v1.8.94 - 1.8.95
2026-07-18 All players. Small quality-of-life updates around the free trial and tokens: buy options right in the app when you want them, honest messaging when you are just waiting on a free-trial slot, and no purchase prompts at all for complimentary keys.
ADDED
- ▸ Buy a token pack from inside the app: the end-of-trial prompt and a new out-of-tokens prompt both offer Go monthly and Buy a token pack (opens your account page in your own browser), shown at most once every 12 hours.
FIXED
- ▸ Free-trial users waiting on a daily slot now see "your free cycle starts tomorrow" instead of an out-of-tokens purchase prompt. You are queued, not out of tokens, and the app says so.
- ▸ Complimentary and tester keys never see purchase prompts.
v1.8.92 - 1.8.93
2026-07-17 All players. We have heard the negative feedback on the live coach and are working through it. This update fixes a family of bugs that made live calls read as nonsense, and it should help a little. Plus: every player now gets one full coaching cycle free.
ADDED
- ▸ Free trial event: every player gets one full coaching cycle on us — a live-coached match, its post-match review, and a Film Room session. No card, nothing to activate; tied to your Steam account, one per person. When it runs out, grab a token pack or go monthly if you want to keep going.
FIXED
- ▸ Coaching state from a previous match no longer bleeds into your next one. If you left a match before the end screen, the coach carried everything over: phantom claims like "you died three rounds in a row" in round two, repeated canned lines because it thought it had already said things, and wrong reads early in the match. Three separate bugs, all fixed.
- ▸ The coach gives one instruction at a time now. Calls that crammed four or five instructions into one line ("buy this, flash there, smoke that, then rotate") are rejected and rewritten to the single thing that matters most, with a short why.
- ▸ Spoken calls that would arrive too late to act on are dropped instead of played. A voice line about a moment that already passed was worse than silence.
- ▸ The coach understands knife rounds. No more "you should have bought kevlar" on a round where buying is disabled.
- ▸ Retired the "you are burning" warning. You know.
- ▸ Live calls that came back empty from the AI service now retry once instead of showing a canned line (the biggest cause of repetitive-feeling calls in our data).
v1.8.91
2026-07-13 All players. A behind-the-scenes update that moves the coach onto current AI models ahead of provider retirements, so live coaching, post-match analysis, and the Pro Visual Coach keep running without interruption. Nothing changes in how you use Game Demon.
CHANGED
- ▸ Moved the coach's AI models to current versions before the old ones are retired by our model provider, so nothing goes dark. The Pro Visual Coach (the feature that reads your screen for crosshair placement and positioning) now runs on an up-to-date vision model, and the rest of the coach continues on the models it already uses. No action needed on your end.
v1.8.79 - 1.8.90
2026-07-10 All players. Our biggest update yet: a full premium redesign, a coach you shape that talks and reads the field, a real conversation grounded in your match history, a new Matches tab, FACEIT demo support, deeper post-match analysis, and fixes for two scoring bugs that could show your result wrong.
ADDED
- ▸ Full premium redesign of every screen, with the chibi crow mascot and a dashboard Home showing your real last match
- ▸ Three-step onboarding that finds Steam and CS2 and writes the config for you
- ▸ Pick your coaching style in Settings (veteran pro, beginner friendly, tough love, chill, just the facts, or write your own) — one shaped coach replaces the old Demon / Savant / Analyst personas
- ▸ Spoken coaching in one clear voice: the coach reads its live calls out loud (tune or mute in Settings)
- ▸ A real conversation: your full recent match list and measured trends ride along on every question — ask "what's my pattern on Dust2?" or "compare my last three matches"
- ▸ Factual questions get factual answers first ("who was MVP?" names the player and the number), then coaching
- ▸ Name a match in plain language ("my last Dust2 game", "five games ago", "everything from 06/16") or reply with a number to pick from a list
- ▸ Location coaching read straight from the demo — the same area labels CS2 shows above the radar, on every map, so the coach cannot invent a spot
- ▸ New Matches tab: every match on record with score, W/L, rating, K/D, and per-row Review / Film / Coach buttons — Film jumps straight into that match's replay
- ▸ FACEIT demo support: .dem.gz files import from Downloads, plus a Check now sweep in Settings for demos you already downloaded
- ▸ Momentum and mid-round tilt awareness in live calls; player memory brings your recent form and per-map history into the advice
