feat(tui): select model reasoning effort
This commit is contained in:
Yichen Jiang
@@ -10,7 +10,7 @@ Tracks live agents and carries the initiating Agent through asynchronous driver
|
||||
|
||||
### Public API
|
||||
|
||||
The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `installAgentLlmTarget(agentCtx, target)` snapshots a mutable provider/model selection during prompt assembly and applies that pair to both prompt variables and request routing for one step. `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves.
|
||||
The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `installAgentLlmTarget(agentCtx, target)` snapshots a mutable provider/model/reasoning-effort selection during prompt assembly, applies the route to prompt variables, and applies the complete target to request routing for one step; an absent selected effort clears an inherited effort so the target uses adapter/provider defaults. `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves.
|
||||
|
||||
- `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber.
|
||||
- Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`.
|
||||
|
||||
@@ -1,17 +1,19 @@
|
||||
/**
|
||||
* Agent-scoped provider/model target snapshot shared by interactive front doors.
|
||||
* Agent-scoped LLM target snapshot shared by interactive front doors.
|
||||
* @module @deepseek-ai/dsh-agent/llm-target
|
||||
*/
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
import type { LlmCallConfig } from '@deepseek-ai/dsh-llm'
|
||||
import type { LlmCallConfig, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
|
||||
|
||||
/** Complete provider/model route selected for one live agent. */
|
||||
/** Complete provider/model route and optional reasoning effort selected for one live agent. */
|
||||
export interface AgentLlmTarget {
|
||||
/** Registered provider route. */
|
||||
provider: string
|
||||
/** Provider-owned model id. */
|
||||
model: string
|
||||
/** Adapter-owned reasoning effort, or provider/default behavior when absent. */
|
||||
reasoningEffort?: ReasoningEffortId
|
||||
}
|
||||
|
||||
/** Mutable selection plus the target captured for the current step. */
|
||||
@@ -24,9 +26,11 @@ export interface AgentLlmTargetRef {
|
||||
|
||||
/**
|
||||
* Couple one mutable target to agent-scoped prompt assembly and request routing.
|
||||
* Prompt assembly snapshots the selected pair before delegating, then applies
|
||||
* both prompt variables and request config to that snapshot so a concurrent
|
||||
* switch takes effect on a later step instead of splitting the two surfaces.
|
||||
* Prompt assembly snapshots the selected target before delegating, then applies
|
||||
* its route to prompt variables and its route/effort to request config so a
|
||||
* concurrent switch takes effect on a later step instead of splitting the two
|
||||
* surfaces. An absent selected effort clears any inherited effort so a model
|
||||
* switch can restore that target's provider/default behavior.
|
||||
*
|
||||
* @param agentCtx - The target agent's scoped context.
|
||||
* @param target - Mutable selection owned by the calling front door.
|
||||
@@ -52,10 +56,15 @@ export function installAgentLlmTarget(agentCtx: Context, target: AgentLlmTargetR
|
||||
async (_agent, _turn, _step, _config, _signal, next): Promise<LlmCallConfig> => {
|
||||
const resolved = await next()
|
||||
const selected = target.assembled
|
||||
return selected === undefined ? resolved : {
|
||||
...resolved,
|
||||
if (selected === undefined) return resolved
|
||||
const { reasoningEffort: _inheritedEffort, ...withoutInheritedEffort } = resolved
|
||||
return {
|
||||
...withoutInheritedEffort,
|
||||
provider: selected.provider,
|
||||
model: selected.model,
|
||||
...selected.reasoningEffort === undefined
|
||||
? {}
|
||||
: { reasoningEffort: selected.reasoningEffort },
|
||||
}
|
||||
},
|
||||
)
|
||||
|
||||
@@ -7,7 +7,7 @@ import {
|
||||
type Agent,
|
||||
type AgentLlmTargetRef,
|
||||
} from '../src/index.ts'
|
||||
import type { LlmCallConfig } from '@deepseek-ai/dsh-llm'
|
||||
import { ReasoningEffortId, type LlmCallConfig } from '@deepseek-ai/dsh-llm'
|
||||
|
||||
describe('installAgentLlmTarget()', () => {
|
||||
it('snapshots prompt variables and request routing together, then disposes both listeners', async () => {
|
||||
@@ -24,16 +24,31 @@ describe('installAgentLlmTarget()', () => {
|
||||
'agent/request', 1, 0, seed, signal, () => Promise.resolve(seed),
|
||||
)).resolves.toBe(seed)
|
||||
|
||||
target.current = { provider: 'alpha', model: 'a1' }
|
||||
target.current = {
|
||||
provider: 'alpha',
|
||||
model: 'a1',
|
||||
reasoningEffort: ReasoningEffortId('high'),
|
||||
}
|
||||
expect((await ctx.systemPrompt.assemble()).variables).toMatchObject({ provider: 'alpha', model: 'a1' })
|
||||
target.current = { provider: 'beta', model: 'b1' }
|
||||
await expect(agentEvents(ctx, agent).waterfall(
|
||||
'agent/request', 1, 0, seed, signal, () => Promise.resolve(seed),
|
||||
)).resolves.toEqual({ provider: 'alpha', model: 'a1', temperature: 0.2 })
|
||||
)).resolves.toEqual({
|
||||
provider: 'alpha',
|
||||
model: 'a1',
|
||||
reasoningEffort: ReasoningEffortId('high'),
|
||||
temperature: 0.2,
|
||||
})
|
||||
|
||||
expect((await ctx.systemPrompt.assemble()).variables).toMatchObject({ provider: 'beta', model: 'b1' })
|
||||
const inherited: LlmCallConfig = {
|
||||
provider: 'alpha',
|
||||
model: 'a1',
|
||||
reasoningEffort: ReasoningEffortId('max'),
|
||||
temperature: 0.2,
|
||||
}
|
||||
await expect(agentEvents(ctx, agent).waterfall(
|
||||
'agent/request', 1, 1, seed, signal, () => Promise.resolve(seed),
|
||||
'agent/request', 1, 1, inherited, signal, () => Promise.resolve(inherited),
|
||||
)).resolves.toEqual({ provider: 'beta', model: 'b1', temperature: 0.2 })
|
||||
|
||||
dispose()
|
||||
|
||||
@@ -10,7 +10,7 @@ This package owns interactive terminal presentation and input only. It injects `
|
||||
|
||||
After terminal startup succeeds, the package provides the terminal-local `ctx.tui` extension service. A plugin that injects it can call `openOverlay()` with a component factory and constrained layout options; the host exposes the viewport, semantic theme, display-text escaping, redraw, close, and a lifetime signal, but not the pi-tui tree, terminal, focus controller, or overlay handle. Plugin overlays, the model selector, and user questions share one FIFO modal queue. Each request is an effect of the calling plugin fiber, so unload removes queued work or closes visible work before cleanup settles; terminal shutdown unloads dependents before stopping pi-tui. Overlay state is not logged or replayed. Component code is trusted and may render ANSI styling, but must pass untrusted text through `host.display()`. The [interactive-extension Agent Note](../../../.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md) owns the boundary and rejected alternatives.
|
||||
|
||||
The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the latest `todo/write` plan above the editor, and presents `ctx.userInteraction` questions in a wide bottom-left keyboard panel with progress, numbered options, and aligned descriptions. The latest logged session title becomes the header subtitle, with `welcome` before a title exists, and the terminal window title becomes `<session title> — <configured title>`. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Its idle view compares token-meter pressure with `ctx.llm.resolveModelContext()` for the current route, displays `context unknown` when the adapter has no capacity metadata, and also shows tool-card mode and the current model with reasoning state; while the agent runs, an elapsed working indicator and `esc interrupt` replace that summary. Surface replacement events rebuild the transcript so compacted history does not reappear.
