dgf1988/codewhale
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

docs: remove stale internal docs (handoffs, old audits, orphaned roadmaps)

Browse Source
This commit is contained in:
Hunter B
2026-06-09 23:22:32 -07:00
parent b4edb4e1ef
commit bf2e5504a2
6 changed files with 0 additions and 503 deletions
Download Patch File Download Diff File Expand all files Collapse all files
HANDOFF_v0.8.51.md
-140
View File
@@ -1,140 +0,0 @@
# v0.8.51 Release Handoff — 2026-06-02
## Workspace
```
/Volumes/VIXinSSD/codewhale
Branch: codex/v0.8.51-arcee-provider (12 commits ahead of origin/main)
```
## What's Already Landed (committed, 12 commits on branch)
| Commit | What |
|--------|------|
| `e54a0a500` | feat(provider): add direct Arcee support |
| `99da87ca1` | fix(cli): wire arcee provider auth |
| `8eca75763` | test(tui): cover arcee provider picker entry |
| `06612495f` | chore(release): prep v0.8.51 — version bump, CHANGELOG |
| `fd69f4c80` | fix(tui): strip DEC private mode CSI fragments (#2592) |
| `5249723e1` | fix(engine): recover from turn panics (#2583, #1269) |
| `478bae451` | fix(tui): find deeply nested files via @/Ctrl+P (#2488) |
| `e95f759cd` | fix(tui): command-palette scroll visibility (#2590) |
| `cccc5ed55` | fix(shell): .NET/NuGet + Windows env (#1857) |
| `7aa73fad5` | fix(config): warn on misplaced shell/sandbox keys (#2589) |
| `a7d482067` | fix(clippy): clear -D warnings (#2599) |
| `79d78878b` | test(mcp): deterministic SSE reconnect (#2597) |
| `f886f28ac` | test(tui): update walk-depth test for new default depth |
**Claude branch `origin/claude/busy-mayer-b66rA` is identical to our HEAD** — same commit `f886f28ac`. Nothing to merge; already up to date.
## What's Applied in Working Tree (NOT committed)
4 files modified (88 insertions, 25 deletions):
| File | Change | Credits |
|------|--------|---------|
| `crates/tui/src/tui/diff_render.rs` | `wrap_text` preserves leading whitespace; fixes extra-space bug in PR #2591; adds 2 regression tests | @zlh124 (PR #2591, fix version from working tree) |
| `crates/tui/src/schema_migration.rs` | `#[allow(dead_code)]` on `pub mod registry` | @reidliu41 (PR #2601) |
| `crates/tui/src/prompts/base.md` | Tool desc: prefer `gh --json` CLI for GitHub triage | — |
| `crates/tui/src/prompts/base.txt` | Same prompt update for text variant | — |
## Ready to Apply (patch saved, NOT yet applied)
The model persistence patch is at `/tmp/model_persist.patch` (240 lines, 2 files):
- `crates/tui/src/commands/core.rs`: `/model` command remembers per-provider model selection + persist warning
- `crates/tui/src/settings.rs`: new `set_provider_model_selection()` and `persist_provider_model_selection()` methods
**Apply it:**
```bash
cd /Volumes/VIXinSSD/codewhale
git apply /tmp/model_persist.patch
```
This is small, self-contained, and directly improves UX for the new Arcee provider (model choice remembered across restarts). No dependency on the deferred image-attachment work.
## Deferred (in stash, do NOT apply for v0.8.51)
The stash (`stash@{0}`) contains:
- **Image attachment** (#2584/#2587): `ContentBlock::ImageUrl`, multimodal chat requests, base64 encoding, + exhaustive match arms across 15 files. Deferred by Hmbown — changes the request shape, needs multimodal endpoint testing.
- **GitHub structured route** (`fetch_url.rs`): new feature — routes GitHub issue/PR URLs through `gh` CLI. Too broad for v0.8.51.
- **Config custom model changes** (`commands/config.rs`): `normalize_custom_model_id` etc. Need review.
To view: `git stash show -p stash@{0}`
## What Remains
```bash
cd /Volumes/VIXinSSD/codewhale
# 1. Apply the model persistence patch
git apply /tmp/model_persist.patch
# 2. Commit all working-tree changes as one harvest commit
git add -A
git commit -m "harvest(v0.8.51): diff-render whitespace fix + schema dead_code + model persistence + prompt updates
- fix(diff-render): preserve leading whitespace in patch content lines
Credit: @zlh124 (PR #2591), with extra-space bug fixed.
