@theihtisham/agent-shadow-brain 7.22.0 → 7.22.1

package/docs/launch/RELEASE_NOTES_v7.1.4.md

@@ -1,30 +1,30 @@
-# Agent Shadow Brain 7.1.4
-
-The local Brain Hub brings actual saved memory, project documents, collaboration, and the activity journal into one control room. Node.js 22.13+ in the 22.x line, 24.x, or 26+ is required.
-
-## Install and open
-
-```bash
-npm install -g @theihtisham/agent-shadow-brain@latest
-shadow-brain --version
-shadow-brain project workspace . --port 62595
-```
-
-Check for `7.1.4`, then open [the project Brain Hub](http://127.0.0.1:62595/hub). Keep the local process running. Reuse the project directory and port after a restart. The classic workspace is still at `/workspace`; detailed activity is at `/live`. [Quickstart](../QUICKSTART.md)
-
-## What changed
-
-- **Control room.** The graph loads actual project, agent, and memory relationships, with a keyboard-accessible node list and record inspector. The local process reports its own health. The page retries when it loses the server, and it reopens the scope when the process instance changes.
-- **PDF intake.** Project PDFs have bounded extraction, stored fingerprints, and page-level review. Approved pages become cited project memory. Image-only pages surface the need for OCR.
-- **Collaboration.** Project rooms contain proposals, replies, leased task claims, artifacts with recorded digests, acknowledgements, and outcomes. The browser and configured project-local MCP clients share these records.
-- **Context and skills.** Build and compare scoped packs, copy the rendered Markdown, save project knowledge, and preview and apply host-specific project skills. The classic Context Lab retains detailed retrieval explanations and memory curation.
-- **Learning.** A recorded outcome can become a candidate. The operator records evaluation and explicitly promotes an eligible lesson. Rollback archives the promoted memory’s retrieval influence.
-- **Setup and usage.** Persist feature changes and copy native client recipes. The Hub separates measured tool activity from explicit reports. Provider usage receipts, model identity, and cost are unavailable without host evidence. Context pack tokens are estimates.
-
-![The running control room with an isolated checkout fixture](../assets/7.1.4-hub-control-room.png)
-
-## Verification scope
-
-Browser checks used isolated fixture data with actual local stores and MCP calls. They exercised graph selection, context copy, PDF review, feature changes, shared work, durable retry, learning rollback, and same-port reconnect. Host file detection and local tool exchange are separate from native host confirmation. The release does not include autonomous model execution or model training.
-
-[Visual guide](../VISUAL_GUIDE_v7.1.4.md) · [Workflow integration](../WORKFLOW_INTEGRATION.md) · [Changelog](../../CHANGELOG.md)
+# Agent Shadow Brain 7.1.4
+
+The local Brain Hub brings actual saved memory, project documents, collaboration, and the activity journal into one control room. Node.js 22.13+ in the 22.x line, 24.x, or 26+ is required.
+
+## Install and open
+
+```bash
+npm install -g @theihtisham/agent-shadow-brain@latest
+shadow-brain --version
+shadow-brain project workspace . --port 62595
+```
+
+Check for `7.1.4`, then open [the project Brain Hub](http://127.0.0.1:62595/hub). Keep the local process running. Reuse the project directory and port after a restart. The classic workspace is still at `/workspace`; detailed activity is at `/live`. [Quickstart](../QUICKSTART.md)
+
+## What changed
+
+- **Control room.** The graph loads actual project, agent, and memory relationships, with a keyboard-accessible node list and record inspector. The local process reports its own health. The page retries when it loses the server, and it reopens the scope when the process instance changes.
+- **PDF intake.** Project PDFs have bounded extraction, stored fingerprints, and page-level review. Approved pages become cited project memory. Image-only pages surface the need for OCR.
+- **Collaboration.** Project rooms contain proposals, replies, leased task claims, artifacts with recorded digests, acknowledgements, and outcomes. The browser and configured project-local MCP clients share these records.