|
||||
The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the latest `todo/write` plan above the editor, and presents `ctx.userInteraction` questions in a wide bottom-left keyboard panel with progress, numbered options, and aligned descriptions. The latest logged session title becomes the header subtitle, with `welcome` before a title exists, and the terminal window title becomes `<session title> — <configured title>`. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Its idle view compares token-meter pressure with `ctx.llm.resolveModelContext()` for the current route, displays `context unknown` when the adapter has no capacity metadata, and also shows tool-card mode plus the current model and any explicitly selected reasoning effort; while the agent runs, an elapsed working indicator and `esc interrupt` replace that summary. Surface replacement events rebuild the transcript so compacted history does not reappear.
|
||||
|
||||
An embedding may provide `TuiRuntime.formatCwd` when its logical workspace label differs from the session's host directory. The override changes only the footer label; tools continue to use the session `cwd`.
|
||||
|
||||
@@ -22,13 +22,13 @@ When optional `ctx.sessionReferences` is mounted, the same `@` menu also offers
|
||||
|
||||
While the agent is running, ordinary editor submissions call `agent.steer()`; otherwise they call `agent.followup()`. A slash at the start of the submitted line enters `ctx.commands` instead: known commands execute directly, unknown commands produce a warning, and neither path automatically reaches the model. A command producer may explicitly schedule agent work; [`dsh-plan-mode`](../../plan/plan-mode/README.md#model-and-human-surfaces) uses that contract for `/plan [message]`. The TUI registers `/help`, `/model`, `/clear`, `/reasoning`, `/tools`, `/redraw`, `/reload`, `/resume`, `/status`, and `/exit` as agent-scoped definitions; every other effective command joins autocomplete and `/help` dynamically, as do `/skill:` completions. A status line above the editor reports the turn phase the TUI derives from session events — waiting for the first token, thinking, responding, or executing tools — with the elapsed time in that phase and the running step total, refreshed each second, and ends with the `Enter sends steering, Esc cancels` hint; while steering messages wait to reach the model it inserts a `N queued ·` badge before the hint that clears as each drains. Ctrl+C or Escape cancels a running turn. Tool cards collapse long bodies into a configurable head/tail preview; Ctrl+O toggles every card between its preview and full output. Ctrl+R toggles reasoning, Ctrl+L redraws, and Ctrl+D exits while idle.
|
||||
|
||||
`/model` opens the advisory `ctx.llm` catalog as a keyboard selector: Up/Down moves, Enter selects, and Escape closes it. `/model <model>` still selects an unambiguous model id directly, while `/model <provider>/<model>` selects an exact target. The configured target or latest logged request header initializes the selector, and an unlisted current model remains visible because catalogs are advisory. Selection is local to this TUI session. Prompt assembly snapshots the target for one step, replaces `{{provider}}` and `{{model}}`, and applies the same pair through `agent/request`; a switch during assembly therefore starts with a later step. The request header durably records targets that reach the model, while an unused selection remains process-local.
|
||||
`/model` opens the advisory `ctx.llm` catalog as a keyboard selector: Up/Down moves, Shift+Tab cycles the focused model's adapter-advertised reasoning efforts in display order, Enter selects the model and effort, and Escape closes it. Models without selectable effort metadata ignore Shift+Tab; the selector does not synthesize `off`, clamp a value, or transfer an effort between models. `/model <model>` still selects an unambiguous model id directly, while `/model <provider>/<model>` selects an exact target and uses its adapter default when one exists. The configured target or latest logged request header initializes the selector, and an unlisted current model remains visible because catalogs are advisory. Selection is local to this TUI session. Prompt assembly snapshots the target for one step, replaces `{{provider}}` and `{{model}}`, and applies the same provider/model/reasoning-effort target through `agent/request`; a switch during assembly therefore starts with a later step. The request header durably records targets that reach the model, while an unused selection remains process-local.
|
||||
|
||||
`/reload` (EXPERIMENTAL, dev-only) re-reads every file-backed loader config tree and applies the diff to the running app — the HMR watcher's config path, invoked manually; it needs the cordis Loader in the context and degrades to a warning without one, runs only while the agent is idle, and refuses re-entry while a reload is in flight. Module-source hot reload remains watcher-owned. When a `skills` service is mounted, `/skill:<name> [instructions]` loads that skill's instructions into the conversation as a user turn; autocomplete lists the model-invocable skills, and any skill (including a model-disabled one) is loadable by its exact name.
|
||||
|
||||
The footer sums the session's reported usage as `↑<uncached input> ↓<output>`, followed by `cache <rate>%` once any input has been billed — the share of billed prompt tokens (uncached input plus cache reads and writes) served from the provider cache, rounded to a percent. It also compares token-meter pressure with `ctx.llm.resolveModelContext()` for the current route (omitting the context share when the adapter has no capacity metadata) and shows the current model and tool-card mode; the right side clips first when the footer is narrow.
|
||||
|
||||
`/status` adds a point-in-time diagnostics card to the transcript and remains available while the agent runs. It reports the session id, title, working directory, selected provider/model, reasoning-block visibility, agent state, event/turn/step/tool-call counts, exact input/output/cache token buckets, KV-cache hit rate, token-meter context use and capacity, creation time, and latest event time. Missing titles, models, cache input, or context capacity are labeled instead of inferred. The card is terminal-only and does not duplicate the compact footer.
|
||||
`/status` adds a point-in-time diagnostics card to the transcript and remains available while the agent runs. It reports the session id, title, working directory, selected provider/model, selected reasoning effort or default behavior, reasoning-block visibility, agent state, event/turn/step/tool-call counts, exact input/output/cache token buckets, KV-cache hit rate, token-meter context use and capacity, creation time, and latest event time. Missing titles, models, cache input, or context capacity are labeled instead of inferred. The card is terminal-only and does not duplicate the compact footer.
|
||||
|
||||
`/resume` opens a full-viewport keyboard selector over the current workspace instead of a centered dialog. Its focused search field starts immediately after the search glyph and emits pi-tui's cursor marker, so terminal IME composition remains anchored inside the field. Candidates are sorted by last logged activity and searchable by log-backed title or session id; each row reports current/live/persisted state, last turn outcome, recent provider/model, and durable goal phase when present. Up/Down and Page Up/Page Down navigate, Enter resumes, Escape clears a non-empty search before a second Escape cancels, and Ctrl+C cancels directly. The current session, a session already live in this runtime, an unreadable log, a mismatched cwd, or a session whose logged provider has no current adapter remains visible but disabled. Selection repeats those checks and requires the current agent to be idle before flushing the current session. The TUI then stops the terminal UI and calls the optional host-owned `TuiRuntime.handoffResume`; where `process.execve` is available, the shipped `dsh` host disposes the app and replaces its process. Resume restores the same `SessionId`, transcript, title, todos, and durable goal; goal activation remains disarmed and the TUI asks for human confirmation or `/goal resume`.
