Magic Context Dashboard: baixar versions anteriors

Dashboard 0.20.18
Reads Broca logs that use three new log features:
- provider-declarations/v1: a run's plan manifest records the result formats and late_results capability its tool providers declare.
- provider-held/v1: held tool-call records and a tool_held pause reason.
- plan-reference-slots/v1: a run's plan manifest records the reference slots its tools declare.
The dashboard doesn't use these fields. Without this release, it stops reading a Broca log at the first record that requires one of them, and the steps after that point don't show.

Fixes
- The Broca runs view reads runs from Broca releases that record when each message was written (message-times/v1). Before this release, the dashboard stopped reading a run's log at the first such record.

Fixes
- The Broca runs view reads runs from Broca releases that record when each tool call started and finished (tool-times/v1). Before this release, the dashboard stopped reading a run's log at the first such record.

Fixed
- Broca sessions that record a client message id, or that waited for a compaction provider before a prompt rewrite, are read in full. Before this release, the dashboard stopped reading such a session at the first record that used either feature.

Dashboard 0.20.13
- Reads Broca session logs that carry the new structured-output paragraph setting, so runs from Broca's next release keep showing their steps and usage.

Dashboard 0.20.12
Fixed
- Broca sessions that record per-part tags in the new runner-tags/v2 format now open and show their steps instead of being treated as written by a newer, unknown version.

Fixed
- The dashboard reads Broca session records that carry the new tool-reply/v1 feature, which adds a reply deadline to long-running tools. Those sessions show their steps and usage as before.

This release makes the Config page readable by screen readers and accessibility tools, and keeps the dashboard reading Broca sessions as Broca records more detail about failed runs and ChatGPT requests.
Fixed
- The Config page now announces which option is selected. The Embedding Provider buttons work as a radio group, so the active provider is announced as selected, and the arrow keys move between options. The User/Project Config and background-model harness tabs announce which one is active. Nothing changes visually.
- Pop-up pickers say what they're set to. Output Language and the primary, default and fallback variant pickers now include their current value, or "not set", in the name a screen reader hears. Before, a blank picker and a set one sounded the same.
- Broca sessions with detailed errors or ChatGPT transport records still open. Broca can now record Google's structured error details on a failed run, and the request shape of ChatGPT runs. The dashboard recognises both. It reads usage, steps and timestamps, which these records don't change, so session timelines and cache charts stay the same.

This release keeps the dashboard reading Broca sessions as Broca records more about how runs end and how sends are handled.
Fixed
- Broca sessions with interrupt reasons and send directives still open. Broca can now record why an interrupted run stopped (for example a runner shutdown) and mark sends that ask to wake a session. The dashboard recognises both records. It reads usage, steps and timestamps, which these records don't change, so session timelines and cache charts stay the same.

This release keeps the dashboard reading Broca sessions as Broca adds a context ceiling to its compaction support.
Fixed
- Broca sessions that record a context ceiling still open. Broca is adding records for a run held at its context ceiling and for the ceiling decision, plus a run end for when a run stops at its ceiling. The dashboard now recognises these. It reads usage, steps and timestamps, which these records don't change, so session timelines and cache charts stay the same.

This release keeps the dashboard reading Broca sessions as Broca adds compaction support.
Fixed
- Broca sessions with compaction records still open. Broca is adding records for applied compaction views, the notices it publishes for them, and a context ceiling. The dashboard now recognises these records. It reads usage, steps and timestamps, which these records don't change, so session timelines and cache charts stay the same.

Fixes
- New Broca sessions stay readable. Broca now records message tags in every new session, and the dashboard reads those sessions instead of showing "no data".

Fixes
- Broca sessions with ordered message delivery stay readable. Broca's new delivery-order/v1 session records are now understood, so sessions that use them show their data instead of "no data".

Fixes
- Broca sessions that recorded a structured-output downgrade show their data. Broca now records when a run falls back from provider-enforced structured output. The dashboard reads those sessions instead of showing "no data".

Fixes
- Broca sessions using OpenRouter reasoning show their data. Broca now records OpenRouter reasoning state in session logs, and the dashboard reads those sessions instead of showing "no data".