+- **Context and skills.** Build and compare scoped packs, copy the rendered Markdown, save project knowledge, and preview and apply host-specific project skills. The classic Context Lab retains detailed retrieval explanations and memory curation.
+- **Learning.** A recorded outcome can become a candidate. The operator records evaluation and explicitly promotes an eligible lesson. Rollback archives the promoted memory’s retrieval influence.
+- **Setup and usage.** Persist feature changes and copy native client recipes. The Hub separates measured tool activity from explicit reports. Provider usage receipts, model identity, and cost are unavailable without host evidence. Context pack tokens are estimates.
+
+![The running control room with an isolated checkout fixture](../assets/7.1.4-hub-control-room.png)
+
+## Verification scope
+
+Browser checks used isolated fixture data with actual local stores and MCP calls. They exercised graph selection, context copy, PDF review, feature changes, shared work, durable retry, learning rollback, and same-port reconnect. Host file detection and local tool exchange are separate from native host confirmation. The release does not include autonomous model execution or model training.
+
+[Visual guide](../VISUAL_GUIDE_v7.1.4.md) · [Workflow integration](../WORKFLOW_INTEGRATION.md) · [Changelog](../../CHANGELOG.md)

package/docs/launch/RELEASE_NOTES_v7.2.0.md

@@ -1,24 +1,24 @@
-# Agent Shadow Brain 7.2.0
-
-Version 7.2 makes it easier to see what agents have saved and choose what to hand to a new session. The default local workspace has five views for overview, memory search, the project and agent graph, context assembly, and feature controls. The previous dashboard remains available at `/advanced`.
-
-## What changed
-
-- Context packs rank memories for the selected project and task, collapse exact duplicates, retain recorded source provenance, and explain what fits the rendered budget. Cross-project context requires both a setting and explicit opt-in.
-- Session briefings use the same assembler. Cached briefings follow the current task and feature settings. Disabling automatic briefings suppresses both new and cached output.
-- Four persistent switches control context packs, cross-project access within context packs, automatic briefings, and dashboard activity. The settings store validates updates, detects revision conflicts, and replaces saved settings atomically.
-- The CLI adds `context-pack` and `features list|set`. MCP clients can call `context_pack` and `feature_flags`. Library consumers can import the assembler and settings store directly.
-- The README includes a conceptual memory-flow illustration and screenshots from the running workspace with synthetic data.
-
-## Start the workspace
-
-```bash
-npm install -g @theihtisham/agent-shadow-brain@7.2.0
-shadow-brain dash . --no-analysis
-```
-
-From a second terminal, run `shadow-brain context-pack "import retry behavior" --project . --token-budget 1200` to inspect what an agent would receive for that task.
-
-Memory storage keeps schema version 1. The six bundled skills and the existing skill install workflow remain available. If you are coming from 6.x, follow the [7.0 migration notes](RELEASE_NOTES_v7.0.0.md).
-
-[Workspace guide](../WORKSPACE.md) · [Skill integration guide](../WORKFLOW_INTEGRATION.md)
+# Agent Shadow Brain 7.2.0
+
+Version 7.2 makes it easier to see what agents have saved and choose what to hand to a new session. The default local workspace has five views for overview, memory search, the project and agent graph, context assembly, and feature controls. The previous dashboard remains available at `/advanced`.
+
+## What changed
+
+- Context packs rank memories for the selected project and task, collapse exact duplicates, retain recorded source provenance, and explain what fits the rendered budget. Cross-project context requires both a setting and explicit opt-in.
+- Session briefings use the same assembler. Cached briefings follow the current task and feature settings. Disabling automatic briefings suppresses both new and cached output.
+- Four persistent switches control context packs, cross-project access within context packs, automatic briefings, and dashboard activity. The settings store validates updates, detects revision conflicts, and replaces saved settings atomically.
