — never undefined.
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
|
||||
const e = events[i]!
|
||||
if (e.type === 'compact/start') return true
|
||||
if (e.type === 'compact/end') break
|
||||
// A turn/end bounds the scan: anything before it belongs to a prior
|
||||
// (closed) turn and cannot be an in-progress compaction of THIS turn.
|
||||
if (e.type === 'turn/end') break
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
/** Resolve the next head-anchored compactable surface range, or `null`. */
|
||||
private _compactableRange(session: Session): { start: number; end: number } | null {
|
||||
const nodes = session.surface.nodes
|
||||
if (nodes.length === 0) return null
|
||||
|
||||
const events = session.events
|
||||
const retainBudget = this.config.retainTokens
|
||||
|
||||
// Walk tail→head summing per-node token estimates. `keepFromIdx` is the
|
||||
// index of the OLDEST node we retain verbatim; everything strictly older
|
||||
// (`[0, keepFromIdx - 1]`) is the compactable range.
|
||||
let accumulated = 0
|
||||
let keepFromIdx = nodes.length // nothing retained yet
|
||||
for (let i = nodes.length - 1; i >= 0; i--) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
|
||||
const node = nodes[i]!
|
||||
const event = events[node.seq]
|
||||
/* v8 ignore next -- node.seq is a surface-node seq, always a valid log index by construction */
|
||||
if (event) accumulated += this.estimateEventTokens(event)
|
||||
keepFromIdx = i
|
||||
if (accumulated >= retainBudget) break
|
||||
}
|
||||
|
||||
// The whole surface fits the retain budget — nothing to compact.
|
||||
if (keepFromIdx === 0) return null
|
||||
|
||||
// Round the cutoff to a tool-pairing boundary: if the cut before
|
||||
// `nodes[keepFromIdx]` is unbalanced (an unanswered tool-call sits before
|
||||
// it — i.e. it is mid-step), extend the retained side head-ward until the
|
||||
// cut is balanced, so the compacted range ends without splitting an
|
||||
// assistant↔result pair. A node that belongs to no step is already a
|
||||
// balanced (free) boundary. Decline if no balanced cut exists at or below
|
||||
// `keepFromIdx` (the compactable range is only an un-splittable open tail
|
||||
// step — retry once it closes).
|
||||
while (keepFromIdx > 0) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
|
||||
if (isToolPairingBalanced(nodes, events, nodes[keepFromIdx]!.seq)) break
|
||||
keepFromIdx -= 1
|
||||
}
|
||||
if (keepFromIdx === 0) return null
|
||||
|
||||
// The compacted range is [head … keepFromIdx - 1], anchored at the head.
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
|
||||
const firstSeq = nodes[0]!.seq
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
|
||||
const cutoffSeq = nodes[keepFromIdx - 1]!.seq
|
||||
return { start: firstSeq, end: cutoffSeq }
|
||||
}
|
||||
|
||||
/**
|
||||
* Keep ONLY text blocks from the model-produced summary before storing it.
|
||||
*
|
||||
* The summary lands on the surface as a synthesized `user/message` (see
|
||||
* {@link _frameSummary}), so the only block type that is both useful and safe
|
||||
* there is `text`. A model assistant message can otherwise carry `reasoning`
|
||||
* (private chain-of-thought, must not leak into the durable checkpoint) and
|
||||
* `tool-call` blocks — and a surviving `tool-call` in a user message would be
|
||||
* an orphaned call with no matching `tool-result`, exactly the tool-pairing
|
||||
* breakage compaction works to avoid. Filtering to text drops both.
|
||||
*/
|
||||
private _textOnly(blocks: readonly ContentBlock[]): ContentBlock[] {
|
||||
return blocks.filter((block): block is Extract<ContentBlock, { type: 'text' }> => block.type === 'text')
|
||||
}
|
||||
|
||||
/**
|
||||
* The turn number of the currently OPEN turn — a `turn/start` not yet
|
||||
* followed by its `turn/end` — or `null` if the session has no open turn.
|
||||
*
|
||||
* Compaction's events must be enclosed in a turn, so scanning back from the
|
||||
* tail: a `turn/start` means that turn is open (return it); a `turn/end` means
|
||||
* the most recent turn already closed (return null). The whole compaction
|
||||
* sequence (compact/start … compact/end) is stamped with this turn.
|
||||
*/
|
||||
private _openTurn(session: Session): number | null {
|
||||
for (let i = session.events.length - 1; i >= 0; i--) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
|
||||
const e = session.events[i]!
|
||||
if (e.type === 'turn/start') return e.data.turn
|
||||
if (e.type === 'turn/end') return null
|
||||
}
|
||||
return null
|
||||
}
|
||||
|
||||
/**
|
||||
* Extract plain-text conversation from a set of surface node seqs, for
|
||||
* feeding into the summarization model. Walks the seqs in the order given
|
||||
* (surface order, as `compactRegion` slices the surface-node list) so the
|
||||
* summary follows the conversation as the model sees it — which, after a
|
||||
* `replace`, is NOT ascending log-seq order (a high-seq summary node heads the
|
||||
* surface before older retained lower-seq nodes).
|
||||
*/
|
||||
private _extractText(session: Session, seqs: number[]): string {
|
||||
const lines: string[] = []
|
||||
|
||||
// Walk seqs in the order given (surface order, as compactRegion slices the
|
||||
// surface-node list) — NOT ascending log-seq order. After a replace the
|
||||
// summary node carries a fresh high seq while sitting at the head of the
|
||||
// surface before older retained lower-seq nodes, so a log-order scan would
|
||||
// feed the transcript out of order and break the checkpoint-merge prompt.
|
||||
for (const seq of seqs) {
|
||||
const event = session.events[seq]
|
||||
/* v8 ignore next -- seq is a surface-node seq, always a valid log index by construction */
|
||||
if (!event) continue
|
||||
|
||||
switch (event.type) {
|
||||
case 'user/message': {
|
||||
const text = this._blocksToText(event.data.content)
|
||||
if (text) lines.push(`User: ${text}`)
|
||||
break
|
||||
}
|
||||
case 'assistant/message': {
|
||||
const text = this._blocksToText(event.data.content)
|
||||
if (text) lines.push(`Assistant: ${text}`)
|
||||
break
|
||||
}
|
||||
case 'tool/result': {
|
||||
const text = this._blocksToText(event.data.content)
|
||||
const label = event.data.isError ? 'Tool error' : 'Tool result'
|
||||
if (text) lines.push(`${label} (call ${event.data.callId}): ${text}`)
|
||||
break
|
||||
}
|
||||
case 'context/message': {
|
||||
const text = this._blocksToText(event.data.content)
|
||||
if (text) lines.push(`[Context: ${text}]`)
|
||||
break
|
||||
}
|
||||
case 'steering/message': {
|
||||
const text = this._blocksToText(event.data.content)
|
||||
if (text) lines.push(`[Steering: ${text}]`)
|
||||
break
|
||||
}
|
||||
// SessionEventMap is merge-extensible — unknown types are
|
||||
// non-message events that carry no extractable text.
|
||||
/* v8 ignore next 2 -- seqs only name surface nodes, always one of the 5 handled SurfaceEventTypes; unreachable */
|
||||
default:
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
return lines.join('\n\n')
|
||||
}
|
||||
|
||||
/**
|
||||
* Render content blocks to a single plain-text string for the summarization
|
||||
* prompt. Text and reasoning contribute their text; every other block type
|
||||
* contributes a type-tagged placeholder (`[image]`, `[tool-call: name(args)]`,
|
||||
* …) so the summarizer is told what non-text content existed in the region
|
||||
* rather than silently losing it. Blocks join with newlines; empty-text
|
||||
* blocks contribute nothing.
|
||||
*/
|
||||
private _blocksToText(blocks: readonly ContentBlock[]): string {
|
||||
const parts: string[] = []
|
||||
for (const block of blocks) {
|
||||
switch (block.type) {
|
||||
case 'text':
|
||||
if (block.text) parts.push(block.text)
|
||||
break
|
||||
case 'reasoning':
|
||||
if (block.text) parts.push(`[reasoning: ${block.text}]`)
|
||||
break
|
||||
case 'tool-call':
|
||||
parts.push(`[tool-call: ${block.name}(${block.arguments})]`)
|
||||
break
|
||||
case 'tool-result': {
|
||||
const inner = this._blocksToText(block.content)
|
||||
parts.push(inner ? `[tool-result: ${inner}]` : '[tool-result]')
|
||||
break
|
||||
}
|
||||
case 'image':
|
||||
parts.push('[image]')
|
||||
break
|
||||
// ContentBlockMap is merge-extensible — render an unknown block as a
|
||||
// bare type-tagged placeholder so a plugin-added block type is still
|
||||
// signalled to the summarizer rather than dropped.
|
||||
default:
|
||||
parts.push(`[${(block as ContentBlock).type}]`)
|
||||
}
|
||||
}
|
||||
return parts.join('\n')
|
||||
}
|
||||
}
|
||||
|
||||
export default BasicCompactService
|
||||
81
packages/compact/compact-basic/src/types.ts
Normal file
81
packages/compact/compact-basic/src/types.ts
Normal file
@@ -0,0 +1,81 @@
|
||||
/**
|
||||
* Configuration vocabulary for the basic compaction backend.
|
||||
*
|
||||
* Every tunable lives here, in the implementation — the abstract contract
|
||||
* (`@deepseek-ai/dsh-compact`) carries no config, because thresholds and
|
||||
* retention policy are HOW decisions a different backend would make
|
||||
* differently.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-compact-basic/types
|
||||
*/
|
||||
|
||||
/**
|
||||
* Backend configuration. Every knob is REQUIRED except `auto`: there is no
|
||||
* concrete data yet to justify default thresholds/budgets, so a consumer must
|
||||
* state each value explicitly rather than inherit a guessed default. `auto`
|
||||
* alone defaults to `true` (auto-compaction is the intended posture).
|
||||
*/
|
||||
export interface BasicCompactConfig {
|
||||
/** Context window size in tokens. */
|
||||
contextWindow: number
|
||||
/** Compact when estimated token usage exceeds this fraction of context window. */
|
||||
thresholdRatio: number
|
||||
/** Number of tokens of recent context to retain during compaction. */
|
||||
retainTokens: number
|
||||
/** Model to use for summarization (`''` — uses the agent's model). */
|
||||
summarizationModel: string
|
||||
/** Provider generation cap for the summarization call. */
|
||||
maxTokens: number
|
||||
/** Extra compaction attempts when the first compacted surface is still over threshold. */
|
||||
compactionRetries: number
|
||||
/** Enable automatic compaction on the `agent/pre-step` seam (default true). */
|
||||
auto?: boolean
|
||||
}
|
||||
|
||||
/** Resolved config with `auto` defaulted. */
|
||||
export type ResolvedConfig = Required<BasicCompactConfig>
|
||||
|
||||
/**
|
||||
* Default `auto` when unset and reject nonsensical numeric knobs.
|
||||
*
|
||||
* Convergence is not a static config invariant: provider generation caps can be
|
||||
* spent on hidden or surfaced reasoning tokens, and the model may emit a summary
|
||||
* of unpredictable size. The backend instead enforces convergence dynamically:
|
||||
* each committed summary must be smaller than the content it shadows, and
|
||||
* `compactIfNeeded` may re-compact up to `compactionRetries` extra times before
|
||||
* throwing if the surface still exceeds the threshold.
|
||||
*/
|
||||
export function resolveConfig(config: BasicCompactConfig): ResolvedConfig {
|
||||
const resolved: ResolvedConfig = { auto: true, ...config }
|
||||
|
||||
assertPositiveInteger('contextWindow', resolved.contextWindow)
|
||||
assertRatio('thresholdRatio', resolved.thresholdRatio)
|
||||
assertNonNegativeInteger('retainTokens', resolved.retainTokens)
|
||||
assertPositiveInteger('maxTokens', resolved.maxTokens)
|
||||
assertNonNegativeInteger('compactionRetries', resolved.compactionRetries)
|
||||
if (typeof resolved.summarizationModel !== 'string') {
|
||||
throw new Error('BasicCompactConfig: summarizationModel must be a string.')
|
||||
}
|
||||
if (typeof resolved.auto !== 'boolean') {
|
||||
throw new Error('BasicCompactConfig: auto must be a boolean.')
|
||||
}
|
||||
return resolved
|
||||
}
|
||||
|
||||
function assertPositiveInteger(name: string, value: number): void {
|
||||
if (!Number.isInteger(value) || value <= 0) {
|
||||
throw new Error(`BasicCompactConfig: ${name} (${value}) must be a positive integer.`)
|
||||
}
|
||||
}
|
||||
|
||||
function assertNonNegativeInteger(name: string, value: number): void {
|
||||
if (!Number.isInteger(value) || value < 0) {
|
||||
throw new Error(`BasicCompactConfig: ${name} (${value}) must be a non-negative integer.`)
|
||||
}
|
||||
}
|
||||
|
||||
function assertRatio(name: string, value: number): void {
|
||||
if (typeof value !== 'number' || !Number.isFinite(value) || value <= 0 || value > 1) {
|
||||
throw new Error(`BasicCompactConfig: ${name} (${value}) must be a number in (0, 1].`)
|
||||
}
|
||||
}
|
||||
1707
packages/compact/compact-basic/tests/compact-basic.spec.ts
Normal file
1707
packages/compact/compact-basic/tests/compact-basic.spec.ts
Normal file
File diff suppressed because it is too large
Load Diff
156
packages/compact/compact-basic/tests/compact-loop-repro.spec.ts
Normal file
156
packages/compact/compact-basic/tests/compact-loop-repro.spec.ts
Normal file
@@ -0,0 +1,156 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import LlmService from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import { isToolPairingBalanced } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
|
||||
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
||||
import * as Invariants from '@deepseek-ai/dsh-invariants'
|
||||
import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
|
||||
import type { SurfaceEvent } from '@deepseek-ai/dsh-session'
|
||||
|
||||
/**
|
||||
* CBR-001 regression: a compaction checkpoint that the REAL loop lands is a
|
||||
* free surface boundary (it carries no tool-call/result pair), so it must be a
|
||||
* valid region edge on BOTH sides. A surface-anchored balance check sees that;
|
||||
* the abandoned log-position scan did not.
|
||||
*
|
||||
* The loop fires the compaction seam mid-flight, so the landed checkpoint
|
||||
* `user/message{replace}` sits at a HIGH log seq positioned beside the current
|
||||
* step even though its SURFACE position is the head. A log-position forward scan
|
||||
* from the checkpoint reaches the step's own later `assistant/message` and
|
||||
* wrongly reports the checkpoint as mid-step — refusing it as a region end. A
|
||||
* SECOND compaction that re-summarizes just that head checkpoint (region end ==
|
||||
* checkpoint) therefore throws and is swallowed, so the surface never
|
||||
* re-consolidates.
|
||||
*
|
||||
* This drives a real auto-compaction through the agent-loop and asserts the
|
||||
* landed checkpoint balances on both sides AND that re-compacting it (end ==
|
||||
* checkpoint) succeeds. RED on the log-position predicates; GREEN once alignment
|
||||
* is decided from surface tool-pairing balance.
|
||||
*/
|
||||
|
||||
const TOKENS_PER_BLOCK = 10
|
||||
|
||||
class ReproCompactService extends BasicCompactService {
|
||||
override estimateContentTokens(blocks: readonly ContentBlock[]): number {
|
||||
return blocks.length * TOKENS_PER_BLOCK
|
||||
}
|
||||
|
||||
override async summarize(): Promise<ContentBlock[]> {
|
||||
return [{ type: 'text', text: 'CHECKPOINT SUMMARY' }]
|
||||
}
|
||||
}
|
||||
|
||||
/** Each call emits one tool-call until exhausted, then a final text answer. */
|
||||
class StepwiseToolAdapter extends LlmAdapter {
|
||||
calls = 0
|
||||
constructor(private toolSteps: number) {
|
||||
super()
|
||||
}
|
||||
|
||||
async * stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
const n = this.calls
|
||||
this.calls += 1
|
||||
if (n < this.toolSteps) {
|
||||
const id = CallId(`c${n}`)
|
||||
const args = `{"i":${n}}`
|
||||
yield { type: 'block-start', index: 0, blockType: 'text' }
|
||||
yield { type: 'block-end', index: 0, block: { type: 'text', text: `step ${n}` } }
|
||||
yield { type: 'block-start', index: 1, blockType: 'tool-call' }
|
||||
yield { type: 'block-end', index: 1, block: { type: 'tool-call', id, name: 'work', arguments: args } }
|
||||
yield { type: 'finish', reason: { kind: 'tool-calls' } }
|
||||
return
|
||||
}
|
||||
yield { type: 'block-start', index: 0, blockType: 'text' }
|
||||
yield { type: 'block-end', index: 0, block: { type: 'text', text: 'all done' } }
|
||||
yield { type: 'finish', reason: { kind: 'stop' } }
|
||||
}
|
||||
}
|
||||
|
||||
async function harness(toolSteps: number): Promise<{ ctx: Context; compact: ReproCompactService }> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(Invariants, {})
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps))
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'work',
|
||||
description: 'does work',
|
||||
parameters: { i: { type: 'number' } },
|
||||
async execute() {
|
||||
return [{ type: 'text', text: 'work result' }]
|
||||
},
|
||||
}))
|
||||
// Tiny window so a couple of tool steps cross the threshold and compaction
|
||||
// fires within the runaway turn.
|
||||
const compact = new ReproCompactService(ctx, {
|
||||
auto: true,
|
||||
contextWindow: 64,
|
||||
thresholdRatio: 0.5,
|
||||
retainTokens: 20,
|
||||
summarizationModel: '',
|
||||
maxTokens: 8192,
|
||||
compactionRetries: 1,
|
||||
})
|
||||
return { ctx, compact }
|
||||
}
|
||||
|
||||
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
const dispose = ctx.on('agent/status', (subject, status) => {
|
||||
if (subject === agent && status === 'idle') {
|
||||
dispose()
|
||||
resolve()
|
||||
}
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () => {
|
||||
it('the head checkpoint the loop lands is a balanced cut on both sides', async () => {
|
||||
const { ctx } = await harness(8)
|
||||
try {
|
||||
const agent = ctx.agentLoop.create(AgentId('repro'), { model: 'mock' })
|
||||
agent.send([{ type: 'text', text: 'do a long multi-step task' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const events = [...agent.session.events]
|
||||
// A compaction ran: at least one checkpoint landed on the surface.
|
||||
const checkpoints = events.filter(
|
||||
(e): e is SurfaceEvent =>
|
||||
e.type === 'user/message'
|
||||
&& typeof (e as SurfaceEvent).surfaceOp === 'object',
|
||||
)
|
||||
expect(checkpoints.length).toBeGreaterThan(0)
|
||||
|
||||
// The loop fired compaction mid-flight, so each landed checkpoint sits at a
|
||||
// high log seq beside the step it landed in, even though its SURFACE
|
||||
// position is the head of the range it shadowed. A checkpoint carries no
|
||||
// tool-call/result pair (only summarized prose), so every checkpoint still
|
||||
// on the surface must be a balanced cut on BOTH sides — the cut before it
|
||||
// (region START) and the cut after it (region END). The abandoned
|
||||
// log-position scan reported the END as mis-aligned because the forward log
|
||||
// scan reached the neighbouring step's assistant/message.
|
||||
const nodes = agent.session.surface.nodes
|
||||
for (const cp of checkpoints) {
|
||||
const node = nodes.find(n => n.seq === cp.seq)
|
||||
if (!node) continue // shadowed by a later checkpoint — no longer an edge.
