Skip to content
Open
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
2 changes: 1 addition & 1 deletion LifeOS/install/LIFEOS/ALGORITHM/LATEST
Original file line number Diff line number Diff line change
@@ -1 +1 @@
8.45.0
8.46.0
95 changes: 95 additions & 0 deletions LifeOS/install/LIFEOS/ALGORITHM/v8.46.0.md

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions LifeOS/install/LIFEOS/DOCUMENTATION/ARCHITECTURE_SUMMARY.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ generator: LIFEOS/TOOLS/ArchitectureSummaryGenerator.ts
LifeOS — the **Life Operating System** — is the AI harness that moves you from your current state to your ideal state: an intent engineering platform that captures what you're ultimately trying to achieve and conveys that intent to your AI on every task, then verifies the output against it.
Everything below is the machinery of that one loop: Current State → Ideal State via verifiable iteration (ISC). Canonical thesis: `LIFEOS/DOCUMENTATION/LifeOs/LifeOsThesis.md`.

**Current versions:** LifeOS 8.761.0 | Algorithm v8.45.0 | System Prompt v4.4.3 | Cortex (Memory) v8.4.0
**Current versions:** LifeOS 8.761.0 | Algorithm v8.46.0 | System Prompt v4.4.3 | Cortex (Memory) v8.4.0

Doc routing lives in CLAUDE.md; founding principles + full section map in the master doc.

Expand All @@ -24,6 +24,6 @@ Pipeline wiring: master doc § Pipeline Topology; per-system doc routing lives i
## Cross-References

