minima-cli 0.5.0__tar.gz → 0.7.1__tar.gz

minima_cli-0.7.1/.github/workflows/catalog-snapshot.yml

@@ -0,0 +1,100 @@
+name: Catalog — refresh vendored snapshot
+
+# Keeps the vendored cold-start model catalog fresh so it stops drifting by hand.
+#
+# WHAT/WHY: src/minima/catalog/data/capability_priors.json is the cold-start
+# fallback the server loads when the live cost feed (LiteLLM/OpenRouter) is
+# unreachable — see src/minima/catalog/store.py (load_snapshot_cards) and the
+# /v1/models router. It used to be hand-maintained and drifted stale (e.g.
+# missing the gpt-5 family). This job pulls the *live* served catalog from
+# api.minima.sh/v1/models — the source-of-truth that already merges curated
+# capability priors with live cost — normalizes it (via jq) into the EXACT
+# shape the loader reads, and opens a PR only when it actually changed.
+#
+# We deliberately DO NOT commit straight to main and DO NOT hand-edit the JSON:
+# a reviewer sees the diff, and the automation (not a human) keeps it current.
+on:
+  schedule:
+    - cron: "17 6 * * *" # daily (~every 24h); minute offset avoids the top-of-hour rush
+  workflow_dispatch: {}
+
+concurrency:
+  group: catalog-snapshot
+  cancel-in-progress: false
+
+# Least privilege: only what's needed to push a chore branch and open a PR.
+permissions:
+  contents: write
+  pull-requests: write
+
+env:
+  # Source-of-truth: the live served catalog. Override via repo/environment var
+  # CATALOG_SOURCE_URL if the prod host ever changes.
+  CATALOG_URL: ${{ vars.CATALOG_SOURCE_URL || 'https://api.minima.sh/v1/models' }}
+  SNAPSHOT_PATH: src/minima/catalog/data/capability_priors.json
+  BRANCH: chore/catalog-snapshot-auto
+
+jobs:
+  refresh:
+    name: Fetch live catalog → PR if changed
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v5
+
+      - name: Fetch + normalize live catalog into the vendored snapshot shape
+        run: |
+          set -euo pipefail
+          # /v1/models returns {models:[ModelCard...], catalog_version, stale}.
+          # ModelCard is a superset of the snapshot object, so we project it back
+          # to the exact fields load_snapshot_cards() reads and drop the runtime
+          # metadata (cost_source/cost_fetched_at/cost_stale/capability_source),
+          # which the loader always re-stamps as "fallback-snapshot".
+          curl -fsSL --retry 3 --retry-delay 5 --max-time 60 "$CATALOG_URL" -o live.json
+
+          count="$(jq '.models | length' live.json)"
+          if [ "$count" -lt 5 ]; then
+            echo "::error::live catalog returned only $count models (<5); refusing to overwrite snapshot"
+            exit 1
+          fi
+
+          version="fallback-snapshot-$(date -u +%Y-%m)"
+          note="Cold-start fallback only. Auto-refreshed by .github/workflows/catalog-snapshot.yml from the live /v1/models catalog — do not hand-edit. Live cost is overlaid from LiteLLM/OpenRouter at runtime; capability_by_task_type are normalized [0,1] heuristic priors, corrected by accumulated memory. Prices are approximate USD per million tokens."
+
+          jq \
+             --arg version "$version" \
+             --arg note "$note" '{
+               version: $version,
+               note: $note,
+               models: (.models | sort_by(.model_id) | map({
+                 model_id, provider, display_name,
+                 input_cost_per_mtok, output_cost_per_mtok, cache_read_cost_per_mtok,
+                 supports_prompt_caching, context_window, max_output_tokens,
+                 capability_priors, capability_by_task_type
+               }))
+             }' live.json > "$SNAPSHOT_PATH.tmp"
+          mv "$SNAPSHOT_PATH.tmp" "$SNAPSHOT_PATH"
+          rm -f live.json
+          echo "Normalized $count models into $SNAPSHOT_PATH"
+
+      - name: Commit + open PR only if the snapshot changed
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          set -euo pipefail
+          if git diff --quiet -- "$SNAPSHOT_PATH"; then
+            echo "Snapshot already up to date; nothing to do."
+            exit 0
+          fi
+
+          git config user.name "github-actions[bot]"
+          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
+          git checkout -B "$BRANCH"
+          git add "$SNAPSHOT_PATH"
+          git commit -m "chore(catalog): refresh vendored model snapshot from live /v1/models"
+          git push -u origin "$BRANCH" --force-with-lease
+
+          gh pr create --base main --head "$BRANCH" \
+            --title "chore(catalog): refresh vendored model snapshot" \
+            --body "Automated refresh of \`$SNAPSHOT_PATH\` from the live catalog at \`$CATALOG_URL\` (normalized to the loader's shape). Opened by \`.github/workflows/catalog-snapshot.yml\`. Review the diff — this is the cold-start fallback the server serves when the live cost feed is unreachable." \
+            || echo "PR already open for $BRANCH; pushed update."

