github can1357/oh-my-pi v17.4.0
on GitHub

3 hours ago

@oh-my-pi/pi-agent-core

Breaking Changes

  • Replaced global token counting functions (countTokens, countTokensConservatively, setTokenizerModel, and estimateTokens) with model-scoped, immutable Tokenizer instances (agent.tokenizer). Use tokenizer.countTokens(text, mode?), tokenizer.countMessage(message), or tokenizer.countMessages(messages).
  • Updated context management functions (findCutPoint, prepareBranchEntries, collectShakeRegions, pruneToolOutputs, pruneSupersededToolResults, and trimRemoteCompactionInputToContextWindow) to require an explicit Tokenizer instance.

Added

  • Added Tokenizer.checkTokenBudget(text, budget) to efficiently verify if text fits within a token limit using fast byte-bound checks before falling back to full tokenization.
  • Added provider-anchored transcript token estimation (findTranscriptUsageAnchor, isTranscriptUsageAnchor, estimateTranscriptTokens) to calculate transcript token counts incrementally from the latest reported assistant turn usage.
  • Added remotePreserveReusable() to check whether a previous remote compaction payload remains reusable with the active model.

Changed

  • Expanded native tokenizer support across catalog models, adding exact embedded token counting for Claude, Qwen 3.5+, DeepSeek V3/V4/R1, Kimi K2/K3, and GLM-5+ models. Tokenizer now constructs from a resolved catalog Model.
  • createCompactionSummaryMessage takes an options object after (summary, tokensBefore, timestamp); CompactionSummaryMessage gained optional method and tokensAfter display metadata.

@oh-my-pi/pi-ai

Added

  • Added model metadata fields (context_length, max_output_tokens, input_modalities, etc.) to auth gateway model listing responses

Fixed

  • Fixed tool-argument repair applying lossy transformations (such as stringifying objects or stripping unrecognized keys) when validating union schemas (anyOf/oneOf), preventing corrupted tool call and subagent payloads
  • Fixed 400 errors when communicating with local OpenAI-compatible inference servers that reject chat_template_kwargs.reasoning_effort by improving reasoning effort parameter fallback and compatibility handling
  • Fixed DeepSeek-family models on hosts like Fireworks losing reasoning whenever tools were offered: a redundant tool_choice: "auto" is now omitted so the provider keeps thinking enabled; forced and "none" selectors still take priority (#1207)

@oh-my-pi/pi-catalog

Added

  • Models now include an optional tokenizer family field across bundled, discovered, and custom models (supporting Claude, Qwen, DeepSeek, Kimi, and GLM families), with support for explicit overrides in model configuration.
  • Added long-context cost tiers (cost.longContext) to subscription Codex GPT-5.6 models (Sol, Terra, Luna) matching first-party API pricing above 272K input tokens.

Changed

  • Bundled model metadata is prebuilt during generation, reducing catalog startup work.

Fixed

  • Fixed tool-call turn failures for opencode-go/muse-spark-1.2 and related variants by ensuring API transport pins apply to live discovery and automatically inferring response routes for gateway-first OpenCode models (#8957).

@oh-my-pi/pi-coding-agent

Added

  • /cleanse (and omp cleanse) — run the checker/repair loop in-session, with a live status board of running checkers, repair subagents, and token/cost totals.
  • omp ps — interactive monitor for daemon-supervised background processes.
  • Composer layouts — composer.shape picks the editor frame (rounded box, Claude Code rules, upstream-pi rules, borderless), with live previews in /settings and the setup wizard.
  • Context line — statusLine.contextLine gauge (percentage, annotated, embedded) showing context usage and compaction boundaries.
  • Backgroundable Python — eval cells can run async and auto-background like bash, with configurable thresholds.
  • Local Claude token counting — Anthropic-family tokens now count via a native local tokenizer, and every counter (session maintenance, advisor, stats, context tools) uses the active model's own tokenizer.
  • extendedContext setting — pick whether models with premium long-context pricing (272K/1M tiers on Codex-class models) use the extended window or compact early and stay on standard pricing.
  • /extended-context — toggle premium long-context windows without leaving the session.
  • Speculative compaction — with compaction.asyncEnabled, all compaction modes compact in parallel while the session continues, then splice the result in instantly.
  • tokenizer property on custom models and modelOverrides to pin the tokenizer family for proxy models.
  • qwenTemplateReasoningEffort in models.yml compat to disable the Qwen 3.8+ reasoning-effort template parameter for strict local servers.
  • Click-to-toggle and drag-to-reorder for list-valued editors in /settings.
  • icon.subscription and icon.advisor symbol-theme tokens (Nerd Font, Unicode, ASCII).