- fix(tui): allow unused schema migration registry
Credit: @reidliu41 (PR #2601).
- feat(tui): persist per-provider model selection from /model command
- docs(prompts): prefer gh --json CLI for GitHub triage in agent instructions"
# 3. Run release gates
cargo fmt --all -- --check
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings
cargo test -p codewhale-tui -- --test-threads=4
# 4. If gates pass, rebuild
cargo install --path crates/tui --locked --force
codewhale --version
codewhale-tui --version
# 5. Final checks
git diff origin/main --stat
gh issue view 2600 --repo Hmbown/CodeWhale # re-read release checklist
```
## Release Checklist Status (issue #2600)
- [x] Arcee provider landed + tested
- [x] Cycle/checkpoint-restart system removed
- [x] Auto-compaction percentage/model-aware
- [x] Provider/gateway HTTP error sanitization
- [x] TUI fixes (blue dot, sidebar scroll, tooltip)
- [x] CHANGELOG + version bump
- [x] Clippy clean (#2599)
- [x] MCP SSE test deterministic (#2597)
- [ ] Full `cargo test --workspace` green — codewhale-tui validated; 1 environment-only Landlock test may fail on macOS
- [ ] `npm test` in `npm/codewhale`
- [ ] Harvest commits applied + re-gated
- [ ] Merge branch to `main`
- [ ] Tag `v0.8.51`, push tag
- [ ] Publish GitHub release + `npm publish`
## Contributors to Credit
| Contributor | Contribution | PR/Issue |
|-------------|-------------|----------|
| @zlh124 (jayzhu) | diff-render whitespace preservation | #2591 |
| @reidliu41 (Reid) | schema migration dead_code allow | #2601 |
| @xyuai | Image attachment root cause + initial PR | #2587, #2584 |
| @IcedOranges | Image attachment bug report | #2584 |
| @idling11 (Hanmiao Li) | Sidebar resize feature request | #2602 |
| @gordonlu (Gordon) | Engine death recovery | #2585 |
| @cyq1017 | File picker depth fix draft | #2593 |
## Risks / Notes
1. **Working tree was stashed** — the image attachment feature and GitHub structured route are deferred for v0.8.52+. The model persistence patch is the only remaining piece worth landing.
2. **DeepSeek naming**: The branch and committed code use "CodeWhale" naming throughout. Do not imply DeepSeek is deprecated.
3. **The `origin/claude/busy-mayer-b66rA` branch is identical to HEAD** — the Claude Code session in #2600 claimed "+8 commits" but those are the same commits already on this branch. Verify with `git rev-parse HEAD origin/claude/busy-mayer-b66rA`.
4. **Landlock test**: `sandbox::tests::test_parity_linux_landlock_available` will fail on macOS (no Landlock LSM). This is environment-only, not a regression. On CI Linux runners it passes.
5. **Cross-platform artifacts**: The release workflow builds macOS + Windows + NSIS installer on tag push. Not buildable locally on macOS alone.
---
Generated by deepseek-v4-pro in CodeWhale v0.8.51 pre-release triage.
Next session: read this file, apply `/tmp/model_persist.patch`, run gates, commit, and prepare the merge.
docs/LEGACY_RUST_AUDIT_0_7_6.md
-37
View File
@@ -1,37 +0,0 @@
# v0.7.6 Legacy Rust Audit
Status date: 2026-04-29
This audit is deliberately non-destructive. No compatibility code is removed in v0.7.6 unless tests prove public CLI, saved-session, tool-schema, and documented command paths no longer depend on it.