- ▸ Live enemy positions and a live round win read when a match is being recorded (community / scrims)
- ▸ Live coaching and chat unified into one Coach screen
- ▸ Deeper post-match: both-team economy, spray and recoil control, trade attribution, flash conversion, and bomb timing
- ▸ Aim coaching prescribes a one-tap Aim Botz routine, and the counter-strafe read judges rifle-class shots only (firing an SMG on the move is correct play, not a mistake)
- ▸ Automatic demo import keeps checking until your demo arrives; demos that fail to parse are skipped instead of retried forever
FIXED
- ▸ Match scores were wrong across halftime: a 12-3 win could show as 9-6, and a win could even show as a loss. Already-imported matches self-correct on load
- ▸ FACEIT scorelines could be wrong (a 13-11 win showing as a 12-12 draw). Existing FACEIT matches self-correct on update, no re-import needed
- ▸ The coach now reads your whole match, not just the first eleven rounds
- ▸ Duplicate rows in the film room timeline are gone, and old polluted timelines heal themselves
- ▸ Film room markers start playback a few seconds before the moment so you see the play develop
- ▸ The coach names the right gun (it could not see a weapon mid-reload and guessed)
- ▸ Coach replies no longer vanish or rewrite themselves mid-answer, and brief rate limits retry silently
- ▸ Live calls clear when the next match starts instead of lingering on screen
- ▸ Hostage maps no longer get bomb advice; match point in overtime is called correctly
- ▸ Leetify ratings display signed (+0.03 / -0.01); scoreboard columns line up across both teams
- ▸ Armor calls respect carried-over armor; no raw map filenames, no "user", no prompt fragments in coach lines
v1.8.78
2026-07-06 All players. A reliability fix so coach calls can never show up blank.
FIXED
- ▸ Coach calls could occasionally appear blank. If the AI service briefly returned nothing — a momentary network drop or rate limit — the coach was displaying an empty call instead of a short backup line. It now always falls back to a real coaching cue, so a call can never come through blank.
v1.8.70 - 1.8.77
2026-07-06 All players. Sharper live coaching — the coach now reads every weapon class correctly — plus a premium polish pass over the Pro Film Room and the accumulated coaching-accuracy fixes from recent test builds.
CHANGED
- ▸ Film Room polish: your coaching notes now cross-fade as you move between moments instead of hard-cutting, mistake cards expand smoothly, film loads with an on-brand spinner instead of a black frame, the Cinema toggle is a proper switch, and the spacing and type are cleaner and more consistent throughout — the Pro film study feels the way it should.
- ▸ Sharper reads in the moment: the coach keeps live callouts short enough to read at a glance and frames post-death advice as "next time" instead of a live command you can no longer act on.
FIXED
- ▸ Live weapon readout: holding an SMG, sniper, or machine gun (MP5, AWP, Negev, M249) no longer shows up as a pistol. The coach was mis-reading those weapon types and defaulting to "USP", which also threw off its buy advice — both are fixed, so eco and full-buy calls now match what you are actually holding.
- ▸ Hostage maps: the coach reliably detects hostage maps (Alpine and other cs_ maps) and coaches around the hostages instead of occasionally giving bomb-site calls.
- ▸ Death-frame armor: the coach no longer calls you "naked" when you died wearing armor (a stale end-of-life reading was zeroing it out), so it stops telling you to buy armor you already had.
v1.8.54 - 1.8.69
2026-06-26 All players. A large batch graduated from the test channel: the Recording Room becomes coach-led film study (a Guided Review that walks your whole match, ranked mistakes with the better line, and ask-the-coach on any moment), the coach gets a correctness pass, the spoken coach voice now works fully offline, and the Visual Coach moves to Pro.
ADDED
- ▸ Guided Review in the Recording Room: open any recorded match and the coach walks you through the whole game, pistol round to final round, in your chosen coach's voice, with the footage following the story. Works on your existing recordings, and falls back to a built-in narration when you're offline.
- ▸ "Your biggest mistakes" on every reviewed match: the few specific things that cost you, ranked, each with the better line to fix it and a one-click jump to that exact moment on the tape. It goes deeper when a demo is connected — untraded opening deaths, force-buys that cost you rounds, feeding the enemy AWP.
- ▸ Ask the coach about any moment: on any coach-call marker or ranked mistake, ask "why was that the wrong call?" or "what should I have done here?" and get an answer grounded in that exact moment, in your coach's voice.