|
||||
expect(isToolPairingBalanced(nodes, events, node.seq),
|
||||
`checkpoint seq ${node.seq} must be a balanced region START`).toBe(true)
|
||||
expect(isToolPairingBalanced(nodes, events, node.next),
|
||||
`checkpoint seq ${node.seq} must be a balanced region END`).toBe(true)
|
||||
}
|
||||
} finally {
|
||||
await ctx.fiber.dispose()
|
||||
}
|
||||
})
|
||||
})
|
||||
16
packages/compact/compact-basic/tsconfig.json
Normal file
16
packages/compact/compact-basic/tsconfig.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"extends": "../../../tsconfig.base.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "lib/types"
|
||||
},
|
||||
"include": ["src"],
|
||||
"references": [
|
||||
{ "path": "../../../vendor/cosmokit" },
|
||||
{ "path": "../../../vendor/cordis" },
|
||||
{ "path": "../../llm/llm" },
|
||||
{ "path": "../../core/session" },
|
||||
{ "path": "../../core/agent" },
|
||||
{ "path": "../compact" }
|
||||
]
|
||||
}
|
||||
@@ -7,10 +7,10 @@ This package is the interface tier of the compaction capability, split so each c
|
||||
| Package | Role |
|
||||
|---|---|
|
||||
| `@deepseek-ai/dsh-compact` (this) | the interface: abstract service + `compact/*` events + `CompactionResult` |
|
||||
| `@deepseek-ai/dsh-compact-basic` | a backend: char/4 estimation + token-budget retention + `llm.stream()` summarization |
|
||||
| `@deepseek-ai/dsh-compact-basic` (deferred) | a backend: char/4 estimation + token-budget retention + `llm.stream()` summarization |
|
||||
| `@deepseek-ai/dsh-tool-compact` (deferred) | the model-facing `/compact` tool over `ctx.compact` |
|
||||
|
||||
Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/proposed/feature/2026-06-18-compaction-capability-seam.md).
|
||||
Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md).
|
||||
|
||||
## Service API (`ctx.compact`)
|
||||
|
||||
@@ -18,10 +18,10 @@ Both methods are **abstract** — the backend owns the entire strategy (token es
|
||||
|
||||
| Member | Semantics |
|
||||
|---|---|
|
||||
| `compactIfNeeded(session, systemPrompt?, model?, signal?)` | Estimate the history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. |
|
||||
| `compactRegion(session, start, end, model, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start > end`. |
|
||||
| `compactIfNeeded(agent, turn, step, fullSystemPrompt, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, lifecycle context, assembled `fullSystemPrompt`, and turn `signal`; router-aware summarizers can use the agent lifecycle context to route their own model call through `agent/request`. |
|
||||
| `compactRegion(session, start, end, agent, turn, step, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. |
|
||||
|
||||
Both methods take an optional `signal: AbortSignal`. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The turn that the `compact/*` events belong to is not a parameter — it is recoverable from the log (the currently-open turn), so the backend stamps it without the caller supplying it.
|
||||
`compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value.
|
||||
|
||||
## Surface contract
|
||||
|
||||
@@ -53,4 +53,4 @@ The `compact/*` events extend `SessionEventMap` (merge-extensible) via declarati
|
||||
|
||||
## Implementing a backend
|
||||
|
||||
Subclass `CompactService`, implement `compactIfNeeded` and `compactRegion`, and load the subclass as a plugin — it registers as `ctx.compact`. See `@deepseek-ai/dsh-compact-basic` for the reference implementation.
|
||||
Subclass `CompactService`, implement `compactIfNeeded` and `compactRegion`, and load the subclass as a plugin — it registers as `ctx.compact`. A tokenizer-, template-, or model-backed implementation can live as a sibling package without changing callers.
|
||||
|
||||
@@ -6,17 +6,17 @@
|
||||
* Implementations subclass {@link CompactService}, implement
|
||||
* {@link CompactService.compactIfNeeded} and {@link CompactService.compactRegion},
|
||||
* and load as a plugin — registering as `ctx.compact` (one implementation per
|
||||
* context). `@deepseek-ai/dsh-compact-basic` (char/4 estimation + token-budget
|
||||
* retention + `ctx.llm.stream()` summarization) is the first. A tokenizer- or
|
||||
* template-based backend swaps in without touching consumers.
|
||||
* context). A tokenizer-, template-, or model-backed implementation can live
|
||||
* as a sibling package; callers stay on the same `ctx.compact` seam without
|
||||
* touching consumers.
|
||||
*
|
||||
* The split follows the capability-seams RFC — interface (this) /
|
||||
* implementation (`dsh-compact-basic`) / consumer (a `/compact` tool, deferred)
|
||||
* — modeled on the bash trio. Unlike `dsh-bash`, this interface necessarily
|
||||
* implementation (deferred) / consumer (a `/compact` tool, deferred) — modeled
|
||||
* on the bash trio. Unlike `dsh-bash`, this interface necessarily
|
||||
* depends on `dsh-session` and `dsh-llm`: the contract's verbs are defined over
|
||||
* a `Session` and its output is the `ContentBlock` vocabulary. That deviation
|
||||
* from the "interface depends only on cordis" guidance is intentional and
|
||||
* recorded in the [compaction capability-seam RFC](../../../../docs/rfc/proposed/feature/2026-06-18-compaction-capability-seam.md).
|
||||
* recorded in the [compaction capability-seam RFC](../../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md).
|
||||
*
|
||||
* @module @deepseek-ai/dsh-compact
|
||||
*/
|
||||
@@ -27,6 +27,12 @@ import type { CompactionResult } from './types.ts'
|
||||
|
||||
export type { CompactionResult } from './types.ts'
|
||||
|
||||
/** Minimal agent context compaction needs without depending on the agent package. */
|
||||
export interface CompactAgentContext {
|
||||
session: Session
|
||||
options: { model?: string }
|
||||
}
|
||||
|
||||
declare module 'cordis' {
|
||||
interface Context {
|
||||
compact: CompactService
|
||||
@@ -62,24 +68,44 @@ export abstract class CompactService extends Service {
|
||||
/**
|
||||
* Check token pressure and compact if the conversation is too large.
|
||||
*
|
||||
* Estimates the current history size (optionally including a system prompt),
|
||||
* and if it exceeds the backend's threshold, compacts an older range via
|
||||
* {@link compactRegion}, keeping recent context intact.
|
||||
* Estimates the current surface-derived history size (including the system
|
||||
* prompt), and if it exceeds the backend's threshold, compacts an older range
|
||||
* via {@link compactRegion}, keeping recent context intact. Returns `null`
|
||||
* when no compaction is needed.
|
||||
*
|
||||
* @param session - the session whose surface may be compacted.
|
||||
* @param systemPrompt - optional system prompt, counted toward the estimate.
|
||||
* @param model - optional summarization model (falls back to backend config).
|
||||
* @param signal - optional cancellation signal. A backend that summarizes via
|
||||
* Scope and guarantees a backend MUST honor:
|
||||
* - **Surface-derived history only.** The decision is made against the history
|
||||
* derived from the session surface — the only thing compaction can act on.
|
||||
* Non-surface context injected downstream (into the request `messages` by a
|
||||
* later listener) is out of this accounting by construction.
|
||||
* - **Head-anchored, best-effort.** Auto-compaction consolidates from the
|
||||
* surface HEAD up to a balanced tool-pairing cutoff, so a prior head
|
||||
* checkpoint is
|
||||
* re-summarized into one fresh checkpoint (the surface holds at most one
|
||||
* auto-generated checkpoint, always at the head). It is best-effort over
|
||||
* CLOSED steps: when the only compactable content left is an un-splittable
|
||||
* open tail step, it declines (`null`) and retries once that step closes.
|
||||
* - **Single-unit overflow is out of scope.** If a single retained unit (one
|
||||
* closed step, or a large free node such as a pasted `user/message`) ALONE
|
||||
* exceeds the budget, compaction cannot help and the call may go out
|
||||
* over-budget. Bounding an individual unit's size is a separate concern.
|
||||
*
|
||||
* @param agent - agent context owning the session surface and model options.
|
||||
* @param turn - turn number of the pre-step checkpoint.
|
||||
* @param step - step number about to start.
|
||||
* @param fullSystemPrompt - assembled system prompt, counted toward the estimate.
|
||||
* @param signal - cancellation signal. A backend summarizing via
|
||||
* `ctx.llm.stream()` MUST forward this into the call's `GenerateOptions.signal`
|
||||
* so an abort/dispose tears down the in-flight summarization rather than
|
||||
* leaving an orphaned model call running past the cancellation.
|
||||
* @returns the compaction result, or `null` if no compaction was needed.
|
||||
*/
|
||||
abstract compactIfNeeded(
|
||||
session: Session,
|
||||
systemPrompt?: string,
|
||||
model?: string,
|
||||
signal?: AbortSignal,
|
||||
agent: CompactAgentContext,
|
||||
turn: number,
|
||||
step: number,
|
||||
fullSystemPrompt: string,
|
||||
signal: AbortSignal,
|
||||
): Promise<CompactionResult | null>
|
||||
|
||||
/**
|
||||
@@ -89,22 +115,40 @@ export abstract class CompactService extends Service {
|
||||
* summarizes their content and appends a replacement surface node. Used by the
|
||||
* (future) `/compact` tool and internally by {@link compactIfNeeded}.
|
||||
*
|
||||
* The region MUST NOT split a step's `assistant/message` tool-calls from their
|
||||
* `tool/result`s, leaving the rehydrated transcript with a dangling tool-call
|
||||
* or an orphaned tool-result that every provider rejects. A region is safe iff
|
||||
* both its edges are balanced cuts on the surface: the cut before `start` and
|
||||
* the cut after `end` each have no unanswered tool-call before them. A node
|
||||
* that belongs to no step (a pre-step user message, inter-step steering, or an
|
||||
* injection context message) is a balanced (free) boundary; an `end` inside an
|
||||
* open (unclosed) tail step is invalid — its tool-calls have no results yet.
|
||||
* `dsh-session` exports `isToolPairingBalanced` for this check.
|
||||
*
|
||||
* @param session - the session whose surface is mutated.
|
||||
* @param start - inclusive seq of the first surface node to compact.
|
||||
* @param end - inclusive seq of the last surface node to compact.
|
||||
* @param model - summarization model.
|
||||
* @param agent - agent context used by router-aware summarizers.
|
||||
* @param turn - lifecycle turn forwarded to request-routing seams.
|
||||
* @param step - lifecycle step forwarded to request-routing seams.
|
||||
* @param signal - optional cancellation signal. A backend that summarizes via
|
||||
* `ctx.llm.stream()` MUST forward this into the call's `GenerateOptions.signal`
|
||||
* so an abort/dispose tears down the in-flight summarization rather than
|
||||
* leaving an orphaned model call running past the cancellation.
|
||||
* @throws if compaction is already in progress, or if `start`/`end` are not
|
||||
* valid surface nodes, or if `start > end`.
|
||||
* @throws if compaction is already in progress, if `start`/`end` are not
|
||||
* valid surface nodes, if `start` is positioned after `end` on the surface
|
||||
* (the range is a surface-POSITION span, not a numeric seq interval — a
|
||||
* prior replace can leave the surface non-monotonic in seq order), or if
|
||||
* either boundary is not a balanced tool-pairing cut (would split a step's
|
||||
* tool-call/result pair).
|
||||
*/
|
||||
abstract compactRegion(
|
||||
session: Session,
|
||||
start: number,
|
||||
end: number,
|
||||
model: string,
|
||||
agent: CompactAgentContext,
|
||||
turn: number,
|
||||
step: number,
|
||||
signal?: AbortSignal,
|
||||
): Promise<CompactionResult>
|
||||
}
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
* events are log-only markers (lock + provenance); only the five
|
||||
* surface-eligible types can carry `surfaceOp`. The actual surface mutation is
|
||||
* performed by a separate `user/message` event carrying the summary (see the
|
||||
* [compaction capability-seam RFC](../../../../docs/rfc/proposed/feature/2026-06-18-compaction-capability-seam.md)).
|
||||
* [compaction capability-seam RFC](../../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)).
|
||||
*
|
||||
* Configuration lives in the backend, not here: the contract states WHAT
|
||||
* compaction produces, while every tunable (context window, thresholds,
|
||||
@@ -48,9 +48,16 @@ export interface CompactionResult {
|
||||
endSeq: number
|
||||
/** The summary content blocks produced by the backend. */
|
||||
summary: ContentBlock[]
|
||||
/** The seq range that was shadowed [start, end] inclusive. */
|
||||
/**
|
||||
* The surface-boundary pair that was shadowed: the seqs of the first
|
||||
* (`start`) and last (`end`) surface nodes of the replaced range. A
|
||||
* surface-POSITION span, not a numeric seq interval — after a prior replace
|
||||
* lands a fresh high-seq summary node at an older range's position, `start`
|
||||
* can be GREATER than `end`. {@link CompactionResult.shadowedSeqs} is the
|
||||
* authoritative set of shadowed nodes, in surface order.
|
||||
*/
|
||||
shadowedRange: { start: number; end: number }
|
||||
/** The seq numbers of all shadowed surface nodes. */
|
||||
/** The seqs of all shadowed surface nodes, in surface order. */
|
||||
shadowedSeqs: number[]
|
||||
/** Estimated token count of the shadowed content. */
|
||||
shadowedTokenCount: number
|
||||
|
||||
@@ -3,6 +3,7 @@ import { Context } from 'cordis'
|
||||
import { CompactService } from '@deepseek-ai/dsh-compact'
|
||||
import type { CompactionResult } from '@deepseek-ai/dsh-compact'
|
||||
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { CompactAgentContext } from '@deepseek-ai/dsh-compact'
|
||||
|
||||
/**
|
||||
* A trivial concrete CompactService implementing the abstract contract. The
|
||||
@@ -15,10 +16,11 @@ class StubCompactService extends CompactService {
|
||||
lastSignal: AbortSignal | undefined
|
||||
|
||||
override async compactIfNeeded(
|
||||
_session: Session,
|
||||
_systemPrompt?: string,
|
||||
_model?: string,
|
||||
signal?: AbortSignal,
|
||||
_agent: CompactAgentContext,
|
||||
_turn: number,
|
||||
_step: number,
|
||||
_fullSystemPrompt: string,
|
||||
signal: AbortSignal,
|
||||
): Promise<CompactionResult | null> {
|
||||
this.lastSignal = signal
|
||||
return null
|
||||
@@ -28,7 +30,9 @@ class StubCompactService extends CompactService {
|
||||
session: Session,
|
||||
start: number,
|
||||
end: number,
|
||||
_model: string,
|
||||
_agent: CompactAgentContext,
|
||||
_turn: number,
|
||||
_step: number,
|
||||
signal?: AbortSignal,
|
||||
): Promise<CompactionResult> {
|
||||
this.lastSignal = signal
|
||||
@@ -54,6 +58,10 @@ class StubCompactService extends CompactService {
|
||||
}
|
||||
|
||||
describe('CompactService seam', () => {
|
||||
function stubAgent(session: Session, model?: string): CompactAgentContext {
|
||||
return { session, options: model === undefined ? {} : { model } }
|
||||
}
|
||||
|
||||
it('registers as ctx.compact', () => {
|
||||
const ctx = new Context()
|
||||
void new StubCompactService(ctx)
|
||||
@@ -72,7 +80,8 @@ describe('CompactService seam', () => {
|
||||
it('exposes the abstract contract methods', async () => {
|
||||
const ctx = new Context()
|
||||
const svc = new StubCompactService(ctx)
|
||||
expect(await svc.compactIfNeeded(new Session(SessionId('s')))).toBeNull()
|
||||
const session = new Session(SessionId('s'))
|
||||
expect(await svc.compactIfNeeded(stubAgent(session), 1, 1, '', new AbortController().signal)).toBeNull()
|
||||
})
|
||||
|
||||
it('compact/* events merge into SessionEventMap and are log-only', async () => {
|
||||
@@ -80,7 +89,7 @@ describe('CompactService seam', () => {
|
||||
const svc = new StubCompactService(ctx)
|
||||
const session = new Session(SessionId('s'))
|
||||
|
||||
const result = await svc.compactRegion(session, 0, 0, 'm')
|
||||
const result = await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'), 1, 1)
|
||||
|
||||
const startEvent = session.events.find(e => e.type === 'compact/start')
|
||||
expect(startEvent).toBeDefined()
|
||||
@@ -98,10 +107,10 @@ describe('CompactService seam', () => {
|
||||
const session = new Session(SessionId('s'))
|
||||
const controller = new AbortController()
|
||||
|
||||
await svc.compactRegion(session, 0, 0, 'm', controller.signal)
|
||||
await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'), 1, 1, controller.signal)
|
||||
expect(svc.lastSignal).toBe(controller.signal)
|
||||
|
||||
await svc.compactIfNeeded(session, undefined, undefined, controller.signal)
|
||||
await svc.compactIfNeeded(stubAgent(session), 1, 1, '', controller.signal)
|
||||
expect(svc.lastSignal).toBe(controller.signal)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -13,4 +13,4 @@ The packages every harness build is assembled from: the session log, the system-
|
||||
|
||||
`agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop; everything else in `core/` is interface/vocabulary. Plugins depend on the `agent` vocabulary, never on `agent-loop` directly, so the loop stays swappable.
|
||||
|
||||
`agent-core` is the composition counterpart: one bundle plugin that loads the whole providerless spine (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + `tool-bash` + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. App packages (`ui/stdio-agent`, `ui/acp-agent`) consume it and add only a front door; a leaf adds only the swappable backends. It lives in `core/` because it composes exclusively `core/` + interface packages and ships no provider, executor, or UI of its own.
|
||||
`agent-core` is the composition counterpart: one bundle plugin that loads the whole providerless spine (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + `tool-bash` + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. App packages (`ui/stdio-agent`, `ui/acp-agent`) consume it and add only a front door; a leaf adds the swappable backends plus any optional product tools it wants to expose. It lives in `core/` because it composes exclusively `core/` + interface packages and ships no provider, executor, or UI of its own.
|
||||
|
||||
@@ -12,10 +12,10 @@ This is the only package in the harness that contains concrete loop logic. Every
|
||||
|
||||
`AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface):
|
||||
|
||||
- `ctx.agents.create({ agentId, sessionId, meta?, agentOptions? }): AgentHandle` — programmatic create on a caller-supplied `sessionId` (e.g. an ACP-generated id), NOT `${id}-session`. Returns an [`AgentHandle`](../agent/README.md) — the owner disposes it to tear down exactly this agent (stop loop + await quiescence + unregister + remove session).
|
||||
- `ctx.agents.create({ agentId, sessionId, meta?, seed?, agentOptions? }): AgentHandle` — programmatic create on a caller-supplied `sessionId` (e.g. an ACP-generated id), NOT `${id}-session`; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix. Returns an [`AgentHandle`](../agent/README.md) — the owner disposes it to tear down exactly this agent (stop loop + await quiescence + unregister + remove session).
|
||||
- `ctx.agents.resume({ agentId, resumeSessionId, agentOptions? }): Promise<AgentHandle>` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)) and resume an agent on it. The live session id is the resumed id; turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). Returns an `AgentHandle`.
|
||||
|
||||
The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loop fiber (it discards the handle) — only the programmatic factory callers (the ACP bridge) hold a handle and own per-agent teardown.
|
||||
The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loop fiber (it discards the handle) — only the programmatic factory callers (the ACP bridge and in-process subagent backends) hold a handle and own per-agent teardown.
|
||||
|
||||
### Injected services
|
||||
|
||||
@@ -52,6 +52,8 @@ forever:
|
||||
STEP loop:
|
||||
drain steering
|
||||
assembly = systemPrompt.assemble()
|
||||
await serial agent/pre-step ⟵ surface mutation (compaction) outside the step
|
||||
session('step/start')
|
||||
request = waterfall agent/request
|
||||
stream llm.stream(request) → session('assistant/chunk')
|
||||
message = waterfall agent/step-result
|
||||
@@ -73,9 +75,9 @@ Cancellation: `agent.cancel()` is the single public stop primitive — it clears
|
||||
### What is NOT here
|
||||
|
||||
Everything that goes beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy:
|
||||
- Hooks: `agent/request`, `agent/step-result`, `tools/execute`, `agent/turn-continuation`
|
||||
- Compaction: `agent/request`
|
||||
- Hooks: `agent/pre-step`, `agent/request`, `agent/step-result`, `tools/execute`, `agent/turn-continuation`
|
||||
- Compaction: `agent/pre-step`
|
||||
- Sandbox, permission, plan mode: `tools/execute`
|
||||
- Sub-agents: TODO seam on `AgentLoop.create()`
|
||||
- Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while child streaming/progress and background/poll collection remain deferred.