|
||||
|
||||
@@ -47,7 +47,7 @@ The footer sums the session's reported usage as `↑<uncached input> ↓<output>
|
||||
| `maxResumeOptions` | `8` | Visible sessions in the resume selector |
|
||||
| `questionDialogWidth` | `200` | Question-panel width in columns, clamped to the terminal |
|
||||
| `questionDialogMaxHeight` | `20` | Question-panel maximum rows |
|
||||
| `modelDialogWidth` | `72` | Model-selector width in columns |
|
||||
| `modelDialogWidth` | `76` | Model-selector width in columns |
|
||||
| `modelDialogMaxHeight` | `20` | Model-selector maximum rows |
|
||||
| `fileSearchMaxResults` | `20` | Maximum file and directory candidates shown for one `@` query |
|
||||
| `fileSearchMaxEntries` | `10000` | Maximum paths retained in the bounded workspace index used by bare fuzzy queries |
|
||||
@@ -114,7 +114,7 @@ The fixed instruction is part of the stable system-prompt prefix and is reusable
|
||||
|
||||
#### What the model sees
|
||||
|
||||
The `/model` command text and keyboard-selector input are not logged or sent. New steps receive the selected provider/model pair in both prompt variables and request routing.
|
||||
The `/model` command text and keyboard-selector input are not logged or sent. New steps receive the selected provider/model route in prompt variables and the selected provider/model/reasoning-effort target in request routing.
|
||||
|
||||
#### Token effect
|
||||
|
||||
|
||||
@@ -31,6 +31,7 @@ import {
|
||||
type EditorTheme,
|
||||
type Focusable,
|
||||
type MarkdownTheme,
|
||||
type SelectItem,
|
||||
type SelectListTheme,
|
||||
type SlashCommand,
|
||||
type Terminal,
|
||||
@@ -53,6 +54,8 @@ import { assertNever, errorChain } from '@deepseek-ai/dsh-llm'
|
||||
import type {
|
||||
ContentBlock,
|
||||
LlmModelInfo,
|
||||
LlmModelReasoningInfo,
|
||||
ReasoningEffortId,
|
||||
StreamChunk,
|
||||
TokenUsage,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
@@ -233,7 +236,7 @@ const maxModelOptionsSchema = z.number().step(1).min(1).default(8)
|
||||
const maxResumeOptionsSchema = z.number().step(1).min(1).default(8)
|
||||
const questionDialogWidthSchema = z.number().step(1).min(20).default(200)
|
||||
const questionDialogMaxHeightSchema = z.number().step(1).min(6).default(20)
|
||||
const modelDialogWidthSchema = z.number().step(1).min(20).default(72)
|
||||
const modelDialogWidthSchema = z.number().step(1).min(20).default(76)
|
||||
const modelDialogMaxHeightSchema = z.number().step(1).min(6).default(20)
|
||||
const fileSearchMaxResultsSchema = z.number().step(1).min(1).default(DEFAULT_FILE_SEARCH_MAX_RESULTS)
|
||||
const fileSearchMaxEntriesSchema = z.number().step(1).min(1).default(DEFAULT_FILE_SEARCH_MAX_ENTRIES)
|
||||
@@ -356,7 +359,7 @@ export function resolveTuiConfig(config: TuiConfig | undefined): ResolvedTuiConf
|
||||
maxResumeOptions: config?.maxResumeOptions ?? 8,
|
||||
questionDialogWidth: config?.questionDialogWidth ?? 200,
|
||||
questionDialogMaxHeight: config?.questionDialogMaxHeight ?? 20,
|
||||
modelDialogWidth: config?.modelDialogWidth ?? 72,
|
||||
modelDialogWidth: config?.modelDialogWidth ?? 76,
|
||||
modelDialogMaxHeight: config?.modelDialogMaxHeight ?? 20,
|
||||
fileSearchMaxResults: config?.fileSearchMaxResults ?? DEFAULT_FILE_SEARCH_MAX_RESULTS,
|
||||
fileSearchMaxEntries: config?.fileSearchMaxEntries ?? DEFAULT_FILE_SEARCH_MAX_ENTRIES,
|
||||
@@ -580,15 +583,34 @@ function textBlocks(content: readonly ContentBlock[], type: 'text' | 'reasoning'
|
||||
interface ModelChoice extends AgentLlmTarget {
|
||||
modelName: string
|
||||
description?: string
|
||||
reasoning?: LlmModelReasoningInfo
|
||||
}
|
||||
|
||||
function targetLabel(target: AgentLlmTarget): string {
|
||||
return `${target.provider}/${target.model}`
|
||||
}
|
||||
|
||||
function compactTargetLabel(target: AgentLlmTarget): string {
|
||||
return `${target.model}${target.reasoningEffort === undefined ? '' : ` ${target.reasoningEffort}`}`
|
||||
}
|
||||
|
||||
function targetReasoningLabel(choice: ModelChoice, effort: ReasoningEffortId | undefined): string | undefined {
|
||||
if (effort === undefined) return choice.reasoning === undefined ? undefined : 'provider default'
|
||||
return choice.reasoning?.efforts.find(candidate => candidate.id === effort)?.name ?? effort
|
||||
}
|
||||
|
||||
function initialTarget(agent: Agent): AgentLlmTarget | undefined {
|
||||
const logged = agent.session.requestHeader()?.config
|
||||
if (logged !== undefined) return { provider: logged.provider, model: logged.model }
|
||||
if (logged !== undefined) {
|
||||
if (logged.reasoningEffort === undefined) {
|
||||
return { provider: logged.provider, model: logged.model }
|
||||
}
|
||||
return {
|
||||
provider: logged.provider,
|
||||
model: logged.model,
|
||||
reasoningEffort: logged.reasoningEffort,
|
||||
}
|
||||
}
|
||||
if (agent.options.provider === undefined || agent.options.model === undefined) return undefined
|
||||
return { provider: agent.options.provider, model: agent.options.model }
|
||||
}
|
||||
@@ -607,11 +629,15 @@ async function readModelChoices(
|
||||
) {
|
||||
models.push({ provider: provider.id, id: current.model, name: current.model })
|
||||
}
|
||||
return models.map((model): ModelChoice => ({
|
||||
provider: provider.id,
|
||||
model: model.id,
|
||||
modelName: model.name,
|
||||
...model.description === undefined ? {} : { description: model.description },
|
||||
return Promise.all(models.map(async (model): Promise<ModelChoice> => {
|
||||
const reasoning = await ctx.llm.resolveModelReasoning(provider.id, model.id)
|
||||
return {
|
||||
provider: provider.id,
|
||||
model: model.id,
|
||||
modelName: model.name,
|
||||
...model.description === undefined ? {} : { description: model.description },
|
||||
...reasoning === undefined ? {} : { reasoning },
|
||||
}
|
||||
}))
|
||||
}))
|
||||
return groups.flat()
|
||||
@@ -1226,6 +1252,10 @@ function renderDialog(
|
||||
|
||||
class ModelDialog implements Component {
|
||||
private readonly list: SelectList
|
||||
private readonly items: Map<string, SelectItem>
|
||||
private readonly choices: Map<string, ModelChoice>
|
||||
private readonly efforts: Map<string, ReasoningEffortId | undefined>
|
||||
private readonly currentValue: string | undefined
|
||||
|
||||
constructor(
|
||||
choices: readonly ModelChoice[],
|
||||
@@ -1235,15 +1265,27 @@ class ModelDialog implements Component {
|
||||
done: (choice: ModelChoice) => void,
|
||||
cancel: () => void,
|
||||
) {
|
||||
this.list = new SelectList(choices.map(choice => ({
|
||||
value: targetLabel(choice),
|
||||