- ▸ Offline coach voice: the spoken-coach voice model now ships inside the app and runs locally, so Speak works without a download or a connection (first use loads it into memory, then speaks).
- ▸ Recording management: every clip now has a delete button, and Game Demon auto-trims the oldest recordings so they can't quietly fill your drive.
CHANGED
- ▸ Visual Coach is now a Pro feature (it was free during the beta). Base accounts no longer spend tokens on it, so your monthly allowance stretches to about 5-7 coached matches; the toggle shows as Pro with an upgrade nudge.
- ▸ The Recording Room got a full visual redesign (a holographic, sigil-sealed reviewer), and coach calls now carry a read / low confidence tag so you can tell a grounded fact from a live read at a glance.
- ▸ Sharper live coaching: after a death the coach names what to buy back first (armor, then rifle, then utility) instead of a generic "reset", calls the exact kit on full-buy rounds, and the Savant stops forcing an enemy read onto moments that are really about you.
- ▸ Each coach now sounds like themselves in the match review; the walkthrough used to read identically no matter which coach you picked.
- ▸ Match recording was rebuilt as an OBS-style capture straight off the graphics card into the hardware encoder, for less overhead while you play.
- ▸ Clearer progress indicators across the Recording Room, the Steam re-scan, and demo parsing, so you can tell when something is working instead of wondering if it hung.
FIXED
- ▸ On hostage maps (Office, Italy, Agency) the coach no longer gives bomb-site calls like "rush B", plant, or defuse; it coaches around the hostages instead.
- ▸ The coach stops giving you live tactical cues (cover, reposition, peek) once you are dead for the round.
- ▸ It no longer calls you defenseless when you are actually wearing armor, and mid-match chat now runs the same safety checks — it won't tell you to buy armor or a helmet you already have, or cite a callout from another map.
- ▸ The coach no longer claims how a round was won when the live data does not report it (it used to always assert "elimination"), and the match walkthrough can no longer invent a stat or a callout.
- ▸ Film Room win/loss is correct: the Guided Review was flipping first-half rounds after the halftime side swap, labeling rounds you won as losses. Outcomes now track your side through the swap.
- ▸ Recording Room sync: coach-call markers and the jump-to-the-moment buttons now land on the right round (a timezone bug and a round-level off-by-one had been placing them seconds-to-rounds late); newly recorded matches get frame-perfect placement.
- ▸ Stability: the Guided Review no longer crashes the app at the end of a walkthrough, and no longer freezes if you toggle the voice off partway through.
v1.8.53
2026-06-19 All players. A security and accuracy pass: your account now talks to the cloud coach over per-user secure tokens, the packaged app is hardened, and the in-app copy was corrected to match how Game Demon actually works.
CHANGED
- ▸ In-app descriptions now match reality: cloud-only coaching, Pro means unlimited tokens, and three coach personas (Demon, Analyst, Savant).
SECURITY
- ▸ Your account now authenticates to the cloud coach with a per-user secure token instead of a shared key.
- ▸ The packaged Windows app was hardened (Electron security fuses) to make the shipped binary tougher to tamper with.
v1.8.31 - 1.8.52
2026-06-16 All players. A large batch graduated from the test channel: the in-game HUD stutter fixed at last, a new Recording Room for reviewing your matches, an optional spoken coach voice, smoother match recording, and a wave of coaching-quality work.
ADDED
- ▸ Recording Room, a new sixth screen: review any recorded match with a marker on every coach call — deaths, eco and buy calls, reads, clutches — and jump straight to the moment. Walk it at your own pace or let Cinema mode follow playback.
- ▸ Optional spoken coach voice in the Film Room: hear the coach read its breakdown aloud in your chosen persona's voice. Free, runs locally on your machine, and off by default — turn it on in Settings, Audio and Voice.
CHANGED
- ▸ Coaching-quality batch from the test channel: the coach now reads the stakes of the round (last round before the side swap, match point, pistol rounds), calls out when the enemy cannot afford to re-buy, eases its delivery when you are tilted, and names the concrete fix after a death or a missed buy instead of a generic reset line.
- ▸ Cleaner in-game overlay: removed decorative animations and textures that cost frames and made calls harder to read at a glance.
FIXED
- ▸ The in-game HUD no longer stutters when you move the mouse. The overlay had been forwarding every mouse movement, which forced it to repaint over the game on each move and caused a constant hitch the moment the HUD was shown.