- Full architecture: `LIFEOS/DOCUMENTATION/LifeosSystemArchitecture.md`
- Algorithm spec: `LIFEOS/ALGORITHM/v8.45.0.md`
- Algorithm spec: `LIFEOS/ALGORITHM/v8.46.0.md`
- ISA format: `LIFEOS/DOCUMENTATION/ISA/ISAFormat.md`
- Config system: `LIFEOS/DOCUMENTATION/Config/ConfigSystem.md`
6 changes: 6 additions & 0 deletions LifeOS/install/LIFEOS/DOCUMENTATION/Fabric/FabricSystem.md
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,12 @@ User: "Use fabric to extract wisdom from this article"
-> Returns IDEAS, INSIGHTS, QUOTES, etc.
```

### Finding a pattern: the catalog and the suggester (2026-11-14)

The pattern files carry no metadata and are overwritten on every sync, so the metadata lives beside them in a generated sidecar, `skills/Fabric/Patterns/catalog.yaml`: one entry per pattern (purpose, category, triggers, input, output, the ported intent that runs instead, and the sha256 of its `system.md`). `Tools/PatternCatalog.ts build` derives it from `pattern_explanations.md` and each pattern's IDENTITY and OUTPUT sections, with one cached model pass only for a pattern no explanation line covers; `check` fails when a pattern has no entry or its hash moved, and `CheckPatterns.ts` runs that check. The install's own local patterns get their own catalog under `USER/CUSTOMIZATIONS/SKILLS/Fabric/`, merged at read time and never written into the shipped file.

A request that names no pattern goes through `Tools/SuggestPattern.ts "<request>"`: trigger and keyword match first, then one shadow Assay question over the shortlist when the engine is reachable (caller `pattern-suggest`, fail-open), and the top three come back with a reason each. ExecutePattern shows the pick as `Pattern: <name> (<reason>)` before the pattern runs; a request that names a pattern or a ported intent skips the suggester and makes no model call. The sixteen-row keyword table this replaced is gone; the catalog is the one source, and `PatternCatalog.ts triggers` can regenerate the skill's USE WHEN list from it.

### When to Use Fabric CLI Directly

Only use `fabric` command for:
Expand Down
4 changes: 4 additions & 0 deletions LifeOS/install/LIFEOS/DOCUMENTATION/ISA/ISAFormat.md
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,8 @@ template_version: 2.30.0
- **Reads:** nothing at run time; the parsers in `LIFEOS/TOOLS/lib/` and Bunker read it.
- **Writes:** nothing. A close (ISAGate) reads the run ledger for the current criteria revision and counts deferrals against `defer_cap`.

> **2026-11-14 — the `Thinking:` line on a feature block (template stays 2.30.0).** A feature may carry one optional `Thinking:` line after `Lane:`: the thinking skills the run ran and the ones it skipped with a phrase each, read by `LIFEOS/ROUTER/ThinkingCheck.ts`. Additive; no parser or gate changes, and an ISA without it reads exactly as before.

> **2026-10-26 — the `Lane:` line on a feature block (template stays 2.30.0).** A feature may carry one optional `Lane: <Agent> · <effort>` or `Lane: inline` line: the run's written route for that feature under Algorithm § Routing, read by `LIFEOS/ROUTER/RouteCheck.ts`. Additive; no parser or gate changes, and an ISA without it reads exactly as before (Router ISA F16).

> **2026-10-12 — one template version and a tool-written checkup stamp (template stays 2.30.0).** This spec's frontmatter gains `template_version`, the one number for the ISA template, kept apart from `version` so the doc's freshness counter still moves on every edit; `ISA_TEMPLATE_VERSION` in `LIFEOS/TOOLS/lib/IsaTemplate.ts` must equal it. Each ISA's `isa_format` becomes that template semver, and the legacy `3` reads as `2.29.0`. ISAs gain a `checkup` frontmatter key, so the last checkup date, verdict and red counts are machine-readable and Pulse can show them. Both keys are written only by `IsaCheck.ts stamp`, and whether an ISA uses the latest template is computed by `IsaCheck.ts conform`, never read from the stamp. There is no per-ISA version counter. Field details: § Field Rules. Work: `20261012-isa-version-checkup-analysis`.
Expand Down Expand Up @@ -568,6 +570,8 @@ Rules (all six are structure, none is a new gate):

- **The `Lane:` line says who builds the feature (2026-10-26).** One optional line after `Why:` (and `Reach:` when present): the agent and effort the run routes this feature to, as `Lane: <Agent> · <effort>` (`Lane: Sonnet · high`), or `Lane: inline` when the session does the work itself. It is the run's written route under Algorithm § Routing: `LIFEOS/ROUTER/RouteCheck.ts` reads it to draw the route line, ask the background fit question, and compare it with the dispatches the run actually made. A dispatch belongs to a feature when its description names `F<n>`. The line is a plan, never a gate: a departure is said in the answer, and nothing refuses the work.

- **The `Thinking:` line says which structured thinking the run did for the feature, and why it skipped the rest (2026-11-14).** One optional line after `Lane:`: the thinking skills the run ran, each with a depth, then the ones it considered and skipped, each with a phrase, as `Thinking: RedTeam·light, FirstPrinciples·full ; skipped Council=one approach, SystemsThinking=no recurring loop` or `Thinking: none=<why no skill fit>`. The skill words are the Router roster in `LIFEOS/ROUTER/Depth.ts` plus `Superior`; a word outside it is drawn as unknown, never dropped. It is the run's written thinking plan under Algorithm § Spend: `LIFEOS/ROUTER/ThinkingCheck.ts` reads it to draw the thinking line beside the route line, compare it with the Skill calls the session made, and ask one shadow Assay question per skipped skill (would running it have changed the result). The line is a record, never a gate: nothing refuses a feature without one, and "too simple" is never the phrase, because size alone is not a reason (PAI v2.5 made the same rule for its THINK phase).

The three affordances this unlocks are free consequences of the shape, requiring no new tooling: **query** (`rg '^### F' <isa>` lists every feature + its Why), **doc-gen** (`ISARender.ts` renders the blocks feature-organized), and **intent** (each feature carries why it was added).

### `## Harness` — how an agent runs and drives the app (v2.30.0)
Expand Down
2 changes: 1 addition & 1 deletion LifeOS/install/LIFEOS/DOCUMENTATION/ISA/ISAHtmlMirror.md
Original file line number Diff line number Diff line change
Expand Up @@ -179,4 +179,4 @@ Before the `complete` transition the mirror never fires; after it, the sibling s