label: displayText(targetLabel(choice)),
|
||||
description: [
|
||||
displayText(choice.modelName),
|
||||
...choice.description === undefined ? [] : [displayText(choice.description)],
|
||||
...current?.provider === choice.provider && current.model === choice.model ? ['current'] : [],
|
||||
].join(' — '),
|
||||
})), maxVisible, dialogSelectTheme(palette))
|
||||
this.items = new Map()
|
||||
this.choices = new Map()
|
||||
this.efforts = new Map()
|
||||
this.currentValue = current === undefined ? undefined : targetLabel(current)
|
||||
for (const choice of choices) {
|
||||
const value = targetLabel(choice)
|
||||
const isCurrent = current?.provider === choice.provider && current.model === choice.model
|
||||
this.choices.set(value, choice)
|
||||
this.efforts.set(
|
||||
value,
|
||||
isCurrent
|
||||
? current.reasoningEffort ?? choice.reasoning?.defaultEffort
|
||||
: choice.reasoning?.defaultEffort,
|
||||
)
|
||||
this.items.set(value, {
|
||||
value,
|
||||
label: displayText(value),
|
||||
description: this.describeChoice(choice, isCurrent),
|
||||
})
|
||||
}
|
||||
this.list = new SelectList([...this.items.values()], maxVisible, dialogSelectTheme(palette))
|
||||
const currentIndex = current === undefined
|
||||
? 0
|
||||
: choices.findIndex(choice => choice.provider === current.provider && choice.model === current.model)
|
||||
@@ -1252,17 +1294,57 @@ class ModelDialog implements Component {
|
||||
const selected = choices.find(choice => targetLabel(choice) === item.value)
|
||||
/* v8 ignore next -- SelectList only returns values built from `choices`. */
|
||||
if (selected === undefined) return
|
||||
done(selected)
|
||||
const effort = this.efforts.get(item.value)
|
||||
done({
|
||||
...selected,
|
||||
...effort === undefined ? {} : { reasoningEffort: effort },
|
||||
})
|
||||
}
|
||||
this.list.onCancel = cancel
|
||||
}
|
||||
|
||||
private describeChoice(choice: ModelChoice, isCurrent: boolean): string {
|
||||
const selectedEffort = this.efforts.get(targetLabel(choice))
|
||||
const effort = choice.reasoning?.efforts.find(candidate => candidate.id === selectedEffort)
|
||||
const effortLabel = selectedEffort === undefined
|
||||
? choice.reasoning === undefined ? undefined : 'provider default'
|
||||
: effort?.name ?? selectedEffort
|
||||
return [
|
||||
displayText(choice.modelName),
|
||||
...choice.description === undefined ? [] : [displayText(choice.description)],
|
||||
...effortLabel === undefined ? [] : [displayText(effortLabel)],
|
||||
...isCurrent ? ['current'] : [],
|
||||
].join(' — ')
|
||||
}
|
||||
|
||||
private cycleReasoningEffort(): void {
|
||||
const selectedItem = this.list.getSelectedItem()
|
||||
/* v8 ignore next -- the dialog is opened only for a non-empty catalog. */
|
||||
if (selectedItem === null) return
|
||||
const choice = this.choices.get(selectedItem.value)
|
||||
if (choice?.reasoning === undefined) return
|
||||
const current = this.efforts.get(selectedItem.value)
|
||||
const currentIndex = choice.reasoning.efforts.findIndex(effort => effort.id === current)
|
||||
const next = choice.reasoning.efforts[(currentIndex + 1) % choice.reasoning.efforts.length]
|
||||
/* v8 ignore next -- validated reasoning metadata always carries at least one effort. */
|
||||
if (next === undefined) return
|
||||
this.efforts.set(selectedItem.value, next.id)
|
||||
const item = this.items.get(selectedItem.value)
|
||||
/* v8 ignore next -- items and choices are constructed from the same values. */
|
||||
if (item === undefined) return
|
||||
item.description = this.describeChoice(choice, selectedItem.value === this.currentValue)
|
||||
}
|
||||
|
||||
invalidate(): void {
|
||||
this.list.invalidate()
|
||||
}
|
||||
|
||||
handleInput(data: string): void {
|
||||
this.list.handleInput(data)
|
||||
if (matchesKey(data, Key.shift(Key.tab))) {
|
||||
this.cycleReasoningEffort()
|
||||
} else {
|
||||
this.list.handleInput(data)
|
||||
}
|
||||
this.invalidate()
|
||||
}
|
||||
|
||||
@@ -1271,7 +1353,7 @@ class ModelDialog implements Component {
|
||||
return renderDialog('Select model', [
|
||||
...this.list.render(innerWidth),
|
||||
'',
|
||||
this.palette.dim('↑/↓ navigate • Enter select • Esc cancel'),
|
||||
this.palette.dim('↑/↓ navigate • Shift+Tab reasoning • Enter select • Esc cancel'),
|
||||
], width, this.palette)
|
||||
}
|
||||
}
|
||||
@@ -1938,7 +2020,7 @@ export function createTuiChat(
|
||||
() => sessionTitle ?? config.welcome,
|
||||
palette,
|
||||
resolved.color && resolved.truecolor,
|
||||
() => target.current?.model,
|
||||
() => target.current === undefined ? undefined : compactTargetLabel(target.current),
|
||||
)
|
||||
const footer = new FooterComponent(
|
||||
agent,
|
||||
@@ -1946,7 +2028,7 @@ export function createTuiChat(
|
||||
() => toolsExpanded,
|
||||
() => tokens,
|
||||
runtime.formatCwd,
|
||||
() => target.current?.model,
|
||||
() => target.current === undefined ? undefined : compactTargetLabel(target.current),
|
||||
() => contextWindow === undefined
|
||||
? undefined
|
||||
: Math.min(100, Math.round(ctx.tokenMeter.measure(agent.session).totalTokens / contextWindow * 100)),
|
||||
@@ -2037,13 +2119,26 @@ export function createTuiChat(
|
||||
resolveContextWindow(target.current)
|
||||
|
||||
const selectModel = (selected: ModelChoice): void => {
|
||||
if (target.current?.provider === selected.provider && target.current.model === selected.model) {
|
||||
appendNotice(`Model is already ${targetLabel(selected)}.`)
|
||||
const sameRoute = target.current?.provider === selected.provider && target.current.model === selected.model
|
||||
const reasoningEffort = selected.reasoningEffort
|
||||
?? (sameRoute ? target.current?.reasoningEffort ?? selected.reasoning?.defaultEffort : selected.reasoning?.defaultEffort)
|
||||
if (sameRoute && target.current?.reasoningEffort === reasoningEffort) {
|
||||
const reasoning = targetReasoningLabel(selected, reasoningEffort)
|
||||
appendNotice(`Model is already ${targetLabel(selected)}${reasoning === undefined ? '' : ` with reasoning effort ${displayText(reasoning)}`}.`)
|
||||
return
|
||||
}
|
||||
target.current = { provider: selected.provider, model: selected.model }
|
||||
target.current = {
|
||||
provider: selected.provider,
|
||||
model: selected.model,
|
||||
...reasoningEffort === undefined ? {} : { reasoningEffort },
|
||||
}
|
||||
resolveContextWindow(target.current)
|
||||
appendNotice(`Model selected: ${targetLabel(selected)}. New steps will use it.`)
|
||||
const reasoning = targetReasoningLabel(selected, reasoningEffort)
|
||||
appendNotice([
|
||||