- ▸ Match recording no longer hitches your game: recording is now a GPU-native background capture, so recording while you play does not cause frame drops. Recordings stay local-only, as before.
- ▸ The Film Room now shows coach-call markers for matches coached live — a match-identifier mismatch had been hiding them.
v1.8.30
2026-06-12 All players. The biggest coach-quality jump since launch: the coach now grades its own accuracy after every match, repeats itself far less, remembers you across matches, notices when you act on its advice, and answers questions mid-match.
ADDED
- ▸ TRUTH-CHECKED badge on the Reckoning: after each match the coach grades every line it said during play against the live game state it was said under, and shows the verified count. The receipt no human coach can offer — and when it catches itself overstating something, it says so.
- ▸ Ask your coach mid-match: a chat bar on the live screen answers one question between fights in your coach's own voice, grounded in the current game state and remembering the conversation. Replies are rateable.
- ▸ Cross-match memory in the Reckoning: the post-match review can reference your recent arc — win/loss streaks, your K/D and ADR trend versus recent matches, and your record on the specific map — once a few matches are on record. It weaves in at most one such pattern and never invents a trend.
- ▸ The coach notices when you fix what it flagged: buy the armor or utility it called for, or finally spend a hoarded bank, and it acknowledges the correction the moment the next round goes live.
- ▸ Enemy pattern reads: freezetime calls surface repeated bomb-site hits and force-buy tendencies the coach has actually observed this half, framed as its own read and never extended past what it saw.
CHANGED
- ▸ Far less repetition — the most common complaint. The coach now sees its own recent calls before it speaks, so it shifts angle instead of restating the same buy with new adjectives, and a rejected line gets one pointed rewrite before any canned fallback ships.
- ▸ Lower boring-line rate overall: templated fallback lines fell from roughly half of coach calls at the low point toward about a fifth, with the retry-on-rejection engine converting many would-be fallbacks back into real coaching.
FIXED
- ▸ Pro subscribers are now correctly routed to the premium coaching model — a tier-mapping bug had been quietly normalizing every Pro license to the free tier, so Pro coaching was not actually running.
- ▸ The coach can no longer recommend buying armor or a helmet you already have: an enforced check now rejects the contradiction instead of only asking the model not to.
v1.8.12
2026-06-06 All players. Channel unification: stable and test now run the same build, so everyone gets the full 1.8 line at once, plus a structurally more honest coach and a roster change.
ADDED
- ▸ Fallback-cause instrumentation: every templated fallback line the coach ships is tagged with why it fired (rate limit, which quality check, repetition) so the boring-line rate is measurable per cause and fixable per cause.
- ▸ New coach quality checks built from real production failures: money-math phrasing like "$3950 down to 3950", invented map callouts after movement verbs ("Play Boma"), and raw telemetry vocabulary (frame counters, position deltas) can no longer ship.
CHANGED
- ▸ The coach can no longer cite a stat that was never captured. A match without a parsed demo has no real headshot percentage, ADR, or rating; the coach now says so instead of asserting zeros as fact, and a final check strips any uncaptured-stat claim from chat and post-match output before it stands.
- ▸ Reprimands respect the team save: when most of your visible teammates are also on light buys, the coach no longer scolds you for correct economic discipline.
- ▸ The Veteran is shelved. He was the least-picked coach by a wide margin and below the quality bar when picked; rather than ship a weak persona he is hidden (not deleted) until the map-knowledge system he is built for is filled with reviewed map data, and he returns as the coach who actually knows the maps. Anyone bound to him is paired with the Demon, now the default for new installs.
FIXED
- ▸ Privacy: 334 legacy feedback rows written before the 2026-06-04 backend fix carried a raw IP address, contradicting the published policy. All swept and verified by full re-scan: zero rows carry an IP. The policy is now true for every row we hold.
v1.8.5 - 1.8.11
2026-06-06 Test channel at release, promoted to all players in 1.8.12. Six releases in one night, driven by live tester sessions: the recording stutter verdict fixed, coach speech starting 3 to 5 times faster, post-match aim analysis, decision-first persona calls, and the overlay coverage complaints closed out.
ADDED
- ▸ Post-match aim analysis in the Reckoning (demo-backed matches): overflick rate and direction, plus a directional sensitivity read (too high / too low / dialed in). Honest by design: every finding carries its sample size, low-sample matches say "not enough engagements" instead of guessing, and it never prescribes a specific sensitivity number.
