humanish 0.89.0 → 0.90.0

package/dist/tui-contract.d.ts

@@ -51,8 +51,9 @@ export interface TuiCapabilities {
     openObserver(cwd: string, observerPath: string): Promise<TuiActionResult>;
     /** Stop the sandboxes an interrupted run left behind, keeping its evidence. */
     reclaimRun(cwd: string, runId: string): Promise<ReclaimResult>;
-    /** End a run that is still going. Stops the PROCESS; `reclaimRun` stops what it provisioned. */
-    stopRun(cwd: string, runId: string): Promise<TuiActionResult>;
+    /** End a run that is still going. "analysis" is marker-only regardless of the current status;
+     * it MUST NOT probe or signal a process. The default "run" intent stops the participant process. */
+    stopRun(cwd: string, runId: string, intent?: "run" | "analysis"): Promise<TuiActionResult>;
     /**
      * Set this directory up as a humanish project. The surface's only WRITING action outside of
      * starting runs — offered because "cd somewhere else and run init" is a dead end shown to

package/dist/tui-contract.js.map

@@ -1 +1 @@
-{"version":3,"file":"tui-contract.js","sourceRoot":"","sources":["../src/tui-contract.ts"],"names":[],"mappings":"AAAA,2DAA2D;AAC3D,EAAE;AACF,6FAA6F;AAC7F,mGAAmG;AACnG,+EAA+E;AAC/E,EAAE;AACF,gGAAgG;AAChG,+FAA+F;AAC/F,gGAAgG;AAChG,mGAAmG;AACnG,6DAA6D;AAC7D,EAAE;AACF,mGAAmG;AACnG,mBAAmB;AA8FnB,mFAAmF;AACnF,MAAM,CAAC,MAAM,kBAAkB,GAAG,EAAE,CAAC;AAErC;;;GAGG;AACH,MAAM,UAAU,eAAe,CAAC,gBAAwB,OAAO,CAAC,OAAO;IACrE,MAAM,KAAK,GAAG,MAAM,CAAC,QAAQ,CAAC,aAAa,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC;IACvF,OAAO,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,KAAK,IAAI,kBAAkB,CAAC;AAC/D,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,YAAY,CAAC,OAAe;IAC1C,OAAO,IAAI,GAAG,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC;AAC1C,CAAC;AAED;;;;;;;;;;GAUG;AACH,MAAM,UAAU,sBAAsB,CAAC,KAKtC;IACC,IAAI,CAAC,KAAK,CAAC,SAAS,EAAE,CAAC;QACrB,OAAO,+BAA+B,kBAAkB,cAAc,KAAK,CAAC,WAAW,mCAAmC,CAAC;IAC7H,CAAC;IACD,IAAI,CAAC,KAAK,CAAC,aAAa,EAAE,CAAC;QACzB,OAAO,8GAA8G,CAAC;IACxH,CAAC;IACD,OAAO,KAAK,CAAC,WAAW;QACtB,CAAC,CAAC,yEAAyE;QAC3E,CAAC,CAAC,kJAAkJ,CAAC;AACzJ,CAAC"}
+{"version":3,"file":"tui-contract.js","sourceRoot":"","sources":["../src/tui-contract.ts"],"names":[],"mappings":"AAAA,2DAA2D;AAC3D,EAAE;AACF,6FAA6F;AAC7F,mGAAmG;AACnG,+EAA+E;AAC/E,EAAE;AACF,gGAAgG;AAChG,+FAA+F;AAC/F,gGAAgG;AAChG,mGAAmG;AACnG,6DAA6D;AAC7D,EAAE;AACF,mGAAmG;AACnG,mBAAmB;AA+FnB,mFAAmF;AACnF,MAAM,CAAC,MAAM,kBAAkB,GAAG,EAAE,CAAC;AAErC;;;GAGG;AACH,MAAM,UAAU,eAAe,CAAC,gBAAwB,OAAO,CAAC,OAAO;IACrE,MAAM,KAAK,GAAG,MAAM,CAAC,QAAQ,CAAC,aAAa,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC;IACvF,OAAO,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,KAAK,IAAI,kBAAkB,CAAC;AAC/D,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,YAAY,CAAC,OAAe;IAC1C,OAAO,IAAI,GAAG,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC;AAC1C,CAAC;AAED;;;;;;;;;;GAUG;AACH,MAAM,UAAU,sBAAsB,CAAC,KAKtC;IACC,IAAI,CAAC,KAAK,CAAC,SAAS,EAAE,CAAC;QACrB,OAAO,+BAA+B,kBAAkB,cAAc,KAAK,CAAC,WAAW,mCAAmC,CAAC;IAC7H,CAAC;IACD,IAAI,CAAC,KAAK,CAAC,aAAa,EAAE,CAAC;QACzB,OAAO,8GAA8G,CAAC;IACxH,CAAC;IACD,OAAO,KAAK,CAAC,WAAW;QACtB,CAAC,CAAC,yEAAyE;QAC3E,CAAC,CAAC,kJAAkJ,CAAC;AACzJ,CAAC"}