`Model selected: ${targetLabel(selected)}.`,
|
||||
...reasoning === undefined ? [] : [`Reasoning effort: ${displayText(reasoning)}.`],
|
||||
'New steps will use it.',
|
||||
].join(' '))
|
||||
}
|
||||
|
||||
const showModelSelector = (choices: readonly ModelChoice[]): void => {
|
||||
@@ -2633,12 +2728,17 @@ export function createTuiChat(
|
||||
const steps = events.filter(event => event.type === 'step/start').length
|
||||
const toolCalls = events.filter(event => event.type === 'tool/call').length
|
||||
const model = target.current === undefined ? 'unset' : displayText(targetLabel(target.current))
|
||||
const effort = target.current === undefined
|
||||
? 'unset'
|
||||
: target.current.reasoningEffort === undefined
|
||||
? 'default'
|
||||
: displayText(target.current.reasoningEffort)
|
||||
const groups: readonly (readonly StatusCardRow[])[] = [
|
||||
[
|
||||
['Session', displayText(agent.session.id)],
|
||||
['Title', displayText(sessionTitle ?? 'untitled')],
|
||||
['Directory', displayText(cwd)],
|
||||
['Model', `${model} ${palette.dim(`(reasoning ${showReasoning ? 'shown' : 'hidden'})`)}`],
|
||||
['Model', `${model} ${palette.dim(`(effort ${effort}; reasoning blocks ${showReasoning ? 'shown' : 'hidden'})`)}`],
|
||||
],
|
||||
[
|
||||
['Agent', [
|
||||
|
||||
@@ -8,7 +8,13 @@ import AgentRegistry, {
|
||||
type AgentStatus,
|
||||
type SendOptions,
|
||||
} from '@deepseek-ai/dsh-agent'
|
||||
import type { ContentBlock, LlmModelContext, LlmModelInfo, LlmProviderInfo } from '@deepseek-ai/dsh-llm'
|
||||
import type {
|
||||
ContentBlock,
|
||||
LlmModelContext,
|
||||
LlmModelInfo,
|
||||
LlmModelReasoningInfo,
|
||||
LlmProviderInfo,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import CommandService from '@deepseek-ai/dsh-commands'
|
||||
import SessionStore, { SessionId, type Session, type SessionHeader } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
@@ -48,6 +54,10 @@ export interface TuiHarnessOptions {
|
||||
models: LlmModelInfo[]
|
||||
listModels?: (provider: string) => Promise<LlmModelInfo[]>
|
||||
resolveModelContext?: (provider: string, model: string) => Promise<LlmModelContext | undefined>
|
||||
resolveModelReasoning?: (
|
||||
provider: string,
|
||||
model: string,
|
||||
) => Promise<LlmModelReasoningInfo | undefined>
|
||||
}
|
||||
/** Provide a fake `sessionPersistence` service so resume surfaces can list sessions. */
|
||||
sessionPersistence?: {
|
||||
@@ -122,6 +132,9 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e
|
||||
return catalog.resolveModelContext?.(provider, model)
|
||||
?? Promise.resolve({ contextWindow: options.contextWindow ?? 128_000 })
|
||||
},
|
||||
resolveModelReasoning(provider: string, model: string) {
|
||||
return catalog.resolveModelReasoning?.(provider, model) ?? Promise.resolve(undefined)
|
||||
},
|
||||
} as never)
|
||||
}
|
||||
if (ctx.get('systemPrompt') === undefined) await ctx.plugin(SystemPrompt)
|
||||
|
||||
@@ -0,0 +1,42 @@
|
||||
terminal 92x32 buffer=normal length=32 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "DSH snapshot"
|
||||
cursor hidden column=92 viewportRow=15 bufferRow=15
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-blue bold
|
||||
style 10-16 bold
|
||||
1| " Snapshot agent ready."
|
||||
style 1-21 fg=bright-black
|
||||
2| " deepseek-v4-flash • main-session"
|
||||
style 1-34 dim
|
||||
3| "────────────────────────────────────────────────────────────────────────────────────────────"
|
||||
style 0-91 dim
|
||||
4| " "
|
||||
style 1-1 inverse
|
||||
5| "────────────────────────────────────────────────────────────────────────────────────────────"
|
||||
style 0-91 dim
|
||||
6| "deepseek-v4-flash /workspace/project ↑0 ↓0 0% context tools:collapsed"
|
||||
style 0-43 dim
|
||||
style 65-91 dim
|
||||
7-12| <blank>
|
||||
13| " ╭ Select model ────────────────────────────────────────────────────────────╮ "
|
||||
style 8-83 fg=bright-blue
|
||||
14| " │ deepseek/deepseek-v4-flash DeepSeek V4 Flash — High — current │ "
|
||||
style 8-8 fg=bright-blue
|
||||
style 38-77 fg=bright-black
|
||||
style 83-83 fg=bright-blue
|
||||
15| " │ → deepseek/deepseek-v4-pro DeepSeek V4 Pro — Max │ "
|
||||
style 8-8 fg=bright-blue
|
||||
style 10-64 fg=bright-blue inverse
|
||||
style 83-83 fg=bright-blue
|
||||
16| " │ │ "
|
||||
style 8-8 fg=bright-blue
|
||||
style 83-83 fg=bright-blue
|
||||
17| " │ ↑/↓ navigate • Shift+Tab reasoning • Enter select • Esc cancel │ "
|
||||
style 8-8 fg=bright-blue
|
||||
style 10-71 dim
|
||||
style 83-83 fg=bright-blue
|
||||
18| " ╰──────────────────────────────────────────────────────────────────────────╯ "
|
||||
style 8-83 fg=bright-blue
|
||||
19-31| <blank>
|
||||
@@ -20,23 +20,23 @@ buffer
|
||||
style 0-43 dim
|
||||
style 65-91 dim
|
||||
7-12| <blank>
|
||||
13| " ╭ Select model ────────────────────────────────────────────────────────╮ "
|
||||
style 10-81 fg=bright-blue
|
||||
14| " │ → deepseek/deepseek-v4-flash DeepSeek V4 Flash — current │ "
|
||||
style 10-10 fg=bright-blue
|
||||
style 12-72 fg=bright-blue inverse
|
||||
style 81-81 fg=bright-blue
|
||||
15| " │ deepseek/deepseek-v4-pro DeepSeek V4 Pro │ "
|
||||
style 10-10 fg=bright-blue
|
||||
style 38-60 fg=bright-black
|
||||
style 81-81 fg=bright-blue
|
||||
16| " │ │ "
|
||||
style 10-10 fg=bright-blue
|
||||
style 81-81 fg=bright-blue
|
||||
17| " │ ↑/↓ navigate • Enter select • Esc cancel │ "
|
||||
style 10-10 fg=bright-blue
|
||||
style 12-51 dim
|
||||
style 81-81 fg=bright-blue
|
||||
18| " ╰──────────────────────────────────────────────────────────────────────╯ "
|
||||
style 10-81 fg=bright-blue
|
||||
13| " ╭ Select model ────────────────────────────────────────────────────────────╮ "
|
||||
style 8-83 fg=bright-blue
|
||||
14| " │ → deepseek/deepseek-v4-flash DeepSeek V4 Flash — High — current │ "
|
||||
style 8-8 fg=bright-blue
|
||||
style 10-77 fg=bright-blue inverse
|
||||
style 83-83 fg=bright-blue
|
||||
15| " │ deepseek/deepseek-v4-pro DeepSeek V4 Pro — High │ "
|
||||
style 8-8 fg=bright-blue
|
||||
style 36-65 fg=bright-black
|
||||
style 83-83 fg=bright-blue
|
||||
16| " │ │ "
|
||||
style 8-8 fg=bright-blue
|
||||
style 83-83 fg=bright-blue
|
||||
17| " │ ↑/↓ navigate • Shift+Tab reasoning • Enter select • Esc cancel │ "
|
||||
style 8-8 fg=bright-blue
|
||||
style 10-71 dim
|
||||
style 83-83 fg=bright-blue
|
||||
18| " ╰──────────────────────────────────────────────────────────────────────────╯ "
|
||||
style 8-83 fg=bright-blue
|
||||
19-31| <blank>
|
||||
|
||||
@@ -8,18 +8,18 @@ buffer
|
||||
style 10-16 bold
|
||||
1| " Snapshot agent ready."
