6 +- Remove the always-on Terse extension; configure personal response style through Pi's `APPEND_SYSTEM.md` instead
7 +- Improve Decay progress with neutral pending history, a combined history and retained-tail row, readable labels, and continuous merge animation with atom and streamed-token counts
8 +- Fix Decay retained-token estimates to measure the actual preserved suffix instead of the configured target, and show unknown counts when unavailable
9 +- Show Ultra workflow phases and live prompt tails while arguments stream, hand off to the execution board when agents start, and retain full received prompts on Ctrl+O
10 +- Fix Ultra failed tool calls to show an error summary instead of an empty progress board, with full diagnostics on Ctrl+O
11 +- Add Parallel and Google WML search fallbacks; use Codex, MiniMax, Parallel, Google WML, DuckDuckGo, then Z.AI, preserving full excerpts and stopping fallback on cancellation
12 +- Add `mise run //extensions/web:evaluate-search` to compare configured search providers live on five fixed queries, recording target rank, latency, and full results
13 +- Fix Leaks to redact and restore only explicit plaintext fields and tool data, preserving protocol metadata, signatures, signed reasoning, encrypted state, and binary content; leave unknown provider fields untouched and warn on unrecognized payloads
14 +- Reduce mockup tool context with shorter metadata while retaining on-demand HTML guidance and option limits; give interactive scripts an explicit reference to their fragment root and preserve fragment-local data scripts
15 +- Reduce cmprss startup context by activating retrieval only when originals are stored; restore it on session resume, keep it available with compression off, and hide it after clearing stored blocks
16 +- Replace Web's separate tools with one compact `web` tool using `action: fetch | map | search`, validating action-specific arguments before I/O; remove legacy aliases and MiniMax image analysis, and require tool allowlists to use `web`
17 +- Reduce Ultra's context footprint with a compact workflow tool schema while retaining strict runtime validation
18 +- Remove Verboten's main-agent prompt instructions and regex inventory while retaining protected-path blocking, grep filtering, and shell judgment
19 +- Add `mise run //:context-extensions` to discover extensions automatically and measure removal savings one at a time, including uncertain registrations; report provider input and heuristic deltas, and withhold savings when repeated controls differ
20 +- Add `mise run //:context-startup-skill-descriptions` to rank visible agent-directory skills by description size and show the five largest descriptions for review
21 +- Add `mise run //:context-startup-sources` to estimate `APPEND_SYSTEM.md`, agent-directory and extension/package skill entries, and shared catalog instructions separately at startup, excluding direct project-local skills, skill bodies, and prompt templates without sending a measurement prompt
22 +- Add `mise run //:context-startup` to compare stock, configured, and agent-text-free headless startup context with three live requests, retaining extensions, settings, and project context while reporting cache-inclusive provider input tokens and labeled Pi heuristic estimates
23 +- Fix Strata cancellation and session shutdown so pending requests and subprocesses settle before cleanup finishes
24 +- Keep Ultra's intermediate results out of orchestrator context, return final output once, and replace output above 50KB or 2000 lines with a full-output file reference while preserving complete results in UI details
25 +- Let Ultra configure named model tiers with default thinking levels and orchestrator selection guidance, merge global and project overrides, use the session model by default across providers, and start fresh checkpoints when effective model or thinking routes change
26 +- Remove Strata Ask's fixed tool-call, round, batch, and cumulative-output caps while retaining per-tool resource limits and cancellation
27 +- Add optional Strata GitHub PR reviews with confirmed checkout switching, attributed read-only discussions, and PR-aware feedback; keep saved plans and drafts separate across PRs and forge hosts
28 +- Add Strata Vim-style line, hunk, layer, and pane navigation, literal diff search, keyboard review actions, whole-layer review toggles, and contextual shortcut guides
29 +- Keep Strata draft saves from overwriting newer edits, preserve focus when toggling review status, confirm submission and close, and keep unavailable workspaces read-only
30 +- Add Strata for browser-based Git review with model-organized layers, layer questions, line comments, resumable drafts, stale-snapshot checks, and feedback sent back to Pi
31 +- Add independently collapsible Strata side panels and keyboard-accessible Details, Ask, and Feedback tabs; keep selected tabs readable on hover
32 +- Keep Strata's layer and All changes conversations and drafts separate, preserve hunk focus, and restore question input focus after answers when appropriate
33 +- Let Strata Ask inspect installed packages and external docs with bounded read, literal grep, and ls tools, enforce protected-path checks, and label live evidence separately from the review snapshot