+- The CLI adds `context-pack` and `features list|set`. MCP clients can call `context_pack` and `feature_flags`. Library consumers can import the assembler and settings store directly.
+- The README includes a conceptual memory-flow illustration and screenshots from the running workspace with synthetic data.
+
+## Start the workspace
+
+```bash
+npm install -g @theihtisham/agent-shadow-brain@7.2.0
+shadow-brain dash . --no-analysis
+```
+
+From a second terminal, run `shadow-brain context-pack "import retry behavior" --project . --token-budget 1200` to inspect what an agent would receive for that task.
+
+Memory storage keeps schema version 1. The six bundled skills and the existing skill install workflow remain available. If you are coming from 6.x, follow the [7.0 migration notes](RELEASE_NOTES_v7.0.0.md).
+
+[Workspace guide](../WORKSPACE.md) · [Skill integration guide](../WORKFLOW_INTEGRATION.md)

package/docs/launch/RELEASE_NOTES_v7.22.0.md

@@ -1,53 +1,53 @@
-# Agent Shadow Brain 7.22.0
-
-Release date: 2026-11-14. See the [verification record](RELEASE_ACCEPTANCE_v7.22.0.md) for tested behavior and integration boundaries.
-
-This release makes project knowledge easier to add, trace, share and correct. Save ordinary notes directly with **Add to memory**, or review longer notes and optional document imports before sharing them. Pending and rejected review items remain outside shared retrieval.
-
-## Knowledge and learning
-
-- Paste a short fact or paragraph and save it with one click, retaining its original evidence and retry identity. Longer notes offer section review, correction and selective approval.
-- Import text PDFs, knowledge JSON and simple transcript JSON. The source review keeps speaker attribution, original text, exact page or item locator, fingerprint and approved corrections.
-- Inspect source evidence through the portal or the read-only `memory_evidence` MCP tool.
-- Rate a retrieved memory for a task. Bounded feedback affects matching future queries; users can pause or remove this influence.
-- Follow a lesson back to its recorded outcome and reported comparison. Promotion and rollback remain explicit.
-
-## Shared memory and handoffs
-
-- Already-running independent project MCP servers refresh their read view before ordinary recall.
-- Archived, contested and superseded records are excluded before project recall ranking. Audit views retain the historical record.
-- `hub_artifact_read` retrieves the saved immutable UTF-8 artifact by room, artifact ID and SHA-256. It does not reread a changed workspace file.
-- Duplicate collapse preserves conservative feedback attribution, and a supplied query without searchable terms no longer falls back to unrelated recent memories.
-
-## Portal and usage
-
-- A tool activity panel uses locally bundled integration icons and accessible detail controls for reported sessions, models, coordination roles and latest observed actions. Fresh event indicators respect pause and reduced-motion settings.
-- Initialized project MCP transports report bounded presence leases, with ten-second renewals, thirty-second expiry and clean-disconnect removal. Presence refreshes independently of the graph and never substitutes for evidence of model execution.
-- Optional usage receipts accept a bounded `reasoningEffort` label. It remains host-reported, with unknown effort omitted; existing receipts keep their retry identity.
-- The brain-shaped graph lays out actual stored records, with depth cues, quieter membership links, recorded relationship filters, search, pan, zoom and reduced motion.
-- Observed client exchanges remain visible even when the memory graph is empty. Replay does not silently switch to a newer event after the selected record expires.
-- Context shows candidates, selection reasons, exclusions, source navigation and the actual added/removed/shared records in a comparison.
-- Cooperating hosts can send optional `usage_report` receipts. Input and output totals remain distinct from cached and reasoning subsets. Missing counts remain unknown and receipts stay labelled host-reported.
-- Legacy model routes no longer discover host configuration files automatically, expose saved credential fields in JSON, or claim a successful provider test without testing it.