|
||||
- Persistence: `session/event` + `session/flush`
|
||||
- UI: `agent/stream-chunk` + `agent/*` events
|
||||
|
||||
@@ -12,6 +12,7 @@ import type { FinishReason, GenerateOptions, Message } from '@deepseek-ai/dsh-ll
|
||||
import { BlockAssembler, HarnessError } from '@deepseek-ai/dsh-llm'
|
||||
import type { Session, TurnEndReason, TurnTrigger } from '@deepseek-ai/dsh-session'
|
||||
import { renderPrompt } from '@deepseek-ai/dsh-system-prompt'
|
||||
import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt'
|
||||
import type {} from '@deepseek-ai/dsh-tools'
|
||||
import type { ReactLoopAgent } from './agent.ts'
|
||||
|
||||
@@ -147,10 +148,11 @@ export interface LoopHandle {
|
||||
* drain queued → 'turn/start' → session('user/message'…) → emit agent/turn-start
|
||||
* STEP loop:
|
||||
* drain steering → session('steering/message') ⟵ catches late steering
|
||||
* session('step/start'); emit agent/step-start ⟵ append before emit (the event-sourcing RFC)
|
||||
* assembly = ctx.systemPrompt.assemble() ⟵ waterfall system-prompt/assemble
|
||||
* await ctx.serial('agent/pre-step') ⟵ surface mutation (compaction) OUTSIDE the step
|
||||
* session('step/start'); emit agent/step-start ⟵ append before emit (the event-sourcing RFC)
|
||||
* req = {model, system, tools, messages: session.deriveMessages(), signal}
|
||||
* req = waterfall agent/request ⟵ hooks/compaction/model-switch
|
||||
* req = waterfall agent/request ⟵ hooks/model-switch
|
||||
* stream ctx.llm.stream(req) ⟵ waterfall llm/stream (raw chunks)
|
||||
* session('assistant/chunk'); emit agent/stream-chunk
|
||||
* msg = waterfall agent/step-result ⟵ BEFORE the log append, so the
|
||||
@@ -386,30 +388,78 @@ async function runTurn(ctx: Context, agent: ReactLoopAgent, handle: LoopHandle,
|
||||
// (or turn-start listeners on the first step) joins before the request.
|
||||
drainSteering(ctx, agent, turn)
|
||||
|
||||
// The step's AbortController exists BEFORE any async pre-step work so a
|
||||
// dispose() or cancel() — in a synchronous turn-start listener or an
|
||||
// async listener whose effect fires before we block — always has an armed
|
||||
// abort to cancel against. isDisposed below covers disposal, which does
|
||||
// NOT set the cancel marker. Cleared on every exit path below.
|
||||
const abort = new AbortController()
|
||||
handle.setAbort(abort)
|
||||
|
||||
// Assemble the system prompt for this step. Done HERE (before step/start)
|
||||
// because the pre-step seam needs it: compaction measures token pressure
|
||||
// against the system prompt (it counts toward the budget). runStep reuses
|
||||
// this same assembly for the request, so the prompt is assembled once per
|
||||
// step.
|
||||
const assembly = await ctx.systemPrompt.assemble()
|
||||
const fullSystemPrompt = [renderPrompt(assembly), agent.options.systemPrompt ?? '']
|
||||
.filter(text => text.length > 0)
|
||||
.join('\n\n')
|
||||
|
||||
// Interruption landing after assembly: dispose() or cancel() in a
|
||||
// turn-start listener (or a listener whose promise resolved before the
|
||||
// await above) arms either handle.isDisposed() or handle.isCancelled().
|
||||
// The Abort was created first, so any concurrent abort also lands on it.
|
||||
// Drop the about-to-start step WITHOUT running the seam — no step is open
|
||||
// yet, so end the turn accordingly (disposed wins for an unambiguous
|
||||
// reason).
|
||||
if (handle.isCancelled() || handle.isDisposed()) {
|
||||
handle.setAbort(undefined)
|
||||
reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() }
|
||||
break
|
||||
}
|
||||
|
||||
// Pre-step surface-mutation checkpoint (compaction), fired OUTSIDE the
|
||||
// step: after `turn/start` (and the prior step's close) but before
|
||||
// `step/start`, so a compaction's log-only `compact/*` records and its
|
||||
// replacement node land cleanly outside any step (honest structure that
|
||||
// crash-safety relies on — a dangling `compact/start` sits before the
|
||||
// synthetic `turn/end` repair appends). Serial (awaited, in order, no
|
||||
// veto): each listener completes its surface mutation before the next, so
|
||||
// concurrent listeners cannot interleave their `session.append`s. A
|
||||
// throwing listener escapes to the outer catch, which closes the (not-yet-
|
||||
// open) step as a no-op and ends the turn via failTurn — a broken
|
||||
// pre-step plugin ends the turn, not the loop.
|
||||
await ctx.serial('agent/pre-step', agent, turn, step, fullSystemPrompt, abort.signal)
|
||||
|
||||
// Interruption landing during the pre-step seam: do not open an empty
|
||||
// step. `agent/step-start` listeners get their own check below because
|
||||
// they necessarily run after step/start is appended/emitted.
|
||||
if (handle.isCancelled() || handle.isDisposed()) {
|
||||
handle.setAbort(undefined)
|
||||
reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() }
|
||||
break
|
||||
}
|
||||
|
||||
session.append('step/start', { turn, step })
|
||||
stepOpen = true
|
||||
ctx.emit('agent/step-start', agent, turn, step)
|
||||
|
||||
const abort = new AbortController()
|
||||
handle.setAbort(abort)
|
||||
|
||||
// Cancel landing in the step-start window: a synchronous `agent/turn-start`
|
||||
// or `agent/step-start` listener (both fire before this point) can have
|
||||
// called `cancel()`, and `runStep` would otherwise run a full extra step
|
||||
// with no AbortController having observed it. Check the marker AFTER
|
||||
// setAbort (so the next-iteration drain sees a clean controller) and before
|
||||
// `runStep`: drop the step, end the turn `aborted`. closeStep balances the
|
||||
// already-appended step/start.
|
||||
if (handle.isCancelled()) {
|
||||
// Cancel landing in the step-start window: a synchronous
|
||||
// `agent/step-start` listener can cancel after the step is already open.
|
||||
// Check AFTER step/start append + emit and before `runStep`: drop the
|
||||
// step, end the turn accordingly. closeStep balances the already-appended
|
||||
// step/start.
|
||||
if (handle.isCancelled() || handle.isDisposed()) {
|
||||
handle.setAbort(undefined)
|
||||
reason = { kind: 'aborted', reason: handle.cancelReason() }
|
||||
reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() }
|
||||
closeStep()
|
||||
break
|
||||
}
|
||||
|
||||
let stepOutcome: { hadToolCalls: boolean; finish: FinishReason } | { error: Error }
|
||||
try {
|
||||
stepOutcome = await runStep(ctx, agent, turn, step, abort.signal)
|
||||
stepOutcome = await runStep(ctx, agent, turn, step, assembly, fullSystemPrompt, abort.signal)
|
||||
} catch (error: unknown) {
|
||||
stepOutcome = { error: toError(error) }
|
||||
} finally {
|
||||
@@ -549,22 +599,22 @@ function drainSteering(ctx: Context, agent: ReactLoopAgent, turn: number): boole
|
||||
return messages.length > 0
|
||||
}
|
||||
|
||||
/** One step: assemble request → stream model → record → execute tools. */
|
||||
/** One step: derive request from the (already pre-step-mutated) surface →
|
||||
* stream model → record → execute tools. The caller assembles the system prompt
|
||||
* and fires the `agent/pre-step` seam BEFORE opening the step, then passes the
|
||||
* resulting `assembly`/`system` here, so the surface this step derives from
|
||||
* already reflects any compaction. */
|
||||
async function runStep(
|
||||
ctx: Context,
|
||||
agent: ReactLoopAgent,
|
||||
turn: number,
|
||||
step: number,
|
||||
assembly: PromptAssembly,
|
||||
system: string,
|
||||
signal: AbortSignal,
|
||||
): Promise<{ hadToolCalls: boolean; finish: FinishReason }> {
|
||||
const { session, options } = agent
|
||||
|
||||
// --- Request assembly ---
|
||||
const assembly = await ctx.systemPrompt.assemble()
|
||||
const system = [renderPrompt(assembly), options.systemPrompt ?? '']
|
||||
.filter(text => text.length > 0)
|
||||
.join('\n\n')
|
||||
|
||||
let request: GenerateOptions = {
|
||||
model: options.model ?? '',
|
||||
messages: session.deriveMessages(),
|
||||
|
||||
@@ -13,7 +13,7 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import LlmService from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore, { TurnEndReason } from '@deepseek-ai/dsh-session'
|
||||
import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
|
||||
@@ -194,6 +194,73 @@ describe('Agent.cancel()', () => {
|
||||
expect(reasons).toEqual([{ kind: 'aborted', reason: 'from turn-start' }])
|
||||
})
|
||||
|
||||
it('cancel from a synchronous agent/step-start listener drops the step (post-step-start window)', async () => {
|
||||
const adapter = new MockAdapter([textResponse('should not stream')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
||||
|
||||
// A step-start listener fires AFTER step/start is appended (and after the
|
||||
// pre-step seam), so cancelling there lands in the SECOND cancel check (the
|
||||
// one that must closeStep() to balance the already-open step) — distinct
|
||||
// from a turn-start cancel, which is caught before the step opens.
|
||||
let streamed = false
|
||||
ctx.on('agent/stream-chunk', () => { streamed = true })
|
||||
const dispose = ctx.on('agent/step-start', (subject) => {
|
||||
if (subject === agent) agent.cancel('from step-start')
|
||||
})
|
||||
|
||||
const reasons: TurnEndReason[] = []
|
||||
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
|
||||
|
||||
send(agent, 'go')
|
||||
await waitForIdle(ctx, agent)
|
||||
dispose()
|
||||
|
||||
// No step streamed, the turn ended aborted with the caller's reason, and the
|
||||
// log is balanced (the open step was closed by the cancel branch).
|
||||
expect(streamed).toBe(false)
|
||||
expect(reasons).toEqual([{ kind: 'aborted', reason: 'from step-start' }])
|
||||
const types = agent.session.events.map(e => e.type)
|
||||
expect(types.filter(t => t === 'step/start').length).toBe(types.filter(t => t === 'step/end').length)
|
||||
})
|
||||
|
||||
it('disposal from a synchronous agent/step-start listener closes the open step as disposed', async () => {
|
||||
const adapter = new MockAdapter([textResponse('should not stream')])
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
|
||||
const handle = ctx.agents.create({
|
||||
agentId: AgentId('a-dispose-step-start'),
|
||||
sessionId: SessionId('dispose-step-start-session'),
|
||||
agentOptions: { model: 'mock' },
|
||||
})
|
||||
const agent = handle.agent as ReactLoopAgent
|
||||
|
||||
let disposalDone: Promise<void> | undefined
|
||||
let streamed = false
|
||||
ctx.on('agent/stream-chunk', () => { streamed = true })
|
||||
ctx.on('agent/step-start', (subject) => {
|
||||
if (subject === agent) disposalDone = handle.dispose()
|
||||
})
|
||||
|
||||
send(agent, 'go')
|
||||
await disposalDone
|
||||
await agent.done
|
||||
|
||||
expect(streamed).toBe(false)
|
||||
expect(adapter.requests).toHaveLength(0)
|
||||
const turnEnd = agent.session.events.findLast(e => e.type === 'turn/end')
|
||||
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'disposed' })
|
||||
const types = agent.session.events.map(e => e.type)
|
||||
expect(types.filter(t => t === 'step/start').length).toBe(types.filter(t => t === 'step/end').length)
|
||||
})
|
||||
|
||||
it('cancel during the continuation window ends the turn aborted and runs no further step', async () => {
|
||||
// A continuation-waterfall listener cancels DURING the continuation decision
|
||||
// (the finished step's AbortController is already cleared), and votes to
|
||||
|
||||
@@ -320,6 +320,110 @@ describe('agent loop', () => {
|
||||
expect(adapter.requests[0]!.model).toBe('other-model')
|
||||
})
|
||||
|
||||
it('agent/pre-step fires once per step before the step is opened', async () => {
|
||||
// Two steps (a tool call, then a final text turn) → two model calls → two
|
||||
// pre-step fires, each carrying the assembled full system prompt, BEFORE
|
||||
// the step is opened and its request is derived (the request the adapter
|
||||
// sees reflects any surface state at fire time).
|
||||
const adapter = new MockAdapter([
|
||||
toolCallResponse('c1', 'echo', {}, 'calling echo'),
|
||||
textResponse('done'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'echo', description: 'echo', parameters: {},
|
||||
async execute() { return [{ type: 'text', text: 'echoed' }] },
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
||||
|
||||
const fires: { turn: number; step: number; fullSystemPrompt: string }[] = []
|
||||
ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => {
|
||||
if (subject === agent) fires.push({ turn, step, fullSystemPrompt })
|
||||
})
|
||||
|
||||
send(agent, 'go')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
// One fire per step, in order, each with the assembled system prompt.
|
||||
expect(fires).toEqual([
|
||||
{ turn: 1, step: 1, fullSystemPrompt: '' },
|
||||
{ turn: 1, step: 2, fullSystemPrompt: '' },
|
||||
])
|
||||
})
|
||||
|
||||
it('agent/pre-step fires BEFORE the step it precedes opens (events land outside the step)', async () => {
|
||||
// A listener appending a surface node in pre-step lands it BEFORE step/start
|
||||
// in the log — proving the seam fires outside the step. The node is still in
|
||||
// the derived request for that step (derive happens after step/start).
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
||||
|
||||
let injected = false
|
||||
ctx.on('agent/pre-step', (subject) => {
|
||||
if (subject === agent && !injected) {
|
||||
injected = true
|
||||
subject.session.append('context/message', {
|
||||
content: [{ type: 'text', text: 'INJECTED-IN-PRE-STEP' }],
|
||||
source: { kind: 'plugin', plugin: 'test' },
|
||||
}, { surfaceOp: 'append' })
|
||||
}
|
||||
})
|
||||
|
||||
send(agent, 'go')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
// The adapter's request includes the node injected during pre-step (derive
|
||||
// reflects it).
|
||||
const text = JSON.stringify(adapter.requests[0]!.messages)
|
||||
expect(text).toContain('INJECTED-IN-PRE-STEP')
|
||||
|
||||
// And the injected event sits BEFORE the first step/start in the log —
|
||||
// the seam fired outside the step.
|
||||
const events = agent.session.events
|
||||
const injectedSeq = events.find(e => e.type === 'context/message')!.seq
|
||||
const firstStepStartSeq = events.find(e => e.type === 'step/start')!.seq
|
||||
expect(injectedSeq).toBeLessThan(firstStepStartSeq)
|
||||
})
|
||||
|
||||
it('a throwing agent/pre-step listener ends the turn (error), not the loop', async () => {
|
||||
// The seam fires before step/start, so a throw escapes to runTurn's outer
|
||||
// catch: the not-yet-open step closes as a no-op, the failure surfaces via
|
||||
// agent/error, and the turn ends `error` (recorded on the durable turn/end).
|
||||
// The loop survives and a follow-up prompt still runs.
|
||||
const adapter = new MockAdapter([textResponse('second turn ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
||||
|
||||
let throwOnce = true
|
||||
ctx.on('agent/pre-step', () => {
|
||||
if (throwOnce) { throwOnce = false; throw new Error('boom in pre-step') }
|
||||
})
|
||||
|
||||
const errors: Error[] = []
|
||||
ctx.on('agent/error', (_a, _t, _s, error) => void errors.push(error))
|
||||
|
||||
send(agent, 'first')
|
||||
await waitForIdle(ctx, agent)
|
||||
// The first turn failed at step 1 (no model call happened), surfaced via
|
||||
// agent/error, with the durable failure on turn/end.reason.
|
||||
expect(errors).toHaveLength(1)
|
||||
expect(errors[0]!.message).toContain('boom in pre-step')
|
||||
expect(adapter.requests.length).toBe(0)
|
||||
const firstTurnEnd = agent.session.events.find(e => e.type === 'turn/end')
|
||||
expect(firstTurnEnd?.type === 'turn/end' && firstTurnEnd.data.reason).toMatchObject({ kind: 'error', step: 1 })
|
||||
// The step opened-and-closed count stays balanced even though it never ran.
|
||||
const types = agent.session.events.map(e => e.type)
|
||||
expect(types.filter(t => t === 'step/start').length).toBe(types.filter(t => t === 'step/end').length)
|
||||
|
||||
// The loop survived: a second prompt runs a normal completed turn.
|
||||
send(agent, 'second')
|
||||
await waitForIdle(ctx, agent)
|
||||
expect(adapter.requests.length).toBe(1)
|
||||
const lastTurnEnd = agent.session.events.findLast(e => e.type === 'turn/end')
|
||||
expect(lastTurnEnd?.type === 'turn/end' && lastTurnEnd.data.reason).toEqual({ kind: 'completed' })
|
||||
})
|
||||
|
||||
it('cancel() mid-stream ends the turn with reason aborted', async () => {
|
||||
const adapter = new MockAdapter(['hang'])
|
||||
const ctx = await harness(adapter)
|
||||
|
||||
@@ -1047,3 +1047,275 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream
|
||||
expect(JSON.stringify(agent.session.deriveMessages())).toContain('injected')
|
||||
})
|
||||
})
|
||||
|
||||
|
||||
|
||||
describe('disposal/cancel honored during pre-step assembly (P1-1)', () => {
|
||||
it('disposal during system-prompt assembly drops the about-to-start step as disposed', { timeout: 30000 }, async () => {
|
||||
// Block `system-prompt/assemble` on a promise. Start disposal (which
|
||||
// calls stop() synchronously, setting status=disposed), then release the
|
||||
// block. The loop must check isDisposed() after assembly and end the turn
|
||||
// `disposed` — no LLM call. Don't await fiber.dispose() before releasing
|
||||
// the blocker: the dispose chain awaits agent.done, which hangs until the
|
||||
// loop unblocks.
|
||||
const adapter = new MockAdapter(['hang'])
|
||||
let releaseAssemble!: () => void
|
||||
const blocked = new Promise<void>(r => void (releaseAssemble = r))
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(Invariants, { freeze: false })
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
|
||||
// Blocking listener on the parent context (survives fiber disposal).
|
||||
const unlisten = ctx.on('system-prompt/assemble', async function (_assembly, next) {
|
||||
await blocked
|
||||
return next()
|
||||
})
|
||||
|
||||
let agent!: ReactLoopAgent
|
||||
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
|
||||
agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { model: 'mock' })
|
||||
}, { inject: ['agentLoop'] }))
|
||||
|
||||
const reasons: TurnEndReason[] = []
|
||||
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
|
||||
|
||||
send(agent, 'go')
|
||||
// Give the loop time to enter the step and reach assemble().
|
||||
await new Promise(r => setTimeout(r, 50))
|
||||
|
||||
// Start disposal — stop() sets status=disposed synchronously, then the
|
||||
// disposer's await agent.done hangs because the loop is blocked in the
|
||||
// waterfall. Do NOT await yet; release the blocker first.
|
||||
const disposalDone = fiber.dispose()
|
||||
|
||||
// Now release the blocked waterfall — the loop unblocks, checks
|
||||
// isDisposed(), and exits, which resolves agent.done and disposalDone.
|
||||
releaseAssemble()
|
||||
await disposalDone
|
||||
await agent.done
|
||||
unlisten()
|
||||
|
||||
const e = [...agent.session.events]
|
||||
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
|
||||
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
|
||||
const turnEnd = e.findLast(x => x.type === 'turn/end')
|
||||
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'disposed' })
|
||||
// No step was opened, no LLM call was made.
