fix(e2e): set busy_timeout in memory-injection seedMemory

.alfonso/plans/workspaces-callsite-inventory.md

@@ -0,0 +1,52 @@
+# Workspaces call-site inventory (plugin side)
+
+Generated from grep over `packages/plugin/src` and `packages/pi-plugin/src` for:
+`getMemoriesByProject`, `getMaxMemoryId`, `getMemoryMutationsForRender`,
+`getMaxMemoryMutationId`, `readNewMemoriesForM1`, `searchMemoriesFTS`, and
+`getProjectMemoryEpoch`.
+
+Test-only call sites are intentionally omitted below; they exercise the single-project primitives directly unless named as new workspace regressions.
+
+## packages/plugin
+
+| File:line | Call | Status | Justification |
+| --- | --- | --- | --- |
+| `src/hooks/magic-context/inject-compartments.ts:320` | `getMemoriesByProject` in legacy `prepareCompartmentInjection` | gated-single-identity | Legacy v1 compartment injection path uses the existing `memory_block_cache` contract. The m[0]/m[1] path below is the workspace-aware path; single-project bytes stay unchanged here. |
+| `src/hooks/magic-context/inject-compartments.ts:870` | local `getMaxMemoryId` helper definition | gated-single-identity | Preserved for the byte-identity path. Workspace callers use `getMaxMemoryIdForProjects`. |
+| `src/hooks/magic-context/inject-compartments.ts:900` | local `getProjectMemoryEpoch` helper definition | gated-single-identity | Preserved for the byte-identity path. Workspace HARD decisions compare `computeWorkspaceEpochFingerprint`. |
+| `src/hooks/magic-context/inject-compartments.ts:925` | `getProjectMemoryEpoch` in `readCurrentM0SnapshotMarkers` | converted | Workspace marker also records `workspaceFingerprint`; `mustMaterialize` compares fingerprint when `identities.length > 1`, plain epoch otherwise. |
+| `src/hooks/magic-context/inject-compartments.ts:933` | `getMaxMemoryId` in `readCurrentM0SnapshotMarkers` | converted | Workspace branch uses `getMaxMemoryIdForProjects(expandedIdentities)`, single branch calls original helper. |
+| `src/hooks/magic-context/inject-compartments.ts:939` | `getMaxMemoryMutationId` in `readCurrentM0SnapshotMarkers` | converted | Workspace branch uses `getMaxMemoryMutationIdForProjects(expandedIdentities)`, single branch unchanged. |
+| `src/hooks/magic-context/inject-compartments.ts:1501` | `getMemoriesByProject` in `materializeM0` | converted | Workspace branch reads `getMemoriesByProjects(expandedIdentities)` and applies source attribution/fair trim; single branch unchanged. |
+| `src/hooks/magic-context/inject-compartments.ts:1589` | `getMaxMemoryId` in Phase-3 stale read | converted | Workspace branch uses union max; single branch unchanged. |
+| `src/hooks/magic-context/inject-compartments.ts:1596` | `getMaxMemoryMutationId` in Phase-3 stale read | converted | Workspace branch uses union max; single branch unchanged. |
+| `src/hooks/magic-context/inject-compartments.ts:1828` | `getMemoryMutationsForRender` in memory-updates | converted | Workspace branch uses `getMemoryMutationsForRenderByProjects(expandedIdentities)`, single branch unchanged. |
+| `src/hooks/magic-context/inject-compartments.ts:1887` | `readNewMemoriesForM1` in `renderM1WithMetadata` | converted | Workspace branch uses `readNewMemoriesForM1Union(expandedIdentities)`, single branch unchanged. |
+| `src/hooks/magic-context/inject-compartments.ts:2187` | `getMemoriesByProject` in `renderFreshM0NonPersisted` | converted | Workspace fallback reads union memories and applies attribution/fair trim; single fallback unchanged. |
+| `src/features/magic-context/search.ts:392` | `searchMemoriesFTS` | converted | Workspace branch uses `searchMemoriesFTSUnion(expandedIdentities)`; single branch unchanged. |
+| `src/features/magic-context/search.ts:516` | `getMemoriesByProject` | converted | Workspace branch uses `getMemoriesByProjects(expandedIdentities)`; single branch unchanged. |