minima_cli-0.7.1/.github/workflows/ci.yml

@@ -0,0 +1,69 @@
+name: CI — PR checks
+
+# Gate on every PR to main (and on push to main) with the exact local test
+# conventions: server (ruff + offline pytest) and TUI (bun test + tsc). Two
+# independent jobs so a red on one surfaces without masking the other. No
+# deploy, no secrets — the suites are offline (`-m "not live and not eval"`).
+# mypy runs after ruff/pytest: src/minima is now type-clean, so it gates too.
+on:
+  pull_request:
+    branches: [main]
+  push:
+    branches: [main]
+
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+env:
+  BUN_VERSION: "1.3.14"
+
+jobs:
+  server:
+    name: Server — ruff + pytest + mypy
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v5
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+
+      - name: Sync deps (dev extra)
+        run: uv sync --extra dev
+
+      - name: Ruff
+        run: uv run ruff check src client_sdk tests
+
+      - name: Pytest (offline)
+        run: uv run pytest -m "not live and not eval" -q
+
+      - name: Mypy
+        run: uv run mypy src/minima
+
+  tui:
+    name: TUI — bun test + tsc
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: packages/tui
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v5
+
+      - name: Set up Bun
+        uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: ${{ env.BUN_VERSION }}
+
+      - name: Install deps
+        run: bun install --frozen-lockfile
+
+      - name: Test
+        run: bun test
+
+      - name: Typecheck
+        run: bun run check

minima_cli-0.7.1/AGENTS.md

@@ -0,0 +1,58 @@
+# AGENTS.md
+
+Guidance for both human and AI agents working in this repo.
+
+## What this repo is
+
+- **`src/minima/`** — Minima: a recommend-only LLM cost-optimization service (FastAPI,
+  Python 3.11+). It does NOT proxy LLM calls. It tells you which model to run, you run
+  it, judge quality, and feed the outcome back via `POST /v1/feedback` so its Mubit
+  memory sharpens. See `docs/concepts.md` for the algorithm.
+- **`client_sdk/minima_client/`** — bundled sync + async Python client. Ships inside the
+  same wheel.
+- **`packages/tui/`** — the `minima` CLI/TUI (TypeScript/Bun, shipped via Homebrew:
+  `brew tap mubit-ai/minima`). It replaced the old Python harness (`src/minima_harness`,
+  removed in v0.7.0). See `packages/tui/README.md`.
+
+## The Minima loop (always respect this)
+
+```
+recommend  ->  run the model yourself  ->  judge quality  ->  feedback
+```
+
+Minima never runs the model. Any harness owns model dispatch + quality judging. Feedback
+MUST include realized `input_tokens` / `output_tokens` / `actual_cost_usd` / `latency_ms`
+so the cost basis can climb `estimate -> observed -> rescaled` (the biggest accuracy
+lever). Outcome thresholds: `success >= 0.8`, `partial >= 0.4`, else `failure`.
+
+## Conventions
+
+- `from __future__ import annotations` at the top of every module.
+- Pydantic v2 `BaseModel` for serializable schemas; `@dataclass(slots=True)` for internal
+  types; `StrEnum` for enums; `Protocol` for seams (`Memory`, `Reasoner`, `Provider`).
+- Async-first. Bridge sync SDKs (Mubit) off the event loop via `anyio`/threadpools.
+- `structlog` via `get_logger("minima.<sub>")`.
+- ruff `line-length=100`, mypy `py311`. Never break the hot path: bookkeeping failures are
+  logged-and-swallowed (`except Exception: # noqa: BLE001`).
+- NO comments unless asked. Match existing style.
+
+## Commands
+
+```bash
+uv sync --extra dev                       # install (uv is the package manager)
+uv run ruff check . && uv run ruff format .  # lint + format
+uv run mypy src/minima                     # typecheck
+uv run pytest                              # unit + integration (hermetic, offline)
+uv run pytest -m live                      # needs a running Mubit (make run-mubit)
+make run                                   # local Minima on :8080
+```
+
+Offline tests MUST stay hermetic: the `conftest.py` autouse fixture neutralizes `.env`.
+Use `tests/factories.py:FakeMemory` + `create_app(...)` + `TestClient` for in-process
+tests without Mubit.
+
+## Agent harness
+
+The Python harness (`src/minima_harness`) was removed in v0.7.0. Its successor is the
+TypeScript harness + TUI in `packages/tui` (the shipped `minima` CLI) — see
+`packages/tui/README.md` for architecture, commands, and hard rules.