- `LIFEOS/DOCUMENTATION/ISA/ISASystem.md` — twenty-one-section body, five identities, three-guardrail taxonomy
- `LIFEOS/DOCUMENTATION/ISA/ISAFormat.md` — file-shape contract (frontmatter spec, locked section order)
- `LIFEOS/ALGORITHM/v8.45.0.md` — the algorithm that produces ISAs, phase progression source
- `LIFEOS/ALGORITHM/v8.46.0.md` — the algorithm that produces ISAs, phase progression source
2 changes: 1 addition & 1 deletion LifeOS/install/LIFEOS/DOCUMENTATION/Pulse/PulseMetadata.md
Original file line number Diff line number Diff line change
Expand Up @@ -146,4 +146,4 @@ The per-mode tabs died with the mode system. Two surfaces remain:
- Pulse System overview: `LIFEOS/DOCUMENTATION/Pulse/PulseSystem.md`
- DA subsystem (design): `LIFEOS/DOCUMENTATION/Pulse/DaSubsystem.md`
- Terminal tabs (kitty integration): `LIFEOS/DOCUMENTATION/Pulse/TerminalTabs.md`
- Current Algorithm doctrine: `LIFEOS/ALGORITHM/v8.45.0.md`
- Current Algorithm doctrine: `LIFEOS/ALGORITHM/v8.46.0.md`
1 change: 1 addition & 0 deletions LifeOS/install/LIFEOS/DOCUMENTATION/Router/RouterSystem.md
Original file line number Diff line number Diff line change
Expand Up @@ -114,6 +114,7 @@ The tooth is at the door every caller shares. `LIFEOS/TOOLS/BriefGate.ts` refuse
| **Audit + contract** | `LIFEOS/ROUTER/RouteAudit.ts` (`router audit`), `LIFEOS/SOCRATES/adapters/router.ts` | Whether delegation actually happens, measured from the harness transcripts and codex rollout logs: per session the output tokens by model and the dispatches by lane; in aggregate the top-rung token share and the off-carrier rate among heavy sessions (≥40 tool calls). A Socrates question holds that rate against an ideal daily. A heavy session with no delegate dispatch is asked, in the route line's text, to state why in one `🔀 INLINE: <reason>` line under Algorithm § Route. That is advice only: the Stop gate that once held the turn for it, RouteGate, was retired 2026-09-21 in the hook minimization, and Router ISA R9 was closed to match on 2026-10-12. The audit also joins `router-decisions.jsonl` to the transcripts by session and turn and prints `below-carrier picks: F of N followed (dispatched D, INLINE I, ignored X)`: of the turns whose pick was a lane below that turn's own carrier, the share answered in the same turn by a dispatch to the lane or by an INLINE line (the line counts only on its own line with words after the colon, never quoted, fenced or as the bare placeholder). Holdout turns, same-rank or higher picks and turns with an unknown carrier are not counted (R57). Never a forced dispatch. |
| **Shape and checker yield** | `LIFEOS/ROUTER/Shape.ts`, `LIFEOS/ROUTER/CheckerYield.ts`, `Router.ts deadlines`, `Router.ts checker-log` | `Shape.ts` reads the two tokens in the principal's own prompt that set a request's shape: `dw` as the first or last word (the principal's Workflow opt-in) and a time at the end such as `10m` or `by 15:30` (a delivery deadline that also counts as that opt-in). It gives the DA one context line and logs ids and times only, never prompt text; the Router never starts a Workflow. `Router.ts deadlines [--days N]` joins each logged deadline to the transcript and says whether the reply landed in time. `CheckerYield.ts` logs whether a separate checker agent found anything, per trigger (`judged`, `high-risk-path`, `no-review`, `fix-round`, `manual`), through `Router.ts checker-log`; `Router.ts audit` reports the yield and flags a trigger as a drop candidate after 20 runs with no catch (Router ISA F5, R94 to R107). |
| **Written route** | `LIFEOS/ROUTER/RouteCheck.ts`, `LIFEOS/SOCRATES/adapters/router.ts`, the `LifeOSHooks` plugin | Each feature block in a run's ISA carries one `Lane: <Agent> · <effort>` or `Lane: inline` line. `RouteCheck.ts route` prints the one-line `🧭 ROUTE ▸ F1 Sonnet·high · F2 inline` the plugin draws; `check` compares it with `subagent-events.jsonl` after the run (a dispatch belongs to a feature when its description names `F<n>`; checkers are left out except for a feature routed to Sol audit); `fit` asks one Assay judgment-layer question per routed feature (caller `route-fit`, shadow, advisory, fail-open). An unknown agent word is named, never dropped, and no subcommand blocks anything. a Socrates standing question holds the week-over-week target from `Router.ts audit` (`untilMs` windows the prior week, `topModel` names the model the top-rung share measures); it needs at least 20 judged turns and reads unknown when the top model changed (Router ISA F16, R165–R170). |
| **Written thinking** | `LIFEOS/ROUTER/ThinkingCheck.ts`, `LIFEOS/SOCRATES/adapters/thinking.ts`, the `LifeOSHooks` plugin | Each feature block in a run's ISA may carry one `Thinking: <Skill>·<light|full>[, …] ; skipped <Skill>=<phrase>` or `Thinking: none=<phrase>` line (ISAFormat § Feature blocks, 2026-11-14): the thinking skills the run ran and the ones it considered and skipped, with a reason each. `ThinkingCheck.ts line` prints the `🧠 THINKING ▸ F1 RedTeam·light (skipped Council) · F2 none` line the plugin draws beside the route line; `check --session` compares it with the Skill tool calls in that session's transcript (roster words only, no model call); `fit` asks one Assay judgment-layer question per skipped skill (caller `thinking-fit`, shadow, advisory, fail-open): would running it have changed the result. The Socrates `thinking` adapter (ref `thinking-skips[:days]`) folds those rows into the weekly share of skips judged would-have-changed, unknown under 10 judged runs. The line is a record the DA writes by intent (Algorithm § Spend); an unknown skill word is named, never dropped, and no subcommand blocks anything. It brings back, as a measured record, the check PAI v2.5 ran as a six-tool INCLUDE/EXCLUDE walk on every request. |
| **Unattended lanes** | `LIFEOS/TOOLS/AgentJob.ts`, `Inference.ts` | Scheduled jobs and helper inference run on subscriptions, never a LifeOS API key: Haiku for low and Sonnet for medium on the Claude subscription, Sol and Astra for high and max through codex on the ChatGPT plan (principal, 2026-10-12). The `defaults` block in `agent-jobs.json` and a job's own `vendor`, `lane` and `fallback` override this. |

---
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -305,7 +305,7 @@ The ISA `## Test Strategy` table's `tool` column gets a new canonical form:
| ISC-7 | bun-test | ANTHROPIC_API_KEY scrubbed from spawned env | env-snapshot diff | bun test ./test/tools/Inference.test.ts -t "Anti: API key" |
```