+| `src/tools/ctx-memory/tools.ts:376` | `getMemoriesByProject` for `list` | gated-single-identity | `list` remains a project-local/dreamer maintenance listing; requested widening is update/archive visibility. |
+| `src/hooks/magic-context/m0-token-breakdown.ts:98` | `getMemoriesByProject` cold-start token estimate | gated-single-identity | Token sidebar falls back only before m[0] exists; materialized m[0] is measured from bytes. It is not a render/tool/search behavior path. |
+| `src/hooks/magic-context/compartment-runner-incremental.ts:349` | `getMemoriesByProject` for historian prompt context | gated-single-identity | Historian memory extraction remains session-own-project scoped; workspace rendering/search/tool visibility does not change write/extraction scope. |
+| `src/features/magic-context/memory/storage-memory.ts:534` | union helper calls `getMemoriesByProject` when arity=1 | gated-single-identity | Intentional byte-identity short-circuit. |
+| `src/features/magic-context/memory/storage-memory-fts.ts:88` | union helper calls `searchMemoriesFTS` when arity=1 | gated-single-identity | Intentional byte-identity short-circuit. |
+| `src/features/magic-context/storage-memory-mutation-log.ts:181` | union helper calls `getMemoryMutationsForRender` when arity=1 | gated-single-identity | Intentional byte-identity short-circuit. |
+| `src/features/magic-context/storage-memory-mutation-log.ts:214` | union helper calls `getMaxMemoryMutationId` when arity=1 | gated-single-identity | Intentional byte-identity short-circuit. |
+
+## packages/pi-plugin
+
+| File:line | Call | Status | Justification |
+| --- | --- | --- | --- |
+| `src/inject-compartments-pi.ts:815` | `getMaxMemoryMutationId` in current markers | converted | Workspace branch uses `getMaxMemoryMutationIdForProjects(expandedIdentities)`, single branch unchanged. |
+| `src/inject-compartments-pi.ts:976` | `getMemoriesByProject` in direct `renderM0Pi` | converted | Workspace branch uses `getMemoriesByProjects(expandedIdentities)` with source attribution/fair trim; single branch unchanged. |
+| `src/inject-compartments-pi.ts:1145` | `getMemoriesByProject` in frozen m[0] inputs | converted | Workspace branch reads union memories in the frozen transaction; single branch unchanged. |
+| `src/inject-compartments-pi.ts:1166` | `getMaxMemoryMutationId` in frozen markers | converted | Workspace branch uses union max; single branch unchanged. |
+| `src/inject-compartments-pi.ts:1487` | `getMemoryMutationsForRender` in Pi memory-updates | converted | Workspace branch uses `getMemoryMutationsForRenderByProjects(expandedIdentities)`, single branch unchanged. |
+| `src/inject-compartments-pi.ts:1586` | `getMemoriesByProject` for Pi new memories | converted | Workspace branch uses `readNewMemoriesForM1Union(expandedIdentities)`, single branch unchanged for byte identity. |
+| `src/inject-compartments-pi.ts:2203` | `getMemoriesByProject` for result memory count | converted | Workspace branch counts `getMemoriesByProjects(expandedIdentities)`, single branch unchanged. |
+| `src/tools/ctx-memory.ts:347` | `getMemoriesByProject` for `list` | gated-single-identity | `list` remains project-local maintenance; update/archive are widened to workspace visibility. |
+| `src/pi-historian-runner.ts:426` | `getMemoriesByProject` in historian runner | gated-single-identity | Historian extraction/prompting remains session-own-project scoped; workspace visibility is render/search/tool-time only. |
+
+## Definitions and tests
+
+The primitive definitions (`storage-memory.ts`, `storage-memory-fts.ts`, `storage-memory-mutation-log.ts`) and their unit tests deliberately continue to call the single-project APIs. New union helpers have arity-1 short-circuits so un-workspaced callers keep the exact existing SQL/order/bytes.