Fixes
- Linux AppImage opens on newer systems. The AppImage bundled old Wayland libraries, so on systems with a newer Mesa the window never opened (EGL_BAD_ALLOC). It now uses the system's own Wayland libraries. The workaround with LD_PRELOAD is no longer needed. (#716)
- Memory search finds a memory by its ID. Typing 1234 or #1234 shows that memory first, followed by text matches, within the current filters. (#626)
- Prompt drops in sessions Magic Context doesn't manage are no longer labelled as Magic Context reclaims. A large drop in, for example, a Broca worker session now reads "Prompt tokens dropped". When the request itself didn't get smaller, it also says that the provider counted fewer tokens.
- Broca sessions that use newer features show their data. The dashboard reads sessions that use Broca's structured output and provider text state.

Fixes
- Broca sessions show their data again. Newer Broca versions write session records with features this dashboard didn't recognise yet, so those sessions showed "no data". The dashboard now reads them.
- Cache Diagnostics no longer blames a pass that changed nothing. A Magic Context pass that left the request unchanged was sometimes shown as the cause of a cache bust. Only passes that actually changed the request are named now. (#713)
- Cache Diagnostics labels cache losses Magic Context didn't cause. It now shows "Cache expired after N min idle" when the gap since the previous request was longer than the cache lifetime. It shows "Provider cache miss (no change recorded by Magic Context)" when a warm cache went cold seconds later and Magic Context recorded no change to the request. When the cache lifetime isn't known and the gap falls between the provider's shortest and longest lifetimes, the bust stays unlabelled, because either cause is possible. A cause Magic Context recorded always takes precedence. (#713)

Dashboard v0.20.0
A light theme, a redesigned Cache page, and a faster, quieter app. Works with Magic Context 0.47.x.
Light theme
The dashboard now has a light theme. A new picker in the sidebar offers System, Light and Dark; System is the default and follows your operating system. The light palette is a warm off-white rather than bright white, and all colours keep readable contrast in both themes. The chosen theme applies before the window paints, so there is no flash of the wrong theme on start.
A redesigned Cache page
- Session cards show readable names instead of raw ids, and no longer repeat the same badges on every card.
- The timeline is drawn to scale against the model's context window, with a fill bar showing how full each request was.
- Turns are a table instead of raw text rows, and each fact appears once.
- Broca runs are measured against each run's own context window, and runs that were paused by a restart keep their later steps.
Lighter on your machine
- The Cache page's Live mode reads only what changed since the last refresh instead of rescanning OpenCode's database and Broca's logs on every poll. With the Broca filter selected, a refresh went from about 627 ms and 454 MB read to under 5 ms.
- The Logs view stops refreshing while the window is hidden, slows down when it is not focused, and re-reads only log files that changed.
Config page
- Protected tools is a small table of tools and how many of their newest results to keep, instead of a JSON box. The built-in defaults (the newest todo list and the newest three ctx_reduce calls) are shown, and an example explains the setting.
- Keep reasoning tokens replaces the old reasoning-age setting, matching Magic Context 0.47.0.
- The cue compressor model is no longer a separate shared field. Magic Context now picks it from each host's dreamer settings, like every other dreamer task; set a per-task model in the dreamer task table to override it. With Magic Context 0.47.x, an existing mural.model key still applies and can be edited in Raw JSONC.
- Session details show the number of historian runs instead of an "Execute hits" counter that always read 0.
- While models are loading, the status shows as a small notice in the corner instead of pushing the page down.

Dashboard v0.19.0
A redesigned configuration page. Works with Magic Context 0.45.x.
A clearer Config page
The configuration form is reorganised into eight sections with an index on the left: General, Context window, History, Memory & search, Background models, Dreamer schedule, Prompt surface and Advanced. Each section is a single column of settings, with the explanation on the left and the control on the right. Below about 1,000 pixels wide, rows stack so controls keep their full width. Raw config keys are hidden unless you turn on "Show config keys", and settings that need a restart are marked.
Pickers instead of free text
- Output language is a searchable list of languages, for example "Turkish (tr)".
- Variants for the historian and dreamer models offer the variants the selected model supports. If they're unknown, you can still type one.
- The cue compressor model uses the same model picker as the historian and dreamer.
- Fallback models each get a full row: model, variant and remove. The model list opens above the page instead of being cut off.
Forms instead of JSON boxes
- Model routes are a table of route and preset.
- Tool descriptions list each Magic Context tool with its built-in text. Edit one to override it, or reset it to the default; only the ones you change are saved.
- Pi subagent extensions are a list with one entry per row.
Help next to each setting
The "How it works" expanders are now a small "?" button beside the setting. It opens a short explanation with a link to the matching page of the documentation, which opens in your browser.
Other changes
- Per-model cache TTL and threshold overrides sit in one collapsible table.
- The dreamer schedule is a compact table of tasks and their schedules.
- The Auto Update setting shows its real default instead of "undefined".
- A dreamer task that was skipped, or refused before reaching the model, says so on its card instead of showing a provider error.
- Config files the dashboard writes are readable only by your user account.

