List view
CodeWhale v0.8.60 release cycle. Target: ~15 issues.
No due date•1/14 issues closedCodeWhale v0.8.59 release cycle. Target: ~15 issues.
No due date•1/12 issues closedCodeWhale v0.8.58 release cycle. Target: ~15 issues.
No due date•2/12 issues closedCodeWhale v0.8.57 release cycle. Target: ~15 issues.
No due date•3/15 issues closedCodeWhale v0.8.56 release cycle. Target: ~15 issues.
No due date•2/13 issues closedCodeWhale v0.8.55 release cycle. Target: ~15 issues.
No due date•1/15 issues closedCodeWhale v0.8.54 release cycle. Target: ~15 issues.
No due date•3/15 issues closedCodeWhale v0.8.53 release cycle. Target: ~15 issues.
No due date•16/72 issues closedCodeWhale v0.8.52 release cycle. Target: ~15 issues.
No due date•0/15 issues closedCodeWhale v0.8.51 release cycle. Post-v0.8.50 stabilization plus direct Arcee AI provider support. In scope: regressions surfaced after v0.8.50 shipped at 2026-06-02T05:20:50Z (#2592, #2590, #2589, #2584/#2587, #2583/#2585, #2488/#2593), low-risk clean PR #2591, and direct [providers.arcee] / ARCEE_* support via #2594/#2595. Provider fallback-chain design and broader feature work remain out of scope unless separately approved.
No due date•20/30 issues closedCodeWhale v0.8.50 release cycle. Target: ~15 issues.
No due date•7/18 issues closedCodeWhale v0.8.49 release cycle. Target: ~15 issues.
No due date•6/16 issues closedFirst run, defaults, visual hierarchy, task finales, website / community front door, contributor guidance, and release smoke feel composed, legible, and exact. The project identity locks in without breaking existing installs. ## In scope - **First-run and default-experience polish.** Provider setup, model/provider clarity, execution-mode defaults, `--model auto` affordances, theme defaults, optional memory/verifier affordances, and clean fallback paths. - **Control panel polish.** `/config` becomes more useful for modes, permissions, provider, model, thinking, memory, MCP, theme, and clear setting explanations. - **Visual direction (project identity).** The orange / blue / white work-state palette against dark navy / near-black remains the target identity. The palette encodes state, not decoration: blue for frame/control/selection, white for readable content, orange for live reasoning/progress/warnings, dark navy / near-black for background. - **Governance + community docs.** `GOVERNANCE.md`, `SPONSORSHIP.md`, `SUPPORT.md`, issue templates, and public contribution paths become clearer. - **Public positioning.** README + landing page frame CodeWhale as an agentic terminal workbench for open-source and open-weight coding models, with DeepSeek first-class and provider/local-runtime paths clearly explained. - **Compatibility cleanup, but not shim-drop.** Legacy `deepseek` / `deepseek-tui` command shims remain for 0.8.48 to honor the v0.8.47 compatibility promise. Their removal is deferred to a future compatibility-cleanup release. ## Out of scope (kept compatible for this release) - `~/.deepseek/` user config directory name. - DeepSeek API env vars (`DEEPSEEK_API_KEY`, `DEEPSEEK_BASE_URL`, `DEEPSEEK_MODEL`, `DEEPSEEK_PROVIDER`). - `api.deepseek.com`, `api.deepseeki.com`. - Model IDs (`deepseek-v4-pro`, `deepseek-v4-flash`). - `ProviderKind::Deepseek` enum + `"deepseek"` provider string. - Historical CHANGELOG entries. - CNB mirror namespace. - Legacy command shims for this release. ## Definition of done - Fresh install via `npm install -g codewhale` or `cargo install codewhale-cli` keeps canonical `codewhale` / `codewhale-tui` commands working and does not break existing legacy shim users. - First-run and provider/model setup paths are clear and recoverable. - `/config` exposes the key control-panel settings with useful explanations. - The work-state palette and alternate themes remain legible and pass contrast checks. - Public docs and website surfaces accurately describe current version, providers, tools, and contribution paths. - A new user sees codewhale-named welcome surfaces while existing DeepSeek compatibility paths still work. ## Release gate - Parity gates green. - `CHANGELOG.md` `[0.8.48]` thanks contributors to the v0.8.x DeepSeek-TUI line and frames v0.8.48 as brand-consolidation + workbench-affordance work. - Release notes document compatibility explicitly: canonical commands are `codewhale` / `codewhale-tui`; legacy shims still exist in 0.8.48 and are scheduled for a later cleanup.