.alfonso/release-notes/dashboard-v0.6.0.md

@@ -0,0 +1,14 @@
+# Dashboard v0.6.0
+
+Adds the Workspaces panel and fixes model dropdowns for version-manager installs.
+
+## New: Workspaces panel
+
+Manage cross-project workspaces directly from the dashboard. Create a workspace, add member projects, and choose which memory categories members share with each other (Constraints only, by default). Edits are staged per card — add and remove members, toggle categories, then **Save** once, so the change applies as a single update instead of one per click.
+
+Memories from other workspace members appear in each member session labelled by their source project. (Requires the v0.23.2 plugin, which owns the workspace schema; the panel degrades gracefully on older plugin versions.)
+
+## Fixes
+
+- **Model dropdowns were empty for version-manager installs.** If your `pi` or `opencode` binary is installed by a version manager (mise, nvm, fnm, volta, asdf), the dashboard couldn't find it — the desktop app doesn't inherit your shell `PATH` — so the model comboboxes came up empty. The dashboard now resolves the binary through your login shell (and known version-manager directories), bounded by a short timeout.
+- **Workspaces panel layout** — corrected double padding on the panel and tidied the shared-categories checkboxes to match the dark theme; Save/Discard now appear only when there are unsaved edits.

.alfonso/release-notes/dashboard-v0.7.0.md

@@ -0,0 +1,43 @@
+## Magic Context Dashboard v0.7.0
+
+### Cache Diagnostics, rebuilt
+
+The Cache page now tracks each session in its own bounded window instead of a
+shared global event pool, so the Recent Sessions cards show **per-session**
+hit-ratio, event count, and bust count that no longer drift with how busy other
+sessions are.
+
+- **Per-session windows.** Pick how many recent events to keep per session
+  (200 / 400 / 600 / 800 / 1000); cards and the timeline both reflect exactly
+  that window.
+- **Live, reliable refresh.** A 1-second loop re-lists sessions and fetches only
+  *new* events per session, so the Recent Sessions strip stays current without
+  the manual pause/unpause it sometimes needed before.
+- **One-line strip.** Recent Sessions render as a single row of equal-width
+  cards; how many show adapts to the window width.
+
+### Cache timeline
+
+- **Context-scaled bars.** Bar height is the prompt size relative to the model's
+  context window, with an inner cached segment — so you can see the prompt grow
+  and drop across a session at a glance.
+- **Accurate severity.** Cache health is judged by comparing each step's cached
+  read against what the previous step predicted, instead of a raw ratio that
+  false-warned on large file reads. Providers that don't report cache data show
+  as "unknown" rather than a misleading bust.
+- **Magic-Context-attributed drops.** Drop markers correlate to the actual
+  scheduler decision recorded by the plugin (execute / materialize / emergency),
+  shown in a tooltip. The blue drop line is now clickable and jumps to the step.
+- **Importance heat-map.** The compartment strip in the session view colors each
+  segment by its importance band (critical / high / medium / low) instead of a
+  meaningless rainbow.
+
+### Memories & projects
+
+- **Edit a memory's category** directly from the dashboard (#158).
+- **Non-git projects** now appear in the project picker and filter their memories
+  correctly (#160).
+- **Real project names.** Sessions that ran in a git repo with no remote/commit
+  no longer display as "/"; they show their actual directory.
+- **Windows model dropdown** is populated for version-manager installs
+  (mise / nvm / fnm / volta / asdf) and via a PATH fallback (#149).

.alfonso/release-notes/v0.24.0.md

@@ -0,0 +1,33 @@
+# v0.24.0
+
+Adds cross-project workspaces and searchable session history, fixes a Pi context-overflow, and removes several prompt-cache busts.
+
+## New: cross-project workspaces
+
+Group related repositories (for example a set of microservices) into a **workspace** and share project memories across them. Member sessions see their own project's memories plus the memories other members choose to share — each one labelled by its source repo. Per-workspace checkboxes control *which* memory categories are shared (Constraints only, by default), so shared knowledge stays relevant and project-specific noise stays local.
+
+Workspaces are managed from the dashboard (Workspaces panel): create a workspace, add member projects, pick the shared categories, and Save. A single project belongs to at most one workspace. Single-project users are completely unaffected — the rendered context is byte-identical to before.
+
+## New: searchable session history
+
+`ctx_search` can now find older discussion by **meaning**, not just keywords. Magic Context embeds each compacted history segment so the agent can recall what was discussed weeks ago even when it doesn't remember the exact wording.
+
+New history is embedded automatically as the session grows. To make an **existing** session's older history searchable, run **`/ctx-embed-history`** once — it backfills that session's compacted history in the background while you keep working. (You'll also see a reminder in the startup dialog.)
+
+Search ranking was improved alongside this: verbatim matches now rank correctly, and common acronyms no longer flood results.
+
+## Fixes
+
+- **Pi: sessions could overflow the model context while still reporting moderate usage.** Pi only refreshed its context measurement at the end of each turn, so a long tool-heavy turn could balloon the request past the model's window before the next measurement — the request was rejected even though the status line still read, say, 68%. Pi now floors its pressure with a live forward estimate (recomputed every step), so it sheds context *before* the request overflows. (OpenCode was never affected — it already measures per step.)
+
+- **GitHub Copilot: `tool_use`/`tool_result` adjacency error on fresh sessions (#135).** Empty-content message markers that Anthropic silently drops were surviving onto the Copilot (openai-compatible) wire and breaking the required tool-call/result pairing. They're now stripped only for providers that drop them.
+
+- **Fewer prompt-cache busts.** Three cases that were re-billing large prompt prefixes unnecessarily:
+  - Editing a project doc (`ARCHITECTURE.md` / `STRUCTURE.md`) no longer rebuilds the cached history baseline — the new content folds in on the next natural cache turn instead.
+  - A processed screenshot in an older message no longer loses its image data mid-conversation on a routine pass.
+  - When the cached history baseline *does* have to rebuild (a memory change, a model switch, idle timeout), any pending tool-output cleanup is now folded into that same rebuild instead of causing a second bust a moment later.
+
+## Also in this release
+
+- **Setup wizard (`npx @cortexkit/magic-context`)** now lists the models you actually have with type-ahead filtering, instead of a fixed recommendation list, and explains what the historian and dreamer do (neither needs a frontier model). Adds a `--dry-run` mode. (#144)
+- **Protected-tail** snapshot is refreshed at history-summarization time, preventing a rare case where the summarizer could starve and stop reclaiming context.