## Summary
| Surface | Owner module | Current consumer | Reference check | Compatibility reason | Current warning | Recommended action |
|---|---|---|---|---|---|---|
| Legacy MCP sync API (`McpServerInput`, `list`, `add`, `remove`, `call_tool`, `load_legacy`) | `crates/tui/src/mcp.rs` | Not wired into current `/mcp` command path; retained behind `#[allow(dead_code)]` | Direct Rust references and current MCP command path inspected; saved/config JSON compatibility still needs a dedicated smoke | Preserves old JSON shape including `mcpServers` alias and sync call helpers while the async MCP manager is the active path | Code TODO only | Gate behind an explicit legacy module or remove after CLI/runtime parity tests prove no caller uses it. Tracked by #218. |
| Legacy prompt constants/functions (`AGENT_PROMPT`, `YOLO_PROMPT`, `PLAN_PROMPT`, `base_system_prompt`, `normal_system_prompt`, etc.) | `crates/tui/src/prompts.rs` | Tests and older callers that still import prompt constants directly | Direct Rust references remain; public-crate and older harness imports are not proven absent | Layered prompt API replaced monolithic prompts, but older call sites may still compile against constants | None | Keep for v0.7.6; add deprecation annotations only after internal callers are migrated. Tracked by #219. |
| `/compact` slash command positioning | `crates/tui/src/commands/mod.rs` | Public slash-command registry and help overlay | Public command registry/docs path still references it | Users may still run `/compact` manually when they want an immediate replacement-style summary | Description is intentionally explicit about manual compaction | Keep as a manual compatibility command; do not remove until context/token issues are resolved. |
| `todo_*` compatibility tools | `crates/tui/src/tools/todo.rs` | Tool registry/model calls that still use `todo_add`, `todo_update`, `todo_list`, `todo_write` | Tool registry compatibility and saved tool-call risk remain | `checklist_*` is canonical, but old tool names may appear in saved prompts, traces, or model priors | Metadata marks `compat_alias: true`; descriptions say compatibility alias | Add explicit deprecation metadata with target version, then remove only after tool-schema migration evidence. Tracked by #220. |
| Deprecated sub-agent alias tools (`spawn_agent`, `send_input`, delegate aliases) | `crates/tui/src/tools/subagent/mod.rs` | Tool registry and model/tool-call compatibility | Tool registry compatibility and saved tool-call risk remain | Canonical names are `agent_spawn`, `agent_send_input`, etc.; alias names preserve older tool-call compatibility | `_deprecation` metadata and tracing warn; removal target is `v0.8.0` | Keep through v0.7.x; removal already has metadata. Tracked by #221. |
| Legacy root/provider TOML `api_key` compatibility | `crates/tui/src/config.rs`, `crates/config/src/lib.rs` | Config resolver; users with existing `api_key` in config files | Public config loading and docs still mention migration behavior | Keyring migration is preferred, but breaking existing configs would block startup/auth | Tracing warnings point to `deepseek auth set` / `deepseek auth migrate` | Keep; warnings are user-actionable. Removal should wait for a migration command and release-note window. |
| Model alias canonicalization (`deepseek-chat`, `deepseek-reasoner`, older V3/R1 aliases) | `crates/tui/src/config.rs`, `crates/config/src/lib.rs` | Config/env/model picker normalization | Public docs and existing configs may still use aliases | Preserves old documented DeepSeek aliases and maps them to `deepseek-v4-flash` | Silent alias by design | Keep; removing aliases would break configs without meaningful benefit. |
| Deprecated palette constants and aliases | `crates/tui/src/palette.rs`, `crates/tui/tests/palette_audit.rs` | Existing call sites plus audit tests | Palette audit enforces the remaining allowlist | Semantic aliases are preferred, but old constants exist to prevent broad style churn | Palette audit blocks direct deprecated uses outside allowlist | Keep aliases; continue moving call sites to semantic roles opportunistically. |
## Follow-Up Removal Candidates
These are not safe to remove in v0.7.6:
1. #218 Legacy MCP sync API: requires a call-graph check and explicit CLI/runtime parity tests for `/mcp`, `deepseek mcp`, and MCP server validation flows.
2. #219 Legacy prompt constants/functions: requires proving no public crate or older test harness imports them.
3. #220 `todo_*` tool aliases: requires deprecation metadata and a saved-trace/tool-schema migration window.
4. #221 Deprecated sub-agent alias tools: removal target is already encoded as `v0.8.0`, but the actual removal should be tracked and tested separately.
## Verification Checklist
Before removing any compatibility surface:
1. Search direct Rust references with `rg`.
2. Search docs and README command examples.
3. Run workspace tests with all features.
4. Run a saved-session/tool-call compatibility smoke if the surface affects tool schemas or persisted history.
5. Keep a release-note entry and, for user-visible config/tool changes, a migration hint for at least one minor release.
docs/MIMO_BENCHMARK_ISSUES.md
-89
View File
@@ -1,89 +0,0 @@
# MiMo v2.5 Benchmarking — Known Issues
Tracking doc for quirks and workarounds when benchmarking Xiaomi MiMo v2.5
through CodeWhale's harness integrations.