When an ISC's `tool` value starts with `bun test`, the named test file MUST exist before `[ ]` → `[x]`. The Algorithm's modality rule (`LIFEOS/ALGORITHM/v8.45.0.md` § A run is complete when, item 8) takes the same row:
When an ISC's `tool` value starts with `bun test`, the named test file MUST exist before `[ ]` → `[x]`. The Algorithm's modality rule (`LIFEOS/ALGORITHM/v8.46.0.md` § A run is complete when, item 8) takes the same row:

| ISC type | Minimum verification tool call |
|----------|-------------------------------|
Expand Down Expand Up @@ -450,7 +450,7 @@ The checkbox is downstream of a real exit code, never upstream of it. A failing

Progressive verification follows ISAFormat's lanes and stages and `skills/Assay/References/Progressive.md`. Frequent checks stay deterministic and token-free; `bunker test --deep --asserts` includes slower deterministic checks. Integrity judges use existing cadence; build judgments and tournaments run explicitly. Failed prerequisites prevent downstream spend. A partial pass proves only selected scope. Judge depth follows measured calibration, never a fixed cascade through agents.

- Algorithm doctrine on ISA-as-test-harness: `~/.claude/LIFEOS/ALGORITHM/v8.45.0.md` § The Loop (the ISA as hill and instrument, each criterion carrying an executable assert) and § A run is complete when
- Algorithm doctrine on ISA-as-test-harness: `~/.claude/LIFEOS/ALGORITHM/v8.46.0.md` § The Loop (the ISA as hill and instrument, each criterion carrying an executable assert) and § A run is complete when
- ISA format spec: `~/.claude/LIFEOS/DOCUMENTATION/ISA/ISAFormat.md`
- Bun test docs: <https://bun.sh/docs/cli/test>, <https://bun.sh/docs/test/writing>, <https://bun.sh/docs/test/lifecycle>, <https://bun.sh/docs/test/snapshots>, <https://bun.sh/docs/test/coverage>, <https://bun.sh/docs/test/mocks>
- Bun's own test doctrine: <https://github.com/oven-sh/bun/blob/main/test/CLAUDE.md>
Expand Down
Loading
Loading