GEMINI LABJP
MEMORY — Memory Profiles in Memory Bank are now GA. A fixed schema means agents reach evolving information without an expensive search mid-sessionSCOPE — Profiles are isolated by the scope you pass at ingest, and each schema-and-scope pair keeps a single profile as its source of truthINGEST — The IngestEvents API reached GA, bringing smoother event streaming, memory revision controls, and metadata supportAUDIO — gemini-3.1-flash-tts-preview now streams through streamGenerateContent, cutting the wait before the first audio arrivesCLASSROOM — From August 10, Gemini in Classroom opens to K-12 and higher education students of all ages who already have accessSUNSET — Shutdown dates are close: image generation models on August 17, the Grok 4.1 family on the 20th, and gemini-robotics-er-1.6-preview on the 31stMEMORY — Memory Profiles in Memory Bank are now GA. A fixed schema means agents reach evolving information without an expensive search mid-sessionSCOPE — Profiles are isolated by the scope you pass at ingest, and each schema-and-scope pair keeps a single profile as its source of truthINGEST — The IngestEvents API reached GA, bringing smoother event streaming, memory revision controls, and metadata supportAUDIO — gemini-3.1-flash-tts-preview now streams through streamGenerateContent, cutting the wait before the first audio arrivesCLASSROOM — From August 10, Gemini in Classroom opens to K-12 and higher education students of all ages who already have accessSUNSET — Shutdown dates are close: image generation models on August 17, the Grok 4.1 family on the 20th, and gemini-robotics-er-1.6-preview on the 31st
TAG

Indie development

25 articles
Back to all tags
Related:
Gemini API18Cost Optimization5Gemini3Memory Bank2Memory profiles2Model Routing2Image Generation2Structured Output2Image Classification2gemini-embedding-22Model Migration2File Search2
Gemini Advanced/2026-08-09Advanced

The Memory Wasn't Lost — It Was Written to a Different Profile

A Memory Bank profile is identified by the pair of schema and scope. When call sites build that scope slightly differently, extra profiles appear with no error at all. Here are the measured numbers for how badly it fragments, and how three candidate fixes actually performed.

Gemini API/2026-08-03Advanced

Measuring Update Policies for Memory Profiles: The Guard That Cost Me 16 Points of Accuracy

Memory profiles went GA in Memory Bank, making structured memory available to downstream code. I built three update policies and compared them under identical conditions. The one that looked obviously correct turned out to be the worst. Full harness code and the path to per-field TTLs.

Gemini API/2026-07-30Advanced

What Decided Our Cascade's Economics Wasn't the Escalation Rate

Putting Flash-Lite in front of 3.6 Flash and escalating only the hard items looks like an easy win. Estimating it from the escalation rate alone will mislead you. Here is the break-even solved with the escalated subset's output length in the equation.

Gemini API/2026-07-19Advanced

Still image or short clip? Deciding feature placement from the cost gap between Nano Banana 2 Lite and Omni Flash

When I froze over whether a wallpaper app's hero asset should be a still image or a short moving loop, the deciding factor was not taste but the order of magnitude of the cost. Here is how to normalize Nano Banana 2 Lite and Omni Flash onto the same footing, down to a working decision function.

Gemini Basics/2026-07-18Intermediate

"No Watermark Detected" Doesn't Mean It Isn't AI — The Asymmetry of SynthID

Images generated with Gemini carry a SynthID watermark. But a positive result and a negative result don't carry the same weight, and that asymmetry changes how you should track provenance.

Gemini Dev/2026-07-18Advanced

I Was Handing Gemini Obfuscated Stack Traces — Until retrace Went In Front, the Diagnoses Were Confident and Wrong

Release stack traces come out of R8 with the names flattened. Feed one to Gemini as-is and the diagnosis arrives calm, well-written, and wrong. Put retrace in front, match the mapping by versionCode, and forbid confident answers when you cannot restore. Numbers from 42 reports.

Gemini Advanced/2026-07-15Advanced

A near-miss label won't fix itself on retry — a normalization layer for closed-vocabulary classification

When responseSchema enum returns an out-of-set label, retrying tends to return the same near-miss. From a wallpaper app's 30-category batch, here is the distribution of how labels miss, plus a normalization layer built on an alias table and gemini-embedding-2 nearest-neighbor, with measured results.

Gemini API/2026-07-11Intermediate

When Gemini's Context Cache Quietly Expires Mid-Run: A TTL Guard for Pipelines That Pause

When a nightly batch or a retry backoff pauses your pipeline, Gemini's explicit context cache can expire on the wall clock while nothing errors out, sending later calls back to full-token billing. Here is a small lease guard that decides whether to re-arm or run uncached based on cost.

Gemini Advanced/2026-07-10Advanced

The Day We Went From 30 Categories to 34 — Reclassifying 1,180 Assets Instead of 8,142

Adding categories to a taxonomy does not require reclassifying everything. Here is how embeddings and confidence margins narrowed a backfill from 8,142 assets to 1,180, with the numbers.

Gemini Advanced/2026-07-10Advanced

Images Made With a Retiring Model Can Never Be Made Again — Tracking Regenerability in a Ledger

When Gemini's image generation models shut down on August 17, the assets you made with them can no longer be reproduced the same way. Here is the ledger design and code I use to decide, before the deadline, which assets are regenerable and which must be frozen.

Gemini Advanced/2026-07-08Advanced

One File Search Store for Many Apps: Splitting Retrieval With customMetadata and Chunk Config

Put several apps' FAQs in a single Gemini File Search store and metadataFilter can silently return empty grounding, or answers get split across chunk boundaries. Here is the customMetadata design, the AIP-160 filter-syntax trap, and measured chunkingConfig tuning.

Gemini API/2026-07-04Advanced

When Two Managed Agents Fight Over the Same Repo: External Leases and Fencing for Isolated Sandboxes

Every Managed Agents run gets its own isolated sandbox, so a local lock cannot stop two runs from touching the same repo or record. Here is how I serialize them safely with an external lease and a fencing token.