- task.maxEffort only clamped the initial thinking level; a retry
fallback candidate could clamp back up to its model floor and run a
low-capped spawn at high.
- The ceiling now rides the session as thinkingLevelCeiling: clamped in
ModelControls (constructor, setThinkingLevel, auto classifier,
restore) and in applyRetryFallbackCandidate; fallback candidates whose
floor exceeds the ceiling are skipped.
- Effort value import moved to @oh-my-pi/pi-catalog/effort; changelog
attribution added.
- Review follow-up for PR #6794.
Two defects in the ceiling work, both found in review.
The local backend shared the online ceiling, so with `autoThinkingMaxEffort:
max` and a sparse ladder the clamp could snap a `hard` bucket up to `max` —
a tier the 3-bucket on-device classifier can never select. The local branch
now pins `xhigh`.
Applying the ceiling before the Low floor also broke the floor's contract:
on `["minimal", "max"]` under an `xhigh` ceiling the intersection hid `max`,
the code concluded the model "maxes out below Low", and it fell through to
`minimal`. The floor is now resolved against the model's own ladder first
and the ceiling filters that pool, so an excluded top tier yields no level
instead of a sub-Low one.
Docs and changelog now scope the guarantee to what `auto` resolves: a
`thinking.requiresEffort` model whose ladder holds nothing under the ceiling
still receives its lowest supported effort from the transport, because it
accepts nothing else. The test that claimed to prove billing is renamed to
say what it checks.
Prompt assertions now cover the `max` criteria and the tie-break exception,
not just the label, since the label alone is inert. Drops the duplicated
pool-level assertions in favour of the contract-level sparse-ladder case.
Capping the classifier result before `clampAutoThinkingEffort` was not
enough. The clamp seeds `chosen` with `pool[0]`, so a sparse ladder whose
tiers all sit above the request snaps upward instead of down: on
`thinking.efforts: ["max"]` an `xhigh` request returned `max`, letting the
default setting bill the top tier with no opt-in. The same upward snap made
`resolveProvisionalAutoLevel` hand back `max`, breaking the invariant its
doc comment had just claimed.
`clampAutoThinkingEffort` now takes the ceiling and intersects it with the
model's supported tiers, returning `undefined` when nothing is eligible so
auto leaves the current level alone instead of billing an excluded tier.
The classifier passes its configured ceiling and the provisional level
passes XHigh.
`max` became a first-class effort tier in d435385a, but the `auto`
classifier prompt still offers only `low|medium|high|xhigh`. On a model
that exposes the tier, `auto` can therefore never reach it — only the
`ultrathink` keyword can, because it bypasses the classifier entirely.
`providers.autoThinkingMaxEffort` (`xhigh` | `max`, default `xhigh`) lifts
that ceiling. Opting in adds `max` to the classifier vocabulary, gated on
the target model actually supporting the tier, and scopes the tie-break
exception to that prompt variant so the default renders byte-for-byte as
before. A classification above the configured ceiling is clamped before
the model clamp, so a hallucinated `max` cannot cross a ceiling the user
did not opt into. The on-device 3-bucket classifier stays capped at
`xhigh`, and the provisional/fallback level still never provisions `max`.
Also corrects the two `Auto-detect per prompt (low-xhigh)` labels and the
stale `xhigh auto ceiling` comment, which the new setting makes wrong.
prewalkWouldBeNoop collapsed both auto and a fixed :inherit selector to an
undefined clamped effort, so a same-model prewalk targeting :inherit while the
session ran auto was dropped as a no-op. Applying :inherit clears per-turn
classification, so that hand-off is a real change. Compare auto/fixed mode before
comparing clamped efforts so an auto<->fixed transition always switches.
Fixes#6659
prewalkWouldBeNoop compared raw selectors, so a target the model cannot honor
(e.g. :xhigh on a model capped at high while running high) read as a change and
triggered an ephemeral model reset plus the plan/checklist nudges even though
setThinkingLevel clamps it straight back to the active effort. Compare the
target- and current-level efforts AFTER model clamping via
resolveThinkingLevelForModel so a clamp-equal target is recognized as a no-op.
Fixes#6659
The prewalk arm/switch guard compared model identity only (modelsAreEqual /
provider+id), discarding the resolved thinkingLevel. A legal same-model target
at a cheaper effort (e.g. prewalk: "@task" resolving to the active model at a
lower level) was dropped as a no-op, so the session ran the expensive effort for
the whole run while still paying the plan/continue nudges — silently on the
session path, logger.debug only on the subagent path.
Compare (provider, id, effective thinking level) via a shared prewalkWouldBeNoop
helper. Effort-only deltas on the same model now switch; a genuine no-op emits a
user-visible notice on the session path and never arms on the subagent path.
Fixes#6659
- Replaced legacy `pi/` role alias prefix with canonical `@` syntax across model resolution, documentation, and tests.