{minima_cli-0.5.0 → minima_cli-0.7.1}/CHANGELOG.md

@@ -4,6 +4,97 @@ All notable changes to Minima are documented here. The format follows
 [Keep a Changelog](https://keepachangelog.com/), and the project aims to follow
 [Semantic Versioning](https://semver.org/).
 
+## [0.7.1] - 2026-07-05
+
+### Changed (API behavior — note for integrators)
+- **`max_cost_per_call` is now a true hard filter.** When no model fits the budget,
+  `POST /v1/recommend` returns **422** (`"no model within max_cost_per_call budget"`)
+  instead of 200 with the cheapest over-budget model plus a `no_model_within_cost_budget`
+  warning. This matches the documented "hard filter" contract and the existing
+  no-candidates behavior. Callers who want "cheapest possible regardless of ceiling"
+  should use the cost-quality slider, not `max_cost_per_call`.
+- **Auth rejects malformed bearer tokens.** A bearer token that is not in the Mubit key
+  format (`mbt_…`) now returns **401** before any work, instead of being accepted and
+  served from priors. A missing bearer with a server-configured `MUBIT_API_KEY` fallback
+  is unaffected.
+
+### Fixed
+- **Cold-start catalog prices were stale.** The vendored fallback snapshot
+  (`capability_priors.json`) is refreshed from the live catalog (e.g. `claude-opus-4-8`
+  `15/75` → `5/25`), and a scheduled workflow now keeps it current so it stops drifting
+  by hand. (The auto-refresh updates prices for the curated model list; it does not add
+  new models — expanded provider coverage such as the gpt-5 family remains a separate
+  curation.)
+- **Server version string can no longer drift.** `minima.__version__` (reported by
+  `/v1/health` and `/v1/capabilities`) now derives from installed package metadata instead
+  of a hardcoded constant that had silently lagged across releases.
+- **Feedback reconciliation types the quality value honestly** as `float | None` — unjudged
+  rows keep `NULL`, no fabricated default (preserves the M-J2 fix).
+
+### Internal
+- **PR CI added** — every PR now runs server (`ruff` + `pytest` + `mypy`) and TUI
+  (`bun test` + `tsc`) checks; the recommender is mypy-clean.
+
+## [0.7.0] - 2026-07-05
+
+### Added
+- **`GET /v1/capabilities`** — server feature handshake (api version, honored constraint
+  fields, feature flags) so clients can gate enforce-mode features on what the server
+  actually supports instead of guessing. (#54)
+- **Sub-agent tree visualization** — a live `▸ step [status] $cost` panel (`/tree`) fed by
+  tagged child events during multi-agent runs. (#55)
+- **Git worktree isolation for parallel sub-agents** — `isolation: "workdir"` delegations run
+  in a temporary `git worktree` (with a dirty-tree warning and automatic cleanup), so parallel
+  children editing the same files can't clobber each other. (#55)
+- **Delegation ops-rules + BLOCKED convention** — sub-agents get explicit operational rules,
+  boundary refusals surface as `BLOCKED` → `partial` outcome so the parent can tell, and the
+  task tool carries anti-retry guidance (no more re-running an identical failed DAG). (#59)
+
+### Fixed
+- **Every Claude call timed out in the harness** — the Anthropic SDK was handed a timeout in
+  seconds where it expects milliseconds (a 30–60 ms budget), so every Claude stream/complete
+  call died with "Request timed out" and fed quality-0 failures into routing. (#56)
+- **Quality-score fabrication in the feedback loop (M-J2)** — unjudged successes no longer
+  default to quality 0.9 in the server decision log; the harness now sends a `judged` flag and
+  unjudged rows reconcile with `quality = NULL`, so calibration and savings metrics stop
+  trusting values that were never measured. (#54)
+- **Judge hardening** — empty-output guard (scores 0 without an API call), head+tail
+  truncation so tail requirements survive long outputs, `<response>` delimiters + scoped-trust
+  system prompt against response-embedded injection, and a `parseScore` fix for
+  "X out of 10" phrasing. (#57)
+- **Gemini reasoner starvation** — advisory JSON calls (classify/rank) no longer burn their
+  entire token budget on thinking before emitting JSON; RANK_SYSTEM invariants hardened. (#58)
+
+### Notes
+- `minima-cli` on PyPI resumes at 0.7.0: the project version had lagged at 0.5.0, so the
+  0.6.0 release build was silently skipped by `--skip-existing` and 0.6.0 was never published.
+
+## [0.6.0] - 2026-07-02
+
+Agent-core release (milestones M-A…M-I): cost-aware sub-agent orchestration — `task` tool
+with sequential and parallel DAG fan-out under a semaphore, per-child routing, budgets and
+timeouts; DB-backed `BudgetLedger` with graduated enforcement; SQLite persistence spine
+(runs/events/decisions + rehydration); recovery ladder walking server-supplied rungs on
+failure; effort routing Phase A + fleet metrics; feedback-loop poisoning fixes; feature-vector
+classifier with strongest-signal scoring. *(Never published to PyPI — see the 0.7.0 note.)*
+
+## [0.5.2] - 2026-07-02
+
+Fixed TUI viewport-overflow rendering corruption; docs rebrand (Manrope, "minima by Mubit"
+nav logo, new favicon).
+
+## [0.5.1] - 2026-07-01
+
+Mubit memory in the TS harness (recall-before-route + outcome write-back with stable session
+ids); benign routing diagnostics no longer render as errors; live model catalog; docs migrated
+to Vocs with a Homebrew install guide.
+
+## [0.5.0] - 2026-07-01
+
+The TypeScript/Bun TUI becomes the shipped CLI: one-click `minima auth` (browser login,
+per-repo project mapping, workspace provisioning), the Homebrew tap ships the compiled binary
+instead of a Python venv formula, and a comprehensive routing/tool test suite lands.
+
 ## [0.4.10] - 2026-06-26
 