- ▸ Map-knowledge foundation: the coach can cite studio-reviewed map knowledge (timings, lineups, tendencies) in freezetime calls. The corpus starts empty and fills as real content passes human review, so nothing is invented.
- ▸ Coach diagnostics now record which transport served each call (streaming or buffered, with time to first token) so streaming performance is verifiable from real sessions.
CHANGED
- ▸ Live coaching text starts much sooner: true streaming transport puts first words on screen in roughly 0.3 to 0.6 seconds instead of 1.5 to 3. If the streaming path is unreachable the call falls back to the previous route automatically.
- ▸ Personas commit to the decision. Freezetime calls lead with the force/save/buy call through each coach's lens; generic buy-list endings are gone. On repeat deaths the coach rotates to a genuinely new angle, names equipment at most once per death sequence, and goes quiet on the third-plus same-mistake death instead of repeating itself.
- ▸ The visual coach captures frames directly from the graphics card via a small helper process (the same OS mechanism OBS uses). The game's render loop is never involved and a helper crash cannot take the app down. Same frames, same cadence, same opt-out.
- ▸ While recording, Game Demon runs itself at below-normal process priority so Windows always favors the game when both want CPU time.
- ▸ Visual Coach is labeled honestly: "Experimental, Free during beta". Visual calls do not spend cloud tokens during the beta; older copy claimed they did.
- ▸ Data-retention disclosure corrected to match the live privacy policy: coaching records up to 12 months, de-identified training archive up to 24, identifier hash still rotates every 90 days.
FIXED
- ▸ In-match stutter while recording ("unplayable" in live testing): a wake-word listener restart loop (measured at 1,171 engine restarts in one 26-minute match) now backs off and gives up cleanly after repeated failures, screen capture is capped at 1080p30, and the recorder prefers the GPU's hardware H.264 encoder.
- ▸ The in-game coach overlay no longer covers half the screen: long calls clamp to three lines at any text scale, the feed is bounded to about a quarter of screen height, and the panel only paints as tall as its content (on stretched 4:3 resolutions it used to fill half the display).
v1.8.2 - 1.8.4
2026-06-05 Test channel. Live-test fix batches from Pegal and Revn sessions, plus new feedback surfaces so more of what the coach says can be rated.
ADDED
- ▸ Post-match feedback asks on the Reckoning: one targeted question fired from specific in-match triggers, capped per session so it never nags.
- ▸ Thumbs ratings on the post-match narrative and Coach Chat replies (previously only live calls could be rated).
- ▸ "Open Captures" button in Settings reveals the visual-perception capture file.
CHANGED
- ▸ Text-size ceiling raised from 1.5x to 2.0x.
- ▸ System-audio (headset loopback) capture is now opt-in and OFF by default.
FIXED
- ▸ Rate-limited coach calls now degrade to a state-aware fallback line instead of erroring.
- ▸ Wake-word crash loop on machines where the speech service is unreachable now backs off exponentially instead of spinning ~25 times per second.
- ▸ Chat no longer hard-blocks on a transient token-spend failure; only a genuinely empty wallet blocks.
- ▸ The coach could attribute a push to your own team or assert a site hit it had no data for; enemy reads are now framed as tendencies, not certainties.
- ▸ Live calls are word-capped to overlay size (between-round 40, post-death 35), enforced in code.
v1.8.0
2026-05-29 All players. Comprehensive coaching capture: the data flywheel the adaptive coach is built on, with the privacy work done first.
ADDED
- ▸ Comprehensive auto-capture of coaching content: every live call, post-match analysis, Coach Chat and Ruby replies, and your own inputs are recorded to improve the coach and train future models. On by default, governed by Settings, Coach Feedback, Share My Coaching Data; turning it off stops capture at the source, and you can delete everything collected.
- ▸ Rotating per-quarter identifier hash: your Steam ID is HMAC-hashed with a server-held secret that rotates every 90 days before anything is stored. The plaintext ID is never written to our database, and records cannot be linked across quarters.
CHANGED
- ▸ First-launch disclosure, Settings privacy copy, and the published privacy policy rewritten to disclose comprehensive capture precisely. Corrects prior copy that stated chat messages were never uploaded.
v1.7.0 / 1.7.1
2026-05-28 All players. The two changes promised at launch, delivered: cloud coaching became the default (and then the only path, because it is simply better), and the six-signal feedback system graduated from the test channel.
