Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions docs/ROADMAP.md
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@ original plan.
| **M7 — Any host** | v0.18 | Session 9: `HostAdapter`, capability matrix, `.aladdin/config.yaml`, host swap, metrics (§4.9–4.10) | done: `HostAdapter` + `host check` in CI, capability matrix, usage accuracy, `.aladdin/config.yaml` with migration, `host swap`, the full metrics table incl. context-window share (tests: `host-adapter`, `portable-config`, `host-swap`, `metrics`); DeepSeek Harness (`dsh`) as a fourth host, tested on its real runtime (tests: `dsh-plugin`, `dsh-runtime`); a measured live dsh run is open (needs a DeepSeek key) |
| **M8 — Aladdin 1.0** | v1.0 | Session 10: `/aladdin` + `aladdin` CLI with aliases, site, measured public runs (§4.11). The rename to aloop shipped early in v0.11.0 | in progress: `bin/aladdin` + `/aladdin` with `aloop`/`agentic` aliases (test: `aladdin-cli.test.py`); natural-language auto-trigger on every host (`intent-trigger`, test: `intent-trigger.test.py`); README reordered product-first; site at `docs/index.html` (Pages switch is the owner's). evidence ledger `docs/evidence/README.md` + `run-summary` (test: `evidence.test.py`). `e2e-live.sh --host codex|opencode` runs the same loop on those hosts (`aloop install <host>` into the run repo, then `codex exec --json` / `opencode run --format json`; `--dry-run` prints the command; test: `e2e-live-hosts.test.py`). Open: the measured public runs themselves (this environment has no `codex`/`opencode` CLI: run `make e2e-live YES=1 HOST=codex` and `HOST=opencode` on a machine with both and add the rows; reason: a number we cannot measure is not published) Mac release run (2026-10-19) found two bugs Linux CI never sees, both fixed with tests: `stats sprint-close` counted 0 attempts when the project sat behind a symlink (macOS `/var` → `/private/var`; paths are now compared by realpath), and `make conformance` hung when another aloop checkout's `plugin/bin` was ahead on PATH (`ensure-tools --resolve` returned that checkout's shim; any aloop bin dir is now skipped). RED is now verified on any language: a non-cargo repo runs its `standards.md` matrix's test command, and a RED whose tests pass or do not collect is blocked (pytest, `go test`; test: `any-language.test.py`). Reason: the north star is any intent, and RED was dynamically checked only for Rust. GREEN and the final gate now refuse Python/Go/JS skips, and the final gate finds a planned `def`/`func` test (before, it found only `fn`, so every planned Python test blocked). `INTENT=slugify` is the Python fixture. Run 36 (slugify, the first Python run): 11/12, 11m37s, $0.83, 5 wakes, 0 plugin-source reads, 15 blocks (9 caught by self-checks). The sprint merged a correct `slugify` with 13 passing tests and the final gate passed. The one failed check was the fixture's own: bare `pytest` leaves the repo root off `sys.path` (now `python3 -m pytest`). It found two gate bugs that Rust runs had hidden. First, a worker's worktree has no `docs/agents/` (git-ignored), so the gates never found `standards.md` and ran the default Rust matrix: RED blocked 4 times on `cargo fmt`, and in a Rust project a custom matrix was silently swapped for the default. Second, `ctx-symbols conflicts` walked the merged task checkout under `.aladdin/worktrees/` and reported `slugify` as a HIGH duplicate, so the structural reviewer was rejected 4 times. Fixed with tests: the gates read the story's sprint `standards.md` (else this tree, else the main tree), and a non-cargo project with no matrix blocks with a message naming `standards.md`; ctx-symbols skips `.aladdin/`. Run 37 on these fixes: 12/12, 9m42s, $0.69, 1 wake, 11 blocks (7 caught by self-checks). It found that a `standards.md` whose matrix is a table parses empty, so RED blocked 3 times; `gate-standards-cited` now refuses a standards.md with no runnable `## Gate matrix` block (test: `any-language.test.py`). Run 38 (`INTENT=roman`, the first Go run): 12/12, 14m15s, $1.02, 3 wakes, 9 blocks (7 caught by self-checks). It found that the sprint dir's `init.md` had no `type: init` header (the supervisor began it with a dispatch block), so the structural reviewer was blocked 7 times; `aloop budget contract` now writes that header (test: `budget-contract.test.py`). Run 39 on the fix: 12/12, 7m52s, $0.56, 0 init.md blocks. It found that GREEN's default scope let it touch Rust test files only, so a Go GREEN removing RED's `_test.go` shim was blocked 10 times; GREEN now shares RED's any-language test globs (test: `any-language.test.py`). Run 40 on it: 12/12, 13m03s, $0.75, 1 wake, 0 GREEN scope blocks (5 blocks, all caught by self-checks). The structural reviewer's HIGH foundation-poisoning finding in runs 38 and 40 was a false positive: a worker's `selfcheck` resolved a stale 0.11.0 `ctx-symbols` (before the `.aladdin/` exclusion) ahead of the session's current build; `ensure-tools --resolve` now skips a stale own build (test: `ensure-tools.test.py`). RED is verified on JS too (a test file that cannot load what it imports is blocked; test: `any-language.test.py`), and `INTENT=camel` is the JS fixture. Run 41 (camel, the first JS run): 12/12, 6m45s, $0.56, 1 wake, 2 blocks (both RED self-checks refusing a source edit). The loop is now measured on Rust, Python, Go and JS. Run 42 (`INTENT=extend`, the first brownfield intent: add `compare` to a crate whose `parse` already works and is tested): 13/13, 7m11s, $0.67, 2 blocks (both self-check catches); the seed's code and tests were left unchanged and still pass (reason: every earlier fixture started from an empty library, and most real intents land on existing code). Run 43 (`INTENT=modify`: change that existing `parse` to accept a leading `v` and trim whitespace): 13/13, 9m10s, $0.67, 6 blocks, all self-check catches; the change was 3 lines in `parse`, with its signature and seed tests kept. `INTENT=cli` (an application: a wc-like binary tested by running it, checked by running the merged binary) is ready; run 44 (the retry after the usage limit lifted): 13/13, 24m55s, $1.54, 6 blocks (all self-check catches), and the merged binary works. Its cost came from planning: 2 stories and 7 tasks for a small tool, so 7 RED/SCAFFOLD/GREEN cycles and 56 supervisor turns (runs 42–43: 1–2 tasks, 16–30 turns). The planner now sizes tasks up to the budget instead of one per behaviour (reason: per-task cost is a fixed ~8 supervisor turns). Run 45 on it: 3 tasks (from 7), 13/13, 16m22s, $1.07. Its HIGH foundation-poisoning halts were `ctx-symbols` reading a test's `const USAGE` as a duplicate of the binary's; a test constant no longer counts (test: `conflicts.rs`). Run 46 on both fixes: 3 tasks, 13/13, 15m19s, $0.99, no review halt, 6/6 blocks self-check catches. Its 4 `targets` "symbol is not defined" blocks were T3 modifying symbols T2 plans in an existing file; a symbol another target plans now counts (test: `semantic-targets.test.py` case 8). Run 47 on it: 13/13, $1.04, 2 blocks (from 6), no "not defined"; but 5 tasks in 2 stories, so planner task count still varies. The spread is now bounded: before execution, `targets check` refuses two adjacent tasks of one story on the same files with 8 or fewer tests between them (replayed on past plans it would have merged runs 23, 40, 43, 44 and 47 and passed every other; test: `semantic-targets.test.py` case 9). Run 48 on it: 2 tasks, 13/13, $0.76, 25 supervisor turns (run 44: 7 tasks, $1.54, 56). One GREEN self-check block in each of runs 46–48 was a false positive: the Rust suppression grep matched an iterator's `args().skip(1)` (a JS pattern); Rust now checks only `#[ignore]` (also with a reason, which it used to miss) and `cfg(not(test))` (test: `suppression-contract.test.py`). Planner friction next: across runs 36–41 the most frequent block was `targets` "create needs planned_symbol" on a new test file (8); a test-file create now takes it from the task's `tests` (test: `semantic-targets.test.py`). The `gate-validate-artifact` plan.md refusals (4) were the persona's bare `stage: 1`, now quoted and checked (test: `persona-shapes.test.py`). Next: the final-gate block order (3). Running every suite under a locally built bash 3.2 found that the `standards.md` gate matrix was silently replaced by the default Rust matrix (`mapfile` does not exist in bash 3.2). It is fixed and guarded by `bash-portable.test.py`. A `macos` CI job now runs the host tests and the conformance fixtures on macOS (reason: both were found only by hand on the owner's Mac). |
| **M9 — Mission layer** | v0.13 | The "Missionary Aladdin Genie" spec (2026-10-17): a human-set mission above goals; fixed roles (research, product testing, state, evaluation, planning, ethics) build a confirmed baseline and a reproducible evaluation layer from user journeys; goals derived from the gap list become Aladdin intents; re-evaluate on a cadence and after each sprint; GA4 usage informs goals and is never a gate; every element has a deterministic check (§4.12). Reason: the owner's mission-driven loop, stacked on Aladdin | in progress: M9.0 core (`aloop mission init / check / approve / status`, sealed mission + approval events, area discovery, test glob; test: `mission-core.test.py`); M9.2 baseline, M9.3 journeys and M9.10 assess/evaluate (`mission-{baseline,journeys,evaluate}.test.py`). Open tracks: M9.1, M9.4–M9.9; the task graph is in §4.12, track notes in `plugin/mission/README.md`; hardened after an adversarial review (ledger records over status fields) |
| **M10 — Agent habitat** | v1.1 | Containment around the gates (§4.13): contained workers, a security and supply-chain gate, fetched content treated as data, one stop for a whole project. Reason: a 2026-10-20 comparison with Replit's "agent habitat" (orchestration, error recovery, safety and sandboxing, networking, identity) found aloop strong on orchestration, recovery and gates but missing containment | planned (2026-10-20): M10.1–M10.4; plan approval as a gate is M0.9 |