 ### Changed

{minima_cli-0.5.0 → minima_cli-0.7.1}/Makefile

@@ -1,7 +1,7 @@
-.PHONY: install run test lint fmt live eval seed refresh-catalog harness-demo harness-live harness-test harness tui-install tui-test tui-check tui-build tui tui-dev
+.PHONY: install run test lint fmt live eval seed refresh-catalog tui-install tui-test tui-check tui-build tui tui-dev
 
 install:
-	uv sync --extra dev   # dev pulls server + harness + tui for the full test suite
+	uv sync --extra dev   # dev pulls server + reasoner extras for the full test suite
 
 run:
 	uv run --extra server uvicorn minima.main:app --reload --host $${MINIMA_HOST:-0.0.0.0} --port $${MINIMA_PORT:-8080}
@@ -26,20 +26,6 @@ eval:
 seed:
 	uv run minima-seed --limit $${LIMIT:-2000} --lane $${LANE:-minima:default}
 
-# --- minima_harness convenience targets (creds live in gitignored .env.harness) ---
-
-harness-demo:
-	uv run python examples/harness_warmup.py
-
-harness-live:
-	uv run --env-file .env.harness python examples/harness_warmup.py --live --rounds $${ROUNDS:-1}
-
-harness-test:
-	uv run --env-file .env.harness pytest tests/harness -m live -v
-
-harness:
-	uv run --extra harness --extra tui --env-file .env.harness minima-harness $(ARGS)
-
 # --- TS TUI (packages/tui) — run from the repo root so .env.harness auto-loads --------
 