- Added support for bare `*` default alias and multiple alias prefix detection with custom role resolution in `resolveConfiguredRolePattern()`.
- Enhanced thinking suffix parsing to accept unambiguous abbreviations (minimum 2 characters) for effort and level selectors.
- Extended `resolveCliModel()` and `filterAvailableModelsByEnabledPatterns()` to accept settings parameter for role alias resolution from `--model` flag.
- Introduced `Max` as a first-class reasoning effort tier across all packages, including AI providers, coding agent configurations, and RPC protocols.
- Refactored model effort ladders to use wire-exact mappings and removed legacy effort aliasing (e.g., `max-to-xhigh` mapping).
- Updated model registry and provider configurations to support `Max` tier routing, color themes, and UI icon associations.
- Expanded test suites to provide end-to-end coverage for the new reasoning tier, including updated compatibility and fallback scenarios.
- Consolidated duplicated inline thinking level comparisons into a unified `concreteThinkingLevel` helper.
- Enhanced legacy tool shims to respect isolated session settings and support legacy options.
- Cleaned up redundant UI render requests and extra status-line updates.
- Refactored `grep` tool shim to configure context dynamically via isolated settings.
- Disabled platform-incompatible shell shim tests on Windows environments.
Devin provider models (devin-agent) advertise reasoning: true but no
thinking.efforts metadata — Cascade selects effort by routing to sibling
model ids, not a wire param. getSupportedEfforts(model) therefore returns
[]. clampAutoThinkingEffort previously short-circuited that empty supported
list by returning the requested effort as-is, so the auto-thinking
classifier-resolved level (e.g. low) reached stream.ts:1163 where
requireSupportedEffort threw 'Thinking effort low is not supported by
devin/<id>. Supported efforts: '. In --print mode the user saw the error
text; in the TUI it was silently swallowed, producing the reported
'working then empty response' symptom.
Returns undefined when supported is empty so the result mirrors
clampThinkingLevelForModel's behavior on the same shape (the explicit
--thinking low / high paths already worked because of this). Updates
classifyDifficulty's return type to Effort | undefined and threads through
to the existing #applyAutoThinkingLevel undefined-effort early-return.
#applyAutoThinkingLevel also short-circuits the classifier call up front
for these models — there is no effort to pick.
Fixes#3356
- Added `off` and `auto` as valid inputs for the `--thinking` CLI flag.
- Centralized thinking level definitions in `CLI_THINKING_LEVELS` to keep flag options, shell completions, and validation in sync.
- Configured CLI parsing to reject `inherit` as an explicit input to prevent unintended configuration suppression.
Mapped the user-facing max thinking selector to the canonical xhigh effort so DeepSeek V4 Pro selectors and --thinking can request provider maximum reasoning.\n\nFixes #2727
Propagated explicit thinking-off state through the agent loop so provider requests receive disableReasoning instead of an undefined effort. Added Ollama and agent-session regressions for the :off path.\n\nFixes #2239
Move bundled models, model cache/manager, thinking metadata, effort helpers,
provider descriptors/discovery, wire constants, and model identity utilities
into the new @oh-my-pi/pi-catalog package.
Update pi-ai to keep provider runtime/auth concerns, move catalog provider
metadata into CATALOG_PROVIDERS, and migrate coding-agent, agent, stats, docs,
and tests to import catalog values from pi-catalog.
Split coding-agent model registry helpers into discovery, roles, and models
config modules while preserving registry orchestration.
BREAKING CHANGE: @oh-my-pi/pi-ai no longer exports catalog subpaths such as
/models, /model-cache, /model-manager, /model-thinking, /effort,
/provider-models*, discovery helpers, and provider wire constants; use the
matching @oh-my-pi/pi-catalog subpaths instead.
- Added AUTO_THINKING as a configured thinking level in settings, schema, SDK, and session plumbing.
- Implemented per-turn auto reasoning classification with online/local prompts, effort clamping, and skip guards.
- Updated model selectors, ACP options, footer/status UI, and events to render auto and auto->resolved states.
- Added AUTO_THINKING parse/clamp tests and fixed local-module cycle and hashline preview regressions.
- Introduced Effort enum and ThinkingConfig metadata for per-model reasoning capabilities with min/max effort levels.
- Migrated thinking level API from string-based ThinkingLevel to structured Effort enum across agent and AI packages.
- Added model-thinking module with effort mapping, policy application, and semantic versioning utilities for provider-specific thinking modes.
- Removed supportsXhigh() function and replaced effort clamping with model-aware validation using ThinkingConfig metadata.
- Expanded models.json with thinking configuration objects for 50+ models including Claude, Gemini, and OpenAI variants.
- Added Python analysis scripts for edit tool usage patterns and tool invocation stream processing.
Brent