5.4 KiB
Chat thinking level
A per-chat thinking (reasoning effort) control in the conversation header, beside the model and mode controls: "Thinking: High". Material opens a menu, Cupertino an action sheet; both list only the levels the chat's current (or saved next-turn) model accepts and check the current one. With no levels the control is not shown. It uses the chat's own gateway, so a chat on another machine is set on that machine's server.
Protocol
- Session rows (
chat_sessions,chat_create, session reads) carryeffort(current level,""= harness default),efforts([{id, name, description?}]) anddefault_effort, only when the server knows the row model's levels without starting a harness. chat_modelsentries carryefforts/default_effortper model, and the reply carrieschat_effortwith the chat's current state.chat_effort {session_id, effort}sets a level. The server validates it against the current model's levels; the reply echoes{session_id, effort, efforts, default_effort}. Errors: unsupported harness, model without levels, a level the model does not list.- Levels apply from the next turn. A running turn keeps its level; the menu says so and the wide label reads "Thinking: Low · next turn" until the turn ends.
Per harness
- Codex (app-server 0.164): levels are model/list
supportedReasoningEffortsfor the chat's model (catalog cached for one minute so a list does not read it per row), the default isdefaultReasoningEffort, and the current level is the thread's ownreasoningEffortfrom thread/read unless Pipelines stored one. The stored level is sent as turn/starteffort(which Codex keeps for later turns). Pipelines stores it inoperator_sessions.chat_effort, re-applies it before every turn and after a restart, and/newcopies it. - Claude Code (2.1.319): levels are the initialize models'
supportedEffortLevelswheresupportsEffortis true (Haiku 4.5 has none, so no control). The level is sent with theapply_flag_settingscontrol request ({"effortLevel": level},nullrestores the default) before the next turn, only when the process was told another level. It is session-only and never written to a settings file. Stored and re-applied like Codex. Claude Code's initialize reports no default level, so with none chosen the label reads "Thinking: Default". The levels come from a CLI's initialize: after a server restart, before any Claude chat has started a CLI, rows carry no levels and the control stays hidden until a CLI initializes (opening the model chooser or sending a turn does that). - OpenCode (2.0.x, v2 API): levels are the
/api/modelentry'svariantsfor the session's model. The chosen variant is the session model'svariant, set withPOST /api/session/{id}/model {model:{id, providerID, variant}}, which OpenCode itself persists, so Pipelines stores nothing. A session without one reportsvariant: "default", which is not a listed level and shows as the default. The v1 serve backend has no variants: no control. - A model switch (Codex/Claude) keeps a stored level the new model accepts;
otherwise it becomes the new model's default (or the harness default). The
open control re-reads the levels from
chat_modelsafter a model switch.
Limits
- The create-chat dialog offers no model choice (new chats start on the server default model), so it shows no level either; set it in the header.
- If the opened row's model had no levels, the control is absent, so a switch to a model with levels shows the control after the list re-reads (reopen).
- Phone widths show the control as an icon (its semantics label and menu name the level), like the mode control.
Verification (2026-11-09)
-
Go:
go test ./internal/protocol ./internal/pipeline ./internal/codex ./internal/serverok../internal/claudeand./internal/opencode: all new tests pass; one pre-existing failure each (TestServiceTokenIsPassedOnlyFromAPrivateFile,TestStageDiscoveryRequiresPrivateRegistrationBeforeSessionWork), which fail identically on base8ca5a1fd. -
Flutter:
tool/memwatch/full.sh test/features/chat:PASS: 1123 passed, 0 failed.tool/analyze.sh: clean. -
Live Claude Code (opt-in
PIPELINES_LIVE_CLAUDE_EFFORT=1 go test ./internal/claude -run TestClaudeEffortLive -v, scratch directory, two Haiku turns through the adapter, thenget_settings):chose low: CLI applied model=claude-haiku-5-5 effort=low chose max: CLI applied model=claude-haiku-5-5 effort=max haiku levels from initialize: [low medium high xhigh max] --- PASS: TestClaudeEffortLive (5.09s) -
Live Codex, read-only (
PIPELINES_LIVE_CODEX_EFFORT=1 go test ./internal/codex -run TestCodexEffortCatalogLive -v): e.g.gpt-6.1-sol default="low" levels=[low medium high xhigh max ultra],gpt-6-luna default="medium" levels=[low medium high xhigh max]. No Codex turn was run, so turn/starteffortwas verified by the adapter test only. -
Live OpenCode, no inference, isolated HOME with
opencode api --standalone: a new session reported"variant":"default"; after postingvariant:"high"the session read back{"id": "inkling-2-small-free", "providerID": "opencode", "variant": "high"}. No OpenCode turn was run. -
Not run: a full Pipelines server with the Flutter app against a live harness. Browser captures used the fixture app (
?chats=2&header=1).