-
-## Compatibility and limits
-
-Existing project memory and ActivityJournal v1 remain compatible. New source and usage records live in separate project-local SQLite stores. No external database service or model download is required. Feature data is bounded and project scoped.
-
-Text organization is deterministic; it is not a separate model interpreting every paragraph. The connected agent reasons over the reviewed context it requests. Learning adapts stored memory and retrieval; it does not train model weights. Scanned PDFs need OCR, which is not included. Model reports do not establish billing or independently prove a proxy's upstream model. Native application connectivity requires that application's configuration and active use of the tools.
-
-## Conversation continuity
-
-Connected tools can register project sessions, report progress, save immutable checkpoints and continue another tool's checkpoint in a new agent-owned session. History is paged and bounded; old checkpoints keep their exact digest. Imported conversation snapshots preserve original IDs, available titles, workspace identity and source locators. A changed export becomes a linked snapshot rather than overwriting the original.
-
-The optional Codex history connection starts only after **Connect**. It uses the installed app-server's read interface, scopes the list to the current project, supports archived conversations and reads selected history in pages. Other supported tools use selected native exports. These interfaces do not reopen another application's native tab or transfer hidden model state.
-
-## Live updates and control
-
-The portal receives bounded pushed invalidations from local stores, with reconnect and polling fallback. Optional file activity reports safe project-relative file metadata; a filesystem event alone cannot identify the editing agent. Graph motion follows observed activity and can be paused.
-
-Project controls set tool participation, conversation sharing, coordination roles and context ceilings. Excluded conversations and their explicitly linked evidence are withheld from subsequent agent delivery, including inherited handoffs. Client labels are cooperative controls, not authenticated enterprise access control. Information already received by another process cannot be recalled.
-
-Project Kit skills with intact ownership receipts can be disabled, restored or removed through an exact preview. Edited and unmanaged files remain protected. Disabling a skill changes future file discovery; a host may need to reload to discard instructions already in its context.
-
-See the [research and acceptance plan](RESEARCH_AND_PLAN_v7.22.0.md), [source intake guide](../SOURCE_INTAKE.md), [sessions guide](../SESSIONS.md), and [visual guide](../VISUAL_GUIDE_v7.22.0.md).
+# Agent Shadow Brain 7.22.0
+
+Release date: 2026-11-14. See the [verification record](RELEASE_ACCEPTANCE_v7.22.0.md) for tested behavior and integration boundaries.
+
+This release makes project knowledge easier to add, trace, share and correct. Save ordinary notes directly with **Add to memory**, or review longer notes and optional document imports before sharing them. Pending and rejected review items remain outside shared retrieval.
+
+## Knowledge and learning
+
+- Paste a short fact or paragraph and save it with one click, retaining its original evidence and retry identity. Longer notes offer section review, correction and selective approval.
+- Import text PDFs, knowledge JSON and simple transcript JSON. The source review keeps speaker attribution, original text, exact page or item locator, fingerprint and approved corrections.
+- Inspect source evidence through the portal or the read-only `memory_evidence` MCP tool.
+- Rate a retrieved memory for a task. Bounded feedback affects matching future queries; users can pause or remove this influence.
+- Follow a lesson back to its recorded outcome and reported comparison. Promotion and rollback remain explicit.
+
+## Shared memory and handoffs
+
+- Already-running independent project MCP servers refresh their read view before ordinary recall.
+- Archived, contested and superseded records are excluded before project recall ranking. Audit views retain the historical record.
+- `hub_artifact_read` retrieves the saved immutable UTF-8 artifact by room, artifact ID and SHA-256. It does not reread a changed workspace file.
+- Duplicate collapse preserves conservative feedback attribution, and a supplied query without searchable terms no longer falls back to unrelated recent memories.
+
+## Portal and usage
+
+- A tool activity panel uses locally bundled integration icons and accessible detail controls for reported sessions, models, coordination roles and latest observed actions. Fresh event indicators respect pause and reduced-motion settings.