**Order rationale:** identity and conformance fixtures first, so every later change is
measured against today's behaviour; budgets and handoff next, because they shape every run;
Expand Down Expand Up @@ -476,6 +477,20 @@ M9.4 + M9.7 → M9.11; (4) Telemetry, M9.6 → M9.14; (5) Loop → skill, M9.8
wiring, M9.9. M9.13 and M9.16 close the milestone. **Exit:** M9.13's offline run passes in CI and
one live mission cycle is measured in `docs/evidence/`.

### 4.13 Agent habitat hardening (M10)

Found on 2026-10-20, comparing aloop with what Replit calls an "agent habitat" (orchestration, error
recovery, safety and sandboxing, networking, identity and authorization) and fact-checking a blog post
about the loop. aloop has the first two and the gate half of safety. These rows close the rest; each
one ships with a deterministic check, test first. Plan approval as a gate, also found then, is M0.9.

| ID | Requirement |
|---|---|
| M10.1 | Workers run contained: RED, SCAFFOLD and GREEN run with the network off and writes confined to their task worktree, through the host's own sandbox (Claude Code sandbox settings; Codex `workspace-write` with network off), with one capability-matrix row per host. Reason: a worktree isolates git history, not processes or the network. |
| M10.2 | Security and supply chain in acceptance: `gate-final` requires a secret scan and the stack's dependency audit (`cargo audit`, `npm audit`, `pip-audit`, `govulncheck`) in the gate matrix, and GREEN refuses a dependency added to a manifest that the approved plan does not name. Reason: acceptance proves behaviour, not safety, and package installs are the usual supply-chain entry. |
| M10.3 | Fetched content is data: before the first live mission cycle (M9.13), roles that read the web fetch through `mission research archive` with no shell, their personas treat fetched text as untrusted, and an eval case with an injected page must leave the role's actions unchanged. Reason: unattended web access plus a shell is the prompt-injection surface. |
| M10.4 | One stop for a whole project: `aloop stop` halts every live worker and sets a stop flag that `mission tick` honours until the human clears it, recorded as a ledger row like the budget stop (M9.24). Reason: limits exist per attempt, but nothing stops a project at once. |

## 5. Delivery sessions

Each session starts from accepted git state and its own contract, ends with accepted commits plus a handoff, and rotates context.
Expand Down
4 changes: 4 additions & 0 deletions docs/TRACKING.md
Original file line number Diff line number Diff line change
Expand Up @@ -92,3 +92,7 @@ Status of every requirement in [ROADMAP.md](ROADMAP.md), in the four states §8
| M9.43 | A goal binds the mission's direction, not its budget | NOT_IMPLEMENTED | §4.12 |
| M9.50 | A goal sprinted with gaps still open gets a next step | NOT_IMPLEMENTED | §4.12 |
| M9.51 | Lifting a mission block is the human's typed line, kept in the ledger | IMPLEMENTED_TESTED | `scripts/test/mission-tick.test.py` |
| M10.1 | Workers run with the network off and writes confined to their worktree, via the host sandbox | NOT_IMPLEMENTED | §4.13 |
| M10.2 | Secret scan and dependency audit in acceptance; no unplanned dependency | NOT_IMPLEMENTED | §4.13 |
| M10.3 | Fetched web content is data (no shell for fetching roles, injection eval case) | NOT_IMPLEMENTED | §4.13 |
| M10.4 | `aloop stop` halts a whole project, honoured by `mission tick` | NOT_IMPLEMENTED | §4.13 |
Loading