No due date•27/37 issues closedA bounded source-linked orientation memory plus a shared state / evidence / permission contract across terminal, server, editor, bridge, and agents. Handoffs become first-class artifacts: the workbench knows where it left off, what it owes, what it changed, and how to resume. Provider abstraction lands so model selection is invisible to the rest of the system — and Hugging Face Inference Providers becomes a first-class provider alongside DeepSeek and OpenRouter, anchoring the harness's open-model story. ## In scope - **Evidence ledger.** Every receipt from v0.8.43 + every decision card + every tool inspection + every memory entry compounds into a per-session evidence ledger. Inspectable, exportable, queryable from `/evidence`. - **Handoff artifacts.** Closing a workbench session writes a handoff artifact (goal, last state, blockers, decisions, evidence). Opening one resumes the workbench — "Resume previous workbench" surfaces matching artifacts. - **Orientation cache.** Bounded, source-linked, evidence-tagged. Decays as freshness drops. First-class fact source from `codewhale.net/api/state.json` (latest release, install commands per platform, published crates, known-bad version ranges). - **Provider abstractions.** Unified `Provider` trait in `codewhale-agent` consolidating env-var precedence, secret resolution, base-URL normalization, and auth-header construction (currently scattered across `crates/config`, `crates/secrets`, `crates/tui/src/client.rs`). `ProviderKind` registry becomes configurable; model selection is provider-agnostic. - **Hugging Face as a first-class provider.** New `[providers.huggingface]` config block with `api_key` (default `HF_TOKEN`, alias `HUGGINGFACE_API_KEY`), `base_url` (default `https://router.huggingface.co/v1`), and `provider = "auto"` (or a specific Inference Provider). OpenAI-compatible route. Model picker pulls model passport metadata from the HF Hub API (license, base model, context length, chat template, tool-call support, reasoning support, gated / private status). Distinct from the **Hugging Face Workset** (#1977) which adds Hub registry / datasets / adapters / Jobs — the two share auth but ship through different surfaces. - **Cross-surface alignment.** Consistent command names, output formats, error messages across CLI (`codewhale`), TUI, runtime API (`codewhale serve --http`), bridges, and web. - **VS Code extension beta.** Scaffold, local runtime detection, chat webview. Ship as VSIX attached to GitHub Release; not Marketplace-published until beta feedback. - **Protocol contract** in `crates/protocol` carries provider-auth shape explicitly so external clients don't have to special-case. - **Per-tool migration PRs.** Start ExternalTool migrations one tool at a time (git, gh, python, node, rust, cargo) with Windows CI green per step. ## Out of scope - New providers beyond the HF Inference Providers integration (the rest stay as they are). - Cloud-hosted runtime API. - Marketplace publish of VS Code extension. - Plugin tool runtime implementation (still gated on v0.8.46 RFC). - Model Lab workset implementation (post-v0.9.0; see #1977). The HF Workset specifically depends on this milestone's provider work landing first. ## Definition of done - Switching providers mid-session is one config change with no surrounding code change. - Hugging Face Inference Providers works end-to-end against `Qwen/*`, `deepseek-ai/*`, and `meta-llama/*` model IDs without per-model special-casing in the engine. - Model picker surfaces HF model passport metadata (license, context length, gated status) before selection. - `/evidence` returns the per-session ledger. - Closing and reopening a session restores the workbench state (active task, last decision, pending blockers). - Orientation cache surfaces the latest published release within freshness window after restart. - VS Code beta VSIX attached to v0.8.47 GitHub Release; smoke-tested against local runtime API. ## Release gate - Parity gates green. - `CHANGELOG.md` `[0.8.47]` entry calls out HF as a first-class provider and provider abstractions as the model-neutral lever. - README provider matrix + "Bring your own open-weight model" section updated; HF Inference Providers and OpenRouter framed as the open-model discovery+routing layer.
No due date•22/32 issues closedMake documents, images, search, execution, previews, dependency probes, and safe approvals feel native to the workbench instead of like loose subprocesses. Tools become first-class workbench objects with inspectors, properties, previews, and copy/select. Preview verifier-native completion hooks behind an opt-in flag so the v0.9.0 surface lands with field experience accumulated. ## In scope - **Tool inspectors.** Every tool call has a properties pane: inputs, outputs, duration, exit, environment, sandbox decision. Tool results render in a preview panel (image, table, diff, doc) rather than as raw text. - **Copy / select mode.** First-class text selection inside the workbench (transcript, properties, previews) without breaking terminal-line semantics. The terminal-copy-includes-wrapped-lines bug (#1853) gets fixed structurally. - **Provider / model diagnostics.** Inspectable view of provider state: active provider + model, last-call latency, last error, prompt-cache hit rate. Surfaces from doctor + `/provider` slash command + properties pane. When the active provider is Hugging Face Inference Providers (via the v0.8.47 first-class integration when that lands first, or via the OpenAI-compatible path in the interim), the pane previews **model passport** metadata pulled from the HF Hub: license, base model, context length, chat template, tool-call support, reasoning support, gated / private status. - **Tool surface polish.