@zhivex-ai/harness 1.2.0-rc.9 → 1.3.0-rc.3

package/CHANGELOG.md

@@ -4,6 +4,61 @@ All notable changes to Zhivex Harness are documented in this file.
 
 The project follows Semantic Versioning. During `0.x`, minor releases may change user-facing contracts when the change is documented with a migration note. Patch releases remain backwards compatible bug fixes.
 
+## 1.3.0-rc.3 - 2026-09-28
+
+- Release Meta stream deadlines after HTTP setup errors, stream completion, cancellation and early iterator closure; retain the original provider error and natural process exit.
+- Certify valid approval recovery using persisted pre-approval validation receipts without accepting additional executions, new errors or mismatched approved calls.
+- Bound Desktop smoke renderer diagnostics and retain phase timing without extending the watchdog or weakening lease/approval checks.
+- Pin the independent Code RC to Harness RC3. Local corrected-artifact acceptance reached 41/42: OpenAI and Qwen 14/14, Meta 13/14 with one HTTP 504. The operator authorized proceeding with RC preparation despite this provider failure; protected certification remains separate and is not recorded as passed.
+
+## 1.3.0-rc.2 - 2026-09-28
+
+- Reject a mismatched `apply_patch` proposal digest during input validation, before requesting operator approval. Invalid calls remain non-mutating and can be corrected by the model; valid calls still require the original approval.
+- Preserve the exact provider certification assertions after the failed RC1 attempt; no historical tag or artifact is changed.
+- Prepare the independent Code RC with an exact Harness RC2 dependency and protected artifact/provenance publication workflow.
+
+## 1.3.0-rc.1 - 2026-09-28
+
+- Add explicit terminal-independent Harness engine, protocol, client, local-service and ACP entrypoints while preserving historical root exports and stable signatures.
+- Extract the Code terminal product into its own unpublished package with the distinct `zhivex-code` binary; Harness 1.x keeps its existing binaries and state contracts.
+- Add transitive architecture checks and installed candidate acceptance for engine approvals/recovery and Code execution/cancellation across npm, pnpm, Yarn and Bun. The new APIs target the future Harness 1.3 line; RC1 targets npm `next` and does not claim completion of the provider roadmap.
+
+## 1.2.0 - 2026-09-27
+
+- Promote the code validated in 1.2.0-rc.13 to the stable release line, targeting npm `latest` through the protected GitHub Actions workflow.
+- Improve interactive CLI model/reasoning selection, activity reporting, task queues and recovery from rejected edits.
+- Preserve user direction and conversational context across compaction, with incremental SQLite history and bounded active checkpoints using Core 1.26.0 and Agents 1.10.1.
+- Retain governed approvals, isolated patch delivery and restart/backup recovery, including segmented exports for large histories.
+- Keep the Meta, Qwen and OpenAI certification cohort unchanged. Gemini remains provisional and Desktop remains a separate private alpha.
+
+## 1.2.0-rc.13 - 2026-09-26
+
+- Store SQLite run history incrementally with published Core 1.26.0 and Agents 1.10.1. Keep the 4 MiB limit on the active checkpoint while retaining steps, tool results and compaction history separately; unchanged history is not rewritten.
+- Export backups above 64 MiB through a bounded, versioned segment stream, preserving legacy JSON imports, checksums and atomic publication.
+- Preserve full history through reopen and portable backup/restore, including legacy inline states. Report state-limit failures with bounded diagnostics and retain the SDK terminal failure checkpoint.
+- Add a 200-read, 99-compaction regression covering more than 11 MB of hydrated history with a checkpoint below 48 KB. Full hydrated loads and disk retention remain proportional to history size.
+- Prepare fresh exact-artifact, live and representative certification for RC13; RC12 publication evidence remains historical.
+
+## 1.2.0-rc.12 - 2026-09-26
+
+- Preserve optional edit/retry fields in OpenAI Responses tool schemas; keep runtime validation, read-bound digests and approval checks unchanged.
+
+- Strengthen release validation with representative fixtures v2, structural workflow checks and installed-runtime regressions; preserve historical evidence and publication gates.
+
+## 1.2.0-rc.11 - 2026-09-26
+
+- Consume Qwen 0.16.2 with Core 1.25.0, retaining typed malformed tool-argument and SSE-event diagnostics through benchmark and release reports without exposing provider payloads or adding automatic retries.
+
+## 1.2.0-rc.10 - 2026-09-26
+
+- Scope deterministic test discovery to maintained root and Desktop suites, excluding historical artifacts stored locally.
+- CLI: featured model ordering, Qwen-hosted GLM/DeepSeek/Kimi choices, phase/total timing, committed file receipts, bounded `/activity` history, and literal task queues isolated from approvals.
+
+- Add model-to-reasoning selection, `/reasoning` and `--reasoning`, with adapter-declared levels, personal-profile persistence and durable run bindings.
+- Reuse bounded rejected edit candidates after targeted reference recovery, without regenerating file contents or bypassing exact-payload approval.
+- Make Qwen's local compacted conversation authoritative instead of continuing remote response chains; retain reasoning and tool history.
+- Guide scoped implementations toward editing and checking without an unnecessary planning-only turn.
+
 ## 1.2.0-rc.9 - 2026-09-26
 
 - Keep current user direction prominent across compaction, retain earlier task context, and migrate legacy summaries. Add a durable advisory for prolonged varied exploration without forcing edits or stopping legitimate investigation. Give the model actionable read-call and line-range corrections while preserving original error receipts and approvals.

package/README.md

@@ -11,12 +11,11 @@ implement a change. Conversation context retains decisions, hypotheses and bound
 diagnostic excerpts across compaction. Edits and command execution keep their
 own permission checks; a conversational summary never grants approval.
 
-Version `1.2.0-rc.9` is prepared as an unpublished release candidate for npm `next`,
-with task continuity, dependency inspection and quieter console progress improvements. Certification
-and publication remain pending. The
-[repository release status](https://raw.githubusercontent.com/Zhivex/zhivex-harness/main/release-status.json)
-preserves historical stable evidence. The installation commands below target
-1.2.0-rc.9 once published; stable users can install `@zhivex-ai/harness@latest`.
+Version `1.3.0-rc.3` prepares the terminal-independent engine API and the local
+Code package for candidate validation on npm `next`. Publication remains pending
+the protected release workflow. This RC does not include the pending Anthropic,
+Gemini/Vertex, Desktop migration or independent Code publication milestones.
+Stable `1.2.0` remains available under npm `latest`.
 Desktop retains its separate private alpha status.
 
 ## Quick start
@@ -24,7 +23,7 @@ Desktop retains its separate private alpha status.
 Requires Node.js 22.13.0 or newer, Git and a provider API key.
 
 ```sh
-npm install -g @zhivex-ai/harness@1.2.0-rc.9
+npm install -g @zhivex-ai/harness@1.3.0-rc.3
 cd /path/to/your/project
 zhx
 ```
@@ -79,7 +78,7 @@ Gemini remains provisional. See the [support matrix](docs/SUPPORT_MATRIX.md) and
 
 [Browse documentation](docs/README.md).
 
-Version `1.1.1` is the current public npm release. Source checkout changes can be
+Version `1.2.0` is the current stable public npm release. Source checkout changes can be
 newer than the published package. Consult the [changelog](CHANGELOG.md) and
 [repository release status](https://raw.githubusercontent.com/Zhivex/zhivex-harness/main/release-status.json)
 for the recorded 1.0.0 release; [release evidence](https://github.com/Zhivex/zhivex-harness/blob/main/docs/LIVE_CERTIFICATION.md)