package/docs/contracts/schemas.md

@@ -3,7 +3,7 @@
 Date: 2026-06-02 (current-state note updated 2026-07-14)
 
 Status: reference map for the major contracts shipped through source version
-`0.89.0`; it is not an exhaustive inventory of command/result envelopes. Exported types,
+`0.90.0`; it is not an exhaustive inventory of command/result envelopes. Exported types,
 schema constants, parsers, and validators in `src/` are authoritative. Rows
 marked "reserved" name layering intent only — no code emits or validates them
 yet. Do not emit a reserved schema.

package/docs/contracts/study-analysis.md

@@ -65,6 +65,15 @@ omissions and unreadable or invalid capture files make declared coverage
 incomplete. Coverage records file availability and selection; it does not
 certify visual legibility, correct interpretation, or exhaustive issue discovery.
 
+New packets declare `captureVersion: 2`, bound into their input digest. They
+include captures attached to `screenshot` and scripted `ui_action` events,
+preserving the original action IDs and evidence basis. Error notices that refer
+to an earlier capture retain that context without creating another frame.
+Scripted lanes use their recorded `ui.intent` goal when no participant assignment
+exists. Missing assignments and declared captures without supported trace
+references are explicit omissions. Artifacts without `captureVersion` continue
+to validate against the original selection rules.
+
 The standard review covers session summary, apparent intent, observed outcome,
 friction, dead ends, recovery, and participant feedback. Findings are ordered by
 observed task impact, replication among exposed participants, and recovery.
@@ -80,6 +89,8 @@ is correct or every consequential issue was found.
 
 Elapsed replay time starts at the first retained capture. It is not a video
 offset. Nonvisual events retain event identity without invented frame offsets.
+Scripted captures without recorded timestamps keep null analysis times; any
+uniform playback pacing is an estimate, not an observed duration.
 