** PDF / image / search / exec ergonomics; dependency probe + skip-on-miss (existing pattern); approval-flow clarity. Ship the small, independent RuntimeTool Windows `.cmd` fallback as a standalone PR. - **Plugin tool design RFC.** Open `docs/proposals/plugin-tools.md` defining how `// approval: auto` frontmatter interacts with the execution modes (Plan / Agent / YOLO), the approval policy, trust, and `--model auto` model routing. Implementation deferred until design lands. - **Verifier preview (general).** Opt-in via `[verifier] enabled = true`. On claim-of-done, auto-spawn a verifier sub-agent with fresh context and read-only tools, time-boxed. Verdict-as-gate: pass / partial / fail. `/force-complete` override is audit-logged. `/tasks` shows a "verified" badge. Extends the Goal-mode-specific Fin wakeup from v0.8.43 to the general claim-of-done case. ## Out of scope - Full ExternalTool / RuntimeTool 65-call-site migration (defer; ship per-tool migration PRs in v0.8.47). - Plugin tool runtime implementation (gated on the RFC). - Verifier as default (preview only — explicit opt-in). - New execution modes — Plan / Agent / YOLO remain the three modes. - Hugging Face Workset implementation (Hub registry / datasets / adapters / Jobs — see #1977). v0.8.46 only previews HF model-passport metadata in the provider pane; the workset surface ships post-v0.9.0. ## Definition of done - Every tool surfaces an inspectable properties pane and a result preview. - Copy / select mode ships with terminal-line semantics preserved. - `/provider` slash command and provider properties pane in place; HF model passport preview works against at least three model IDs (`Qwen/*`, `deepseek-ai/*`, `meta-llama/*`). - Verifier preview enables via config; verdict appears on completed tasks; `/force-complete` writes to audit log. - Plugin tool design RFC lands as draft; one round of maintainer review captured in PR. ## Release gate - Parity gates green. - `CHANGELOG.md` `[0.8.46]` entry marks verifier preview as experimental and tool inspectors as the headline. - `docs/verifier-preview.md` explains opt-in + override semantics.
No due date•43/43 issues closedThe v0.9.0 architectural release promotes CodeWhale from a turn/subagent workbench into a WhaleFlow workflow workbench: typed branch-and-leaf workflows, pod-style background workflow monitoring, shared ARMH/RLM memoization, deterministic replay, external-memory evaluation, and a GEPA-style teacher/student promotion loop that turns validated lessons into a cached-main overlay. Primary tracker: #2667 EPIC: v0.9.0 WhaleFlow branch/leaf workflow mode ## In scope - WhaleFlow workflow mode: background workflow runs, /workflows-style monitoring, done/total progress, longest-running item peek, inspect/replay/report surfaces. - Typed Workflow IR as the source of truth: Starlark/YAML/generated plans compile to Rust-owned IR before execution. - Rust async executor: bounded branches, bounded leaves, cancellation, budgets, permissions, LoopUntil, Cond, Expand, BranchTournament, and Pareto reducers. - Branch/leaf semantics: isolated speculative branches, bounded leaves, losing-branch fruit harvesting, typed results. - ARMH/RLM integration: exact-context shared memo across branches with visible hit/miss/cost telemetry. - External-memory evaluation: decide whether Aleph-style memory belongs in core, optional plugins, or explicit workflow nodes, with visible state and clear/export controls. - TraceStore and deterministic replay: replay from recorded leaf/control outputs, not live model calls, unless explicitly allowed. - Teacher harness: TeacherReview proposes reusable lessons; StudentReplay and PromotionGate validate before promotion. - Cached-main overlay: promoted notes, workflows, tests, branch heuristics, model/cache policies, and prompt patches warm future runs without mutating Git main. - Janitor: stale invalidation, memo cleanup, candidate demotion, trace compaction, capacity enforcement. - Model-provider abstraction: workflow roles map to capabilities and configured providers; no workflow logic hardcodes Arcee, DeepSeek, Claude, tool calls, JSON mode, or large context. ## Non-goals - No model-weight RL in v0.9.0. - No arbitrary JS/Python as workflow source of truth. - No script-level async/await. Starlark is a pure graph builder; Rust executes IR. - No hidden external-memory dependency for normal CodeWhale operation. - No uncontrolled self-modifying agent. Teacher output is inspectable, replayed, and reversible. - No public performance claims until evals are reproducible. ## Definition of done - workflows/rlm_cache_change.star runs with mock provider in CI and can dogfood CodeWhale RLM/ARMH/provider changes. - Branch/leaf engine, control flow, TraceStore, replay, ARMH shared memo, TeacherReview, StudentReplay, PromotionGate, overlay, and janitor have focused tests. - Workflow mode can run, inspect, and replay a workflow from CLI and TUI. - ARMH savings, provider costs, and any external-memory use are visible in workflow telemetry. - All behavior is behind config/feature flags until stable. ## Release gate - Parity gates green on the v0.9.0 integration branch. - CHANGELOG [0.9.0] frames the release as WhaleFlow branch/leaf workflows and validated cached-main learning. - Docs explain the Claude-workflow-inspired UX while preserving CodeWhale's typed IR/Rust executor safety model.
No due date•15/151 issues closed