## PinchBench
### Issue 1: Model validation requires OpenRouter prefix
PinchBench validates models against OpenRouter's `/models` endpoint. If you
pass `mimo-v2.5-pro` without the `openrouter/xiaomi/` prefix, validation is
skipped entirely (it assumes it's a non-OpenRouter model). This means you
won't know if the model ID is wrong until the run fails.
**Workaround:** Always use `openrouter/xiaomi/mimo-v2.5-pro` for OpenRouter
routing, or use `--direct-mimo` for the Xiaomi API.
### Issue 2: PinchBench requires OPENROUTER_API_KEY
Even when using a direct provider, PinchBench's `lib_agent.py` checks for
`OPENROUTER_API_KEY` in some code paths. The `--direct-mimo` flag in our
runner works around this by setting up a custom OpenAI-compatible provider
entry in OpenClaw's `models.json` and exporting `OPENAI_API_KEY`/`OPENAI_BASE_URL`.
### Issue 3: Token Plan vs Pay-as-you-go key mismatch
Xiaomi MiMo has two API endpoints:
- **Token Plan** (`tp-` keys): `https://token-plan-sgp.xiaomimimo.com/v1`
- **Pay-as-you-go** (`sk-` keys): `https://api.xiaomimimo.com/v1`
Using the wrong key type with the wrong endpoint produces auth errors. The
runner now detects this and warns.
### Issue 4: OpenClaw is the runtime, not CodeWhale
PinchBench runs tasks through OpenClaw, not CodeWhale. This means the
benchmark measures MiMo v2.5's performance through OpenClaw's agent harness,
not through CodeWhale's tool system. For CodeWhale-native evaluation,
Terminal-Bench (via Harbor) is the better fit.
**Future:** Create a CodeWhale-native PinchBench adapter that loads tasks
from PinchBench's `tasks/` directory and runs them through `codewhale exec`.
## Terminal-Bench (Harbor)
### Issue 1: MiMo provider routing
Harbor passes models as `provider/model` format. For MiMo via OpenRouter,
use `openrouter/xiaomi/mimo-v2.5-pro`. For direct Xiaomi API, pass
`--provider xiaomi-mimo` as an extra agent flag.
### Issue 2: Container environment
The Harbor adapter installs codewhale via npm in the container. MiMo API
keys must be forwarded from the host environment. The adapter checks for
`XIAOMI_MIMO_API_KEY`, `OPENROUTER_API_KEY`, and `OPENAI_API_KEY`.
## SWE-bench
### Issue 1: MiMo thinking mode
MiMo v2.5 Pro supports extended thinking. For SWE-bench patch generation,
ensure the thinking level is set appropriately. The `--thinking high` flag
is passed through the CLI.
### Issue 2: Context window
MiMo v2.5 Pro has a 128K context window. Large SWE-bench instances (e.g.,
Django, sympy) may benefit from the full window. No special handling needed,
but worth monitoring token usage.
## Environment Variables Reference
```
# Xiaomi MiMo direct API
XIAOMI_MIMO_API_KEY=tp-... # Token Plan key
XIAOMI_MIMO_API_KEY=sk-... # Pay-as-you-go key
XIAOMI_MIMO_BASE_URL=https://token-plan-sgp.xiaomimimo.com/v1
XIAOMI_MIMO_MODEL=mimo-v2.5-pro
# Aliases also accepted
XIAOMI_API_KEY=...
MIMO_API_KEY=...
MIMO_BASE_URL=...
MIMO_MODEL=...
# OpenRouter (for MiMo via OpenRouter)
OPENROUTER_API_KEY=...
```
docs/REVIEW_PIPELINE.md
-84
View File
@@ -1,84 +0,0 @@
\# CodeWhale Review Pipeline
Welcome to CodeWhale! We receive a high volume of community PRs. To ensure a smooth and fast review process, please review our pipeline expectations below.
\## 1. CI Gates (Pre-Review Checklist)
Before a maintainer reviews your PR, it must pass our continuous integration (CI) checks.
\*\*Required Checks (Must Pass):\*\*
Please run these locally before pushing your code to avoid CI failures:
\* \*\*Format:\*\* `cargo fmt --all -- --check`
\* \*\*Linting:\*\* `cargo clippy --workspace --all-targets --all-features`
\* \*\*Tests:\*\* `cargo test --workspace --all-features --locked`
\*\*Informational Checks:\*\*
Checks from \*\*Greptile\*\* and \*\*GitGuardian\*\* are informational. If they flag something, review it, but they do not strictly block a review on their own unless a secret is leaked.