.alfonso/release-notes/v0.24.1.md

@@ -0,0 +1,23 @@
+# v0.24.1
+
+Patch release: a fix for session titles never generating, fewer cache busts, embedding-endpoint safety, calmer reduction reminders, and a persistent TUI sidebar.
+
+## Fixes
+
+- **Session titles generate again.** With the plugin enabled, a new session could keep the default `New session - <timestamp>` title forever (most visibly in non-git directories). Magic Context injects its compacted history as synthetic context messages, and those weren't flagged correctly, so OpenCode's auto-title step counted them as real user turns and skipped titling. The injected history is now marked synthetic — it still reaches the model, but no longer blocks the title. ([#129](https://github.com/cortexkit/magic-context/issues/129))
+
+- **No embedding under the wrong model.** When a local OpenAI-compatible endpoint (LM Studio, Ollama) serves a *different* embedding model than the one you configured — e.g. a shared endpoint where another tool keeps a smaller model loaded — the returned vectors have a different dimensionality and don't belong in your index. Magic Context now checks the model the endpoint reports and refuses mismatched vectors instead of silently corrupting the store. A clear log line names what was requested vs. served.
+
+- **Embedded history chunks no longer get truncated.** Chunks are now sized with a safety margin below the endpoint's input limit, so cross-tokenizer rounding can't push a chunk slightly over the limit and clip its tail.
+
+- **Two more prompt-cache busts removed.** (1) A stuck overflow-recovery flag could keep forcing a session to behave as if it were at the emergency ceiling — re-running cleanup every turn — after a `/ctx-recomp` had already relieved the pressure; the flag now clears when there's nothing left to compact and on a successful recomp. (2) A dropped older message could flip between two equivalent placeholder forms across passes, changing one block of the prompt prefix and re-billing the tail; the two placeholder paths now agree byte-for-byte.
+
+## Improvements
+
+- **Quieter, better-calibrated reduction reminders.** The reminder that nudges the agent to drop spent tool output was over-firing — it measured against the wrong budget, so a modest pile triggered "urgent" on a large-context model. It now scales against the agent's actual working window, ignores output that can't be dropped yet (the protected recent window), and is worded as advisory rather than a directive. If the agent has already reduced enough, approaching the threshold no longer nags it.
+
+- **Persistent TUI sidebar preferences.** The Magic Context sidebar can now remember its collapsed/expanded state across restarts, and you can reorder it, rename its header, or hide individual sections — via a shared `~/.config/opencode/tui-preferences.jsonc` file (one `magic-context` key). See the [TUI sidebar reference](https://docs.cortexkit.io/magic-context/reference/tui-sidebar/).
+
+## Also in this release
+
+- New documentation: **[why your token count can stay high after the execute threshold](https://docs.cortexkit.io/magic-context/concepts/context-reduction/#why-your-token-count-can-stay-high-after-the-threshold)** — the execute threshold compresses older conversation; tool outputs are reclaimed by `ctx_reduce` or the 85% safety net, not by the threshold itself.