|
||||
expect(e.some(x => x.type === 'step/start')).toBe(false)
|
||||
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
|
||||
// agent/turn-end may not fire when disposal happens during assembly: the
|
||||
// fiber's disposer (stop→status=disposed) runs before closeTurn(true)'s
|
||||
// emit, and the LIFO chain disposes effects in reverse registration order.
|
||||
// The turn/end durable record is the one that matters.
|
||||
})
|
||||
|
||||
it('cancel during system-prompt assembly drops the about-to-start step as aborted', { timeout: 30000 }, async () => {
|
||||
const adapter = new MockAdapter([textResponse('should not appear')])
|
||||
let releaseAssemble!: () => void
|
||||
const blocker = new Promise<void>(r => void (releaseAssemble = r))
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(Invariants, { freeze: false })
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
|
||||
const unlisten = ctx.on('system-prompt/assemble', async function (_assembly, next) {
|
||||
await blocker
|
||||
return next()
|
||||
})
|
||||
|
||||
let agent!: ReactLoopAgent
|
||||
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
|
||||
agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { model: 'mock' })
|
||||
}, { inject: ['agentLoop'] }))
|
||||
|
||||
const reasons: TurnEndReason[] = []
|
||||
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
|
||||
|
||||
send(agent, 'go')
|
||||
await new Promise(r => setTimeout(r, 50))
|
||||
agent.cancel('user cancelled during assembly')
|
||||
|
||||
releaseAssemble()
|
||||
await waitForIdle(ctx, agent)
|
||||
await fiber.dispose()
|
||||
await agent.done
|
||||
unlisten()
|
||||
|
||||
const e = [...agent.session.events]
|
||||
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
|
||||
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
|
||||
const turnEnd = e.findLast(x => x.type === 'turn/end')
|
||||
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({
|
||||
kind: 'aborted',
|
||||
reason: 'user cancelled during assembly',
|
||||
})
|
||||
expect(e.some(x => x.type === 'step/start')).toBe(false)
|
||||
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
|
||||
expect(e.some(x => x.type === 'assistant/message')).toBe(false)
|
||||
expect(adapter.requests).toHaveLength(0)
|
||||
expect(reasons).toEqual([{ kind: 'aborted', reason: 'user cancelled during assembly' }])
|
||||
})
|
||||
|
||||
it('disposal during agent/pre-step seam ends the turn disposed', { timeout: 15000 }, async () => {
|
||||
// Block the `agent/pre-step` serial seam on a promise we control, then
|
||||
// dispose the agent's fiber. When the block releases, the loop must see
|
||||
// isDisposed() at the post-seam check and end the turn disposed.
|
||||
const adapter = new MockAdapter(['hang'])
|
||||
let releasePreStep!: () => void
|
||||
const blocker = new Promise<void>(r => void (releasePreStep = r))
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(Invariants, { freeze: false })
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
|
||||
ctx.on('agent/pre-step', async () => {
|
||||
await blocker
|
||||
})
|
||||
|
||||
let agent!: ReactLoopAgent
|
||||
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
|
||||
agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { model: 'mock' })
|
||||
}, { inject: ['agentLoop'] }))
|
||||
|
||||
const reasons: TurnEndReason[] = []
|
||||
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
|
||||
|
||||
send(agent, 'go')
|
||||
await new Promise(r => setTimeout(r, 50))
|
||||
|
||||
// Start disposal, then release the block, then await disposal.
|
||||
const disposalDone = fiber.dispose()
|
||||
releasePreStep()
|
||||
await disposalDone
|
||||
await agent.done
|
||||
|
||||
// After the pre-step seam finishes, the post-seam cancel/dispose check
|
||||
// catches disposal. The step was never opened, no LLM call was made.
|
||||
const e = [...agent.session.events]
|
||||
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
|
||||
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
|
||||
const turnEnd = e.findLast(x => x.type === 'turn/end')
|
||||
// Disposal wins the post-seam check — reason is `disposed`.
|
||||
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'disposed' })
|
||||
expect(e.some(x => x.type === 'step/start')).toBe(false)
|
||||
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
|
||||
// agent/turn-end may not fire when disposal happens during pre-step: the
|
||||
// fiber's disposer runs before closeTurn(true)'s emit. The durable turn/end
|
||||
// is the authoritative record.
|
||||
})
|
||||
|
||||
it('cancel during agent/pre-step seam ends the turn aborted', { timeout: 15000 }, async () => {
|
||||
// Block `agent/pre-step`, then cancel() the agent. When the block releases,
|
||||
// the post-seam check catches cancellation and ends the turn aborted.
|
||||
const adapter = new MockAdapter(['hang'])
|
||||
let releasePreStep!: () => void
|
||||
const blocker = new Promise<void>(r => void (releasePreStep = r))
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(Invariants, { freeze: false })
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
|
||||
ctx.on('agent/pre-step', async () => {
|
||||
await blocker
|
||||
})
|
||||
|
||||
let agent!: ReactLoopAgent
|
||||
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
|
||||
agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { model: 'mock' })
|
||||
}, { inject: ['agentLoop'] }))
|
||||
|
||||
const reasons: TurnEndReason[] = []
|
||||
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
|
||||
|
||||
send(agent, 'go')
|
||||
await new Promise(r => setTimeout(r, 30))
|
||||
agent.cancel('user cancelled')
|
||||
|
||||
releasePreStep()
|
||||
await waitForIdle(ctx, agent)
|
||||
await fiber.dispose()
|
||||
await agent.done
|
||||
|
||||
const e = [...agent.session.events]
|
||||
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
|
||||
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
|
||||
const turnEnd = e.findLast(x => x.type === 'turn/end')
|
||||
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted', reason: 'user cancelled' })
|
||||
expect(e.some(x => x.type === 'step/start')).toBe(false)
|
||||
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
|
||||
expect(reasons).toEqual([{ kind: 'aborted', reason: 'user cancelled' }])
|
||||
})
|
||||
|
||||
it('disposal during assembly does not leak an LLM call or append assistant/chunk', { timeout: 15000 }, async () => {
|
||||
// The key assertion from the original bug report: after disposal, no
|
||||
// assistant/chunk or assistant/message appears — the turn ends disposed
|
||||
// before any model interaction.
|
||||
const adapter = new MockAdapter([textResponse('should not appear')])
|
||||
let releaseAssemble!: () => void
|
||||
const blocker = new Promise<void>(r => void (releaseAssemble = r))
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(Invariants, { freeze: false })
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
|
||||
ctx.on('system-prompt/assemble', async function (_assembly, next) {
|
||||
await blocker
|
||||
return next()
|
||||
})
|
||||
|
||||
let agent!: ReactLoopAgent
|
||||
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
|
||||
agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { model: 'mock' })
|
||||
}, { inject: ['agentLoop'] }))
|
||||
|
||||
send(agent, 'go')
|
||||
await new Promise(r => setTimeout(r, 50))
|
||||
|
||||
const disposalDone = fiber.dispose()
|
||||
releaseAssemble()
|
||||
await disposalDone
|
||||
await agent.done
|
||||
|
||||
const e = [...agent.session.events]
|
||||
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
|
||||
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
|
||||
// The critical assertions: after disposal, the turn has no assistant
|
||||
// artifacts — the turn ended disposed before the model was invoked.
|
||||
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
|
||||
expect(e.some(x => x.type === 'assistant/message')).toBe(false)
|
||||
expect(adapter.requests).toHaveLength(0)
|
||||
// The durable turn/end reason is the authoritative record; agent/turn-end
|
||||
// may not fire when disposal interleaves with closeTurn(true)'s emit.
|
||||
})
|
||||
})
|
||||
|
||||
@@ -17,10 +17,10 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i
|
||||
Agent *creation* is provided by whichever plugin implements `AgentFactory` (phase 1: `dsh-agent-loop`), registered via `setFactory`. This keeps creation on the `dsh-agent` interface so consumers (UI, the ACP bridge) program against `ctx.agents` without depending on the concrete loop package.
|
||||
|
||||
- `ctx.agents.setFactory(factory: AgentFactory): () => void` — register the creation factory (the loop calls this on construction). Throws on a second factory; the slot clears on dispose.
|
||||
- `ctx.agents.create(options: CreateAgentOptions): AgentHandle` — construct, start, AND register a new agent on a caller-supplied `sessionId` (with optional `meta.cwd`). Distinct from `register` (which only records). Throws if no factory is registered.
|
||||
- `ctx.agents.create(options: CreateAgentOptions): AgentHandle` — construct, start, AND register a new agent on a caller-supplied `sessionId` (with optional `meta.cwd`/`meta.parentSession`/`meta.seedLength` and optional `seed` events for forked children). Distinct from `register` (which only records). Throws if no factory is registered.
|
||||
- `ctx.agents.resume(options: ResumeAgentOptions): Promise<AgentHandle>` — load a persisted session ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)) and resume an agent on it. Async; rejects if no factory is registered, or if the factory finds session persistence unconfigured.
|
||||
|
||||
`AgentHandle = { agent: Agent; dispose(): Promise<void> }`. The disposer is a **capability** — only the holder can tear this agent down. `dispose()` stops the loop, `await`s its exit (quiescence — NOT just the `disposed` status flip), unregisters the agent, and removes its session from the store, in an order that captures the loop's final `session/flush` before the session is detached. `ctx.agents.get(id)` still returns a bare `Agent` — the handle is only for the OWNER that created it. The ACP bridge is the production consumer (one handle per session, disposed on disconnect/teardown); config-created agents are owned by the loop fiber and never need a handle.
|
||||
`AgentHandle = { agent: Agent; dispose(): Promise<void> }`. The disposer is a **capability** — only the holder can tear this agent down. `dispose()` stops the loop, `await`s its exit (quiescence — NOT just the `disposed` status flip), unregisters the agent, and removes its session from the store, in an order that captures the loop's final `session/flush` before the session is detached. `ctx.agents.get(id)` still returns a bare `Agent` — the handle is only for the OWNER that created it. The ACP bridge and in-process subagent backends are production consumers; config-created agents are owned by the loop fiber and never need a handle.
|
||||
|
||||
### Events
|
||||
|
||||
@@ -37,11 +37,12 @@ The full `agent/*` event taxonomy is declared via declaration merging in `dsh-ag
|
||||
- `agent/turn-start`, `agent/turn-end` (carries `TurnEndReason`)
|
||||
- `agent/step-start`, `agent/step-end`
|
||||
|
||||
#### Interception seams (waterfall)
|
||||
#### Interception seams
|
||||
|
||||
- `agent/request` — mutate `GenerateOptions` before the model call (hooks, compaction, model switching, tool filtering)
|
||||
- `agent/step-result` — post-process the assembled assistant message before tool dispatch (validates what the log records)
|
||||
- `agent/turn-continuation` — override the continue/stop decision (force-continue /loop, force-stop budget guard)
|
||||
- `agent/pre-step` (serial) — mutate the session surface before the step opens and history is derived (compaction). Fires after `turn/start` and before `step/start`, so a listener's appended events land outside the step.
|
||||
- `agent/request` (waterfall) — mutate `GenerateOptions` before the model call (hooks, model switching, tool filtering)
|
||||
- `agent/step-result` (waterfall) — post-process the assembled assistant message before tool dispatch (validates what the log records)
|
||||
- `agent/turn-continuation` (waterfall) — override the continue/stop decision (force-continue /loop, force-stop budget guard)
|
||||
|
||||
#### Streaming + tool (emit)
|
||||
|
||||
@@ -62,9 +63,10 @@ The handle every plugin programs against:
|
||||
|
||||
### Extension points
|
||||
|
||||
- Agent creation: `AgentLoop.create()` is the concrete implementation (in `dsh-agent-loop`). Replace the loop by implementing `Agent` and registering via `ctx.agents.register()`.
|
||||
- Agent creation: `AgentLoop.create()` is the concrete config-path implementation (in `dsh-agent-loop`), while programmatic consumers create/resume owned agents through `ctx.agents.create()` / `ctx.agents.resume()`. Replace the loop by implementing `Agent` and registering via `ctx.agents.register()`.
|
||||
- Event listeners: all `agent/*` events are declared here — no dependency on the loop package needed.
|
||||
- Subagent delegation: implemented by `@deepseek-ai/dsh-subagent`, not by a method on `Agent`; providers create or drive ordinary `Agent` handles through the factory seam, so spawn/fork/ACP transports stay outside the core agent interface.
|
||||
|
||||
### What is NOT here (TODO)
|
||||
|
||||
- **Sub-agent spawn/fork** — seam on `AgentLoop.create()`, semantics deferred.
|
||||
- **Inter-agent channels beyond delegation** — shared state, streaming child output, and background/poll semantics remain outside the current synchronous `ctx.subagents` seam.
|
||||
|
||||
@@ -179,11 +179,45 @@ declare module 'cordis' {
|
||||
*/
|
||||
'agent/step-end'(agent: Agent, turn: number, step: number): void
|
||||
|
||||
// ---- interception seams (waterfall) ----
|
||||
// ---- step/request extension seams (serial + waterfall) ----
|
||||
/**
|
||||
* Awaited pre-step surface-mutation checkpoint, fired once per step AFTER
|
||||
* `turn/start` (and after the prior step closed) but BEFORE this step's
|
||||
* `step/start` — so anything a listener appends lands OUTSIDE the step,
|
||||
* between `turn/start`/`step/end` and the upcoming `step/start`. `step` is
|
||||
* the number of the step about to start. The loop awaits
|
||||
* `ctx.serial('agent/pre-step', …)` after assembling the system prompt, then
|
||||
* opens the step and derives the request history ONCE from whatever the
|
||||
* surface now holds. This is where compaction belongs: it mutates the session
|
||||
* surface in place (shadowing an older range with a summary node) with its
|
||||
* log-only `compact/*` records cleanly outside any step, and the single
|
||||
* subsequent derive reflects the mutation — so there is no double-derive and
|
||||
* no listener can see (or be expected to act on) an assembled `messages`
|
||||
* array that does not exist yet.
|
||||
*
|
||||
* Serial (awaited in registration order), not a waterfall: a listener
|
||||
* mutates the surface as a side effect; there is nothing to transform, but
|
||||
* the loop must wait for the mutation to complete before opening the step
|
||||
* and deriving. Cordis `serial` bails early if a listener returns a bail
|
||||
* value; this event is typed and documented as `void`, so listeners must not
|
||||
* return a semantic veto value. `fullSystemPrompt` is the assembled prompt a
|
||||
* listener needs to measure pressure (the system prompt counts toward the
|
||||
* budget). `signal` cancels any in-flight work a listener starts (e.g. a
|
||||
* summarization model call).
|
||||
* @mode serial
|
||||
*/
|
||||
// TODO: `fullSystemPrompt` is a smell on a generic per-step seam — compaction
|
||||
// is its only consumer, so a wide event carries a string just one listener
|
||||
// reads. Revisit if no second consumer appears: e.g. hand listeners a lazy
|
||||
// prompt provider, or move token-pressure measurement behind a
|
||||
// compaction-specific seam instead of the shared pre-step checkpoint.
|
||||
'agent/pre-step'(agent: Agent, turn: number, step: number, fullSystemPrompt: string, signal: AbortSignal): Promise<void> | void
|
||||
/**
|
||||
* Waterfall: mutate the fully-assembled {@link GenerateOptions} before the
|
||||
* model call (hooks, compaction, model switching, tool filtering, …). Call
|
||||
* `next()` to delegate, or return without it to short-circuit.
|
||||
* model call (hooks, model switching, tool filtering, …). Call `next()` to
|
||||
* delegate, or return without it to short-circuit. For surface mutation that
|
||||
* must precede history derivation (compaction), use {@link agent/pre-step}
|
||||
* instead — by the time this fires, `options.messages` is already derived.
|
||||
* @mode waterfall
|
||||
*/
|
||||
'agent/request'(agent: Agent, turn: number, step: number, options: GenerateOptions, next: () => Promise<GenerateOptions>): Promise<GenerateOptions>
|
||||
|
||||
@@ -8,7 +8,7 @@ Creates and holds event-sourced `Session` instances. Persistence is intentionall
|
||||
|
||||
### Public API
|
||||
|
||||
- `ctx.sessions.create(id?: SessionId, options?: { seed?: SessionEvent[]; meta?: { cwd?: string; parentSession?: SessionId; createdAt?: number } }): Session` — Create a session. `options.seed` replays/forks an existing event log; `options.meta` attaches creation metadata (validated absolute `cwd`, `parentSession` lineage) as the immutable `SessionHeader`. The store fills `version`/`id` and defaults `createdAt` to now; a caller reconstructing a persisted session passes the original `createdAt` to preserve it. Disposed with the calling fiber.
|
||||
- `ctx.sessions.create(id?: SessionId, options?: { seed?: SessionEvent[]; meta?: { cwd?: string; parentSession?: SessionId; createdAt?: number; seedLength?: number } }): Session` — Create a session. `options.seed` replays/forks an existing event log; `options.meta` attaches creation metadata (validated absolute `cwd`, `parentSession` lineage, seed boundary) as the immutable `SessionHeader`. The store fills `version`/`id` and defaults `createdAt` to now; a caller reconstructing a persisted session passes the original `createdAt` and persisted `seedLength` to preserve them. Disposed with the calling fiber.
|
||||
- `ctx.sessions.get(id: SessionId): Session | undefined`
|
||||
- `ctx.sessions.list(): Session[]`
|
||||
|
||||
@@ -38,7 +38,7 @@ Plain class (not a Cordis Service). Create via `ctx.sessions.create()`.
|
||||
- `session.deriveMessages(): Message[]` — derive the LLM message history by walking the surface linked list (skipping non-surface events like chunks and boundaries; a `replace` shadows the nodes it covers). The surface is the single source of derived history — there is no raw-log fallback.
|
||||
- `session.surface: SurfaceManager` — the derived surface, lazily rebuilt from `surfaceOp` markers in the log. Processes only new events (delta) on each access — the log is append-only, so prior events never change.
|
||||
- `session.events`, `session.seq`, `session.id`
|
||||
- `session.header: SessionHeader` — immutable creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`). Kept out of the event log (a storage concern, not replayable state); a minimal header (stamped with the current `SESSION_FORMAT_VERSION`) is synthesized for bare `Session` construction.
|
||||
- `session.header: SessionHeader` — immutable creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`). Kept out of the event log (a storage concern, not replayable state); a minimal header (stamped with the current `SESSION_FORMAT_VERSION`) is synthesized for bare `Session` construction.
|
||||
|
||||
### Surface types
|
||||
|
||||
@@ -49,26 +49,26 @@ Plain class (not a Cordis Service). Create via `ctx.sessions.create()`.
|
||||
|
||||
### Session event vocabulary (`types.ts`)
|
||||
|
||||
The append-only log: `turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `assistant/message`, `assistant/chunk`, `tool/call`, `tool/result`, `steering/message`, `context/message`. Token usage rides on `assistant/message.usage`; an operational error's step is on `turn/end.reason` for `kind: 'error'`.
|
||||
The append-only log: `turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `assistant/message`, `assistant/chunk`, `tool/call`, `tool/result`, `steering/message`, `context/message`, `todo/write`. Token usage rides on `assistant/message.usage`; an operational error's step is on `turn/end.reason` for `kind: 'error'`.
|
||||
|
||||
Merge-extensible via `SessionEventMap` — a compaction plugin adds `compaction/marker`, etc.
|
||||
Merge-extensible via `SessionEventMap` — the compaction seam adds `compact/start`, `compact/summary`, and `compact/end`.
|
||||
|
||||
Also defines `TurnTriggerMap` and `TurnEndReasonMap` (merge-extensible sum types for typed turn boundaries — `kind`-tagged instead of strings).