\## 2. Common Failure Modes \& Local Fixes
If CI fails, it is usually one of these three reasons:
\* \*\*Version Drift (`Cargo.lock` out of date):\*\* Run `cargo update` or `cargo build` locally to update the lockfile and commit the changes.
\* \*\*Lint Failures:\*\* Check the clippy warnings from the command above and fix the specific lines flagged.
\* \*\*Windows Test Flakiness:\*\* Occasionally, tests may time out on Windows runners. If you are confident your code didn't break it, leave a comment asking a maintainer to re-trigger the CI.
\## 3. PR Etiquette
To help us review your code quickly, please adhere to the following:
\* \*\*One Concern Per PR:\*\* Keep diffs highly focused. Do not mix refactoring with new feature additions.
\* \*\*Link the Issue:\*\* Always include `Closes #N` (replace N with the issue number) in your PR description so GitHub automatically links them.
\* \*\*Rebase:\*\* Always rebase your branch onto the latest `main` branch before requesting a review.
\## 4. The Review Workflow
Once CI is green, your PR enters the review queue.
\* \*\*Who reviews:\*\* Core maintainers will review the PR.
\* \*\*`autonomous-ready` Label:\*\* If a maintainer applies this label, it means the PR is approved in concept and is queued for our automated integration system.
\* \*\*The Nightly Loop:\*\* We run extensive integration loops overnight. If your PR is approved, it may wait for this nightly loop before final merging to ensure system stability.
\## 5. Post-Merge Actions
After your code is merged, the following automated actions occur:
\* `CHANGELOG.md` is updated.
\* `npm` wrappers are synced.
\* Binary rebuilds are triggered for all platforms.
\* Website and documentation are synced with your new changes.
Thank you for contributing to CodeWhale!
docs/RLM_BRANCHING_ROADMAP.md
-92
View File
@@ -1,92 +0,0 @@
# RLM Branching Roadmap
This note records the v0.8.45 design direction for RLM, DSPy, GEPA, and Model
Lab without adding runtime dependencies or changing the live agent loop.
## Branching Primitive
CodeWhale uses the same branching primitive at three scales:
1. Release tracks. Each milestone fans into named tracks. A track must stay
independently reviewable, mergeable, and slippable. Unfinished work rolls
forward instead of blocking the release.
2. Capability worksets. Model Lab capabilities such as Hugging Face,
observability, evals, serving, DSPy, GEPA, and training infrastructure ship
as opt-in worksets with their own feature flag, install path, license note,
and telemetry posture.
3. Pareto compile branches. Optimizable modules keep candidate
`(instructions, demos, score)` triples. Branches that violate pinned
constitution clauses are pruned; branches that win at least one eval remain
on the frontier until the maintainer lands or rejects them.
The maintainer chooses the frontier point. CodeWhale should not collapse
branches prematurely.
## v0.8.45
- Close the current control-plane and workbench issues before the broader
fan-out begins: #1982, #2027, #2032, #2016, and #2034.
- Keep `AGENTS.md` and `CLAUDE.md` maintainer-local. `AGENTS.md` is ignored
from this milestone forward.
- Land the RLM symbolic-object substrate: active prompt, session metadata,
transcript, latest user message, and per-message refs are named objects that
RLM can open without copying raw prompt/history text into the parent
transcript.
## v0.8.46
- Generalize Fin into a structured-feedback verifier substrate.
- Add first replay-eval definitions harvested from existing trajectories.
- Scaffold the Repeatability Score footer slot as pending until evals populate
it.
- Add module artifact schema v0 as Rust types only.
- Draft the "Compiled Word" constitution article.
## v0.8.47
- Promote Hugging Face as a first-class provider through Inference Providers
and Router.
- Add deterministic RLM replay: context snapshot, seed, child model IDs, and
temperatures.
- Route large logs and payloads to RLM workbench sessions instead of the
parent transcript.
- Add sub-query memoization keyed by prompt, context hash, and model.
- Enforce RLM budgets at the Rust registry layer: depth, calls, wall time, and
cost.
## v0.8.48
- Remove the legacy `deepseek` and `deepseek-tui` shim binaries.
- Finish Docker and Homebrew rename cleanup.
- Populate Repeatability Score from a small offline eval suite that ships in
core.
## v0.9.0
- Emit per-turn `trajectory.jsonl` as the trainset substrate.