 ## Durable records
 
@@ -94,8 +105,15 @@ status, usage and validated findings:
   analysis/<analysis>/corrections/<correction>/correction.json
   analysis-attempts/<analysis>/receipt.json
   observer/study-analysis.json
+  analysis-automatic/job.json  # opt-in run lifecycle; never a retry instruction
 ```
 
+The optional automatic job is separate from the immutable analysis. Its view
+binds terminal state to the exact execution receipt and report. A stale or
+unverifiable job remains unknown; reading or exporting it never dispatches.
+Automatic job metadata is omitted from shared derivatives. See
+[automatic analysis](../product/automatic-analysis.md).
+
 Version and correction directories are claimed exclusively; publication is
 atomic. Source evidence is not rewritten. Minimal execution receipts retain
 model, budget, status and known usage even if source changes prevent report

package/docs/goals/current.md

@@ -1,9 +1,9 @@
 # Current Goals
 
-Status date: 2026-09-14. Release baseline: `0.89.0`.
+Status date: 2026-09-15. Release baseline: `0.90.0`.
 
 This page guides work on current merged source. Published behavior is described
-in the [release notes](../release/0.89.0-study-findings.md).
+in the [release notes](../release/0.90.0-automatic-analysis.md).
 The [September 9 history](https://github.com/danielgwilson/humanish/blob/main/docs/goals/current-history-2026-09-09.md)
 preserves the former status log; its queues do not supersede this page.
 
@@ -88,7 +88,7 @@ requires decision-equivalent retained evidence and a real deletion branch.
 No first-party deletion branch has met that gate. Public demonstrations do not
 substitute for it.
 
-## Current Program Truth (source `0.89.0`)
+## Current Program Truth (source `0.90.0`)
 
 | Surface | Available in merged source | Remaining boundary |
 | --- | --- | --- |
@@ -99,7 +99,7 @@ substitute for it.
 | Shared state | Sequential and concurrent single-origin shared-world studies with retained evidence | Multi-origin implementation remains gated; concurrent state change does not establish per-action causation |
 | Observer | Live/recorded views, participant assignments, action-specific links, saved moments, zoom, comparison and phone-width review | Sparse captures cannot prove every action's effect; visual comparison alone is not a controlled experiment |
 | Review and feedback | Verification grades, feedback drafts, portable HTML, redacted bundle derivatives and computer-use completion-source labels | Sharing requires the appropriate grade; participant reports and condition matches still need task adjudication |
-| Study findings | Explicit `analyze`, bounded evidence selection, versioned findings, exact source links and append-only corrections within the Observer study shell | Model interpretation needs review; bounded selection and source truncation limit coverage; opening Observer never dispatches analysis |
+| Study findings | Explicit `analyze` or opt-in post-run analysis, bounded evidence selection, versioned findings, exact source links and append-only corrections within the Observer study shell | Model interpretation needs review; bounded selection and source truncation limit coverage; opening Observer never dispatches analysis |
 | TUI and serving | Detached starts, run stopping, reclamation, Observer attachment, loopback serving and run library | Stopping a process does not itself prove sandbox cleanup; TUI views over CLI `stats`/`export` remain follow-ups |
 | Off-app communication | In-sandbox email/SMS catch and digest-only thread evidence | This does not establish real-provider delivery |
 | Mobile and media | Hosted viewport/emulation, desktop geometry checks, bounded dwell and declared camera feed | Physical-device and touch fidelity remain unproven; unsupported microphone declarations are rejected |

package/docs/product/automatic-analysis.md

@@ -0,0 +1,63 @@
+# Automatic study analysis
+
+A lab can request analysis after each live recording finishes. Findings remain
+separate from participant feedback and the recorded study verdict.
+
+```yaml
+review:
+  analysis:
+    maxCostUsd: 3
+    # Optional; these values match manual analysis defaults.
+    model: gpt-6-astra
+    timeoutMs: 300000
+    maxOutputTokens: 16384
+    # question: Where did participants need to recover?
+```
+
+Omit `review.analysis` to leave the existing run behavior unchanged. The budget
+is required when analysis is present. It limits an admission estimate, not the
+provider's final bill, and is separate from participant spending limits. Analysis
+sends selected retained text and captures to OpenAI using `OPENAI_API_KEY`.
+Analysis runs in the Humanish runner using its credentials. This setting adds no
+credential channel to the target application; each participant backend retains
+its existing authentication boundary. Review a manifest's opt-in before running
+it live.
+
+The same configuration works through `humanish run <lab>`, `lab run <lab>`,
+`watch <lab>`, and TUI live starts. Direct library calls to the five recording
+producers honor it too. Supported routes are computer-use, scripted-browser,
+terminal-product, sequential shared-world and concurrent shared-world. Synthetic,
+smoke and meta routes reject the setting before execution. Dry runs show analysis
+as skipped, without reading analysis credentials or making a provider request.
+
+Participant execution finishes and its recording is finalized before analysis is
+queued. A participant who was blocked or interrupted can still have useful
+retained evidence; analysis requires a verified live recording, not a successful
+participant outcome. An active, missing or invalid recording is not analyzed.
+
+The command waits for analysis and reports its separate state. A TUI-launched
+runner continues after the TUI closes; reopening the TUI or Observer reads the
+existing job and does not start another request. Concurrent or repeated automatic
+invocations cannot silently retry a paid attempt. If a process disappears while