 TUI := packages/tui

{minima_cli-0.5.0 → minima_cli-0.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: minima-cli
-Version: 0.5.0
+Version: 0.7.1
 Summary: Minima CLI: cost-aware LLM model routing — recommend cheaper models, backed by Mubit memory.
 Project-URL: Homepage, https://docs.minima.sh
 Project-URL: Documentation, https://docs.minima.sh
@@ -30,7 +30,6 @@ Provides-Extra: dev
 Requires-Dist: anthropic>=0.40; extra == 'dev'
 Requires-Dist: fastapi>=0.115; extra == 'dev'
 Requires-Dist: google-genai>=0.3; extra == 'dev'
-Requires-Dist: keyring>=24; extra == 'dev'
 Requires-Dist: mypy>=1.10; extra == 'dev'
 Requires-Dist: psycopg2-binary>=2.9; extra == 'dev'
 Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
@@ -38,11 +37,7 @@ Requires-Dist: pytest>=8.2; extra == 'dev'
 Requires-Dist: redis>=5.0; extra == 'dev'
 Requires-Dist: respx>=0.21; extra == 'dev'
 Requires-Dist: ruff>=0.5; extra == 'dev'
-Requires-Dist: textual>=3.0; extra == 'dev'
 Requires-Dist: uvicorn[standard]>=0.30; extra == 'dev'
-Provides-Extra: harness
-Requires-Dist: anthropic>=0.40; extra == 'harness'
-Requires-Dist: google-genai>=0.3; extra == 'harness'
 Provides-Extra: reasoner-anthropic
 Requires-Dist: anthropic>=0.40; extra == 'reasoner-anthropic'
 Provides-Extra: reasoner-gemini
@@ -55,9 +50,6 @@ Requires-Dist: fastapi>=0.115; extra == 'server'
 Requires-Dist: psycopg2-binary>=2.9; extra == 'server'
 Requires-Dist: redis>=5.0; extra == 'server'
 Requires-Dist: uvicorn[standard]>=0.30; extra == 'server'
-Provides-Extra: tui
-Requires-Dist: keyring>=24; extra == 'tui'
-Requires-Dist: textual>=3.0; extra == 'tui'
 Description-Content-Type: text/markdown
 
 # Minima
@@ -176,7 +168,6 @@ Sync + async clients and zero-code `autocapture`: **[Python Client SDK](docs/cli
 | [Multi-Tenancy](docs/multi-tenancy.md) | One deployment, many orgs, per-org Mubit instances. |
 | [Operations](docs/operations.md) | Deployment, health, degradation, monitoring, secrets. |
 | [Examples](docs/examples.md) | Guided tour of the runnable examples. |
-| [Agent Harness](docs/harness.md) | `minima_harness`: a Minima-routing port of PI's agent toolkit. |
 
 ## Examples
 
@@ -191,33 +182,21 @@ Runnable, progressively advanced — in **[`examples/`](examples/)**:
 | 5 | [`05_autocapture.py`](examples/05_autocapture.py) | Zero-code intake via `mubit.learn`. |
 | 6 | [`06_routed_llm_call.py`](examples/06_routed_llm_call.py) | Routing a real Claude call + feedback. |
 | 7 | [`07_multitenant_admin.py`](examples/07_multitenant_admin.py) | Provision an org, call as that tenant. |
-| 8 | [`harness_warmup.py`](examples/harness_warmup.py) | The `minima_harness` agent loop (demo mode needs no keys). |
 
-## Agent harness
+## The `minima` CLI
 
-[`minima_harness/`](src/minima_harness) is a lean Python port of
-[`@earendil-works/pi`](https://github.com/earendil-works/pi)'s agent toolkit, made
-Minima-native: an `Agent` runtime with tool calling **plus** a `MinimaAgent` that routes
-every prompt through Minima and feeds the realized tokens/cost/quality back. It is the
-"run the model yourself" half of the Minima loop, packaged.
-
-```python
-from minima_harness.minima import MinimaAgent, HarnessConfig
-
-agent = MinimaAgent(HarnessConfig.from_env())   # MINIMA_URL, candidates, judge policy
-await agent.prompt("Summarize this incident.", task_type="summarization", slider=3)
-# -> Minima picked the model, the agent ran it, judged quality, fed the outcome back
-```
-
-Try it with no keys via the in-process demo:
+The `minima` CLI/TUI — a coding agent that routes every prompt through Minima and feeds
+realized tokens/cost/quality back — is a TypeScript/Bun binary that lives in
+[`packages/tui/`](packages/tui/) and installs via Homebrew:
 
 ```bash
-uv run python examples/harness_warmup.py          # demo (in-process Minima + fake provider)
-uv run python examples/harness_warmup.py --live   # real Minima + real providers
+brew tap mubit-ai/minima
+brew install minima
 ```
 
-Full architecture, the loop mapping, and extension guide:
-**[Agent Harness](docs/harness.md)**.
+The PyPI package (`pip install minima-cli`) is **not** the CLI: it ships the Python
+client SDK (`minima_client`) and the server + operator tooling (`minima-seed`,
+`minima-calibration-report`). The old Python harness/TUI was removed in v0.7.0.
 