|
||||
|
||||
Every `SessionEvent` carries two optional top-level fields (structural metadata):
|
||||
|
||||
- `sourceEventSeqs?: number[]` — seq numbers of provenance sources (e.g., the `assistant/chunk` seqs behind an `assistant/message`, or the shadowed nodes behind a compaction marker).
|
||||
- `sourceEventSeqs?: number[]` — seq numbers of provenance sources (e.g., the `assistant/chunk` seqs behind an `assistant/message`, or the shadowed nodes behind a compaction replace node).
|
||||
- `surfaceOp?: SurfaceOp` — how this event entered the surface. Absent for non-surface events (boundaries, chunks, usage, errors).
|
||||
|
||||
### Metadata types (`types.ts`)
|
||||
|
||||
- `SessionHeader` — immutable session metadata, written once: `{ version, id, createdAt, cwd?, parentSession? }`. Owned here (beside `SessionId`) because `Session.header` is typed by it; persistence backends re-export it rather than own it (which would force a package cycle).
|
||||
- `SessionHeader` — immutable session metadata, written once: `{ version, id, createdAt, cwd?, parentSession?, seedLength? }`. Owned here (beside `SessionId`) because `Session.header` is typed by it; persistence backends re-export it rather than own it (which would force a package cycle).
|
||||
|
||||
### Extension points
|
||||
|
||||
- Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`, `session.header`) is what such a backend stores beside the log.
|
||||
- Replay/fork: `ctx.sessions.create(id, { seed })` seeds a new session with an existing event log. The surface rebuilds deterministically from `surfaceOp` markers in the seeded events. The seed is validated to the SAME invariants `append` enforces — including that every surface-eligible event (`SurfaceEventType`) carries a `surfaceOp` marker — so a marker-less message event is rejected at construction rather than silently vanishing from `deriveMessages()` (the surface is the sole derivation path) on resume.
|
||||
- Compaction: a future plugin appends a new event with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes.
|
||||
- Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes behind a summary checkpoint.
|
||||
|
||||
### What is NOT here (TODO)
|
||||
|
||||
|
||||
@@ -19,6 +19,7 @@ export { isJsonValue } from './json.ts'
|
||||
export { interruptedTurnClosers } from './repair.ts'
|
||||
export type { SurfaceNode } from './surface.ts'
|
||||
export { isSurfaceEvent, isSurfaceEligibleType } from './surface.ts'
|
||||
export { isToolPairingBalanced } from './tool-pairing.ts'
|
||||
|
||||
declare module 'cordis' {
|
||||
interface Context {
|
||||
@@ -95,12 +96,12 @@ export class Session {
|
||||
}
|
||||
|
||||
/**
|
||||
* Immutable creation metadata (format version, cwd, lineage). Supplied by
|
||||
* the store via `ctx.sessions.create()`. When a `Session` is constructed
|
||||
* bare (tests, ad-hoc replay), a minimal header is synthesized (stamped with
|
||||
* the current {@link SESSION_FORMAT_VERSION}) so `session.header` is always
|
||||
* present. Kept out of the event log — it is a storage concern, not
|
||||
* replayable conversation state.
|
||||
* Immutable creation metadata (format version, cwd, lineage, seed boundary).
|
||||
* Supplied by the store via `ctx.sessions.create()`. When a `Session` is
|
||||
* constructed bare (tests, ad-hoc replay), a minimal header is synthesized
|
||||
* (stamped with the current {@link SESSION_FORMAT_VERSION}) so
|
||||
* `session.header` is always present. Kept out of the event log — it is a
|
||||
* storage concern, not replayable conversation state.
|
||||
*/
|
||||
readonly header: SessionHeader
|
||||
|
||||
|
||||
100
packages/core/session/src/tool-pairing.ts
Normal file
100
packages/core/session/src/tool-pairing.ts
Normal file
@@ -0,0 +1,100 @@
|
||||
/**
|
||||
* Tool-pairing balance over a session's SURFACE: is a given cut point in the
|
||||
* surface a safe edge for a collapsed region (e.g. compaction)?
|
||||
*
|
||||
* The invariant a consumer needs: a collapsed region must never separate an
|
||||
* `assistant/message`'s `tool-call` blocks from their answering `tool/result`s
|
||||
* — that would leave the rehydrated transcript with a dangling tool-call or an
|
||||
* orphaned tool-result, which every provider rejects. (This is the
|
||||
* compaction-time mirror of the crash-recovery imbalance that
|
||||
* {@link interruptedTurnClosers} repairs on load.) Steps were once used as a
|
||||
* proxy for this bracketing, but a compaction REWRITES the surface — it lands a
|
||||
* replacement node at a high log seq whose SURFACE position is the head — so a
|
||||
* scan over the LOG's `step/*` markers mis-reads such a node's neighbours. The
|
||||
* pairing the invariant actually protects lives in the surface nodes' own
|
||||
* content (a `tool-call` block's id, a `tool/result`'s `callId`), which travels
|
||||
* with the node through any reshaping, so alignment is decided over the surface
|
||||
* directly.
|
||||
*
|
||||
* A **cut** is a gap between two adjacent surface nodes (named by the node it
|
||||
* sits immediately before), or the after-tail gap (`null`). Walking the surface
|
||||
* head→tail and assigning each node a delta — `+1` per `tool-call` block on an
|
||||
* `assistant/message`, `-1` per `tool/result`, `0` otherwise — the depth at a
|
||||
* cut is the number of still-unanswered tool calls before it. A cut is
|
||||
* **balanced** when that depth is `0`. A region `[start..end]` is safe to
|
||||
* collapse iff BOTH its edges are balanced cuts: the cut before `start` and the
|
||||
* cut after `end`. Nodes that belong to no step (a pre-step `user/message`, an
|
||||
* inter-step `steering/message`, an injection `context/message`) carry no
|
||||
* pairing, contribute `0`, and so are free boundaries — exactly as before, but
|
||||
* now as a consequence of the balance rather than a special case. An open
|
||||
* trailing step (an assistant whose `tool/result`s have not landed yet) keeps
|
||||
* the depth positive through the tail, so no cut inside it is balanced — the
|
||||
* old explicit open-step check falls out of the same counter.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-session/tool-pairing
|
||||
*/
|
||||
|
||||
import type { SessionEvent } from './types.ts'
|
||||
import type { SurfaceNode } from './surface.ts'
|
||||
|
||||
/**
|
||||
* The tool-pairing delta of a surface node: how it shifts the count of
|
||||
* unanswered tool calls. An `assistant/message` opens one bracket per
|
||||
* `tool-call` block; a `tool/result` closes one; every other surface node
|
||||
* (`user/message`, `context/message`, `steering/message`, a usage-only
|
||||
* `assistant/message` with no tool-call blocks) is pairing-neutral.
|
||||
*/
|
||||
function nodeDelta(event: SessionEvent): number {
|
||||
switch (event.type) {
|
||||
case 'assistant/message':
|
||||
return event.data.content.filter(block => block.type === 'tool-call').length
|
||||
case 'tool/result':
|
||||
return -1
|
||||
// Non-pairing surface nodes and every non-surface event contribute nothing.
|
||||
default:
|
||||
return 0
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Whether the surface prefix ending at the given cut has BALANCED tool-call /
|
||||
* tool-result brackets — i.e. every `tool-call` block on the surface before the
|
||||
* cut has its answering `tool/result` before the cut too, so the cut is a safe
|
||||
* edge for a collapsed region (it cannot split an assistant↔result pair).
|
||||
*
|
||||
* `nodes` is the surface linked list in head→tail order (e.g.
|
||||
* `session.surface.nodes`); `events` is the session log, used to look each
|
||||
* node's event up by `seq`. `beforeSeq` names the cut by the surface node it
|
||||
* sits immediately before; the after-tail cut (the whole surface) is `null`,
|
||||
* as is any `beforeSeq` not present on the surface.
|
||||
*
|
||||
* A region `[start..end]` is collapsible iff both edges are balanced cuts: call
|
||||
* `isToolPairingBalanced(nodes, events, start)` for the cut before `start`, and
|
||||
* `isToolPairingBalanced(nodes, events, after)` — where `after` is `end`'s
|
||||
* surface successor (`SurfaceNode.next`), or `null` when `end` is the tail —
|
||||
* for the cut after `end`.
|
||||
*
|
||||
* @throws if the surface prefix drives the unanswered-call depth negative — a
|
||||
* `tool/result` with no preceding open `tool-call` on the surface. That is a
|
||||
* corrupt surface (a structural invariant violation), surfaced loudly here
|
||||
* rather than silently mis-classifying a boundary.
|
||||
*/
|
||||
export function isToolPairingBalanced(
|
||||
nodes: readonly SurfaceNode[],
|
||||
events: readonly SessionEvent[],
|
||||
beforeSeq: number | null,
|
||||
): boolean {
|
||||
let depth = 0
|
||||
for (const node of nodes) {
|
||||
if (node.seq === beforeSeq) return depth === 0
|
||||
// node.seq is a surface-node seq, always a valid log index by construction.
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
|
||||
depth += nodeDelta(events[node.seq]!)
|
||||
if (depth < 0) {
|
||||
throw new Error(`tool-pairing balance: tool/result at surface seq ${node.seq} has no matching tool-call (corrupt surface)`)
|
||||
}
|
||||
}
|
||||
// Reached the after-tail cut (beforeSeq === null, or a seq not on the
|
||||
// surface): the whole-surface prefix is balanced iff depth returned to 0.
|
||||
return depth === 0
|
||||
}
|
||||
@@ -149,6 +149,24 @@ export interface TurnEndReasonMap {
|
||||
|
||||
export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap]
|
||||
|
||||
/**
|
||||
* One entry in an agent's todo list — the unit of the `todo/write`
|
||||
* {@link SessionEventMap} event's whole-list snapshot.
|
||||
*
|
||||
* Deliberately minimal: a human-readable `content` line and a three-state
|
||||
* `status`. No id, priority, or `activeForm` — the list is replaced wholesale
|
||||
* on every write (last-write-wins), so entries need no stable identity, and the
|
||||
* status triple is exactly the ACP `PlanEntryStatus`, so a UI bridge can map a
|
||||
* todo list onto an ACP `plan` 1:1 (synthesizing the priority ACP additionally
|
||||
* requires).
|
||||
*/
|
||||
export interface TodoItem {
|
||||
/** What this task is — a short imperative line shown in the UI. */
|
||||
content: string
|
||||
/** Lifecycle state. `in_progress` marks the single task being worked now. */
|
||||
status: 'pending' | 'in_progress' | 'completed'
|
||||
}
|
||||
|
||||
/**
|
||||
* The session event vocabulary — the append-only source of truth for an
|
||||
* agent's whole interaction history. The LLM message history is *derived*
|
||||
@@ -156,7 +174,8 @@ export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap]
|
||||
* same events; trace/telemetry = subscribe to the log.
|
||||
*
|
||||
* Merge-extensible: plugins declare extra event types via declaration merging
|
||||
* (e.g. a compaction plugin adds `'compaction/marker'`).
|
||||
* (e.g. the compaction plugin adds `'compact/start'`, `'compact/summary'`,
|
||||
* `'compact/end'`).
|
||||
*
|
||||
* Durability contract (what a persistence backend relies on): the durable log
|
||||
* persists every event verbatim, INCLUDING `assistant/chunk` — `seq` must stay
|
||||
@@ -194,6 +213,20 @@ export interface SessionEventMap {
|
||||
'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string } }
|
||||
/** Steering content injected between steps of a running turn. */
|
||||
'steering/message': { turn: number; content: ContentBlock[]; source: MessageSource }
|
||||
/**
|
||||
* The agent's whole todo list, carried as a full snapshot and replaced
|
||||
* wholesale on each write — the current list is the most recent `todo/write`
|
||||
* (last-write-wins on replay, no fold). Appended by an owning agent via
|
||||
* `session.append('todo/write', { todos })`.
|
||||
*
|
||||
* NOT a {@link SurfaceEventType}: it produces no LLM message and never reaches
|
||||
* `deriveMessages()`, so it carries no `surfaceOp` and stays off the surface —
|
||||
* it is durable, replayable UI state, distinct from the conversation history.
|
||||
* It is a `SessionEventMap` member riding the existing `session/event` emit,
|
||||
* not a first-class Cordis `interface Events` notification, so it has no
|
||||
* cordis-catalog row.
|
||||
*/
|
||||
'todo/write': { todos: TodoItem[] }
|
||||
}
|
||||
|
||||
export type SessionEventType = keyof SessionEventMap
|
||||
@@ -279,7 +312,7 @@ export type SessionEvent<T extends SessionEventType = SessionEventType> = {
|
||||
/**
|
||||
* Seq numbers of events that are provenance sources of this event
|
||||
* (e.g. the `assistant/chunk` seqs that built an `assistant/message`,
|
||||
* or the surface nodes shadowed by a compaction marker).
|
||||
* or the surface nodes shadowed by a compaction replace node).
|
||||
*/
|
||||
sourceEventSeqs?: number[]
|
||||
/** How this event entered the surface; absent for non-surface events. */
|
||||
|
||||
@@ -2,7 +2,7 @@ import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore, { SESSION_FORMAT_VERSION, Session, SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEventType } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEventType, TodoItem } from '@deepseek-ai/dsh-session'
|
||||
|
||||
describe('Session', () => {
|
||||
it('derives message history from the event log', () => {
|
||||
@@ -365,3 +365,63 @@ describe('SessionStore', () => {
|
||||
expect(events).toHaveLength(1)
|
||||
})
|
||||
})
|
||||
|
||||
describe('todo/write event', () => {
|
||||
it('appends the whole-list snapshot and isolates the log from later mutation', () => {
|
||||
const session = new Session(SessionId('t1'))
|
||||
const todos: TodoItem[] = [
|
||||
{ content: 'plan the work', status: 'in_progress' },
|
||||
{ content: 'write the code', status: 'pending' },
|
||||
]
|
||||
session.append('todo/write', { todos })
|
||||
|
||||
const event = session.events.findLast(e => e.type === 'todo/write')!
|
||||
expect(event.type).toBe('todo/write')
|
||||
expect(event.data.todos).toEqual(todos)
|
||||
|
||||
// The append snapshots its input: mutating the caller's array afterward must
|
||||
// not change what the log holds (the durable-source-of-truth contract).
|
||||
todos.push({ content: 'sneak in', status: 'pending' })
|
||||
todos[0]!.status = 'completed'
|
||||
expect(event.data.todos).toEqual([
|
||||
{ content: 'plan the work', status: 'in_progress' },
|
||||
{ content: 'write the code', status: 'pending' },
|
||||
])
|
||||
})
|
||||
|
||||
it('is last-write-wins: the current list is the most recent todo/write', () => {
|
||||
const session = new Session(SessionId('t2'))
|
||||
session.append('todo/write', { todos: [{ content: 'first', status: 'pending' }] })
|
||||
session.append('todo/write', { todos: [
|
||||
{ content: 'first', status: 'completed' },
|
||||
{ content: 'second', status: 'in_progress' },
|
||||
] })
|
||||
|
||||
const current = session.events.findLast(e => e.type === 'todo/write')!.data.todos
|
||||
expect(current).toEqual([
|
||||
{ content: 'first', status: 'completed' },
|
||||
{ content: 'second', status: 'in_progress' },
|
||||
])
|
||||
})
|
||||
|
||||
it('is NOT a surface event: it produces no derived message and joins no surface node', () => {
|
||||
const session = new Session(SessionId('t3'))
|
||||
session.append('user/message', { content: [{ type: 'text', text: 'q' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
|
||||
const before = session.deriveMessages().length
|
||||
session.append('todo/write', { todos: [{ content: 'a task', status: 'pending' }] })
|
||||
// The todo event must not add a message to the derived history…
|
||||
expect(session.deriveMessages()).toHaveLength(before)
|
||||
// …and must not appear on the surface linked list.
|
||||
expect(session.surface.nodes.some(node => node.seq === session.seq - 1)).toBe(false)
|
||||
})
|
||||
|
||||
it('round-trips through a seeded replay identically (durable, no surfaceOp needed)', () => {
|
||||
const original = new Session(SessionId('t4'))
|
||||
original.append('todo/write', { todos: [{ content: 'only', status: 'completed' }] })
|
||||
// Seeding a non-surface event with no surfaceOp must not throw.
|
||||
const replayed = new Session(SessionId('t4-replay'), [...original.events])
|
||||
expect(replayed.events.findLast(e => e.type === 'todo/write')!.data.todos)
|
||||
.toEqual([{ content: 'only', status: 'completed' }])
|
||||
expect(replayed.seq).toBe(original.seq)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -278,6 +278,23 @@ describe('Session.append surface opts', () => {
|
||||
// The string 'append' is a primitive — identity-preserving is fine.
|
||||
expect(event.surfaceOp).toBe('append')
|
||||
})
|
||||
|
||||
it('isSurfaceEvent rejects a surface-eligible type missing its surfaceOp marker', () => {
|
||||
// A raw event (not built via append, which mandates the marker) of a
|
||||
// surface-eligible type but with no surfaceOp must NOT narrow to a
|
||||
// SurfaceEvent — it would otherwise be silently dropped from the surface.
|
||||
const noMarker: SessionEvent = {
|
||||
type: 'user/message', seq: 0, time: 1,
|
||||
data: { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } },
|
||||
}
|
||||
expect(isSurfaceEvent(noMarker)).toBe(false)
|
||||
// A non-surface type is rejected too (the type gate).
|
||||
const boundary: SessionEvent = { type: 'turn/start', seq: 1, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } }
|
||||
expect(isSurfaceEvent(boundary)).toBe(false)
|
||||
// A properly-marked surface event narrows.
|
||||
const marked = { ...noMarker, surfaceOp: 'append' } as SurfaceEvent
|
||||
expect(isSurfaceEvent(marked)).toBe(true)
|
||||
})
|
||||
})
|
||||
|
||||
describe('surface type guards', () => {
|
||||
|
||||
314
packages/core/session/tests/tool-pairing.spec.ts
Normal file
314
packages/core/session/tests/tool-pairing.spec.ts
Normal file
@@ -0,0 +1,314 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import { Session, SessionId, isToolPairingBalanced } from '../src/index.ts'
|
||||
import type { SessionEvent, SurfaceNode } from '../src/index.ts'
|
||||
|
||||
/**
|
||||
* Unit coverage for the tool-pairing balance check. It decides whether a CUT in
|
||||
* the surface (a gap before a given surface node, or the after-tail gap) is a
|
||||
* safe edge for a collapsed region (compaction): a region must never split an
|
||||
* `assistant/message`'s tool-calls from their `tool/result`s. A cut is balanced
|
||||
* when no unanswered tool-call sits before it on the surface. Nodes belonging to
|
||||
* no step (pre-step user message, inter-step steering, injection context) are
|
||||
* pairing-neutral, so their cuts are free boundaries.
|
||||
*
|
||||
* The fixtures are built through a real {@link Session} so the surface linked
|
||||
* list is derived exactly as production does — including the non-monotonic
|
||||
* surface a `replace` op leaves (a compaction checkpoint at a high log seq
|
||||
* sitting at the surface head), which is the case the abandoned log-position
|
||||
* scan mis-classified.
|
||||
*
|
||||
* Builders mirror the agent loop's real append order: queued user messages land
|
||||
* BEFORE `step/start`; within a step the order is `assistant/message` then
|
||||
* `tool/result`(s); injection turns are a bare `turn/start → context/message →
|
||||
* turn/end` with no step.