34 +- Keep Strata on the model selected when the workspace opens and fix current-file tracking near the end of long diffs
35 +- Let larger Strata reviews and layer questions fit within the existing prompt limit without dropping diff text or line anchors
36 +- Track secret encryption rules in `.gitattributes`, migrate obsolete local rules, and block commits when `.secrets` or generated attributes are not fully staged
6 37 - Add on-demand IntelliJ MCP connections with project-scoped tools, saved loopback endpoints, connection health status, readable tool results, connection management commands, and faster large tool-catalog loading
7 38 - Improve IntelliJ footer status readability and report saved-settings read failures in `/intellij status`
8 39 - Add Verboten protected-path blocking, filtered grep results, and judged Bash or PowerShell commands
9 40 - Fix IQ scoring and storage across platforms, including stable session-settling checks
10 41 - Make Nu diagnostics tests compatible with supported version differences
11 42 - Fix Web so its extension tools activate when a session starts
43 +- Prevent extension diagnostics from corrupting Pi's terminal UI and machine-readable output
12 44 - Add IQ for confirmed longitudinal model scoring with cited evidence, safe concurrent scans, and a responsive `/iq` leaderboard
13 45 - Add Masks for quickly switching between named model and thinking combinations with `/masks`, `Alt+M`, configurable direct shortcuts, and fuzzy matching
14 -- Let prompts select a Mask for one agent turn with an optional `mask` frontmatter field
46 +- Let prompt templates select a Mask through their tool loop and automatic recovery with an optional `mask` frontmatter field; restore before ordinary follow-ups and block prompts when switching or restoration fails
47 +- Queue masked follow-ups after Pi's native queue with attached images, a footer count, and `/masks-cancel`; discard deferred prompts on abort, error, tree navigation, or shutdown, and reject masked steering and competing input during preparation
15 48 - Change Tune's fullscreen shortcut to `Ctrl+Alt+T`
16 49 - Generate git-safe's fixed-executable wrapper on first Bash use and reuse it across reloads
17 50 - Defer unused extension implementations, PATH checks, settings reads, prompt loading, and RTK probes beyond startup and reload
27 60 - Let Ultra repair dynamic extensions after consumer failures and rerun the original workflow, reusing unaffected checkpoints without a fixed repair-cycle limit
28 61 - Give dynamic extensions bounded, redacted NDJSON debug logs in the platform cache that Ultra can inspect on demand and retain for seven days
29 62 - Let Ultra search only canonical dynamic extensions with bounded deterministic matching over manifest metadata and selected README sections
30 -- Make Ultra progress rows task-first, with two-line active/failure detail and compact terminal rows for completed work
63 +- Make Ultra progress rows task-first and put metadata below summaries, live activity, and failure details across tool rows, command overlays, and result reports
31 64 - Count every Ultra sub-agent response and failed result-submission attempt in token and cost totals
32 65 - Remove synchronous Pulse Git processes, use the current Node process version, and fold vcs-status stash detection into its existing Git status process
33 66 - Remove the Overkill and Q extensions
48 81 - Treat Klaus request timeouts as sliding Claude-activity timeouts, paused while Pi tools run; ignore unsupported output-token limits
49 82 - Make Klaus discover available Claude models with Pi's OAuth and never auto-probe undiscovered models that could consume usage credits
50 83 - Advertise one current Klaus model per Claude family and map each explicit Pi model ID to Fable, Opus, Sonnet, or Haiku without silently upgrading it
51 -- Let Fable proceed when absent from authenticated discovery, with a usage-credit warning shown once per Pi session
84 +- Target Fable 5.1 with verified routing and API-equivalent pricing; let it proceed when absent from authenticated discovery, with a usage-credit warning shown once per Pi session
52 85 - Support Pi thinking in Klaus, mapping `minimal` to `low`, preserving supported levels, disabling it for `off`, and warning when unsupported levels are reduced
53 86 - Preserve Pi steering and follow-up order across Klaus provider turns and pending-tool boundaries
54 87 - Fix Klaus parallel tool continuations, sessionless tool-call failures, and aborted requests
55 88 - Fix Klaus lifecycle cleanup so concurrent completion and session teardown await one Agent SDK shutdown
56 -- Fix Klaus prompt translation so subscription-triggering phrases no longer cause third-party-app usage errors while the available skills section, `.pi`, paths, and compound names such as `pi-ext` remain unchanged; keep Pi identifiable to the model and warn once per session when upstream prompt changes prevent expected translations
89 +- Fix Klaus prompt translation so subscription-triggering phrases no longer cause third-party-app usage errors while the available skills section, `.pi`, paths, and compound names such as `pi-ext` remain unchanged; keep Pi identifiable to the model and warn once per session only when recognizable Pi prompts change upstream and prevent expected translations
