diff --git a/docs/ROADMAP.md b/docs/ROADMAP.md index 89c44caf..24b8125d 100644 --- a/docs/ROADMAP.md +++ b/docs/ROADMAP.md @@ -27,7 +27,7 @@ original plan. | **M5 — Narrow context** | v0.16 | Session 6: semantic execution map, shadow workspace, `target` / `context` CLI (§4.6) | done: targets, shadow workspace, `target`/`context`, LSP seam, GREEN scope from targets, and tasks.md/validate.md/plan.md rendered from the semantic plan (`targets render`; tests: `semantic-targets`, `lsp-adapter`, `targets-scope`, `plan-render`) | | **M6 — Audit** | v0.17 | Sessions 7–8: event stream, rationale, authority, lineage query (§4.7); provider seam (§4.8) | done: `aladdin.event/1` stream, decisions, authority, lineage, `events trace SHA`, commit messages and graph export (§4.7); impact provider seam (§4.8) | | **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`) | -| **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 ` 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). 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). | +| **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 ` 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 (next: measure the spread before tightening the rule). 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) | **Order rationale:** identity and conformance fixtures first, so every later change is diff --git a/docs/evidence/README.md b/docs/evidence/README.md index 5aea8e5b..b7c9f519 100644 --- a/docs/evidence/README.md +++ b/docs/evidence/README.md @@ -53,6 +53,7 @@ the cost cell reads — and the intent cell names the host. What each run found | run 44 | cli (Rust binary), first run | v0.12.0 + #68 (216dd4c) | 13/13 | 24m55s | $1.54 | 3 | 0 | 6 | `make e2e-live YES=1 INTENT=cli` | | run 45 | cli (Rust binary), on the task-sizing rule | v0.12.0 + #76 (eb00a74) | 13/13 | 16m22s | $1.07 | 3 | 0 | 8 | `make e2e-live YES=1 INTENT=cli` | | run 46 | cli (Rust binary), on both #76 fixes | v0.12.0 + #76 (286bf45) | 13/13 | 15m19s | $0.99 | 2 | 2 | 6 | `make e2e-live YES=1 INTENT=cli` | +| run 47 | cli (Rust binary), on #81 | v0.12.0 + #81 (a653fd4) | 13/13 | 15m19s | $1.04 | 2 | 1 | 2 | `make e2e-live YES=1 INTENT=cli` | Columns: *checks* are the e2e script's own assertions (12 for `semver`, 13 for `wordfreq` since the commit-trace check); *wakes* are supervisor turns that ended and resumed (each re-reads @@ -88,3 +89,6 @@ no longer counts as a duplicate definition; a test function redefining a source Run 46 is the same tool on both fixes: 3 tasks, $0.99 and 15m19s, no structural-review halt, and all 6 blocks were the workers' own self-checks (targets naming symbols not yet written, RED's `cargo fmt`). The `cli` loop now costs about what one-task brownfield runs do. +Run 47 (on #81, which lets a later task modify a symbol an earlier one plans) had 2 blocks (from +6), both the workers' own self-checks, and no `targets` "not defined" refusal. The planner made 2 +stories and 5 tasks this time, so cost stayed at $1.04: task count still varies run to run.