Dashboard v0.18.2
Fixes for Broca sessions, dreamer cards, the config editor and the serve mode. Works with Magic Context 0.44.x.
Broca sessions show their cache data
Broca 0.3.166 and later write a newer log record format for sessions that use scopes, steers or module tool calls. The dashboard treated those records as a damaged file and dropped the whole session, so these sessions showed no cache data. It now reads them. A record in a format newer than this build knows stops the read at that point and shows a notice, and the entries before it are kept.
Dreamer cards show the latest run (#596)
A task card showed a provider error from any earlier failed run, even after later runs succeeded. Cards now reflect the newest run only.
The config form keeps your comments
Saving from the structured config form rewrote magic-context.jsonc without its comments. Edits now change only the values you touched, and comments stay where they were. Config saves also follow a symlinked config file to its target, keep the file's permissions, and no longer delete the old file before the new one is in place.
Other fixes
- Serve mode no longer stalls other requests while a slow database read runs.
- The dashboard follows the database path the plugin uses, even if it changes after the app starts.
- Memory search escapes backslashes correctly, and paging past the full-text results no longer mixes in results from the fallback search.
- A config file with a trailing comma followed by a comment now parses.
- Pi session details reuse cached parent sessions, notice when a parent changes, and keep the cache bounded.
- Cron descriptions use the right ordinals (21st, 22nd, 23rd), and invalid field values are rejected instead of described.
- The session list keeps loading pages while you stay at the bottom.
- The log view labels note nudges correctly and names each bust cause once.

Dashboard v0.18.1
Fixes for the Cache tab and for converted OpenCode 2 stores. Works with Magic Context 0.44.x.
Converted OpenCode stores show every session (#559)
An OpenCode store converted from 1 to 2 keeps older sessions in OpenCode 1's tables and adds new ones to session_v2. The dashboard read only one of them, so newer OpenCode 2 sessions were missing, or older ones were. It now reads both and merges them by session: a session present in both is shown from its OpenCode 2 record, and its messages and cache history are read from there.
Running Broca sessions show their steps
Broca stamps a session's time only when a run starts and when it ends, so the Cache tab saw no change during a run and a gather session stayed at "0 events" until it finished. The tab now dates a running Broca session by its live log file, so steps appear while the run is going.
Cache cards keep one height
A card whose provider reported no cached tokens showed "No cached tokens reported" in the figure slot, which wrapped and made that card taller than the others. The slot now shows a grey dash, with "cache not reported" in small text below it, and every card keeps the same height.
Fewer false cache warnings on OpenAI
For providers that don't report cache writes, the tab estimated the cache it expected from the previous turn's input plus its output. Output isn't re-read from the cache on the next turn, so healthy turns often showed as warnings. The estimate now uses the previous turn's input only.