 ## Configuration
 
@@ -254,7 +233,7 @@ src/minima/
   tenancy/          runtime · registry · context · keys · secrets
   seeding/          routerbench · synthetic · run_seed (minima-seed CLI)
   schemas/          common · recommend · workflow · feedback · models_catalog · strategies · admin
-src/minima_harness/   ported pi-ai (ai/) + pi-agent-core (agent/) + Minima integration (minima/) — see docs/harness.md
+packages/tui/         the `minima` CLI/TUI (TypeScript/Bun, ships via Homebrew)
 client_sdk/minima_client/   client (sync+async) · autocapture · errors
 docs/               full documentation       examples/   runnable examples
 tests/              unit · integration (FakeMemory) · live (-m live) · eval (-m eval)

{minima_cli-0.5.0 → minima_cli-0.7.1}/README.md

@@ -114,7 +114,6 @@ Sync + async clients and zero-code `autocapture`: **[Python Client SDK](docs/cli
 | [Multi-Tenancy](docs/multi-tenancy.md) | One deployment, many orgs, per-org Mubit instances. |
 | [Operations](docs/operations.md) | Deployment, health, degradation, monitoring, secrets. |
 | [Examples](docs/examples.md) | Guided tour of the runnable examples. |
-| [Agent Harness](docs/harness.md) | `minima_harness`: a Minima-routing port of PI's agent toolkit. |
 
 ## Examples
 
@@ -129,33 +128,21 @@ Runnable, progressively advanced — in **[`examples/`](examples/)**:
 | 5 | [`05_autocapture.py`](examples/05_autocapture.py) | Zero-code intake via `mubit.learn`. |
 | 6 | [`06_routed_llm_call.py`](examples/06_routed_llm_call.py) | Routing a real Claude call + feedback. |
 | 7 | [`07_multitenant_admin.py`](examples/07_multitenant_admin.py) | Provision an org, call as that tenant. |
-| 8 | [`harness_warmup.py`](examples/harness_warmup.py) | The `minima_harness` agent loop (demo mode needs no keys). |
 
-## Agent harness
+## The `minima` CLI
 
-[`minima_harness/`](src/minima_harness) is a lean Python port of
-[`@earendil-works/pi`](https://github.com/earendil-works/pi)'s agent toolkit, made
-Minima-native: an `Agent` runtime with tool calling **plus** a `MinimaAgent` that routes
-every prompt through Minima and feeds the realized tokens/cost/quality back. It is the
-"run the model yourself" half of the Minima loop, packaged.
-
-```python
-from minima_harness.minima import MinimaAgent, HarnessConfig
-
-agent = MinimaAgent(HarnessConfig.from_env())   # MINIMA_URL, candidates, judge policy
-await agent.prompt("Summarize this incident.", task_type="summarization", slider=3)
-# -> Minima picked the model, the agent ran it, judged quality, fed the outcome back
-```
-
-Try it with no keys via the in-process demo:
+The `minima` CLI/TUI — a coding agent that routes every prompt through Minima and feeds
+realized tokens/cost/quality back — is a TypeScript/Bun binary that lives in
+[`packages/tui/`](packages/tui/) and installs via Homebrew:
 
 ```bash
-uv run python examples/harness_warmup.py          # demo (in-process Minima + fake provider)
-uv run python examples/harness_warmup.py --live   # real Minima + real providers
+brew tap mubit-ai/minima
+brew install minima
 ```
 
-Full architecture, the loop mapping, and extension guide:
-**[Agent Harness](docs/harness.md)**.
+The PyPI package (`pip install minima-cli`) is **not** the CLI: it ships the Python
+client SDK (`minima_client`) and the server + operator tooling (`minima-seed`,
+`minima-calibration-report`). The old Python harness/TUI was removed in v0.7.0.
 
 ## Configuration
 
@@ -192,7 +179,7 @@ src/minima/
   tenancy/          runtime · registry · context · keys · secrets
   seeding/          routerbench · synthetic · run_seed (minima-seed CLI)
   schemas/          common · recommend · workflow · feedback · models_catalog · strategies · admin
-src/minima_harness/   ported pi-ai (ai/) + pi-agent-core (agent/) + Minima integration (minima/) — see docs/harness.md
+packages/tui/         the `minima` CLI/TUI (TypeScript/Bun, ships via Homebrew)
 client_sdk/minima_client/   client (sync+async) · autocapture · errors
 docs/               full documentation       examples/   runnable examples
 tests/              unit · integration (FakeMemory) · live (-m live) · eval (-m eval)