+an attempt is in flight, its state can be unknown rather than falsely complete.
+Use manual `humanish analyze --run <exact-run-id> --max-cost 3` for an intentional
+follow-up after inspecting the existing attempt and its accounting.
+
+Stopping participant execution does not start a fresh automatic analysis. A
+recorded harness cancellation is skipped; ordinary time limits and participant
+abandonment remain eligible evidence.
+
+During analysis, Ctrl-C asks the request to cancel. The TUI's **Cancel analysis**
+action writes a cancellation request for that recording; it does not signal the
+finished participant process. Cancelling cannot undo provider work already
+accepted. Known usage is retained; missing usage remains unknown.
+
+The CLI's JSON keeps `runOk` for the original backend result, `automaticAnalysis`
+for post-run analysis, and `ok` for the overall request. Failed, cancelled or
+unknown analysis produces exit code 2 without discarding the recording. Partial
+findings remain visibly partial; a valid partial result can succeed, while a
+partial result with an analysis error still fails the command. Recorded task
+outcomes and the deterministic review verdict are never rewritten by analysis.
+
+See the [analysis contract](../contracts/study-analysis.md) for selection limits,
+evidence validation, actual usage, corrections and share-safe export behavior.

package/docs/ramp/README.md

@@ -2,7 +2,7 @@
 
 Status: public-safe contributor and agent ramp.
 
-Package/source version in this tree: `0.89.0` (2026-09-14). The Observer is phone-usable as a stated requirement (observer/AGENTS.md); interactive primitives start from Base UI. The Observer renderer is the observer/ workspace artifact only; the legacy string-concat renderer was deleted at cutover (#426), and rollback is a version pin to 0.42.0. The containment boundary introduced in
+Package/source version in this tree: `0.90.0` (2026-09-15). The Observer is phone-usable as a stated requirement (observer/AGENTS.md); interactive primitives start from Base UI. The Observer renderer is the observer/ workspace artifact only; the legacy string-concat renderer was deleted at cutover (#426), and rollback is a version pin to 0.42.0. The containment boundary introduced in
 `0.15.1` remains in force: managed run and output paths bind to validated
 physical filesystem identities, and stored provider IDs are evidence, not
 cleanup authority. The bundled OSS meta-lab is dry-run only until
@@ -47,6 +47,13 @@ If a change does not improve one of those loops, it probably belongs elsewhere.
 
 ## Current State
 
+The [0.90.0 release note](../release/0.90.0-automatic-analysis.md) describes
+opt-in analysis after live runs, truthful job states, cancellation, and scripted
+captures and assignments in findings and playback.
+
+The [0.89.1 release note](../release/0.89.1-analysis-finished-notice.md)
+clarifies that an analysis with limitations has finished.
+
 The [0.89.0 release note](../release/0.89.0-study-findings.md) describes explicit
 analysis of completed studies, versioned findings and review corrections, exact
 evidence links, and Participants / Findings within one Observer shell. Analysis

package/docs/release/0.89.1-analysis-finished-notice.md

@@ -0,0 +1,24 @@
+# Humanish 0.89.1: finished analysis notice
+
+Observer now labels a partial analysis result **“Analysis finished with
+limitations.”** The previous notice described findings as covering evidence
+“included so far,” which could make a finished analysis appear to be running.
+
+A partial result can contain validated findings after evidence selection limits
+or an exceeded admission estimate. Review the recorded coverage, limitations and
+usage when interpreting that result. The analysis status and saved evidence keep
+their existing meaning.
+
+## Update an existing recording
+
+```bash
+npm install humanish@0.89.1
+npx humanish observe --run latest
+```
+
+This renders the existing study with the updated Observer. An already exported
+HTML file is a saved snapshot; export it again to get the new wording. Reuse the
+appropriate sharing options for that run. No new analysis request is needed.
+
+The [0.89.0 release note](0.89.0-study-findings.md) describes the underlying study
+findings feature and its verification limits.

package/docs/release/0.90.0-automatic-analysis.md

@@ -0,0 +1,21 @@
+# 0.90.0 — Findings after live studies
+
+Labs can opt into independent analysis after their recording finishes with
+`review.analysis.maxCostUsd`. The command waits for the result; the TUI and
+Observer show analysis separately from participant execution and task outcomes.
+Without the setting, run behavior stays unchanged.
+
+The five supported live recording producers share the same completion boundary.
+Automatic analysis claims one attempt per recording, preserves usage and prior
+findings, and never starts again merely because a view is reopened. Cancellation
+requests target analysis without signaling the finished participant process.
+Recording identity remains pinned through dispatch, reuse and artifact writes.
+
+Scripted browser recordings now contribute their action-attached screenshots and
+declared goal to analysis and playback. Earlier saved analyses retain their
+original evidence mapping. Referenced error captures do not become duplicate
+frames. Missing assignments or unmapped captures remain visible limitations.
+
+See [automatic analysis](../product/automatic-analysis.md) for configuration,
+route support, spending and cancellation behavior. Analysis uses an admission
+estimate separate from participant caps; it is not a provider billing hard cap.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "humanish",
-  "version": "0.89.0",
+  "version": "0.90.0",
   "description": "Open-source-safe CLI for persona simulation, observer review, and public-safe feedback drafts.",
   "author": "Daniel G Wilson <daniel@danielgwilson.com>",
   "keywords": [