Dashboard v0.18.0
Works with Magic Context 0.44.0, including OpenCode 2.
OpenCode 2 sessions and projects are listed (#542)
The dashboard read sessions from OpenCode 1's session table. OpenCode 2 keeps its sessions in session_v2, and a fresh OpenCode 2 store has no session table at all, so no OpenCode 2 session was listed and the Projects page stayed empty. A store converted from OpenCode 1 showed only the sessions from before the upgrade. On an OpenCode 2 store, the Projects page, the Sessions list, session details and the Cache tab's session list and titles now read session_v2.
Logs page reads the OpenCode 2 log
The Logs page read only the OpenCode 1, Pi and OMP logs. It now also reads the OpenCode 2 plugin's log, at opencode2/magic-context/magic-context.log in the temp directory and logs/magic-context.opencode2.log in the storage directory.
OpenCode 2 filter in the Sessions viewer
The Sessions viewer's harness filter now offers OpenCode 2, next to OpenCode, Pi and OMP, and remembers it like the other choices.
Cache tab follows a live OpenCode 2 turn
OpenCode 2 updates a session's time when a prompt is sent and not again during the turn, so the Cache tab saw no change until the next prompt. It now dates an OpenCode 2 session by its newest message as well, so steps appear while the turn runs. If an OpenCode 2 store's session_message table has no time_updated column, the tab still lists its sessions but refreshes them only when a new prompt starts, and says so above the session cards.
The Cache tab's OpenCode 2 filter listed nothing before; it now lists OpenCode 2 sessions, and the OpenCode filter no longer includes them.
Broca runs are shown as run totals
Broca's run index records one usage sum per run, covering every model step in it. The Cache tab compared each run's sum with the previous run's, which showed busts that did not happen and a red 0% for a session's first run. A run total is now labelled RUN TOTAL and shows its own cached share; it is never marked stable or bust, and never compared with another run. A run that did not complete normally names how it ended, for example RUN TOTAL · ERROR. Every Broca session is now listed, not only historian and dreamer sessions.
Broca steps are read live
The Cache tab reads each Broca session's model steps from Broca's write-ahead log files as Broca writes them, including its archived logs, and shows one row per step, compared step against step as for OpenCode. Steps of a run that is still going appear, and a session whose only run is still active is listed. The files are only read, never written. When a session's log can't be read, its runs are shown as run totals.
Broca cache counts that were not reported
When a provider does not report cache reads or cache writes, Broca leaves the count out. The Cache tab showed these as 0; it now shows "not reported" in the list and in the timeline tooltip, and a reported 0 still shows as 0. A row with no reported cache reads shows "No cached tokens reported" instead of a percentage and is left out of the session's cached share. A turn where only some rows reported cache writes shows its total marked "(partial)". The timeline tooltip now also lists cache writes.
Session header and cards in the Cache tab
Above the timeline, the Cache tab shows the selected session's full name and its latest provider and model, with "(+N)" when the loaded rows used more than one model; the tooltip lists them all. For a Broca session it also shows the harness Broca ran it for ("via …") and puts the project root in the tooltip. On OpenCode 2 the model is read from model.id, where OpenCode 2 stores it.
Session cards shorten long names, such as alfonso:consult-<uuid>, and show the full name in a tooltip. A card is shown in a neutral color instead of red when no row in the window read anything from the cache, or when only the session's first run is loaded. A card of Broca run totals counts runs instead of events.
Pi todowrite default in the config editor
When the co

Dashboard v0.17.0
Works with Magic Context 0.43.0, including OpenCode 2.
OpenCode 2 sessions
The dashboard reads OpenCode 2's store as well as OpenCode 1's, including a store OpenCode 2 has converted in place. A store counts as OpenCode 2 only when the OpenCode 1 message tables are absent, so an OpenCode 1 store that merely contains the newer tables is no longer misread. A session converted from OpenCode 1 keeps its id, and the dashboard now matches it by that id across both labels, so its timeline uses the real context limit instead of scaling to its own largest prompt.
Model pickers survive OpenCode 2's cold start
On a cold start opencode models can print nothing for over 30 seconds while OpenCode 2 installs its plugins. Model discovery now waits up to 45 seconds, shows a readable error (such as "timed out after 45s") instead of an empty picker, retries once on its own and offers a manual retry, and never replaces a catalog that already loaded with an empty one.
Live config keys are marked
Settings that take effect without a restart (historian and dreamer models, fallbacks and variants, dreamer schedules and several others) carry a Live badge in the config editor. The list comes from the same schema mark that drives the docs, so the two cannot disagree.
Cache Diagnostics shows Broca runs
Runs recorded in Broca's run index appear as their own harness, with the same cache figures and timeline as other sessions. The index is opened read-only. Each Broca run is one point on the timeline, because Broca keeps usage per run rather than per step.
Compartments count includes the newest history
The context breakdown now counts compartments served in <session-history-since> as well as <session-history>, so a session whose main history block was built before its first compartment no longer shows a near-zero Compartments figure.
Log viewer reads the current fleet log format
The log viewer parses the fleet's current log format (schema 2), decodes the control-character escapes it writes inside field values, and still reads the older formats.
Smaller changes
- Historian runs that timed out or returned empty output are labelled "Timed out" and "Empty output" in the session viewer.
- The /ctx-session-upgrade reference is gone from the session viewer, matching its removal from the plugin.