Changed

  • Typing anywhere in the /models UI now immediately focuses the model list for instant search and arrow navigation.
  • Revamped the todo HUD — overall progress renders along the tree-spine connector with smooth completion transitions.
  • Compaction divider now names the maintenance method that fired (remote-compacted, soft-compacted, handed-off, snap-compacted) and shows the before → after context size (e.g. 256K→20K).
  • /handoff (and automatic handoff compaction) now compacts in place, replacing the session context instead of forking a new session.
  • Compaction method priorities — compaction.methodOrder takes an ordered preference list (e.g. [remote, snap] uses remote compaction where the provider supports it, such as OpenAI, and snap everywhere else), replacing compaction.strategy/compaction.remoteEnabled.
  • Unified inline overlays and selectors (model picker, settings, /cleanse) into one titled rounded-box panel style.
  • Risk badges and warnings on /settings rows, starting with External Thinking.
  • Faster CLI Startup

Fixed

  • /models keeps auto thinking on non-default roles such as task instead of changing the active model and displaying the role as max.
  • Subagent yield structured results no longer get corrupted by lossy argument repairs; prompt guidance improved for weak callers.
  • GitHub file_read returns proper image blocks and direct view URLs for image/binary files.
  • Cancelled prompts during pre-stream turn setup restore the text and image attachments to the editor.
  • top builtin accepts single-dash macOS flags such as -pid and -stats.
  • GNU/BSD compat sweep across built-in shell utilities (timeout, diff, find, date, tail, head, rg, stat, truncate, cksum, sleep, which, nohup, kill).

@oh-my-pi/hashline

Added

  • Added an opener-escape landing correction for insertions anchored on a construct's opening line to place shallower sibling constructs after the enclosing block rather than splitting the opener from its body.

Fixed

  • Fixed an issue where single-line replacements echoing attributes or decorators (such as #[napi] or @Injectable()) could lead to silently duplicated annotations.
  • Increased the default snapshot-store path capacity from 30 to 256 to prevent early tags in wide sessions from aging out and triggering misleading "hash is not from this session" errors.

@oh-my-pi/pi-natives

Added

  • Added offline countTokens support for Anthropic Claude families (ClaudeV3, ClaudeV47, ClaudeV5) via a high-performance native port of ctok.
  • Added exact offline token counting support for Qwen (3.5+, 3.6+, 3.8), DeepSeek (V3, V4, R1), Kimi (K2, K3), and GLM-5 models alongside rebuilt OpenAI encodings, with optimized zero-allocation string passing from JavaScript.
  • Added nodeChainAt native API to retrieve innermost-first tree-sitter node chains with grammar kinds and line spans for structural syntax analysis.

Changed

  • Improved shell builtins (grep, rg, sed, cat, head, tail, jq, ls, etc.) to stream output progressively with destination-aware line buffering for pipes, terminals, and live TUI output, while maintaining block buffering for file writes.
  • Updated compound blocks ({ ...; }, (...)) and shell-function pipeline stages to run concurrently with other pipeline stages, preventing head-of-line blocking and pipe buffer deadlocks.

Fixed

  • Fixed the shell output minimizer dropping failure details from non-TTY bun test runs: the (fail) line, code frame, error: assertion, and stack trace are now kept instead of collapsing a failing run to bare pass/fail counts; unrecognized failing test formats now fall back to head/tail instead of counts-only output.

@oh-my-pi/omp-stats

Changed

  • Window token estimates now incorporate broker-reported fleet token burn when an auth broker is configured, accurately tracking fleet-wide usage instead of undercounting with local-only statistics.

Fixed

  • Fixed an issue in subscription-window insights where distinct limits sharing a duration label (such as Anthropic overall vs. model-scoped 7-day windows) were incorrectly merged, which inflated window-equivalents and skewed tokens-per-window estimates. Windows are now grouped by provider limit ID.

@oh-my-pi/pi-tui

Added

  • Added composer border styles (box, claude, pi, borderless) via ComposerStyle objects and getComposerStyle, unifying chrome geometry and rendering across the editor and previews.
  • Added support for warning risk notes and row markers in settings lists.

Full Changelog: v17.3.8...v17.4.0

Check out latest releases or
releases around can1357/oh-my-pi v17.4.0

Don't miss a new oh-my-pi release

NewReleases is sending notifications on new releases.

Get notifications