|
||||
*/
|
||||
|
||||
const SURFACE = { surfaceOp: 'append' as const }
|
||||
|
||||
/** Surface nodes + log for a session, the two args the balance check takes. */
|
||||
function surfaceOf(session: Session): { nodes: readonly SurfaceNode[]; events: readonly SessionEvent[] } {
|
||||
return { nodes: session.surface.nodes, events: session.events }
|
||||
}
|
||||
|
||||
/** The cut BEFORE the surface node at `seq` is balanced (safe region start). */
|
||||
function startBalanced(session: Session, seq: number): boolean {
|
||||
const { nodes, events } = surfaceOf(session)
|
||||
return isToolPairingBalanced(nodes, events, seq)
|
||||
}
|
||||
|
||||
/** The cut AFTER the surface node at `seq` is balanced (safe region end). */
|
||||
function endBalanced(session: Session, seq: number): boolean {
|
||||
const { nodes, events } = surfaceOf(session)
|
||||
const node = nodes.find(n => n.seq === seq)
|
||||
if (!node) throw new Error(`seq ${seq} is not a surface node`)
|
||||
return isToolPairingBalanced(nodes, events, node.next)
|
||||
}
|
||||
|
||||
/** Surface seq of the nth (0-based) event of a given type. */
|
||||
function seqOf(s: Session, type: SessionEvent['type'], nth = 0): number {
|
||||
return s.events.filter(e => e.type === type)[nth]!.seq
|
||||
}
|
||||
|
||||
/** A closed turn with one closed step holding an assistant + its tool result. */
|
||||
function toolStepSession(): Session {
|
||||
const s = new Session(SessionId('tool-step'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('user/message', { content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }, SURFACE)
|
||||
s.append('step/start', { turn: 1, step: 1 })
|
||||
s.append('assistant/message', {
|
||||
turn: 1, step: 1,
|
||||
content: [
|
||||
{ type: 'text', text: 'calling' },
|
||||
{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' },
|
||||
],
|
||||
}, SURFACE)
|
||||
s.append('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: '{}' })
|
||||
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, SURFACE)
|
||||
s.append('step/end', { turn: 1, step: 1 })
|
||||
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
|
||||
return s
|
||||
}
|
||||
|
||||
describe('isToolPairingBalanced — region START (cut before a node)', () => {
|
||||
it('is true for a pre-step user/message (belongs to no step)', () => {
|
||||
const s = toolStepSession()
|
||||
expect(startBalanced(s, seqOf(s, 'user/message'))).toBe(true)
|
||||
})
|
||||
|
||||
it('is true for the first surface node of a step (the assistant/message)', () => {
|
||||
// The cut before the assistant is balanced — nothing unanswered precedes it.
|
||||
const s = toolStepSession()
|
||||
expect(startBalanced(s, seqOf(s, 'assistant/message'))).toBe(true)
|
||||
})
|
||||
|
||||
it('is false for a tool/result whose assistant/message precedes it in the same step', () => {
|
||||
// The cut before the tool/result has one unanswered tool-call (the
|
||||
// assistant's) → starting the region here would orphan that call.
|
||||
const s = toolStepSession()
|
||||
expect(startBalanced(s, seqOf(s, 'tool/result'))).toBe(false)
|
||||
})
|
||||
|
||||
it('is true at the surface head (nothing precedes)', () => {
|
||||
const s = new Session(SessionId('lone'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, SURFACE)
|
||||
expect(startBalanced(s, seqOf(s, 'user/message'))).toBe(true)
|
||||
})
|
||||
})
|
||||
|
||||
describe('isToolPairingBalanced — region END (cut after a node)', () => {
|
||||
it('is true for the last surface node of a closed step (the tool/result)', () => {
|
||||
// After the tool/result the assistant's single call is answered → balanced.
|
||||
const s = toolStepSession()
|
||||
expect(endBalanced(s, seqOf(s, 'tool/result'))).toBe(true)
|
||||
})
|
||||
|
||||
it('is false for an assistant/message with a later tool/result in the same step', () => {
|
||||
// After the assistant its tool-call is still unanswered → ending here strands
|
||||
// the result.
|
||||
const s = toolStepSession()
|
||||
expect(endBalanced(s, seqOf(s, 'assistant/message'))).toBe(false)
|
||||
})
|
||||
|
||||
it('is true for a pre-step user/message', () => {
|
||||
const s = toolStepSession()
|
||||
expect(endBalanced(s, seqOf(s, 'user/message'))).toBe(true)
|
||||
})
|
||||
|
||||
it('is false at the tail when the node is inside an open (unclosed) step', () => {
|
||||
// step/start then an assistant tool-call, but no tool/result yet (mid-flight).
|
||||
// The after-tail cut still has one unanswered call → not balanced.
|
||||
const s = new Session(SessionId('open-step'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('step/start', { turn: 1, step: 1 })
|
||||
s.append('assistant/message', {
|
||||
turn: 1, step: 1,
|
||||
content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }],
|
||||
}, SURFACE)
|
||||
expect(endBalanced(s, seqOf(s, 'assistant/message'))).toBe(false)
|
||||
})
|
||||
|
||||
it('is true at the tail when the node is a trailing inter-step node (step already closed)', () => {
|
||||
// A steering message appended after step/end, at the tail. The prior step's
|
||||
// pair is balanced and steering is neutral → the after-tail cut is balanced.
|
||||
const s = new Session(SessionId('trailing-steer'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('step/start', { turn: 1, step: 1 })
|
||||
s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, SURFACE)
|
||||
s.append('step/end', { turn: 1, step: 1 })
|
||||
s.append('steering/message', { turn: 1, content: [{ type: 'text', text: 's' }], source: { kind: 'user' } }, SURFACE)
|
||||
expect(endBalanced(s, seqOf(s, 'steering/message'))).toBe(true)
|
||||
})
|
||||
|
||||
it('is true at the tail when no step ever opened', () => {
|
||||
const s = new Session(SessionId('no-step'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, SURFACE)
|
||||
expect(endBalanced(s, seqOf(s, 'user/message'))).toBe(true)
|
||||
})
|
||||
})
|
||||
|
||||
describe('isToolPairingBalanced — multiple tool calls in one assistant message', () => {
|
||||
// An assistant message with two tool-calls needs BOTH results before the cut
|
||||
// after it is balanced — depth +2, then -1, -1.
|
||||
function twoCallStep(): Session {
|
||||
const s = new Session(SessionId('two-call'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('step/start', { turn: 1, step: 1 })
|
||||
s.append('assistant/message', {
|
||||
turn: 1, step: 1,
|
||||
content: [
|
||||
{ type: 'tool-call', id: CallId('c1'), name: 'a', arguments: '{}' },
|
||||
{ type: 'tool-call', id: CallId('c2'), name: 'b', arguments: '{}' },
|
||||
],
|
||||
}, SURFACE)
|
||||
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: '1' }], isError: false }, SURFACE)
|
||||
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c2'), content: [{ type: 'text', text: '2' }], isError: false }, SURFACE)
|
||||
s.append('step/end', { turn: 1, step: 1 })
|
||||
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
|
||||
return s
|
||||
}
|
||||
|
||||
it('is unbalanced after the first of two results (one call still open)', () => {
|
||||
const s = twoCallStep()
|
||||
expect(endBalanced(s, seqOf(s, 'tool/result', 0))).toBe(false)
|
||||
})
|
||||
|
||||
it('is balanced after the second result (both calls answered)', () => {
|
||||
const s = twoCallStep()
|
||||
expect(endBalanced(s, seqOf(s, 'tool/result', 1))).toBe(true)
|
||||
})
|
||||
})
|
||||
|
||||
describe('isToolPairingBalanced — a mid-step injection context/message', () => {
|
||||
// A background task-done inject() lands a context/message INSIDE an open step,
|
||||
// between the assistant (with a tool-call) and its tool/result. It is
|
||||
// pairing-neutral, so the cut on EITHER side of it is unbalanced (the call is
|
||||
// still open across it) — it is NOT a free boundary in this position.
|
||||
function midStepInjection(): Session {
|
||||
const s = new Session(SessionId('mid-inject'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('step/start', { turn: 1, step: 1 })
|
||||
s.append('assistant/message', {
|
||||
turn: 1, step: 1,
|
||||
content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }],
|
||||
}, SURFACE)
|
||||
s.append('context/message', { content: [{ type: 'text', text: 'bg task done' }], source: { kind: 'plugin', plugin: 'tool-bash' } }, SURFACE)
|
||||
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, SURFACE)
|
||||
s.append('step/end', { turn: 1, step: 1 })
|
||||
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
|
||||
return s
|
||||
}
|
||||
|
||||
it('start cut before the mid-step context/message is unbalanced (call still open)', () => {
|
||||
const s = midStepInjection()
|
||||
expect(startBalanced(s, seqOf(s, 'context/message'))).toBe(false)
|
||||
})
|
||||
|
||||
it('end cut after the mid-step context/message is unbalanced (call still open)', () => {
|
||||
const s = midStepInjection()
|
||||
expect(endBalanced(s, seqOf(s, 'context/message'))).toBe(false)
|
||||
})
|
||||
})
|
||||
|
||||
describe('isToolPairingBalanced on an injection turn (no step)', () => {
|
||||
// An idle inject() wraps a context/message in a bare turn/start →
|
||||
// context/message → turn/end with NO step. The context node is a free boundary
|
||||
// both ways (pairing-neutral, nothing open around it).
|
||||
function injectionSession(): Session {
|
||||
const s = new Session(SessionId('injection'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: { kind: 'user' } } })
|
||||
s.append('context/message', { content: [{ type: 'text', text: 'ctx' }], source: { kind: 'user' } }, SURFACE)
|
||||
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
|
||||
return s
|
||||
}
|
||||
|
||||
it('start: balanced', () => {
|
||||
const s = injectionSession()
|
||||
expect(startBalanced(s, seqOf(s, 'context/message'))).toBe(true)
|
||||
})
|
||||
|
||||
it('end: balanced', () => {
|
||||
const s = injectionSession()
|
||||
expect(endBalanced(s, seqOf(s, 'context/message'))).toBe(true)
|
||||
})
|
||||
})
|
||||
|
||||
describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace op', () => {
|
||||
// The case the log-position scan got wrong. After a compaction, a replacement
|
||||
// user/message lands at a HIGH log seq but sits at the SURFACE head, beside
|
||||
// the still-open step whose events follow it in the log. It carries no
|
||||
// tool-call/result pair (just summarized prose), so it must be a balanced cut
|
||||
// on BOTH sides regardless of its log neighbours.
|
||||
function checkpointHeadedSession(): Session {
|
||||
const s = new Session(SessionId('checkpoint'))
|
||||
// A closed turn with a tool step → surface [u1, asst(call), result].
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('step/start', { turn: 1, step: 1 })
|
||||
s.append('user/message', { content: [{ type: 'text', text: 'u1' }], source: { kind: 'user' } }, SURFACE)
|
||||
s.append('assistant/message', {
|
||||
turn: 1, step: 1,
|
||||
content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }],
|
||||
}, SURFACE)
|
||||
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, SURFACE)
|
||||
s.append('step/end', { turn: 1, step: 1 })
|
||||
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
|
||||
// An OPEN turn whose step is in progress (loop fires compaction here).
|
||||
s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('step/start', { turn: 2, step: 1 })
|
||||
// Compaction replaces the whole turn-1 surface ([u1, asst, result]) with one
|
||||
// summary user/message — appended now, so it carries a high log seq.
|
||||
const u1 = seqOf(s, 'user/message')
|
||||
const result = s.events.find(e => e.type === 'tool/result')!.seq
|
||||
s.append('user/message', {
|
||||
content: [{ type: 'text', text: 'CHECKPOINT' }],
|
||||
source: { kind: 'plugin', plugin: 'compact' },
|
||||
}, { surfaceOp: { op: 'replace', start: u1, end: result } })
|
||||
// The step's own assistant/message lands AFTER the checkpoint in the log,
|
||||
// still inside the open step.
|
||||
s.append('assistant/message', { turn: 2, step: 1, content: [{ type: 'text', text: 'a2' }] }, SURFACE)
|
||||
return s
|
||||
}
|
||||
|
||||
it('the head checkpoint sits at the surface head while a later surface node follows it in the log', () => {
|
||||
const s = checkpointHeadedSession()
|
||||
const nodes = s.surface.nodes
|
||||
const checkpointSeq = nodes[0]!.seq
|
||||
// The checkpoint heads the surface, yet a surface node (the open step's
|
||||
// assistant) follows it in LOG order — the exact split between surface
|
||||
// position and log position that the log-position scan tripped on.
|
||||
const laterSurfaceInLog = s.events.find(
|
||||
e => e.seq > checkpointSeq && nodes.some(n => n.seq === e.seq),
|
||||
)
|
||||
expect(laterSurfaceInLog).toBeDefined()
|
||||
expect(nodes[0]!.seq).toBe(checkpointSeq)
|
||||
})
|
||||
|
||||
it('start cut before the head checkpoint is balanced (it is the head)', () => {
|
||||
const s = checkpointHeadedSession()
|
||||
expect(startBalanced(s, s.surface.nodes[0]!.seq)).toBe(true)
|
||||
})
|
||||
|
||||
it('end cut after the head checkpoint is balanced (it carries no tool pair)', () => {
|
||||
// This is the exact assertion the log-position scan failed: the forward log
|
||||
// scan from the checkpoint reached the open step's assistant/message and
|
||||
// wrongly reported mid-step. The surface balance sees a neutral node whose
|
||||
// following cut closes no open call.
|
||||
const s = checkpointHeadedSession()
|
||||
expect(endBalanced(s, s.surface.nodes[0]!.seq)).toBe(true)
|
||||
})
|
||||
})
|
||||
|
||||
describe('isToolPairingBalanced — corrupt surface guard', () => {
|
||||
it('throws when a tool/result has no preceding tool-call (depth goes negative)', () => {
|
||||
// A surface that opens with a tool/result (no assistant call before it) is
|
||||
// structurally corrupt — surfaced loudly rather than mis-classified.
|
||||
const s = new Session(SessionId('corrupt'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('step/start', { turn: 1, step: 1 })
|
||||
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'x' }], isError: false }, SURFACE)
|
||||
const { nodes, events } = surfaceOf(s)
|
||||
expect(() => isToolPairingBalanced(nodes, events, null)).toThrow(/no matching tool-call/)
|
||||
})
|
||||
})
|
||||
@@ -34,4 +34,4 @@ Merge-extensible: plugins can declare extra fields on `PromptAssembly` via decla
|
||||
### What is NOT here
|
||||
|
||||
- Any hardcoded prompt text — every section comes from plugins.
|
||||
- Prompt compaction (belongs on the `agent/request` seam in `dsh-agent`).
|
||||
- Prompt compaction (belongs on the `agent/pre-step` seam in `dsh-agent`).
|
||||
|
||||
@@ -10,7 +10,7 @@ The JSONL durable session-persistence backend — a concrete `SessionPersistence
|
||||
<encoded-id>.jsonl # header line + one SessionEvent per line (verbatim)
|
||||
```
|
||||
|
||||
- The first `.jsonl` line is the immutable `SessionHeader` tagged `{ type: 'session', version, id, cwd?, createdAt, parentSession? }`; every subsequent line is one `SessionEvent` JSON, **verbatim including `assistant/chunk`** so `seq` stays contiguous (`events[i].seq === i`).
|
||||
- The first `.jsonl` line is the immutable `SessionHeader` tagged `{ type: 'session', version, id, cwd?, createdAt, parentSession?, seedLength? }`; every subsequent line is one `SessionEvent` JSON, **verbatim including `assistant/chunk`** so `seq` stays contiguous (`events[i].seq === i`).
|
||||
- Session ids are unvalidated branded strings, so they are percent-encoded to a single safe path segment before use (no traversal, no collision).
|
||||
|
||||
## Config
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
The abstract durable session-persistence seam (`ctx.sessionPersistence`). Defines WHAT a persistence backend does — durably store, reload, and list sessions — without saying HOW. Mirrors the `dsh-bash` capability-seam template ([capability seams](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract service here, a concrete implementation in a sibling package, consumers that inject the interface.
|
||||
|
||||
The persisted unit IS the existing `SessionEvent` (event-sourced model — the log is the single source of truth), so there is no parallel "persisted message" type. Metadata that is NOT replayable conversation state (format version, cwd, lineage) travels separately as `SessionHeader`, owned by `dsh-session` and re-exported here.
|
||||
The persisted unit IS the existing `SessionEvent` (event-sourced model — the log is the single source of truth), so there is no parallel "persisted message" type. Metadata that is NOT replayable conversation state (format version, cwd, lineage, seed boundary) travels separately as `SessionHeader`, owned by `dsh-session` and re-exported here.
|
||||
|
||||
## Service API (`ctx.sessionPersistence`)
|
||||
|
||||
@@ -44,8 +44,8 @@ The `tornMarker` is fully OPAQUE: the coordinator only tests `!== undefined` and
|
||||
|
||||
Import `runPersistenceContract` from `tests/contract.ts` (the public-API contract) and `runCoordinatorContract` from `tests/coordinator-contract.ts` (the shared write-path orchestration: adoption, HMR, collision, dispose-drain, crash-tail repair) and call each with a fixture for your backend. Every backend is held to the same append-only / contiguous-seq / lazy-materialization / serializability semantics AND the same orchestration, so a backend's own spec is left with only storage-mechanics tests (path sanitization, fsync rollback; schema version, transaction rollback) on top.
|
||||
|
||||
Three backends run these suites: an in-memory reference (in `tests/`), `dsh-session-persistence-jsonl` (append-only file log) and `dsh-session-persistence-sqlite` (`node:sqlite`, each `SessionEvent` one row `(session_id, seq, type, time, data)`). All passing the same contract + coordinator suite is the proof that the seam is genuinely backend-agnostic — lazy materialization, crash-tail-on-load, and contiguous-seq hold identically over file bytes and over a transactional store.
|
||||
Three backends run these suites: an in-memory reference (in `tests/`), `dsh-session-persistence-jsonl` (append-only file log) and `dsh-session-persistence-sqlite` (`node:sqlite`, each `SessionEvent` one row `(session_id, seq, type, time, data, source_event_seqs, surface_op)`). All passing the same contract + coordinator suite is the proof that the seam is genuinely backend-agnostic — lazy materialization, crash-tail-on-load, and contiguous-seq hold identically over file bytes and over a transactional store.
|
||||
|
||||
## Metadata types
|
||||
|
||||
Re-exported from `dsh-session`: `SessionHeader` (immutable session metadata: `version`, `id`, `createdAt`, `cwd?`, `parentSession?`).
|
||||
Re-exported from `dsh-session`: `SessionHeader` (immutable session metadata: `version`, `id`, `createdAt`, `cwd?`, `parentSession?`, `seedLength?`).
|
||||
|
||||
@@ -15,8 +15,8 @@
|
||||
* parallel "persisted message" type the log must be converted to and from
|
||||
* (faithful to the event-sourced model: the log is the single source of
|
||||
* truth). Metadata that is NOT replayable conversation state (format version,
|
||||
* cwd, lineage) travels separately as {@link SessionHeader}, which is owned by
|
||||
* `dsh-session` and re-exported here.
|
||||
* cwd, lineage, seed boundary) travels separately as {@link SessionHeader},
|
||||
* which is owned by `dsh-session` and re-exported here.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-session-persistence
|
||||
*/
|
||||
|
||||
@@ -7,5 +7,6 @@ Packages that exist to serve development, testing, and the examples rather than
|
||||
| `invariants/` | Dev-mode event-contract invariants + session-log freeze | (listens on `session/*`, `agent/*`) |
|
||||
| `ui-stdio/` | Minimal stdio (readline) UI plugin: renders `agent/*` events, feeds stdin lines to the agent | (drives `ctx.agents`) |
|
||||
| `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) |
|
||||
| `subagent-mock/` | Scripted `SubagentProvider` for deterministic seam/tool tests | (registers on `ctx.subagents`) |
|
||||
|
||||
`invariants` runs only in dev mode (contract checks, not runtime behavior). `ui-stdio` and `llm-replay` were extracted from the examples for reuse and to bring them under the per-file coverage gate; they back the demos and the snapshot test tier. A package graduates OUT of `support/` into a product group only when it gains documented product consumers.
|
||||
`invariants` runs only in dev mode (contract checks, not runtime behavior). `ui-stdio` and `llm-replay` were extracted from the examples for reuse and to bring them under the per-file coverage gate; they back the demos and the snapshot test tier. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers.