|
||||
style 1-21 fg=bright-black
|
||||
2| " deepseek-v4-pro • main-session"
|
||||
style 1-32 dim
|
||||
2| " deepseek-v4-pro max • main-session"
|
||||
style 1-36 dim
|
||||
3| <blank>
|
||||
4| " Model selected: deepseek/deepseek-v4-pro. New steps will use it. "
|
||||
style 1-64 fg=bright-black
|
||||
4| " Model selected: deepseek/deepseek-v4-pro. Reasoning effort: Max. New steps will use it. "
|
||||
style 1-87 fg=bright-black
|
||||
5| "────────────────────────────────────────────────────────────────────────────────────────────"
|
||||
style 0-91 dim
|
||||
6| " "
|
||||
style 1-1 inverse
|
||||
7| "────────────────────────────────────────────────────────────────────────────────────────────"
|
||||
style 0-91 dim
|
||||
8| "deepseek-v4-pro /workspace/project ↑0 ↓0 0% context tools:collapsed"
|
||||
style 0-41 dim
|
||||
8| "deepseek-v4-pro max /workspace/project ↑0 ↓0 0% context tools:collapsed"
|
||||
style 0-45 dim
|
||||
style 65-91 dim
|
||||
9-31| <blank>
|
||||
|
||||
@@ -41,13 +41,13 @@ buffer
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 55-55 dim
|
||||
16| "│ Model: deepseek/deepseek-v4-pro (reasoning │"
|
||||
16| "│ Model: deepseek/deepseek-v4-pro (effort │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 40-55 dim
|
||||
17| "│ shown) │"
|
||||
17| "│ default; reasoning blocks shown) │"
|
||||
style 0-0 dim
|
||||
style 15-20 dim
|
||||
style 15-46 dim
|
||||
style 55-55 dim
|
||||
18| "│ │"
|
||||
style 0-0 dim
|
||||
|
||||
@@ -25,68 +25,68 @@ buffer
|
||||
style 1-9 fg=bright-magenta bold
|
||||
10| " Session inspected. "
|
||||
11| <blank>
|
||||
12| "╭─ Session status ─────────────────────────────────────────────────╮"
|
||||
12| "╭─ Session status ───────────────────────────────────────────────────────────────╮"
|
||||
style 0-2 dim
|
||||
style 3-16 fg=bright-blue bold
|
||||
style 17-67 dim
|
||||
13| "│ Session: main-session │"
|
||||
style 17-81 dim
|
||||
13| "│ Session: main-session │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 67-67 dim
|
||||
14| "│ Title: Inspect session diagnostics │"
|
||||
style 81-81 dim
|
||||
14| "│ Title: Inspect session diagnostics │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 67-67 dim
|
||||
15| "│ Directory: /workspace/project │"
|
||||
style 81-81 dim
|
||||
15| "│ Directory: /workspace/project │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 67-67 dim
|
||||
16| "│ Model: deepseek/deepseek-v4-pro (reasoning shown) │"
|
||||
style 81-81 dim
|
||||
16| "│ Model: deepseek/deepseek-v4-pro (effort default; reasoning blocks shown) │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 40-56 dim
|
||||
style 67-67 dim
|
||||
17| "│ │"
|
||||
style 40-79 dim
|
||||
style 81-81 dim
|
||||
17| "│ │"
|
||||
style 0-0 dim
|
||||
style 67-67 dim
|
||||
18| "│ Agent: idle · 6 events · 1 turn · 1 step · 1 tool call │"
|
||||
style 81-81 dim
|
||||
18| "│ Agent: idle · 6 events · 1 turn · 1 step · 1 tool call │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 67-67 dim
|
||||
19| "│ │"
|
||||
style 81-81 dim
|
||||
19| "│ │"
|
||||
style 0-0 dim
|
||||
style 67-67 dim
|
||||
20| "│ Tokens: 1,250 input + 340 output │"
|
||||
style 81-81 dim
|
||||
20| "│ Tokens: 1,250 input + 340 output │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 67-67 dim
|
||||
21| "│ KV cache: [███████████░░░░░] 67% hit (3,000 read + 250 write) │"
|
||||
style 81-81 dim
|
||||
21| "│ KV cache: [███████████░░░░░] 67% hit (3,000 read + 250 write) │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 15-15 dim
|
||||
style 16-26 fg=bright-blue
|
||||
style 27-32 dim
|
||||
style 67-67 dim
|
||||
22| "│ Context: [█████░░░░░░░░░░░] 33% used (42,000 / 128,000) │"
|
||||
style 81-81 dim
|
||||
22| "│ Context: [█████░░░░░░░░░░░] 33% used (42,000 / 128,000) │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 15-15 dim
|
||||
style 16-20 fg=bright-blue
|
||||
style 21-32 dim
|
||||
style 67-67 dim
|
||||
23| "│ │"
|
||||
style 81-81 dim
|
||||
23| "│ │"
|
||||
style 0-0 dim
|
||||
style 67-67 dim
|
||||
24| "│ Created: 2026-07-22 09:10:11 UTC │"
|
||||
style 81-81 dim
|
||||
24| "│ Created: 2026-07-22 09:10:11 UTC │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 67-67 dim
|
||||
25| "│ Active: 2026-07-22 09:10:11 UTC │"
|
||||
style 81-81 dim
|
||||
25| "│ Active: 2026-07-22 09:10:11 UTC │"
|
||||
style 0-0 dim
|
||||
style 3-12 fg=bright-black
|
||||
style 67-67 dim
|
||||
26| "╰──────────────────────────────────────────────────────────────────╯"
|
||||
style 0-67 dim
|
||||
style 81-81 dim
|
||||
26| "╰────────────────────────────────────────────────────────────────────────────────╯"
|
||||
style 0-81 dim
|
||||
27| "────────────────────────────────────────────────────────────────────────────────────────────"
|
||||
style 0-91 dim
|
||||
28| " "
|
||||
|
||||
@@ -5,7 +5,7 @@ import { fileURLToPath } from 'node:url'
|
||||
import { afterAll, describe, expect, it, vi } from 'vitest'
|
||||
import type { Context } from 'cordis'
|
||||
import { agentEvents } from '@deepseek-ai/dsh-agent'
|
||||
import { CallId, type ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, ReasoningEffortId, type ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import type {} from '@deepseek-ai/dsh-llm-retry'
|
||||
import { SessionId, type JsonValue, type Session } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
@@ -45,6 +45,7 @@ const CHECKPOINTS = [
|
||||
'surface-after-compaction-narrow',
|
||||
'surface-after-compaction-wide',
|
||||
'model-selector',
|
||||
'model-effort-switching',
|
||||
'model-switching',
|
||||
'errors-and-help',
|
||||
'disposed-terminal',
|
||||
@@ -632,7 +633,22 @@ describe('TUI terminal-state snapshots', () => {
|
||||
})
|
||||
|
||||
it('pins the model selector and selection notice', async () => {
|
||||
const harness = await setupSnapshot({}, { columns: 92, rows: 32 })
|
||||
const harness = await setupSnapshot({
|
||||
catalog: {
|
||||
providers: [{ id: 'deepseek', name: 'DeepSeek' }],
|
||||
models: [