57 90 - Add automatic Klaus setup on Android through an isolated `grun` launcher
58 91 - Support concurrent Klaus calls from extensions that create Pi agent sessions or make direct model calls
92 +- Make Angel, Pulse, session renaming, TLDR, and Ultra action summaries work with custom extension providers such as Klaus
93 +- Make session renaming use medium reasoning when the active model supports it
59 94 - Reap idle secondary Klaus queries after 15 minutes, refreshing the timeout on provider or tool activity and replaying canonical Pi context if a later result arrives
60 95 - Report Klaus API-equivalent spend using Pi's current Anthropic rates and recognized fallback model rates while keeping token usage and warning that actual subscription or Fable credit usage may differ
61 96 - Document that Klaus uses Anthropic's proprietary Claude Agent SDK under its commercial terms without vendoring the SDK
124 159 - Auto-prune closed mockup cache entries when their sessions are missing, after 30 days of inactivity, or by oldest use above 256 MiB
125 160 - Use `/ultra exec <instructions>` to design or execute a workflow and `/ultra run <name> [args]` to run a saved workflow; bare `/ultra` enables the hidden `run_workflow` tool and confirms activation
126 161 - Use Ultra only when independent parallel work, staged agent handoffs, or isolated specialist contexts materially improve the result
127 -- Make `/ultra exec` show the complete orchestration prompt as a user message, choose between a one-off and saved workflow from reuse intent, and ask one focused question when uncertain
162 +- Make `/ultra exec` send a short visible instruction and the user's request without injecting authoring guides; choose between a one-off and saved workflow from reuse intent, and ask one focused question when uncertain
128 163 - Add `/ultra` autocomplete for `exec` and `run`, with saved workflows completed under `run`
129 164 - Remove Ultra background runs and `/ultra history`; workflows now run interactively without persisted run history
130 165 - Improve Ultra progress with phase-first expandable views, transcript navigation, native Pi tool rows and `Ctrl+O` output expansion, checkpoint, token, and cost details, and final outcomes
131 166 - Add optional `ultra.actionSummarizerModel` summaries that replace raw Ultra tool arguments with concise action phrases; rapid actions coalesce per agent, only one summary request runs at a time, final pending actions are flushed when an agent finishes, collapsed transcripts hide redundant tool previews, summaries are bounded, and `Ctrl+O` still shows native tool details and results
132 167 - Hide Ultra's internal `structured_output` completion tool from progress summaries
133 168 - Make every Ultra workflow step submit structured output through one validated contract, with strict schema sampling where supported and same-session reminders for missing results
169 +- Fix Ultra workflow thinking-level schemas for providers that require string enums
134 170 - Improve Ultra's review workflow with readable analysis, verified findings, and concrete next steps instead of raw JSON output
135 171 - Add Ultra's shipped `research` workflow with parallel web evidence gathering, gap auditing, adversarial verification, and a cited human-readable report
136 172 - Load skills in Ultra's tool-using sub-agents by default with `ultra.subagentSkills: "none"` as the opt-out, and refuse workflows requiring unavailable tools
138 174 - Fix Ultra progress so phase transitions and completion preserve terminal scrollback
139 175 - Require two Esc presses to confirm aborting an entire Ultra run
140 176 - Fix Ultra tool-step cleanup so teardown errors do not hide a completed workflow step
141 -- Remove Ultra's exported authoring skill; `/ultra exec` now sends the workflow authoring prompt internally
177 +- Make Ultra's authoring skill available on demand through the active workflow tool, without a global skill entry or inactive-tool guidance
178 +- Fix Ultra native tool transcripts so partial results stay hidden until expanded
142 179 - Fix Pulse TAB completion
143 180 - Fix Notes so `/tree` restores notes from the selected branch and `/new` asks whether to carry pending notes into the new session
144 181 - Disable all mise-managed tools on Android to avoid platform-specific tool failures
155 192 - Rename autoresearch to tune; add jj backend, state migration, timeout clamps
156 193 - Rework diff-review to SSR reviews; add headless Vitest coverage
157 -- Add sparse safe clones, capped web fetch cache, and goal planner dossier
158 194 - Rework q extraction; add benchmark and 112 parser tests
159 195 - Retire superpowers; move workspace to npm, Vitest, dprint, Biome, tsc, mise
170 206 goal, tldr, leaks, tps, quota, vcs-status
172 208 autocomplete, progress UI, standing prompts, judge-gated updates
173 -- Add tldr live summaries, model footer, quota parsers, jj-aware workspace
209 +- Add tldr live summaries; model footer; quota parsers; jj-aware workspace
175 211 - Fix session startup races, stale telemetry, aux LLM calls, provider secret
177 -- Measure TPS from first assistant delta; ignore baseline stream chunks