|
||||
|
||||
@@ -162,9 +162,6 @@ function checkEvent(trace: SessionTrace, event: SessionEvent): void {
|
||||
trace.surface.push(event.seq)
|
||||
} else {
|
||||
const { start, end } = se.surfaceOp
|
||||
if (start > end) {
|
||||
throw new InvariantError(`surface replace: start ${start} must be <= end ${end}`)
|
||||
}
|
||||
const startIdx = trace.surface.indexOf(start)
|
||||
if (startIdx === -1) {
|
||||
throw new InvariantError(`surface replace: start seq ${start} is not on the surface`)
|
||||
|
||||
@@ -530,16 +530,17 @@ describe('surface invariants', () => {
|
||||
}).toThrow(/unknown seq 2/)
|
||||
})
|
||||
|
||||
it('rejects replace op with start > end', async () => {
|
||||
it('rejects a replace whose start is positioned after its end on the surface', async () => {
|
||||
const { ctx } = await setup()
|
||||
const session = ctx.sessions.create()
|
||||
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
session.append('step/start', { turn: 1, step: 1 })
|
||||
session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2
|
||||
// start > end is invalid (reversed order).
|
||||
session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3
|
||||
// Reversed range: start seq 3 is at a later surface position than end seq 2.
|
||||
expect(() => {
|
||||
session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 1 }, sourceEventSeqs: [2] })
|
||||
}).toThrow(/must be <= end/)
|
||||
session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 2 }, sourceEventSeqs: [2, 3] })
|
||||
}).toThrow(/is after end seq 2 .* on the surface/)
|
||||
})
|
||||
|
||||
it('rejects a replace whose sourceEventSeqs omits a shadowed surface node', async () => {
|
||||
@@ -608,6 +609,23 @@ describe('surface invariants', () => {
|
||||
}).toThrow(/is after end seq 4 .* on the surface/)
|
||||
})
|
||||
|
||||
it('accepts a replace whose start seq exceeds its end seq when the surface position order is valid', async () => {
|
||||
const { ctx } = await setup()
|
||||
const session = ctx.sessions.create()
|
||||
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
session.append('step/start', { turn: 1, step: 1 })
|
||||
session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2
|
||||
session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3
|
||||
// Replace node 2 (position 0) with seq 4 — surface becomes [4, 3], so the
|
||||
// head seq (4) is numerically GREATER than the tail seq (3): the surface is
|
||||
// not seq-ordered. A replace spanning start=4 (pos 0) … end=3 (pos 1) is
|
||||
// valid positionally and must be accepted even though start seq > end seq.
|
||||
session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4
|
||||
expect(() => {
|
||||
session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 4, end: 3 }, sourceEventSeqs: [4, 3] }) // seq 5
|
||||
}).not.toThrow()
|
||||
})
|
||||
|
||||
it('rejects a replace that omits sourceEventSeqs entirely', async () => {
|
||||
const { ctx } = await setup()
|
||||
const session = ctx.sessions.create()
|
||||
|
||||
@@ -110,6 +110,13 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt
|
||||
const { content } = event.data
|
||||
const text = content.filter(block => block.type === 'text').map(block => block.text).join('')
|
||||
output.write(`\n [tool result] ${text}\n `)
|
||||
} else if (event.type === 'todo/write') {
|
||||
if (inReasoning) output.write('\x1B[0m')
|
||||
inReasoning = false
|
||||
const glyph = (status: string): string =>
|
||||
status === 'completed' ? '[x]' : status === 'in_progress' ? '[~]' : '[ ]'
|
||||
const lines = event.data.todos.map(todo => ` ${glyph(todo.status)} ${todo.content}`).join('\n')
|
||||
output.write(`\n [todos]\n${lines}\n `)
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
@@ -151,6 +151,35 @@ describe('createStdioChat rendering', () => {
|
||||
expect(out.text()).toContain('[tool result] file.txt')
|
||||
})
|
||||
|
||||
it('renders a todo/write session event as a glyphed checklist', async () => {
|
||||
const { ctx, out } = await setup()
|
||||
const session = {} as Session
|
||||
ctx.emit('session/event', session, {
|
||||
type: 'todo/write', seq: 1, time: 0,
|
||||
data: { todos: [
|
||||
{ content: 'read the code', status: 'completed' },
|
||||
{ content: 'write the fix', status: 'in_progress' },
|
||||
{ content: 'run the tests', status: 'pending' },
|
||||
] },
|
||||
} as SessionEvent)
|
||||
const text = out.text()
|
||||
expect(text).toContain('[todos]')
|
||||
expect(text).toContain('[x] read the code')
|
||||
expect(text).toContain('[~] write the fix')
|
||||
expect(text).toContain('[ ] run the tests')
|
||||
})
|
||||
|
||||
it('resets dim styling when a todo/write interrupts reasoning', async () => {
|
||||
const { ctx, out } = await setup()
|
||||
const agent = makeAgent('main')
|
||||
ctx.emit('agent/stream-chunk', agent, 1, 0, { type: 'reasoning-delta', index: 0, text: 'r' })
|
||||
ctx.emit('session/event', {} as Session, {
|
||||
type: 'todo/write', seq: 1, time: 0,
|
||||
data: { todos: [{ content: 'a task', status: 'pending' }] },
|
||||
} as SessionEvent)
|
||||
expect(out.text()).toContain('\x1B[2mr\x1B[0m')
|
||||
})
|
||||
|
||||
it('resets dim styling when a tool/call interrupts reasoning', async () => {
|
||||
const { ctx, out } = await setup()
|
||||
const agent = makeAgent('main')
|
||||
|
||||
9
packages/todo/README.md
Normal file
9
packages/todo/README.md
Normal file
@@ -0,0 +1,9 @@
|
||||
# todo/ — todo / planning capability family
|
||||
|
||||
The model-facing todo tool. A single **product** package — there is no interface/implementation seam here, because the list is single-owner session state (one agent session owns its own list), not a swappable capability.
|
||||
|
||||
| Package | Role | ctx key |
|
||||
|---|---|---|
|
||||
| `tool-todo/` | Model-facing `todo_write` tool; writes the whole list to the session log (`todo/write`) | (registers on `ctx.tools`) |
|
||||
|
||||
The list lives on the event-sourced session log (`SessionEventMap['todo/write']`, owned by [`dsh-session`](../core/session)); this package is the thin consumer that appends the snapshot. UIs render off `session/event`: the [stdio UI](../support/ui-stdio) prints the list, the [ACP bridge](../ui/acp) maps it to a `plan` sessionUpdate.
|
||||
25
packages/todo/tool-todo/README.md
Normal file
25
packages/todo/tool-todo/README.md
Normal file
@@ -0,0 +1,25 @@
|
||||
# @deepseek-ai/dsh-tool-todo
|
||||
|
||||
The model-facing `todo_write` tool: the agent's whole task list, replaced wholesale on each call.
|
||||
|
||||
## What it does
|
||||
|
||||
Registers one tool, `todo_write(todos: [{ content, status }])`, on `ctx.tools`. The model sends the ENTIRE list every call — there are no partial updates or per-item edits. Each call appends a `todo/write` event (the full list snapshot) to the calling agent's session log via `agent.session.append('todo/write', { todos })`; the current list is the most recent such event (last-write-wins on replay).
|
||||
|
||||
`status` is one of `pending`, `in_progress`, `completed` — exactly the ACP `PlanEntryStatus` triple.
|
||||
|
||||
## Single owner
|
||||
|
||||
The list belongs to the ONE agent session that called the tool. There is no subagent/shared/swarm scope: a non-agent caller (no `exec.agent`) has nowhere to write the list and is rejected. This is a deliberate scope limit — see the RFC.
|
||||
|
||||
## Validation
|
||||
|
||||
Beyond the schema's type/required/enum checks, `execute` rejects an empty or duplicate `content` and more than one `in_progress` task (a coherent plan has at most one task active). Ordering and the discipline of keeping the list current are left to the model via the tool description.
|
||||
|
||||
## Rendering
|
||||
|
||||
The tool writes only the session event; it does not render. UIs subscribe to `session/event` and render the `todo/write` data themselves: the [stdio UI](../../support/ui-stdio) prints a glyphed checklist, and the [ACP bridge](../../ui/acp) maps the list to a `plan` sessionUpdate (synthesizing the `priority` ACP requires).
|
||||
|
||||
## Export shape
|
||||
|
||||
A function/namespace plugin: it exports `name` / `inject` / `apply` and NO default. A stray `export default` would collapse the module via the Loader's `unwrapExports` and drop `inject` (see [docs/postmortem/0001](../../../docs/postmortem/0001-acp-default-export-drops-inject.md)).
|
||||
39
packages/todo/tool-todo/package.json
Normal file
39
packages/todo/tool-todo/package.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"name": "@deepseek-ai/dsh-tool-todo",
|
||||
"description": "Model-facing todo_write tool over the DeepSeek Harness event-sourced session log",
|
||||
"version": "0.0.1",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"main": "lib/index.js",
|
||||
"types": "lib/types/index.d.ts",
|
||||
"exports": {
|
||||
".": {
|
||||
"types": "./lib/types/index.d.ts",
|
||||
"default": "./lib/index.js"
|
||||
},
|
||||
"./src/*": "./src/*",
|
||||
"./package.json": "./package.json"
|
||||
},
|
||||
"files": [
|
||||
"lib/index.js",
|
||||
"lib/types/**/*.d.ts",
|
||||
"lib/types/**/*.d.ts.map",
|
||||
"src"
|
||||
],
|
||||
"license": "BSD-3-Clause",
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tools": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-loop": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"@deepseek-ai/dsh-tools": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
}
|
||||
}
|
||||
123
packages/todo/tool-todo/src/index.ts
Normal file
123
packages/todo/tool-todo/src/index.ts
Normal file
@@ -0,0 +1,123 @@
|
||||
/**
|
||||
* The model-facing `todo_write` tool: the agent's whole task list, replaced
|
||||
* wholesale on each call. Every call appends a `todo/write` event (the full
|
||||
* list snapshot) to the calling agent's session log via
|
||||
* `exec.agent.session.append('todo/write', { todos })`; the current list is the
|
||||
* most recent such event (last-write-wins on replay). UIs render off
|
||||
* `session/event`: the stdio UI prints the checklist, the ACP bridge maps it to
|
||||
* a `plan` sessionUpdate.
|
||||
*
|
||||
* Single owner: the list belongs to the ONE agent session that called the tool.
|
||||
* There is no subagent/shared/swarm scope — a non-agent caller (no
|
||||
* `exec.agent`) has nowhere to write the list and is rejected.
|
||||
*
|
||||
* Plugin export shape: named exports, NO default. The cordis Loader's
|
||||
* `unwrapExports` does `exports.default ?? exports`, so a stray default would
|
||||
* collapse the module to the bare `apply` and drop `inject`, crashing at load
|
||||
* (see docs/postmortem/0001).
|
||||
*
|
||||
* @module @deepseek-ai/dsh-tool-todo
|
||||
*/
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import type { TodoItem } from '@deepseek-ai/dsh-session'
|
||||
|
||||
export const name = 'tool-todo'
|
||||
export const inject = ['tools']
|
||||
|
||||
/** The valid {@link TodoItem} statuses, as a runtime set for input narrowing. */
|
||||
const STATUSES = ['pending', 'in_progress', 'completed'] as const
|
||||
|
||||
const DESCRIPTION =
|
||||
'Record and update a structured task list for the current work. Send the ENTIRE '
|
||||
+ 'list every call — it REPLACES the previous list (there are no partial updates, '
|
||||
+ 'no per-item edits). Use it to plan multi-step work and show progress: add one '
|
||||
+ 'todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` '
|
||||
+ 'at a time; while work remains, exactly one active task should be '
|
||||
+ '`in_progress`. Mark a todo `completed` the moment it is done (do not batch '
|
||||
+ 'completions), and allow no `in_progress` item only once all work is complete. '
|
||||
+ 'Skip the list for trivial single-step tasks. Statuses: `pending` '
|
||||
+ '(not started), `in_progress` (being worked on now), `completed` (finished).'
|
||||
|
||||
/**
|
||||
* Validate the value constraints the SchemaSpec can't express and build the
|
||||
* canonical {@link TodoItem}[].
|
||||
*
|
||||
* `defineTool` already validates type/required/enum before `execute` runs (a
|
||||
* bad `status` is rejected by the registry's `validateArgs`, never reaching
|
||||
* here), so `status` is guaranteed to be one of the three enum literals. But
|
||||
* `InferArgs` maps an `enum` string prop to plain `string`, so the compiler sees
|
||||
* `args.todos` as `{ content: string; status: string }[]`; the
|
||||
* `status as TodoItem['status']` narrowing records that registry guarantee
|
||||
* rather than re-checking it (an unreachable re-check would be dead code — see
|
||||
* AGENTS.md "don't validate scenarios that can't happen"). What remains is the
|
||||
* value rules the DSL has no vocabulary for: non-empty unique content (stored
|
||||
* trimmed, so the persisted value matches the dedupe/length key), and at most
|
||||
* one `in_progress` task.
|
||||
*/
|
||||
function toTodoList(raw: { content: string; status: string }[]): TodoItem[] {
|
||||
const todos: TodoItem[] = []
|
||||
const seen = new Set<string>()
|
||||
let inProgress = 0
|
||||
for (const item of raw) {
|
||||
const content = item.content.trim()
|
||||
if (content.length === 0) {
|
||||
throw new Error('invalid todo: `content` must be a non-empty string')
|
||||
}
|
||||
if (seen.has(content)) {
|
||||
throw new Error(`invalid todos: duplicate content ${JSON.stringify(content)}`)
|
||||
}
|
||||
seen.add(content)
|
||||
const status = item.status as TodoItem['status']
|
||||
if (status === 'in_progress') inProgress++
|
||||
todos.push({ content, status })
|
||||
}
|
||||
if (inProgress > 1) {
|
||||
throw new Error(`invalid todos: at most one task may be in_progress, got ${inProgress}`)
|
||||
}
|
||||
return todos
|
||||
}
|
||||
|
||||
/** Register the `todo_write` tool on `ctx.tools`. */
|
||||
export function apply(ctx: Context): void {
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'todo_write',
|
||||
description: DESCRIPTION,
|
||||
parameters: {
|
||||
todos: {
|
||||
type: 'array',
|
||||
required: true,
|
||||
description: 'The COMPLETE task list, replacing any previous list.',
|
||||
items: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
content: { type: 'string', required: true, description: 'What the task is — a short imperative line.' },
|
||||
status: {
|
||||
type: 'string',
|
||||
required: true,
|
||||
enum: [...STATUSES],
|
||||
description: 'pending (not started) | in_progress (now) | completed (done).',
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
execute(args, exec): Promise<ContentBlock[]> {
|
||||
const todos = toTodoList(args.todos)
|
||||
if (!exec.agent) {
|
||||
// The list is per-agent-session state; a non-agent caller (no owning
|
||||
// session) has nowhere to write it. Reject rather than silently no-op.
|
||||
throw new Error('todo_write requires an owning agent session')
|
||||
}
|
||||
exec.agent.session.append('todo/write', { todos })
|
||||
const count = (status: TodoItem['status']): number => todos.filter(t => t.status === status).length
|
||||
return Promise.resolve([{
|
||||
type: 'text',
|
||||
text: `Updated todo list: ${count('pending')} pending, ${count('in_progress')} in progress, ${count('completed')} completed.`,
|
||||
}])
|
||||
},
|
||||
presentCall: args => ({ title: 'Update todo list', kind: 'other', rawInput: args.todos }),
|
||||
}))
|
||||
}
|
||||
107
packages/todo/tool-todo/tests/integration.spec.ts
Normal file
107
packages/todo/tool-todo/tests/integration.spec.ts
Normal file
@@ -0,0 +1,107 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import LlmService from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
|
||||
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
||||
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
|
||||
import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
|
||||
|
||||
/**
|
||||
* Full-loop integration: a scripted mock model drives the REAL todo_write tool
|
||||
* through the agent loop, exercising the same seams a live model would — the
|
||||
* tool/call + tool/result session events AND the todo/write event the tool
|
||||
* appends. Only the model is mocked; the tool and the session log are real.
|
||||
*/
|
||||
async function harness(adapter: MockAdapter): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(ToolTodo)
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
return ctx
|
||||
}
|
||||
|
||||
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
const dispose = ctx.on('agent/status', (subject, status) => {
|
||||
if (subject === agent && status === 'idle') {
|
||||
dispose()
|
||||
resolve()
|
||||
}
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
function findEvent<T extends SessionEvent['type']>(
|
||||
log: readonly SessionEvent[],
|
||||
type: T,
|
||||
position: 'first' | 'last' = 'first',
|
||||
): Extract<SessionEvent, { type: T }> {
|
||||
const found = position === 'first'
|
||||
? log.find(event => event.type === type)
|
||||
: log.findLast(event => event.type === type)
|
||||
if (!found) throw new Error(`no ${type} event in the session log`)
|
||||
return found as Extract<SessionEvent, { type: T }>
|
||||
}
|
||||
|
||||
describe('todo_write tool through the agent loop', () => {
|
||||
it('model calls todo_write: a tool/call, a non-error tool/result, and a todo/write snapshot land', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
toolCallResponse('call-1', 'todo_write', {
|
||||
todos: [
|
||||
{ content: 'read the code', status: 'in_progress' },
|
||||
{ content: 'write the fix', status: 'pending' },
|
||||
],
|
||||
}, 'Planning the work.'),
|
||||
textResponse('Plan recorded.'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('it-todo'), { model: 'mock' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'plan a two-step task' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const log = agent.session.events
|
||||
expect(findEvent(log, 'tool/call').data.name).toBe('todo_write')
|
||||
expect(findEvent(log, 'tool/result').data.isError).toBe(false)
|
||||
|
||||
const todoEvent = findEvent(log, 'todo/write')
|
||||
expect(todoEvent.data.todos).toEqual([
|
||||
{ content: 'read the code', status: 'in_progress' },
|
||||
{ content: 'write the fix', status: 'pending' },
|
||||
])
|
||||
})
|
||||
|
||||
it('a second todo_write replaces the list (last-write-wins on the log)', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
toolCallResponse('call-1', 'todo_write', { todos: [{ content: 'step one', status: 'in_progress' }] }),
|
||||
toolCallResponse('call-2', 'todo_write', {
|
||||
todos: [
|
||||
{ content: 'step one', status: 'completed' },
|
||||
{ content: 'step two', status: 'in_progress' },
|
||||
],
|
||||
}),
|
||||
textResponse('Done planning.'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { model: 'mock' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'plan then update' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const todoEvents = agent.session.events.filter(e => e.type === 'todo/write')
|
||||
expect(todoEvents).toHaveLength(2)
|
||||
expect(findEvent(agent.session.events, 'todo/write', 'last').data.todos).toEqual([
|
||||
{ content: 'step one', status: 'completed' },
|
||||
{ content: 'step two', status: 'in_progress' },
|
||||
])
|
||||
})
|
||||
})
|
||||
167
packages/todo/tool-todo/tests/tool-todo.spec.ts
Normal file
167
packages/todo/tool-todo/tests/tool-todo.spec.ts
Normal file
@@ -0,0 +1,167 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import Loader from '@cordisjs/plugin-loader'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { TodoItem } from '@deepseek-ai/dsh-session'
|
||||
import { AgentId, type Agent } from '@deepseek-ai/dsh-agent'
|
||||
import * as tool from '../src/index.ts'
|
||||
|
||||
/**
|
||||
* Drives the REAL plugin body: mounts `dsh-tool-todo` on a real `ToolRegistry`
|
||||
* and invokes the registered `todo_write` tool through `ctx.tools.execute`,
|
||||
* with a fake parent Agent carrying a real `Session` — so the append the tool
|
||||
* makes is observable on a genuine session log (only the agent wrapper is a
|
||||
* stand-in; the session and the tool are the shipping code).