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-flash', name: 'DeepSeek V4 Flash' },
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-pro', name: 'DeepSeek V4 Pro' },
|
||||
],
|
||||
resolveModelReasoning: () => Promise.resolve({
|
||||
efforts: [
|
||||
{ id: ReasoningEffortId('high'), name: 'High' },
|
||||
{ id: ReasoningEffortId('max'), name: 'Max' },
|
||||
],
|
||||
defaultEffort: ReasoningEffortId('high'),
|
||||
}),
|
||||
},
|
||||
}, { columns: 92, rows: 32 })
|
||||
await renderAfter(harness, () => {
|
||||
harness.terminal.send('/model')
|
||||
harness.terminal.send('\r')
|
||||
@@ -640,6 +656,10 @@ describe('TUI terminal-state snapshots', () => {
|
||||
await checkpoint('model-selector', harness.terminal, { includeScrollback: true })
|
||||
await renderAfter(harness, () => {
|
||||
harness.terminal.send('\x1b[B')
|
||||
harness.terminal.send('\x1b[Z')
|
||||
})
|
||||
await checkpoint('model-effort-switching', harness.terminal, { includeScrollback: true })
|
||||
await renderAfter(harness, () => {
|
||||
harness.terminal.send('\r')
|
||||
})
|
||||
await checkpoint('model-switching', harness.terminal, { includeScrollback: true })
|
||||
|
||||
@@ -5,7 +5,7 @@ import { describe, expect, it, vi } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { CombinedAutocompleteProvider, type Terminal } from '@earendil-works/pi-tui'
|
||||
import AgentRegistry, { agentEvents, assembleContextFor, AgentMessageId, type Agent } from '@deepseek-ai/dsh-agent'
|
||||
import { type LlmCallConfig } from '@deepseek-ai/dsh-llm'
|
||||
import { ReasoningEffortId, type LlmCallConfig } from '@deepseek-ai/dsh-llm'
|
||||
import { GOAL_CHANGE_VERSION, GoalId, renderGoalChange, type GoalSnapshotChangeMeta } from '@deepseek-ai/dsh-goal'
|
||||
import CommandService, { type CommandInvocation } from '@deepseek-ai/dsh-commands'
|
||||
import SessionStore, { SessionId, type JsonValue, type SessionEvent, type SessionHeader, type TurnEndReason } from '@deepseek-ai/dsh-session'
|
||||
@@ -157,7 +157,7 @@ describe('TUI config', () => {
|
||||
maxResumeOptions: 8,
|
||||
questionDialogWidth: 200,
|
||||
questionDialogMaxHeight: 20,
|
||||
modelDialogWidth: 72,
|
||||
modelDialogWidth: 76,
|
||||
modelDialogMaxHeight: 20,
|
||||
fileSearchMaxResults: 20,
|
||||
fileSearchMaxEntries: 10_000,
|
||||
@@ -1712,7 +1712,8 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
expect(result.terminal.output).toContain('main-session')
|
||||
expect(result.terminal.output).toContain('Inspect status \\x1b]2;unsafe\\x07')
|
||||
expect(result.terminal.output).toContain('/workspace/status')
|
||||
expect(result.terminal.output).toContain('deepseek/deepseek-v4-pro (reasoning hidden)')
|
||||
expect(result.terminal.output).toContain('deepseek/deepseek-v4-pro (effort default; reasoning blocks')
|
||||
expect(result.terminal.output).toContain('hidden)')
|
||||
expect(result.terminal.output).toContain('running · 6 events · 1 turn · 1 step · 2 tool calls')
|
||||
expect(result.terminal.output).toContain('1,250 input + 340 output')
|
||||
expect(result.terminal.output).toContain('[███████████░░░░░] 67% hit (3,000 read + 250 write)')
|
||||
@@ -1748,7 +1749,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
await tick()
|
||||
|
||||
expect(result.terminal.output).toContain('untitled')
|
||||
expect(result.terminal.output).toContain('unset (reasoning shown)')
|
||||
expect(result.terminal.output).toContain('unset (effort unset; reasoning blocks shown)')
|
||||
expect(result.terminal.output).toContain('idle · 0 events · 0 turns · 0 steps · 0 tool calls')
|
||||
expect(result.terminal.output).toContain('n/a (0 read + 0 write)')
|
||||
expect(result.terminal.output).toContain('7 used · capacity unknown')
|
||||
@@ -2301,6 +2302,35 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
resolveModelContext: (provider, model) => provider === 'alpha' && model === 'a1'
|
||||
? initialContext.promise
|
||||
: Promise.resolve({ contextWindow: 200 }),
|
||||
resolveModelReasoning: (provider, model) => {
|
||||
if (model === 'a1') {
|
||||
return Promise.resolve({
|
||||
efforts: [
|
||||
{ id: ReasoningEffortId('low'), name: 'Low' },
|
||||
{ id: ReasoningEffortId('high'), name: 'High' },
|
||||
],
|
||||
defaultEffort: ReasoningEffortId('low'),
|
||||
})
|
||||
}
|
||||
if (model === 'b1') {
|
||||
return Promise.resolve({
|
||||
efforts: [
|
||||
{ id: ReasoningEffortId('high'), name: 'High' },
|
||||
{ id: ReasoningEffortId('max'), name: 'Max' },
|
||||
],
|
||||
defaultEffort: ReasoningEffortId('high'),
|
||||
})
|
||||
}
|
||||
if (provider === 'alpha' && model === 'shared') {
|
||||
return Promise.resolve({
|
||||
efforts: [
|
||||
{ id: ReasoningEffortId('standard'), name: 'Standard' },
|
||||
{ id: ReasoningEffortId('ultra'), name: 'Ultra' },
|
||||
],
|
||||
})
|
||||
}
|
||||
return Promise.resolve(undefined)
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
@@ -2325,6 +2355,62 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
result.terminal.send('\x1b')
|
||||
await tick()
|
||||
|
||||
const providerDefaultOutput = result.terminal.output.length
|
||||
result.terminal.send('/model alpha/shared')
|
||||
result.terminal.send('\r')
|
||||
await vi.waitFor(() => {
|
||||
expect(result.terminal.output.slice(providerDefaultOutput)).toContain('Reasoning effort: provider default.')
|
||||
})
|
||||
result.terminal.send('/model')
|
||||
result.terminal.send('\r')
|
||||
await vi.waitFor(() => {
|
||||
expect(result.terminal.output.slice(providerDefaultOutput)).toContain('Select model')
|
||||
})
|
||||
expect(result.terminal.output.slice(providerDefaultOutput)).toContain('Alpha Shared — provider default')
|
||||
result.terminal.send('\x1b[Z')
|
||||
await tick()
|
||||
expect(result.terminal.output.slice(providerDefaultOutput)).toContain('Alpha Shared — Standard')
|
||||
result.terminal.send('\r')
|
||||
await tick()
|
||||
expect(result.terminal.output.slice(providerDefaultOutput)).toContain('Reasoning effort: Standard.')