+- Initialized project MCP transports report bounded presence leases, with ten-second renewals, thirty-second expiry and clean-disconnect removal. Presence refreshes independently of the graph and never substitutes for evidence of model execution.
+- Optional usage receipts accept a bounded `reasoningEffort` label. It remains host-reported, with unknown effort omitted; existing receipts keep their retry identity.
+- The brain-shaped graph lays out actual stored records, with depth cues, quieter membership links, recorded relationship filters, search, pan, zoom and reduced motion.
+- Observed client exchanges remain visible even when the memory graph is empty. Replay does not silently switch to a newer event after the selected record expires.
+- Context shows candidates, selection reasons, exclusions, source navigation and the actual added/removed/shared records in a comparison.
+- Cooperating hosts can send optional `usage_report` receipts. Input and output totals remain distinct from cached and reasoning subsets. Missing counts remain unknown and receipts stay labelled host-reported.
+- Legacy model routes no longer discover host configuration files automatically, expose saved credential fields in JSON, or claim a successful provider test without testing it.
+
+## Compatibility and limits
+
+Existing project memory and ActivityJournal v1 remain compatible. New source and usage records live in separate project-local SQLite stores. No external database service or model download is required. Feature data is bounded and project scoped.
+
+Text organization is deterministic; it is not a separate model interpreting every paragraph. The connected agent reasons over the reviewed context it requests. Learning adapts stored memory and retrieval; it does not train model weights. Scanned PDFs need OCR, which is not included. Model reports do not establish billing or independently prove a proxy's upstream model. Native application connectivity requires that application's configuration and active use of the tools.
+
+## Conversation continuity
+
+Connected tools can register project sessions, report progress, save immutable checkpoints and continue another tool's checkpoint in a new agent-owned session. History is paged and bounded; old checkpoints keep their exact digest. Imported conversation snapshots preserve original IDs, available titles, workspace identity and source locators. A changed export becomes a linked snapshot rather than overwriting the original.
+
+The optional Codex history connection starts only after **Connect**. It uses the installed app-server's read interface, scopes the list to the current project, supports archived conversations and reads selected history in pages. Other supported tools use selected native exports. These interfaces do not reopen another application's native tab or transfer hidden model state.
+
+## Live updates and control
+
+The portal receives bounded pushed invalidations from local stores, with reconnect and polling fallback. Optional file activity reports safe project-relative file metadata; a filesystem event alone cannot identify the editing agent. Graph motion follows observed activity and can be paused.
+
+Project controls set tool participation, conversation sharing, coordination roles and context ceilings. Excluded conversations and their explicitly linked evidence are withheld from subsequent agent delivery, including inherited handoffs. Client labels are cooperative controls, not authenticated enterprise access control. Information already received by another process cannot be recalled.
+
+Project Kit skills with intact ownership receipts can be disabled, restored or removed through an exact preview. Edited and unmanaged files remain protected. Disabling a skill changes future file discovery; a host may need to reload to discard instructions already in its context.
+
+See the [research and acceptance plan](RESEARCH_AND_PLAN_v7.22.0.md), [source intake guide](../SOURCE_INTAKE.md), [sessions guide](../SESSIONS.md), and [visual guide](../VISUAL_GUIDE_v7.22.0.md).

package/docs/launch/RELEASE_NOTES_v7.22.1.md

@@ -0,0 +1,11 @@
+# Agent Shadow Brain 7.22.1
+
+This patch adds creator and repository links to the Brain Hub footer and public README, plus a live total-download badge. npm author metadata links to [Ihtisham on GitHub](https://github.com/theihtishaam).
+
+[View the source and star Agent Shadow Brain](https://github.com/theihtishaam/agents-brain).
+
+Memory, context, and agent behavior are unchanged. Install or update with:
+
+```sh
+npm install -g @theihtisham/agent-shadow-brain@latest
+```