|
||||
*/
|
||||
|
||||
/** A parent Agent backed by a real Session — the tool reads `agent.session`. */
|
||||
function agentWithSession(id = 'parent-1'): Agent & { session: Session } {
|
||||
const session = new Session(SessionId(id))
|
||||
return { id: AgentId(id), session } as unknown as Agent & { session: Session }
|
||||
}
|
||||
|
||||
async function setup(): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(tool)
|
||||
return ctx
|
||||
}
|
||||
|
||||
let callCounter = 0
|
||||
function callTodo(ctx: Context, args: unknown, over: { agent?: Agent | undefined } = {}) {
|
||||
const agent = 'agent' in over ? over.agent : agentWithSession()
|
||||
return ctx.tools.execute({
|
||||
callId: CallId(`call-${++callCounter}`),
|
||||
name: 'todo_write',
|
||||
arguments: args,
|
||||
...agent ? { agent } : {},
|
||||
})
|
||||
}
|
||||
|
||||
function text(result: { content: { type: string; text?: string }[] }): string {
|
||||
return result.content.filter(b => b.type === 'text').map(b => b.text).join('')
|
||||
}
|
||||
|
||||
describe('dsh-tool-todo', () => {
|
||||
it('registers a `todo_write` tool whose schema is an array of {content,status}', async () => {
|
||||
const ctx = await setup()
|
||||
const schema = ctx.tools.schemas().find(s => s.name === 'todo_write')
|
||||
expect(schema).toBeDefined()
|
||||
const props = (schema!.parameters as { properties?: Record<string, unknown> }).properties ?? {}
|
||||
expect(Object.keys(props)).toEqual(['todos'])
|
||||
const todos = props.todos as { type: string; items?: { properties?: Record<string, { type: string; enum?: string[] }> } }
|
||||
expect(todos.type).toBe('array')
|
||||
const itemProps = todos.items?.properties ?? {}
|
||||
expect(Object.keys(itemProps).sort()).toEqual(['content', 'status'])
|
||||
expect(itemProps.status?.enum).toEqual(['pending', 'in_progress', 'completed'])
|
||||
})
|
||||
|
||||
it('appends a todo/write event carrying the whole list to the calling session', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = agentWithSession('writer')
|
||||
const todos: TodoItem[] = [
|
||||
{ content: 'plan', status: 'in_progress' },
|
||||
{ content: 'build', status: 'pending' },
|
||||
]
|
||||
const result = await callTodo(ctx, { todos }, { agent })
|
||||
expect(result.isError).toBe(false)
|
||||
expect(text(result)).toContain('1 pending, 1 in progress, 0 completed')
|
||||
|
||||
const event = agent.session.events.findLast(e => e.type === 'todo/write')!
|
||||
expect(event.data.todos).toEqual(todos)
|
||||
})
|
||||
|
||||
it('stores the trimmed content (the dedupe/length key), not the raw input', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = agentWithSession('trim')
|
||||
const result = await callTodo(ctx, { todos: [{ content: ' plan the work ', status: 'pending' }] }, { agent })
|
||||
expect(result.isError).toBe(false)
|
||||
|
||||
const event = agent.session.events.findLast(e => e.type === 'todo/write')!
|
||||
expect(event.data.todos).toEqual([{ content: 'plan the work', status: 'pending' }])
|
||||
})
|
||||
|
||||
it('replaces the list on a second call (last-write-wins on the log)', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = agentWithSession('writer-2')
|
||||
await callTodo(ctx, { todos: [{ content: 'a', status: 'pending' }] }, { agent })
|
||||
await callTodo(ctx, { todos: [
|
||||
{ content: 'a', status: 'completed' },
|
||||
{ content: 'b', status: 'in_progress' },
|
||||
] }, { agent })
|
||||
|
||||
const current = agent.session.events.findLast(e => e.type === 'todo/write')!.data.todos
|
||||
expect(current).toEqual([
|
||||
{ content: 'a', status: 'completed' },
|
||||
{ content: 'b', status: 'in_progress' },
|
||||
])
|
||||
})
|
||||
|
||||
it('rejects a malformed status before execute runs (registry arg-validation)', async () => {
|
||||
const ctx = await setup()
|
||||
const result = await callTodo(ctx, { todos: [{ content: 'x', status: 'doing' }] })
|
||||
expect(result.isError).toBe(true)
|
||||
})
|
||||
|
||||
it('rejects a non-array todos argument', async () => {
|
||||
const ctx = await setup()
|
||||
const result = await callTodo(ctx, { todos: 'nope' })
|
||||
expect(result.isError).toBe(true)
|
||||
})
|
||||
|
||||
it.each([
|
||||
{ label: 'empty content', todos: [{ content: ' ', status: 'pending' }], fragment: 'non-empty' },
|
||||
{ label: 'duplicate content', todos: [{ content: 'dup', status: 'pending' }, { content: 'dup', status: 'completed' }], fragment: 'duplicate' },
|
||||
{ label: 'two in_progress', todos: [{ content: 'a', status: 'in_progress' }, { content: 'b', status: 'in_progress' }], fragment: 'in_progress' },
|
||||
])('rejects $label as an isError result', async ({ todos, fragment }) => {
|
||||
const ctx = await setup()
|
||||
const result = await callTodo(ctx, { todos })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain(fragment)
|
||||
})
|
||||
|
||||
it('rejects a non-agent caller (the list has no owning session)', async () => {
|
||||
const ctx = await setup()
|
||||
const result = await callTodo(ctx, { todos: [{ content: 'a', status: 'pending' }] }, { agent: undefined })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain('owning agent session')
|
||||
})
|
||||
|
||||
it('presents the call with a stable title and the list as raw input', async () => {
|
||||
const ctx = await setup()
|
||||
const def = ctx.tools.get('todo_write')!
|
||||
const todos = [{ content: 'a', status: 'pending' }]
|
||||
expect(def.presentCall?.({ todos })).toEqual({ title: 'Update todo list', kind: 'other', rawInput: todos })
|
||||
})
|
||||
|
||||
it('unregisters the tool when its contributing fiber is disposed (HMR-safety)', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
const fiber = await ctx.plugin(tool)
|
||||
expect(ctx.tools.schemas().some(s => s.name === 'todo_write')).toBe(true)
|
||||
await fiber.dispose()
|
||||
expect(ctx.tools.schemas().some(s => s.name === 'todo_write')).toBe(false)
|
||||
})
|
||||
|
||||
it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/inject/apply', () => {
|
||||
// Postmortem 0001 guard: this plugin HAS `inject = ['tools']`, so a stray
|
||||
// `export default apply` would collapse the module via `unwrapExports`
|
||||
// (`exports.default ?? exports`), DROP `inject`, and crash at load with
|
||||
// "cannot get property … without inject". Guard the shape directly.
|
||||
expect('default' in tool).toBe(false)
|
||||
expect(tool.name).toBe('tool-todo')
|
||||
expect(tool.inject).toEqual(['tools'])
|
||||
|
||||
const loader = Object.create(Loader.prototype) as Loader
|
||||
const unwrapped = loader.unwrapExports(tool) as Record<string, unknown>
|
||||
expect(unwrapped).toBe(tool)
|
||||
expect(unwrapped.name).toBe('tool-todo')
|
||||
expect(unwrapped.inject).toEqual(['tools'])
|
||||
expect(typeof unwrapped.apply).toBe('function')
|
||||
})
|
||||
})
|
||||
27
packages/todo/tool-todo/tsconfig.json
Normal file
27
packages/todo/tool-todo/tsconfig.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"extends": "../../../tsconfig.base.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "lib/types"
|
||||
},
|
||||
"include": [
|
||||
"src"
|
||||
],
|
||||
"references": [
|
||||
{
|
||||
"path": "../../../vendor/cosmokit"
|
||||
},
|
||||
{
|
||||
"path": "../../../vendor/cordis"
|
||||
},
|
||||
{
|
||||
"path": "../../core/tools"
|
||||
},
|
||||
{
|
||||
"path": "../../core/agent"
|
||||
},
|
||||
{
|
||||
"path": "../../core/session"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -10,4 +10,4 @@ Integrations that expose the agent to an external editor or client. These are **
|
||||
|
||||
A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The readline `ui-stdio` plugin is the unstructured analogue but lives in `support/` because it exists chiefly for the examples and the coverage gate — `ui/` is reserved for surfaces shipped as product.
|
||||
|
||||
`stdio-agent` and `acp-agent` are the two **app packages**: each composes the [`core/agent-core`](../core/agent-core/README.md) spine with its coupled front-door cluster (and owns the boot `bin`), so a leaf `cordis.yml` is just the swappable backends plus one app entry. They live in `ui/` because each IS a user-facing front door; the stdout-purity coupling (logger vs. no logger) becomes a property of the artifact rather than a leaf convention.
|
||||
`stdio-agent` and `acp-agent` are the two **app packages**: each composes the [`core/agent-core`](../core/agent-core/README.md) spine with its coupled front-door cluster (and owns the boot `bin`), so a leaf `cordis.yml` is the swappable backends plus one app entry plus any optional product tools. They live in `ui/` because each IS a user-facing front door; the stdout-purity coupling (logger vs. no logger) becomes a property of the artifact rather than a leaf convention.
|
||||
|
||||
@@ -14,11 +14,12 @@
|
||||
* which this app does not prevent — so the rule "never add a stdout logger to an
|
||||
* ACP leaf" still stands; the app just gives the leaf nothing to misconfigure.)
|
||||
*
|
||||
* The leaf supplies only the swappable backends: the LLM adapter (`llm-deepseek`
|
||||
* for the real model, `llm-replay` for keyless snapshot replay) and the bash
|
||||
* executor (`bash-local`). This app's {@link Config} (model, system prompt,
|
||||
* persistence root) routes each value to where it is wired — model/prompt onto
|
||||
* the bridge's per-session agent template, the root onto the JSONL backend.
|
||||
* The leaf supplies the swappable backends: the LLM adapter (`llm-deepseek` for
|
||||
* the real model, `llm-replay` for keyless snapshot replay), the bash executor
|
||||
* (`bash-local`), and any optional product tools it wants to expose. This app's
|
||||
* {@link Config} (model, system prompt, persistence root) routes each value to
|
||||
* where it is wired — model/prompt onto the bridge's per-session agent
|
||||
* template, the root onto the JSONL backend.
|
||||
*
|
||||
* Plugin export shape: named `name`/`Config`/`apply`, NO default export — the
|
||||
* cordis Loader's `unwrapExports` does `exports.default ?? exports`, so a stray
|
||||
|
||||
@@ -44,6 +44,7 @@
|
||||
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-bash": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-todo": "workspace:^",
|
||||
"@deepseek-ai/dsh-tools": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
}
|
||||
|
||||
@@ -53,6 +53,8 @@ import {
|
||||
type LoadSessionResponse,
|
||||
type NewSessionRequest,
|
||||
type NewSessionResponse,
|
||||
type Plan,
|
||||
type PlanEntry,
|
||||
type PromptRequest,
|
||||
type PromptResponse,
|
||||
type SessionNotification,
|
||||
@@ -64,7 +66,7 @@ import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent'
|
||||
import { AgentId } from '@deepseek-ai/dsh-agent'
|
||||
import { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEvent, TodoItem, TurnEndReason } from '@deepseek-ai/dsh-session'
|
||||
import type { ToolCallKind, ToolCallPresentation, ToolRegistry, ToolResultPresentation, ToolTerminal } from '@deepseek-ai/dsh-tools'
|
||||
// Side-effect type import: declaration-merges `ctx.sessionPersistence` onto
|
||||
// Context (the bridge injects it and reads `list()` for load cwd validation).
|
||||
@@ -873,6 +875,10 @@ export function streamSessionEventUpdate(
|
||||
})
|
||||
return
|
||||
}
|
||||
case 'todo/write': {
|
||||
notify({ sessionId, update: { sessionUpdate: 'plan', ...todosToPlan(event.data.todos) } })
|
||||
return
|
||||
}
|
||||
// turn/step boundaries, context/message, steering,
|
||||
// assistant/message — no direct ACP client update.
|
||||
default:
|
||||
@@ -880,6 +886,18 @@ export function streamSessionEventUpdate(
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Map a harness todo list to an ACP `plan` body. ACP's `PlanEntry` requires
|
||||
* `content` + `priority` + `status`, but a {@link TodoItem} carries no priority,
|
||||
* so synthesize a constant `'medium'` on every entry; `status` maps 1:1 (the
|
||||
* harness status triple IS `PlanEntryStatus`). The ACP client REPLACES its whole
|
||||
* plan on each `plan` update, matching the harness's whole-list-replace
|
||||
* semantics, so no per-entry diffing is needed.
|
||||
*/
|
||||
export function todosToPlan(todos: TodoItem[]): Plan {
|
||||
return { entries: todos.map((todo): PlanEntry => ({ content: todo.content, priority: 'medium', status: todo.status })) }
|
||||
}
|
||||
|
||||
/**
|
||||
* Per-connection terminal-rendering context threaded into
|
||||
* {@link streamSessionEventUpdate}: whether the client advertised the
|
||||
|
||||
@@ -20,6 +20,7 @@ import AgentLoop from '@deepseek-ai/dsh-agent-loop'
|
||||
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
|
||||
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
|
||||
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
|
||||
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
|
||||
import {
|
||||
ClientSideConnection,
|
||||
ndJsonStream,
|
||||
@@ -158,6 +159,12 @@ export async function makeBridgeHarness(options: {
|
||||
* implementation over a mock in tests").
|
||||
*/
|
||||
withBash?: boolean
|
||||
/**
|
||||
* Plug the REAL `dsh-tool-todo` tool so a test can drive `todo_write` through
|
||||
* the bridge and assert the resulting `plan` sessionUpdate — the shipping
|
||||
* tool + the bridge's own todo/write→plan mapping, not a stand-in.
|
||||
*/
|
||||
withTodo?: boolean
|
||||
} = { storageDir: '' }): Promise<BridgeHarness> {
|
||||
const adapter = new MockAdapter(options.script ?? [])
|
||||
|
||||
@@ -173,6 +180,9 @@ export async function makeBridgeHarness(options: {
|
||||
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
|
||||
await ctx.plugin(ToolBash)
|
||||
}
|
||||
if (options.withTodo) {
|
||||
await ctx.plugin(ToolTodo)
|
||||
}
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
|
||||
// Two identity byte pipes cross-wired into the two ndJsonStreams: bytes the
|
||||
|
||||
@@ -94,6 +94,44 @@ describe('acp bridge — session/load replay', () => {
|
||||
expect(content[0]?.content.text).toBe('```console\nhello\n```')
|
||||
})
|
||||
|
||||
it('replays a persisted todo/write as a plan sessionUpdate on load', async () => {
|
||||
// A turn whose model called todo_write persists a todo/write event. A fresh
|
||||
// bridge loading the session must re-emit the ACP `plan` update from the log
|
||||
// (the load replay runs every event through streamSessionEventUpdate), so an
|
||||
// editor reopening the session sees the current plan.
|
||||
live = await makeBridgeHarness({
|
||||
storageDir,
|
||||
withTodo: true,
|
||||
script: [
|
||||
toolCallResponse('c1', 'todo_write', {
|
||||
todos: [
|
||||
{ content: 'first step', status: 'in_progress' },
|
||||
{ content: 'second step', status: 'pending' },
|
||||
],
|
||||
}),
|
||||
textResponse('planned'),
|
||||
],
|
||||
})
|
||||
await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
|
||||
const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
|
||||
await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'plan it' }] })
|
||||
await live.dispose()
|
||||
live = undefined
|
||||
|
||||
loader = await makeBridgeHarness({ storageDir, withTodo: true, script: [] })
|
||||
await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
|
||||
await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] })
|
||||
|
||||
const plan = loader.updates.find(u => u.sessionUpdate === 'plan')
|
||||
expect(plan).toEqual({
|
||||
sessionUpdate: 'plan',
|
||||
entries: [
|
||||
{ content: 'first step', priority: 'medium', status: 'in_progress' },
|
||||
{ content: 'second step', priority: 'medium', status: 'pending' },
|
||||
],
|
||||
})
|
||||
})
|
||||
|
||||
it('replays a persisted bash call as a TERMINAL card when the loader advertises the capability', async () => {
|
||||
// The presentation is resolved at replay time, so a loader that advertised
|
||||
// _meta.terminal_output must reconstruct the terminal card (content + _meta)
|
||||
|
||||
@@ -3,7 +3,7 @@ import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionNotification } from '@agentclientprotocol/sdk'
|
||||
import type { ToolDefinition, ToolRegistry } from '@deepseek-ai/dsh-tools'
|
||||
import { streamSessionEventUpdate, agentOptions, ToolPresenter } from '../src/index.ts'
|
||||
import { streamSessionEventUpdate, agentOptions, todosToPlan, ToolPresenter } from '../src/index.ts'
|
||||
|
||||
/** Collect the updates a single event produces (no presenter → generic fallback). */
|
||||
function updatesFor(event: SessionEvent): SessionNotification['update'][] {
|
||||
@@ -118,6 +118,43 @@ describe('streamSessionEventUpdate', () => {
|
||||
expect(updatesFor(evt('turn/end', { turn: 1, reason: { kind: 'completed' } }))).toEqual([])
|
||||
expect(updatesFor(evt('step/start', { turn: 1, step: 1 }))).toEqual([])
|
||||
})
|
||||
|
||||
it('maps todo/write to a plan sessionUpdate with priority synthesized as medium', () => {
|
||||
expect(updatesFor(evt('todo/write', {
|
||||
todos: [
|
||||
{ content: 'plan the work', status: 'in_progress' },
|
||||
{ content: 'write the code', status: 'pending' },
|
||||
{ content: 'run the tests', status: 'completed' },
|
||||
],
|
||||
}))).toEqual([{
|
||||
sessionUpdate: 'plan',
|
||||
entries: [
|
||||
{ content: 'plan the work', priority: 'medium', status: 'in_progress' },
|
||||
{ content: 'write the code', priority: 'medium', status: 'pending' },
|
||||
{ content: 'run the tests', priority: 'medium', status: 'completed' },
|
||||
],
|
||||
}])
|
||||
})
|
||||
|
||||
it('maps an empty todo list to a plan with no entries', () => {
|
||||
expect(updatesFor(evt('todo/write', { todos: [] }))).toEqual([{ sessionUpdate: 'plan', entries: [] }])
|
||||
})
|
||||
})
|
||||
|
||||
describe('todosToPlan', () => {
|
||||
it('maps status 1:1 and stamps every entry priority medium', () => {
|
||||
expect(todosToPlan([
|
||||
{ content: 'a', status: 'pending' },
|
||||
{ content: 'b', status: 'in_progress' },
|
||||
{ content: 'c', status: 'completed' },
|
||||
])).toEqual({
|
||||
entries: [
|
||||
{ content: 'a', priority: 'medium', status: 'pending' },
|
||||
{ content: 'b', priority: 'medium', status: 'in_progress' },
|
||||
{ content: 'c', priority: 'medium', status: 'completed' },
|
||||
],
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
describe('ToolPresenter (tool-owned presentation via the tool registry)', () => {
|
||||
|
||||
@@ -6,9 +6,10 @@
|
||||
*
|
||||
* The cluster is BAKED IN, not left to the leaf: a stdio app always logs to the
|
||||
* console (stdout is just the terminal) and always pre-creates the `main` agent
|
||||
* `ui-stdio` sends to. The leaf supplies only the swappable backends (the LLM
|
||||
* adapter, the bash executor), the optional `hmr` dev-reload plugin, and this
|
||||
* app's {@link Config} (model, prompt, persistence root, welcome banner).
|
||||
* `ui-stdio` sends to. The leaf supplies the swappable backends (the LLM
|
||||
* adapter, the bash executor), optional product tools, the optional `hmr`
|
||||
* dev-reload plugin, and this app's {@link Config} (model, prompt, persistence
|
||||
* root, welcome banner).
|
||||
*
|
||||
* `hmr` is deliberately a LEAF entry, not baked in here: it is a Loader-only,
|
||||
* subprocess-only dev plugin (its constructor throws without `--expose-internals`
|
||||
|
||||
Reference in New Issue
Block a user