From d31386590993b72c6bb5430ec13a269d53610f87 Mon Sep 17 00:00:00 2001 From: Adeel Ahmad Date: Tue, 20 Oct 2026 09:30:31 +0000 Subject: [PATCH 1/2] docs(roadmap): add M10 agent habitat hardening (M10.1-M10.5) A comparison with Replit's "agent habitat" found aloop strong on orchestration, recovery and gates but missing containment. Record the gaps as planned requirements: plan approval as a gate, contained workers, a security and supply-chain gate, fetched content as data, and one stop for a whole project. Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01QoagJDnsTcVnZvuXwTHTWy --- docs/ROADMAP.md | 16 ++++++++++++++++ docs/TRACKING.md | 5 +++++ 2 files changed, 21 insertions(+) diff --git a/docs/ROADMAP.md b/docs/ROADMAP.md index bb78ecae..ba2808fe 100644 --- a/docs/ROADMAP.md +++ b/docs/ROADMAP.md @@ -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 ` 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): plan approval as a gate, 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–M10.5 | **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; @@ -476,6 +477,21 @@ 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. + +| ID | Requirement | +|---|---| +| M10.1 | Plan approval is a gate: in reviewed mode, `gate-dispatch` refuses a sprint's first execution dispatch (RED, SCAFFOLD, GREEN) until a `plan.approved` event exists for its frozen plan. Reason: the stop is a playbook rule today (SKILL.md Part A), and a prompt is advice. | +| M10.2 | 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. | +| M10.3 | 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. | +| M10.4 | 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. | +| M10.5 | 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 an event. 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. diff --git a/docs/TRACKING.md b/docs/TRACKING.md index ede22209..dab91a08 100644 --- a/docs/TRACKING.md +++ b/docs/TRACKING.md @@ -92,3 +92,8 @@ 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 | Plan approval is a gate (`gate-dispatch` refuses execution before `plan.approved`) | NOT_IMPLEMENTED | §4.13 | +| M10.2 | Workers run with the network off and writes confined to their worktree, via the host sandbox | NOT_IMPLEMENTED | §4.13 | +| M10.3 | Secret scan and dependency audit in acceptance; no unplanned dependency | NOT_IMPLEMENTED | §4.13 | +| M10.4 | Fetched web content is data (no shell for fetching roles, injection eval case) | NOT_IMPLEMENTED | §4.13 | +| M10.5 | `aloop stop` halts a whole project, honoured by `mission tick` | NOT_IMPLEMENTED | §4.13 | From 7df4ffb799dc953dd61184d1bd5f8f84f99d1484 Mon Sep 17 00:00:00 2001 From: Adeel Ahmad Date: Tue, 20 Oct 2026 09:31:57 +0000 Subject: [PATCH 2/2] docs(roadmap): M10 drops plan approval (it is M0.9) and renumbers to M10.1-M10.4 Plan approval as a gate is already M0.9 (#99), so M10 keeps the four containment rows. The project stop reuses the ledgered budget stop. Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01QoagJDnsTcVnZvuXwTHTWy --- docs/ROADMAP.md | 13 ++++++------- docs/TRACKING.md | 9 ++++----- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/docs/ROADMAP.md b/docs/ROADMAP.md index ba2808fe..54c71958 100644 --- a/docs/ROADMAP.md +++ b/docs/ROADMAP.md @@ -29,7 +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 ` 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): plan approval as a gate, 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–M10.5 | +| **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; @@ -482,15 +482,14 @@ one live mission cycle is measured in `docs/evidence/`. 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. +one ships with a deterministic check, test first. Plan approval as a gate, also found then, is M0.9. | ID | Requirement | |---|---| -| M10.1 | Plan approval is a gate: in reviewed mode, `gate-dispatch` refuses a sprint's first execution dispatch (RED, SCAFFOLD, GREEN) until a `plan.approved` event exists for its frozen plan. Reason: the stop is a playbook rule today (SKILL.md Part A), and a prompt is advice. | -| M10.2 | 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. | -| M10.3 | 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. | -| M10.4 | 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. | -| M10.5 | 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 an event. Reason: limits exist per attempt, but nothing stops a project at once. | +| 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 diff --git a/docs/TRACKING.md b/docs/TRACKING.md index dab91a08..0a6933c0 100644 --- a/docs/TRACKING.md +++ b/docs/TRACKING.md @@ -92,8 +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 | Plan approval is a gate (`gate-dispatch` refuses execution before `plan.approved`) | NOT_IMPLEMENTED | §4.13 | -| M10.2 | Workers run with the network off and writes confined to their worktree, via the host sandbox | NOT_IMPLEMENTED | §4.13 | -| M10.3 | Secret scan and dependency audit in acceptance; no unplanned dependency | NOT_IMPLEMENTED | §4.13 | -| M10.4 | Fetched web content is data (no shell for fetching roles, injection eval case) | NOT_IMPLEMENTED | §4.13 | -| M10.5 | `aloop stop` halts a whole project, honoured by `mission tick` | NOT_IMPLEMENTED | §4.13 | +| 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 |