ADDED
- ▸ Six-signal feedback on every live coach call, graduated from rc: Good call, Wrong call, Wrong timing, Wrong tone, Too generic, Not right now, with optional tone suggestion and freeform note.
- ▸ Settings, My Coach: a real window into what the coach has learned about you, with manual overrides.
- ▸ Audible tactile feedback on UI buttons: a short soft pluck (720Hz sine, not the old harsh click), gated on the same audio-cues toggle.
- ▸ The CS2 card now has two explicit buttons: ENTER (open the module without launching the game) and LAUNCH CS2 + ENTER. Clicking the card no longer auto-launches CS2 every time.
CHANGED
- ▸ Coaching is cloud-only for every tier. At launch we said local models would stay as an opt-in toggle; after measuring quality and the mouse-lag cost side by side, local inference was removed entirely. Base remains a one-time $14.99 purchase and now includes a monthly cloud-coaching allowance; Pro is unlimited.
- ▸ Skill-tier calibration across every coaching path: veterans never get fundamentals ("buy armor", "crosshair at head level"), noobs do. Previously only the mechanic-teach triggers were tier-aware.
FIXED
- ▸ Leetify parsing rewritten for the current public API shape; match lists and per-match metrics were silently empty.
- ▸ GSI-only stat honesty: ADR and headshot percentage do not exist in CS2's live data feed, so matches without a parsed demo now show those stats as unavailable instead of a misleading 0.
v1.7.0-rc1
2026-05-19 Test channel only. Rich feedback signals, per-user coach adaptation, and the foundation for the global training pipeline.
ADDED
- ▸ Six-signal feedback chip selector on every live coach call (Good call, Wrong call, Wrong timing, Wrong tone, Too generic, Not right now). Optional tone suggestion (sharper / softer / shorter / longer) and freeform note.
- ▸ Settings → My Coach: a real window into what the coach has learned about you. Per-persona tone bias, length bias, topic emphasis, suppressed cue list. Manual overrides stick until you reset.
- ▸ Preference aggregator: a "Refresh from recent feedback" button in Settings → My Coach turns repeated signals into the coaching prompt. Scheduled cadence (daily background tick) is the next iteration; today the user triggers it manually.
- ▸ First-launch data collection disclosure modal with a real opt-out at Settings → Coach Feedback.
- ▸ GDPR data request page at altrosstudios.games/privacy/data-request. Today the form opens a pre-filled email to support@altrosstudios.games (we fulfill manually within 7 days); the self-serve backend ships in the next release.
- ▸ Approach warnings on map callouts: T pushing into a common CT hold (Mirage Window from jungle, Dust2 Long A from spawn) gets a fact-grounded warning at freezetime.
- ▸ Player experience tier (noob / casual / veteran) in onboarding and Settings. Coach assumes the right level of mechanic literacy.
- ▸ Tier 0 mechanic teaches for noob and casual players: shift_walk, counter_strafe, no_run_shoot (noob only), crouch_cover, drop_bomb_safely. Three teaches max per match. Veteran tier suppresses entirely.
- ▸ Mechanics Learned section on the post-match Reckoning with Learn-more explainers. Lifetime review in Settings.
CHANGED
- ▸ Pro tier no longer warms the local 8B Ollama model at startup. Eliminates the mouse stutter from CPU spill when VRAM cannot fit the model. keep_alive=0 on every Ollama call so models unload immediately.
- ▸ HUD overlay coach calls hold for 15 seconds then fade over 3 seconds (was 5 minutes, was piling up and covering the game). Stack capped at 3 visible.
- ▸ Cross-map specificity validator: coach mentioning "banana" on Mirage (Inferno only) or "apartments" on Dust2 (Mirage / Inferno only) gets rejected before the call ships.
- ▸ Visual coach sample interval increased from 10 seconds to 30 seconds and frame width reduced from 1280 to 720 to cut GPU contention with CS2.
FIXED
- ▸ Leetify ingestion path was hitting /v2/profile/{id} and /v2/games/{id} URLs that do not exist on Leetify's public API. Every call silently 404'd. Rewritten against the documented v3 endpoints.
- ▸ primarySource value mismatch: onboarding wrote "both", Settings used "merge", orchestrator gated on "merge". Players who picked "both" in onboarding never got merge behavior. Unified on "both" across all surfaces.