- Add `codewhale replay <turn_id>` for deterministic replay.
- Render module artifacts from the `[[ ## field ## ]]` form through a Rust
adapter.
- Land the eval pipeline: suites, replay evals, and measurement substrate.
- Add a `/compile` command stub that explains the offline loop.
## v0.10.0
- Add opt-in Model Lab workset installers for DSPy and GEPA. The default
install keeps zero Python dependencies.
- Build the first offline compile pipeline: Rust harvests trainsets, a Python
sidecar runs the optimizer, and CodeWhale emits a reviewed Module JSON
artifact.
- Add the Compile TUI panel with Pareto frontier, lineage tree, and
Land/Reject/Revise actions.
- Land the first optimized tool-description and agent-prompt artifacts through
PRs. Constitution clauses remain pinned outside the optimized region.
- Add whale-species module passports, for example
`Sei: codewhale-agent-prompt.v0.10.0-gepa-1`.
## Trust Boundary
Compilation is offline. Runtime consumes reviewed JSON artifacts. Online
closed-loop optimization is out of scope because adversarial users could game a
live coding harness. Any workset can fail independently without dragging the
release, the core runtime, or other Pareto branches with it.
docs/archive/V0_7_5_IMPLEMENTATION_PLAN.md
-61
View File
@@ -1,61 +0,0 @@
# v0.7.5 Implementation Plan
Scope: background shell job UX, in-TUI MCP management/discovery, and V4
context/cache policy. Do not include provider expansion or Whalescale
rename/migration work in this release lane.
## Context/cache decision
Default path:
- Keep the transcript append-only and preserve the stable prefix for DeepSeek V4 cache reuse.
- Disable replacement-style `auto_compact` by default.
- Keep replacement compaction manual or late: if a user enables `auto_compact`, V4 compacts only near the 80% model-window guard (`800000` tokens for 1M-context models), not at reasoning-effort soft caps.
- Keep the Flash seam manager (`[context].enabled`) opt-in until issue #200 has repeatable cache-hit/miss evidence.
- Keep the capacity controller disabled by default. Treat it as telemetry or an experimental guardrail unless `capacity.enabled = true` is set.
- Use emergency overflow recovery only when the request would otherwise exceed the model input budget.
Rationale: V4's 1M-token window and prefix-cache economics make early
replacement compaction suspect. The first shippable slice should prevent old
128K-era heuristics from rewriting context before there is evidence that the
rewrite is cheaper and more reliable than preserving a hot prefix.
## Shippable slices
### Slice 1: Context policy and docs
- Change default `auto_compact` to off.
- Keep V4 replacement-compaction thresholds late and independent of reasoning effort.
- Make `[context].enabled` default to false.
- Make `docs/CONFIGURATION.md`, `docs/capacity_controller.md`, and `config.example.toml` match code defaults.
- Add focused tests for defaults and V4 threshold behavior.
### Slice 2: Background shell job center (#195)
- Add a job-center view fed by `ShellManager::list()`.
- Show command, cwd, linked task id when available, status, elapsed time, exit code, and latest output.
- Add controls to inspect full output, poll latest output, send stdin for PTY/stdin-capable jobs, kill a background job, and attach completed output as task evidence.
- Mark restart-stale jobs explicitly rather than presenting them as live.
- Add lifecycle tests for start, poll, cancel, complete, stale/restart, plus TUI snapshots for running and completed job details.
### Slice 3: MCP manager (#196)
- Add `/mcp` or a command-palette action that opens an MCP manager view.
- Show resolved config path, server enabled/disabled state, transport, command/url, timeout settings, startup errors, and discovered tool/resource/prompt counts.
- Wire `mcp_config_path` into the interactive config surface.
- Support init, add stdio server, add HTTP/SSE server, enable, disable, remove, validate, reconnect, and inspect tools/resources/prompts.
- Preserve both `servers` and `mcpServers` config shapes.
### Slice 4: MCP discoverability (#197)
- Add an MCP command-palette section backed by the same discovery state as the manager.
- Group tools/resources/prompts by server.
- Show disabled/failed servers without blocking palette rendering.
- Keep model-visible names consistent with `mcp_<server>_<tool>`.
## Stop rules
- Do not close #159 or #162 unless a verified PR actually resolves them.
- Do not add provider expansion.
- Do not rename or migrate anything to Whalescale.
- Do not broaden the TUI into a large redesign; each slice should remain independently testable and shippable.