|
||||
|
||||
const nonReasoningOutput = result.terminal.output.length
|
||||
result.terminal.send('/model')
|
||||
result.terminal.send('\r')
|
||||
await vi.waitFor(() => {
|
||||
expect(result.terminal.output.slice(nonReasoningOutput)).toContain('Select model')
|
||||
})
|
||||
result.terminal.send('\x1b[B')
|
||||
result.terminal.send('\x1b[B')
|
||||
result.terminal.send('\x1b[Z')
|
||||
result.terminal.send('\r')
|
||||
await tick()
|
||||
expect(result.terminal.output.slice(nonReasoningOutput)).toContain('Model selected: beta/shared.')
|
||||
result.terminal.send('/model beta/shared')
|
||||
result.terminal.send('\r')
|
||||
await vi.waitFor(() => {
|
||||
expect(result.terminal.output.slice(nonReasoningOutput)).toContain('Model is already beta/shared.')
|
||||
})
|
||||
await result.ctx.systemPrompt.assemble(assembleContextFor(result.agent))
|
||||
result.terminal.send('/model alpha/a1')
|
||||
result.terminal.send('\r')
|
||||
await vi.waitFor(() => {
|
||||
expect(result.terminal.output.slice(nonReasoningOutput)).toContain('Reasoning effort: Low.')
|
||||
})
|
||||
const inheritedEffort: LlmCallConfig = {
|
||||
provider: 'alpha',
|
||||
model: 'a1',
|
||||
reasoningEffort: ReasoningEffortId('max'),
|
||||
}
|
||||
await expect(agentEvents(result.ctx, result.agent).waterfall(
|
||||
'agent/request',
|
||||
0,
|
||||
0,
|
||||
inheritedEffort,
|
||||
new AbortController().signal,
|
||||
() => Promise.resolve(inheritedEffort),
|
||||
)).resolves.toEqual({ provider: 'beta', model: 'shared' })
|
||||
|
||||
result.agent.status = 'running'
|
||||
const runningSelectorOutput = result.terminal.output.length
|
||||
result.terminal.send('/model')
|
||||
@@ -2333,13 +2419,18 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
const output = result.terminal.output.slice(runningSelectorOutput)
|
||||
expect(output).toContain('Select model')
|
||||
expect(output).toContain('alpha/a1')
|
||||
expect(output).toContain('Alpha One — Fast — current')
|
||||
expect(output).toContain('Alpha One — Fast — Low — current')
|
||||
expect(output).toContain('Beta One — High')
|
||||
})
|
||||
result.terminal.send('\x1b[B')
|
||||
result.terminal.send('\x1b[B')
|
||||
result.terminal.send('\x1b[Z')
|
||||
await tick()
|
||||
expect(result.terminal.output).toContain('Beta One — Max')
|
||||
result.terminal.send('\r')
|
||||
await tick()
|
||||
expect(result.terminal.output).toContain('Model selected: beta/b1')
|
||||
expect(result.terminal.output).toContain('Reasoning effort: Max.')
|
||||
expect(result.agent.sent).toEqual([])
|
||||
expect(result.agent.steered).toEqual([])
|
||||
initialContext.resolve({ contextWindow: 100 })
|
||||
@@ -2358,8 +2449,12 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
result.agent.status = 'idle'
|
||||
result.ctx.emit('agent/status', result.agent, 'idle')
|
||||
await tick()
|
||||
expect(result.terminal.output).toContain('b1 ')
|
||||
expect(result.terminal.output).toContain('b1 max ')
|
||||
expect(result.terminal.output).toContain('25% context tools:collapsed')
|
||||
result.terminal.send('/status')
|
||||
result.terminal.send('\r')
|
||||
await tick()
|
||||
expect(result.terminal.output).toContain('beta/b1 (effort max; reasoning blocks shown)')
|
||||
|
||||
const assembly = await result.ctx.systemPrompt.assemble(assembleContextFor(result.agent))
|
||||
expect(assembly.variables).toMatchObject({ provider: 'beta', model: 'b1' })
|
||||
@@ -2367,7 +2462,12 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
const request = await agentEvents(result.ctx, result.agent).waterfall(
|
||||
'agent/request', 1, 0, seed, new AbortController().signal, () => Promise.resolve(seed),
|
||||
)
|
||||
expect(request).toEqual({ provider: 'beta', model: 'b1', temperature: 0.2 })
|
||||
expect(request).toEqual({
|
||||
provider: 'beta',
|
||||
model: 'b1',
|
||||
reasoningEffort: ReasoningEffortId('max'),
|
||||
temperature: 0.2,
|
||||
})
|
||||
await dispose(result)
|
||||
})
|
||||
|
||||
@@ -2377,7 +2477,13 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
catalog: { providers: [{ id: 'beta', name: 'Beta' }], models: [] },
|
||||
beforeMount(session) {
|
||||
session.append('request/header', {
|
||||
header: { config: { provider: 'beta', model: 'private' } },
|
||||
header: {
|
||||
config: {
|
||||
provider: 'beta',
|
||||
model: 'private',
|
||||
reasoningEffort: ReasoningEffortId('ultra'),
|
||||
},
|
||||
},
|
||||
reason: 'initial',
|
||||
})
|
||||
},
|
||||
@@ -2387,9 +2493,30 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
await tick()
|
||||
expect(resumed.terminal.output).toContain('Select model')
|
||||
expect(resumed.terminal.output).toContain('beta/private')
|
||||
expect(resumed.terminal.output).toContain('private — current')
|
||||
expect(resumed.terminal.output).toContain('private — ultra — current')
|
||||
resumed.terminal.send('\x1b')
|
||||
await tick()
|
||||
resumed.terminal.send('/model beta/private')
|
||||
resumed.terminal.send('\r')
|
||||
await tick()
|
||||
expect(resumed.terminal.output).toContain('with reasoning effort ultra')
|
||||
await dispose(resumed)
|
||||
|
||||
const resumedDefault = await setup({
|
||||
catalog: {
|
||||
providers: [{ id: 'alpha', name: 'Alpha' }],
|
||||
models: [{ provider: 'alpha', id: 'default', name: 'Default Model' }],
|
||||
},
|
||||
beforeMount(session) {
|
||||
session.append('request/header', {
|
||||
header: { config: { provider: 'alpha', model: 'default' } },
|
||||
reason: 'initial',
|
||||
})
|
||||
},
|
||||
})
|
||||
expect(resumedDefault.terminal.output).toContain('default • main-session')
|
||||
await dispose(resumedDefault)
|
||||
|
||||
const unset = await setup({
|
||||
agentOptions: {},
|
||||
catalog: {
|
||||
@@ -2437,6 +2564,20 @@ describe('pi-tui chat lifecycle and transcript', () => {
|
||||
})
|
||||
expect(failed.terminal.output).toContain('Could not resolve model context: capacity offline')
|
||||
await dispose(failed)
|
||||
|
||||
const reasoningFailed = await setup({
|
||||
catalog: {
|
||||
providers: [{ id: 'deepseek', name: 'DeepSeek' }],
|
||||
models: [{ provider: 'deepseek', id: 'model-1', name: 'Model One' }],
|
||||
resolveModelReasoning: () => Promise.reject(new Error('reasoning metadata offline')),
|
||||
},
|
||||
})
|
||||
reasoningFailed.terminal.send('/model')
|
||||
reasoningFailed.terminal.send('\r')
|
||||
await vi.waitFor(() => {
|
||||
expect(reasoningFailed.terminal.output).toContain('Could not read the model catalog: reasoning metadata offline')
|
||||
})
|
||||
await dispose(reasoningFailed)
|
||||
})
|
||||
|
||||
it('does not render a model catalog that resolves after TUI disposal', async () => {
|
||||
|
||||
Reference in New Issue
Block a user