- ▸ Post-match auto-route off the Live screen no longer fires when you are actively rating calls. Window also bumped to 120s for the off-screen case.
v1.4.3
2026-05-18 Coaching maturity push. Voice Q&A, the Tier 5 and Tier 6 surfaces (goals, weakness, tilt, career arc, curriculum, life context), per-persona coach quality tuning, and a batch of UI bug fixes from playtester feedback.
ADDED
- ▸ "Hey Ruby" wake word for voice questions to the chat persona.
- ▸ Push-to-talk voice Q&A with Ruby. AWS Polly neural voices for spoken responses.
- ▸ Per-player goal declaration: rank target, match volume target, skill target.
- ▸ Weakness profile aggregation per coaching category.
- ▸ In-match tilt detection: 3+ consecutive losses flips the coach into a softer delivery for the rest of the match. Per-persona softening sentence layered into every cue. Cue cadence unchanged — only the tone shifts.
- ▸ Career-arc timeline in the post-match Reckoning. Rank changes, milestone matches, comeback arcs.
- ▸ Auto-generated weekly curriculum based on your weakness profile.
- ▸ Life-context inputs (opt-in): stress and time-constraint adjustments.
- ▸ Tendency tracker observes opponent patterns mid-match.
- ▸ Strategy learner records outcomes across sessions for cross-match comparison.
- ▸ Team awareness: alive count, dead count, estimated team economy.
- ▸ nice_kill positive praise trigger when you win a duel cleanly.
- ▸ LLM dispatch budget per persona to control call frequency.
- ▸ Halftime shift trigger: explicit side-swap framing at the half.
- ▸ Internal quality dashboard for per-persona signal trends.
CHANGED
- ▸ Topic cooldown: the same theme of advice no longer fires across consecutive rounds.
- ▸ Variant rotation across fallback strings so templated lines do not repeat verbatim.
- ▸ Ruby push-to-talk hotkey is now configurable in Settings → Audio & Voice with conflict detection.
FIXED
- ▸ Leetify settings click no longer blanks the entire UI. ErrorBoundary now wraps every settings panel.
- ▸ Eco call no longer races buy phase. economy_decision fires on freezetime end so state is final when assessed.
- ▸ "How Demos Get Here" tutorial no longer plays twice.
- ▸ Match list now has explicit loading / empty / error states with retry.
- ▸ Prompt-leak root cause: removed ALL-CAPS section headers (GROUND TRUTH, VOICE TONE, RULES FOR THIS RESPONSE, etc.) from system prompts that the language model was echoing structurally into coaching output. The v1.2.3 prompt-leak validator stays as defense in depth.
v1.1.1
2026-05-16 Post-Steam-retirement direct-distribution stopgap. Valve retired the Steam page on 2026-05-15 on category-fit grounds; this is everything that had to ship the next day to keep the lights on.
ADDED
- ▸ Direct-distribution checkout via Stripe at altrosstudios.games.
- ▸ DynamoDB license storage with hardware binding.
- ▸ Magic-link JWT auth for the account portal.
- ▸ Self-service refund within 14 days or 2 hours of play.
- ▸ In-app updater via the Altros Studios Launcher.
- ▸ Customizable post-match Reckoning slot grid (five player-configured stats).
- ▸ Optional Leetify integration for richer post-match stats.
- ▸ Ruby companion: in-app navigation assistant with voice and chat.
CHANGED
- ▸ Post-match Reckoning page redesigned for readability: type scaling, slot grid as the centerpiece.
- ▸ Overlay default text scale reduced 15% per playtester feedback.
- ▸ Coaching persona accents desaturated 20% on the in-game overlay.
FIXED
- ▸ Profile video render failure on lobby and chat surfaces.
- ▸ Stat ID mismatch when Leetify fallback fires for unlinked players.
v1.0.5
2026-05-14 Final Steam submission. Initial public release. Distribution pivoted to direct-from-Altros on 2026-05-16 after Valve retired the Steam page on category-fit grounds.
ADDED
- ▸ Real-time AI coach for Counter-Strike 2 with four personas: Demon, Analyst, Veteran, Savant.
- ▸ Live in-match coaching pipeline via Game State Integration with sub-2-second latency.
- ▸ Post-match Reckoning narrative analysis.
- ▸ Voice in (push-to-talk question to Ruby) and out (AWS Polly neural).
- ▸ Validator chain: arithmetic, length, peek-blame, dedup, prompt-leak.
- ▸ Full Tier 1-4 coaching surfaces.